CN118332484B - Resonance pressure sensor detection system and method for auxiliary signal conditioning - Google Patents
Resonance pressure sensor detection system and method for auxiliary signal conditioning Download PDFInfo
- Publication number
- CN118332484B CN118332484B CN202410773910.7A CN202410773910A CN118332484B CN 118332484 B CN118332484 B CN 118332484B CN 202410773910 A CN202410773910 A CN 202410773910A CN 118332484 B CN118332484 B CN 118332484B
- Authority
- CN
- China
- Prior art keywords
- signal conditioning
- conditioning
- signal
- module
- pressure sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003750 conditioning effect Effects 0.000 title claims abstract description 330
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims abstract description 23
- 238000010276 construction Methods 0.000 claims abstract description 18
- 238000012937 correction Methods 0.000 claims description 35
- 238000006731 degradation reaction Methods 0.000 claims description 29
- 230000003044 adaptive effect Effects 0.000 claims description 28
- 230000015556 catabolic process Effects 0.000 claims description 27
- 230000009471 action Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 13
- 230000007787 long-term memory Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 7
- 230000003449 preventive effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000007850 degeneration Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 abstract description 19
- 230000004044 response Effects 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 7
- 238000005259 measurement Methods 0.000 description 25
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 6
- 230000003321 amplification Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000007774 longterm Effects 0.000 description 5
- 238000003199 nucleic acid amplification method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000001143 conditioned effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004643 material aging Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013433 optimization analysis Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/10—Measuring force or stress, in general by measuring variations of frequency of stressed vibrating elements, e.g. of stressed strings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L7/00—Measuring the steady or quasi-steady pressure of a fluid or a fluent solid material by mechanical or fluid pressure-sensitive elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a system and a method for detecting a resonance pressure sensor for auxiliary signal conditioning, belonging to the field of sensor signal conditioning, wherein the system comprises: the basic information acquisition module is used for acquiring basic information of equipment; the model construction module is used for constructing a signal conditioning model framework; the drift characteristic analysis module is used for determining a first conditioning characteristic; a performance optimization module for determining a second conditioning characteristic; the performance feedback verification module is used for carrying out performance feedback verification by combining the sensing task and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter; the state recognition module is used for setting a signal state recognition model; and the signal conditioning module is used for determining the optimal conditioning parameter combination and conditioning the signals of the resonant pressure sensor. By correcting drift caused by environmental factors, optimizing dynamic response and combining signal state identification, the technical effect of improving the detection precision and stability of the resonant pressure sensor is achieved.
Description
Technical Field
The invention relates to the field of sensor signal conditioning, in particular to a system and a method for detecting a resonant pressure sensor for auxiliary signal conditioning.
Background
Resonant pressure sensors are widely used in a variety of fields due to their high sensitivity, wide range, and other advantages. However, there are still some problems to be solved in the prior art of resonant pressure sensors. First, the resonant pressure sensor is easily affected by external factors such as ambient temperature and humidity, resulting in a decrease in measurement accuracy and stability. Changes in environmental factors can cause sensor parameters to drift, causing deviations in the measurement results. Secondly, the resonance pressure sensor also faces the problems of poor dynamic response, obvious hysteresis effect and the like in practical application. When the pressure changes rapidly, the sensor may not respond in time, affecting the timeliness of the measurement. Meanwhile, due to hysteresis characteristics of the device, in the rising and falling processes of pressure, the output of the sensor is often unrepeatable, and the measurement accuracy is reduced. In addition, performance degradation problems such as sensitivity degradation, resolution degradation and the like can also occur in the long-term operation of the sensor. These all result in that the detection accuracy and stability of the resonant pressure sensor cannot be ensured.
Disclosure of Invention
The application provides a system and a method for detecting a resonance pressure sensor for auxiliary signal conditioning, and aims to solve the technical problems that in the prior art, the resonance pressure sensor is easily affected by environmental factors, and the detection precision and stability are poor.
In view of the above, the present application provides a resonant pressure sensor detection system and method that assists in signal conditioning.
In a first aspect of the present disclosure, a resonant pressure sensor detection system for aiding signal conditioning is provided, the system comprising: the basic information acquisition module is used for connecting the resonance pressure sensor to acquire basic information of equipment, wherein the basic information of the equipment comprises a resonance type and a resonance frequency range; the model construction module is used for acquiring detection precision information, designing a signal conditioning circuit by combining equipment basic information, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity; the drift characteristic analysis module is used for reading the sensing task and combining the drift characteristic analysis network layer in the signal conditioning model framework to determine a first conditioning characteristic; the performance optimization module is used for determining a second conditioning characteristic based on a historical signal conditioning example limited by the detection precision information and combining a performance optimization network layer in a signal conditioning model architecture; the performance feedback verification module is used for setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit based on the first conditioning characteristic and the second conditioning characteristic, carrying out performance feedback verification by combining the sensing task, and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter; the state recognition module is used for setting a signal state recognition model based on the signal conditioning circuit and combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter; and the signal conditioning module is used for connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining the optimal conditioning parameter combination and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
In another aspect of the present disclosure, a method for detecting a resonant pressure sensor for assisting signal conditioning is provided, the method comprising: connecting a resonance pressure sensor, and acquiring equipment basic information, wherein the equipment basic information comprises a resonance type and a resonance frequency range; acquiring detection precision information, designing a signal conditioning circuit by combining equipment basic information, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity; reading a sensing task, analyzing a network layer by combining drift characteristics in a signal conditioning model framework, and determining a first conditioning characteristic; determining a second conditioning characteristic based on a historical signal conditioning example limited by the detection precision information and combining a performance optimization network layer in a signal conditioning model architecture; based on the first conditioning characteristic and the second conditioning characteristic, setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit, performing performance feedback verification in combination with a sensing task, and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter; based on the signal conditioning circuit, setting a signal state identification model by combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter; connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining the optimal conditioning parameter combination, and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Because the basic information acquisition module is connected with the resonance pressure sensor, the resonance type and the resonance frequency range of the equipment are acquired, and necessary parameter bases are provided for the subsequent signal conditioning circuit design and model construction; the model construction module acquires detection precision information, including linearity error characteristics, temperature and humidity drift characteristics and the like, designs a signal conditioning circuit by combining equipment basic information, and constructs a signal conditioning model framework; the drift characteristic analysis module reads a specific sensing task, combines the drift characteristic analysis network layer in the constructed signal conditioning model, determines a first conditioning characteristic, namely a correction characteristic of drift caused by environmental factors, and aims to find out key drift factors influencing measurement accuracy so as to prepare for subsequent correction and compensation; the performance optimization module is used for determining a second conditioning characteristic, namely a conditioning characteristic for optimizing dynamic response and reducing hysteresis error, based on a historical conditioning example under the limit of detection precision and combining with a performance optimization network layer in the signal conditioning model; the performance feedback verification module is used for setting an adaptive correction conditioning layer based on the first conditioning characteristic and the second conditioning characteristic, carrying out closed-loop feedback verification by combining a sensing task, recording various stability parameters, and further improving the reliability of the sensor in actual use through self-adaptive conditioning and real-time feedback; on the basis, the state recognition module synthesizes all stability parameters, and builds a state recognition model oriented to signal conditioning so as to evaluate the signal quality in real time and screen and early warn abnormal fluctuation; the signal conditioning module combines the constructed signal conditioning model with the adaptive correction conditioning layer to determine optimal conditioning parameters, and combines the signal state identification model to correct and characteristic-enhanced condition the sensor signal, so that the technical scheme of improving the detection precision and stability of the resonant pressure sensor is solved, the technical problem that the resonant pressure sensor is easily influenced by environmental factors and has poor detection precision and stability in the prior art is solved, and the technical effect of improving the detection precision and stability of the resonant pressure sensor is achieved by correcting drift caused by the environmental factors, optimizing dynamic response and combining signal state identification.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic diagram of a resonant pressure sensor detection system for auxiliary signal conditioning according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for detecting a resonant pressure sensor for auxiliary signal conditioning according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a basic information acquisition module 11, a model construction module 12, a drift characteristic analysis module 13, a performance optimization module 14, a performance feedback verification module 15, a state identification module 16 and a signal conditioning module 17.
Detailed Description
The technical scheme provided by the application has the following overall thought:
The embodiment of the application provides a system and a method for detecting a resonant pressure sensor for auxiliary signal conditioning. Firstly, acquiring characteristic parameters of a sensor through a basic information acquisition and model construction module, and constructing a signal conditioning model framework. And then, respectively determining key conditioning characteristics aiming at environmental drift and dynamic performance improvement under a signal conditioning model frame by utilizing a drift characteristic analysis and performance optimization module to obtain a first conditioning characteristic and a second conditioning characteristic. And then, a performance feedback verification module is adopted, and the conditioning effect and stability are further improved through self-adaptive correction and closed-loop feedback. Meanwhile, a state recognition module is introduced to evaluate the signal quality in real time and early warn abnormal fluctuation. Finally, through the signal conditioning module, each functional unit is integrated to perform conditioning and self-adaptive correction on the sensor signal, so that the environmental interference factors are eliminated, the dynamic response characteristic is optimized, and the detection precision and stability of the resonant pressure sensor are improved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a resonant pressure sensor detection system for auxiliary signal conditioning, the system comprising:
the basic information acquisition module 11 is used for connecting the resonance pressure sensor and acquiring basic information of equipment, wherein the basic information of the equipment comprises a resonance type and a resonance frequency range.
Specifically, the basic information acquisition module 11 is connected with the resonant pressure sensor through a wired or wireless communication mode, and a stable and reliable data transmission channel is established. After communication is established, the module will send a data read command to the resonant pressure sensor requesting acquisition of device basis information. The basic information of the equipment comprises a resonance type and a resonance frequency range, wherein the resonance type refers to a resonance principle adopted by a sensor, such as capacitive resonance, inductive resonance and the like; the resonance frequency range represents the resonance frequency variation range of the sensor in the normal working state.
The basic information acquisition module 11 can determine the basic working principle and characteristics of the sensor by acquiring resonance type information, so that an important basis is provided for signal conditioning; the acquisition of the resonance frequency range can determine the measurement range and sensitivity of the sensor, and provide necessary reference data for subsequent signal processing.
The model construction module 12 is configured to obtain detection accuracy information, design a signal conditioning circuit in combination with the equipment basic information, and construct a signal conditioning model architecture, where the detection accuracy information includes linearity error characteristic information and drift characteristic information corresponding to temperature and humidity.
Specifically, the model building module 12 first needs to acquire detection accuracy information, where the detection accuracy information includes linearity error characteristic information and drift characteristic information corresponding to temperature and humidity. The linearity error characteristic information characterizes the linear relation between the sensor output signal and the actual measured and the error distribution characteristics generated in the linear fitting process; the drift characteristic information corresponding to the temperature and the humidity reflects the rule and trend of drift of the output signal of the sensor under different environmental temperature and humidity conditions.
After obtaining the detection precision information, the model building module 12 performs comprehensive analysis on the detection precision information and the equipment basic information provided by the basic information obtaining module 11 to design an optimal signal conditioning circuit. The circuit needs to be capable of effectively processing the original signals output by the sensor, reducing the influence of various errors and noise, and carrying out necessary amplification, filtering and other conditioning on the signals so as to meet the requirements of subsequent model construction and performance optimization. After the signal conditioning circuit design is completed, the model building block 12 will build a complete signal conditioning model architecture. The signal conditioning model framework is a multi-level and modularized data processing framework and comprises a drift characteristic analysis network layer and a performance optimization network layer, and the drift characteristic analysis network layer and the performance optimization network layer are used for determining a first conditioning characteristic and a second conditioning characteristic, so that the measuring precision and stability of the sensor are effectively improved, and high-quality signal output is realized.
The drift characteristic analysis module 13 is configured to read the sensing task, analyze the network layer in combination with the drift characteristic in the signal conditioning model architecture, and determine a first conditioning characteristic.
Specifically, the drift characteristic analysis module 13 first needs to read the sensing task. The sensing task contains key information such as specific application scenes, measuring objects, precision requirements and the like of the sensor, and is an important basis for determining conditioning characteristics. By analyzing the sensing task, the main environmental factors affecting the performance of the sensor, such as temperature, humidity, vibration, etc., are identified, and the range of variation and the degree of influence thereof are determined. After the sensing task is acquired, the drift characteristic analysis module 13 combines the sensing task with a drift characteristic analysis network layer in the signal conditioning model architecture to further analyze the drift characteristic of the sensor. The drift characteristic analysis network layer establishes a mathematical mapping relation between the sensor output signal and the environmental factors through mining and analyzing historical data and real-time acquisition data, so that the drift behavior of the sensor is accurately described and predicted.
By taking into account both the sensing task requirements and the drift characteristic analysis results, the drift characteristic analysis module 13 may determine the first conditioning characteristic. The first conditioning characteristic is a signal conditioning characteristic set by indicating drift caused by environmental factors, and aims to eliminate or reduce the influence of drift on measurement accuracy, such as a temperature compensation coefficient, a humidity correction curve, an adaptive filtering threshold value and the like, as much as possible through preprocessing or correcting signals.
The performance optimization module 14 is configured to determine a second conditioning feature based on the historical signal conditioning instance defined by the detection accuracy information and in combination with a performance optimization network layer in the signal conditioning model architecture.
Specifically, the performance optimization module 14 first obtains historical signal conditioning instances under the definition of the detection accuracy information. These examples refer to signal conditioning data and experience accumulated by the sensor during historical operation, including various conditioning parameter settings, algorithm selection, optimization strategies, etc., under specific accuracy requirements. By analyzing and mining the examples, effective methods and rules for optimizing the sensor performance are summarized. After the historical signal conditioning instance is obtained, the performance optimization module 14 combines it with the performance optimization network layer in the signal conditioning model architecture to perform in-depth analysis on the dynamic performance and measurement errors of the sensor. The performance optimization network layer is used for revealing key factors influencing the dynamic performance of the sensor by modeling and simulating the input and output characteristics, frequency response, nonlinear factors and the like of the sensor, and providing theoretical basis for optimizing conditioning strategies.
By taking into account the historical conditioning examples and the performance optimization analysis results, the performance optimization module 14 determines a second conditioning characteristic. The second conditioning characteristic is a signal conditioning characteristic set by indicating dynamic response characteristics and measurement errors of the sensor, and aims to improve the response speed of the sensor, reduce hysteresis errors and reduce repeatability errors through dynamic compensation or correction of signals, so that high-precision and high-stability measurement results, such as dynamic compensation filter parameters, nonlinear correction functions, adaptive gain control thresholds and the like, are realized.
And the performance feedback verification module 15 is configured to set an adaptive correction conditioning layer corresponding to the signal conditioning circuit based on the first conditioning feature and the second conditioning feature, perform performance feedback verification in combination with the sensing task, and record an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter.
Specifically, the performance feedback verification module 15 first sets an adaptive correction conditioning layer corresponding to the signal conditioning circuit according to the first conditioning characteristic and the second conditioning characteristic. The adaptive correction conditioning layer is a dynamically adjustable signal processing unit, and the adaptive correction conditioning layer automatically optimizes the parameter configuration and the processing strategy of the signal conditioning circuit according to the working state and the change of the environmental condition of the sensor through real-time analysis and adaptive adjustment of the conditioning characteristics, so that the dynamic compensation and correction of the performance of the sensor are realized.
After the adaptive correction conditioning layer is set, the performance feedback verification module 15 performs performance feedback verification on the conditioned sensor output signal in combination with a specific sensing task. The verification process evaluates the effectiveness and reliability of the signal conditioning circuit and the adaptive correction conditioning layer by comparing the actual output and the expected output of the sensor, and performs necessary correction and optimization on the conditioning parameters so as to ensure that the performance of the sensor meets the task requirements. At the same time as the performance feedback verification, the performance feedback verification module 15 records the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter of the sensor. The anti-interference stability parameter characterizes the capability of maintaining measurement precision and reliability when the sensor is influenced by factors such as external electromagnetic interference, vibration, impact and the like; the linearity stability parameter reflects the ability of the sensor to maintain good linearity over the entire measurement range; the resolution stability parameter then embodies the ability of the sensor to accurately identify and quantify the small changes measured.
The state recognition module 16 is configured to set a signal state recognition model based on the signal conditioning circuit in combination with the anti-interference stability parameter, the linearity stability parameter, and the resolution stability parameter.
Specifically, the state recognition module 16 first obtains the output signal of the signal conditioning circuit. The signal is subjected to conditioning treatment and adaptive correction, has higher signal-to-noise ratio and measurement accuracy, and can accurately reflect the actual working state of the sensor. The state recognition module collects and analyzes the signals in real time, and extracts key characteristic parameters such as signal amplitude, frequency, phase and the like, and the key characteristic parameters are used as important basis for state recognition. After the signal characteristic parameters are acquired, the state recognition module 16 combines the recorded anti-interference stability parameters, linearity stability parameters and resolution stability parameters to construct a state recognition model of the sensor output signal. The model establishes a mapping relation between signal characteristic parameters and the working state of the sensor through training and learning historical data and real-time acquisition data, and judges and classifies the state of the sensor.
Based on the state recognition model, the state recognition module 16 may monitor the operating state of the sensor in real time and diagnose the abnormality thereof. When the characteristic parameters of the output signals of the sensor have abnormal changes and deviate from the normal working range, the state identification model can rapidly judge the abnormal state of the sensor, such as sensor faults, measurement misalignment, environmental interference and the like, and give an alarm according to the abnormal type and severity to prompt corresponding calibration operation.
And the signal conditioning module 17 is used for connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining an optimal conditioning parameter combination, and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
Specifically, the signal conditioning module 17 first connects the signal conditioning model architecture with the adaptive correction conditioning layer. After the signal conditioning model architecture and the adaptive correction conditioning layer are connected, the signal conditioning module 17 comprehensively considers factors such as performance requirements, working environment, measurement precision and the like of the sensor, and then determines an optimal conditioning parameter combination, wherein parameter settings of various links such as signal amplification, filtering, ADC (analog to digital converter), digital processing and the like are included, such as amplifier gain, filter cut-off frequency, sampling rate, quantization bit number and the like. The signal conditioning module searches an optimal solution in a parameter space, so that the conditioned sensor output signal reaches optimal balance on characteristic parameters such as amplitude, frequency, phase and the like, and the requirements of measurement precision and stability are met. After determining the optimal conditioning parameter combination, the signal conditioning module 17 further combines the signal state recognition model set by the state recognition module 16 to perform comprehensive conditioning processing on the output signal of the resonant pressure sensor. Specifically, the signal conditioning module dynamically adjusts conditioning parameters according to the judging result of the state identification model, and performs self-adaptive correction and compensation on the sensor output signals. For example, when the state recognition model judges that the sensor is in the interference environment, the signal conditioning module automatically increases the damping coefficient of the filter to inhibit the interference signal; when the state recognition model judges that the sensor is faulty or misaligned, the signal conditioning module starts a self-calibration program to recalibrate the sensor, so that accuracy of measured data is ensured.
By organically combining the signal conditioning model framework, the adaptive correction conditioning layer, the optimal conditioning parameter combination and the signal state identification model, the signal conditioning module 17 can realize omnibearing intelligent conditioning of the output signal of the resonant pressure sensor, and effectively improve the detection precision and stability of the sensor.
Further, the model building module includes:
analyzing signal interference characteristics based on the detection precision information to acquire signal interference characteristics; setting a minimized linear error and an allowable error range by combining physical characteristics of linearity error characteristic information in the detection precision information through the signal interference characteristics; and adding the minimized linear error and the allowable error range to the signal conditioning model architecture as constraint information.
In a possible implementation manner, in order to build a signal conditioning model architecture, a model building module firstly obtains detection precision information of a sensor, wherein the information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity. Based on the detection precision information, the model construction module analyzes the interference characteristics of the output signal of the sensor, examines the characteristics of distortion, attenuation, phase shift and the like of the signal under different frequencies, amplitudes, phases and the like, extracts characteristic parameters capable of describing the degree and rule of signal interference, and forms signal interference characteristics. And then, the model construction module combines the signal interference characteristics with linearity error characteristics in the detection precision information, and analyzes physical mechanisms and influence factors generated by the linearity errors. On the basis, the model construction module sets an optimization target for minimizing the linear error, namely, nonlinear distortion of the sensor output signal is reduced as much as possible in the signal conditioning process, so that the sensor output signal is close to an ideal linear response. Meanwhile, the tolerance requirement and the cost limit in practical engineering application are considered, and the model construction module sets an allowable error range, namely, the requirement on linearity is properly relaxed on the premise of ensuring the measurement accuracy so as to balance the performance and the cost. The model building module then embeds the minimized linearity error and the allowable error range as constraints into the signal conditioning model architecture to ensure that the conditioned signal meets the linearity and accuracy requirements.
Further, the model building module further includes:
generating an initial solution set based on the minimized linear error and the allowable error range; based on the initial solution set, calculating fitness according to an objective function corresponding to the signal conditioning model architecture, and obtaining a fitness sequence according to the sequence of the fitness values from large to small; and carrying out self-adaptive iteration according to the adaptability sequence based on the initial solution set.
In a preferred embodiment, the model building module will use the constraint information to generate a set of initial solutions after adding the minimized linearity errors and the allowable error ranges as constraints to the signal conditioning model architecture. The initial solution set contains candidate parameter combinations meeting constraint conditions, such as set values of acupressure and tension, signal amplification factors, filter orders and the like, covers main optimization variables of the signal conditioning model, and provides a good starting point for subsequent fitness calculation and iterative optimization. And then, substituting each candidate parameter combination in the initial solution set into an objective function corresponding to the signal conditioning model architecture by the model construction module for calculation to obtain an adaptability value for measuring the combination quality. The objective function generally comprehensively considers a plurality of performance indexes such as linearity, sensitivity, stability, measurement speed and the like of the sensor, and the mathematical form of the objective function is designed according to actual requirements. The higher the fitness value, the better the parameter combination can meet the performance requirements of the sensor. The model construction module sorts the fitness values of all candidate parameter combinations to obtain a fitness sequence from good to bad, and indicates the direction for subsequent iterative optimization.
Then, the model construction module takes the initial solution set as a starting point, and performs optimization search on the parameter combination through a self-adaptive iterative algorithm according to the sequence of the fitness sequence, for example, a genetic algorithm, a particle swarm optimization algorithm, a simulated annealing algorithm and the like, and the solution set is gradually converged to an optimal solution in the iterative process through continuous selection, intersection, variation and other operations. In the iterative process, the model construction module dynamically adjusts parameters and strategies of an algorithm, such as variation probability, temperature reduction rate and the like, so as to adapt to optimization requirements of different stages and improve convergence speed and stability.
By further optimizing the setting of key parameters such as acupressure and tension on the basis of a signal conditioning model framework, the linearity error of the sensor is minimized and controlled within an allowable range. The self-adaptive iterative optimization method fully utilizes constraint conditions and fitness evaluation, efficiently searches parameter space, and rapidly locks the optimal parameter combination, thereby greatly improving signal conditioning performance and sensor measurement accuracy.
Further, the signal conditioning module further includes:
Based on the matching degree of the sensing task, extracting key features corresponding to the sensing task requirements; updating the signal conditioning circuit through key features corresponding to the sensing task demands to obtain an updated signal conditioning circuit; and based on the updated signal conditioning circuit, performing synchronous signal conditioning on the resonant pressure sensor.
In one possible implementation, after receiving a specific sensing task, the signal conditioning module first performs a comprehensive analysis on the task's requirements to evaluate its degree of matching with the current sensor performance. The matching degree evaluation considers a plurality of dimensions such as measurement range, precision, response speed, working environment and the like so as to judge whether the sensor can be qualified for the task, thereby obtaining the matching degree of the sensing task. On the basis of the matching degree of the sensing task, the signal conditioning module extracts key characteristics closely related to the task requirement, such as the frequency range, amplitude, signal-to-noise ratio requirement and the like of a target signal, and the conditions of temperature, humidity, vibration and the like of a working environment, and provides important basis for the optimization of a subsequent signal conditioning circuit. Then, the signal conditioning module uses the extracted key characteristics as an optimization target to update and improve the existing signal conditioning circuit in a targeted manner, and the signal conditioning module relates to a plurality of aspects such as a topological structure of the conditioning circuit, the selection of key components, the adjustment of parameter values and the like. For example, when the frequency range of the task requirement changes, the signal conditioning module needs to redesign the filter circuit to adjust the cut-off frequency and the attenuation degree of the stop band; when the signal-to-noise ratio of the task requirement is improved, the signal conditioning module needs to increase the gain of the amplifier and optimize the layout to reduce noise interference; when the temperature fluctuation of the working environment is aggravated, the signal conditioning module needs to be added with a temperature compensation circuit so as to reduce the temperature drift effect. The updated signal conditioning circuit matched with the task requirement is obtained by the signal conditioning module through updating and optimizing, and a foundation is laid for subsequent sensor signal conditioning.
And then, the signal conditioning module connects the updated signal conditioning circuit with the resonant pressure sensor to form a complete signal link. On the basis, the signal conditioning module processes and conditions the original signal output by the sensor in real time according to the updated signal conditioning circuit. Meanwhile, the signal conditioning module is communicated with other functional modules such as the state identification module, the performance feedback module and the like in real time, and the conditioning strategy is dynamically adjusted according to the working state of the sensor and the change of the performance index, so that the self-adaptive optimization and the closed-loop control of the signal conditioning are realized.
The signal conditioning circuit is dynamically updated and optimized according to specific sensing task requirements, and the output signal of the resonant pressure sensor is accurately conditioned on the basis, so that the performance of the sensor is optimally matched with the task requirements, and the measuring precision, reliability and applicability are remarkably improved.
Further, the signal conditioning module further includes:
Comparing the historical signal conditioning examples defined by the detection precision information to define a state space, an action space and a reward signal; acquiring sensing task feedback information, and updating the state space and the action space; based on the reward signal, analyzing the feedback information of the sensing task, extracting forward excitation, and establishing a feedback loop through the updated state space and action space.
In a preferred embodiment, first, the signal conditioning module screens a series of related conditioning examples from a case library for conditioning historical signals according to a range defined by the detection precision information, so as to obtain the historical signal conditioning examples, wherein the historical signal conditioning examples comprise information such as sensor states, conditioning actions, performance feedback and the like under different working conditions. On the basis, the signal conditioning module extracts and generalizes and abstracts the characteristics of the historical signal conditioning examples to define a general state space and a general action space. The state space characterizes various state combinations which can be presented by the sensor under different working conditions, such as environmental parameters of temperature, humidity, vibration and the like, output signal characteristics of the sensor and the like; the action space characterizes various conditioning actions which can be taken by the signal conditioning module, such as amplification factor, filtering mode, digital algorithm and the like. Meanwhile, the signal conditioning module also defines a reward signal for judging the quality of each conditioning action in a specific state and guiding the convergence towards the optimization direction.
And then, after the sensor is put into actual work, the signal conditioning module acquires sensing task feedback information in real time, wherein the sensing task feedback information comprises performance indexes such as precision, stability and the like of a measurement result, change conditions of environmental conditions and the like. These feedback information will be compared to the previously defined state space and action space to determine if a new state combination or a possible conditioning action has occurred. If a new situation occurs, the signal conditioning module dynamically updates the state space and the action space to expand the exploration range and improve the adaptability and the robustness of the signal conditioning module. At the same time, these new state and action samples will also be added to the historical example library, providing more empirical data.
Meanwhile, the signal conditioning module analyzes and evaluates the acquired feedback information of the sensing task based on the defined reward signal. When the feedback result shows that a certain conditioning action achieves good performance improvement under a specific state, the action is stimulated in the forward direction, and the corresponding rewarding value is obviously improved. The signal conditioning module will extract these forward stimuli, leading to the exploration and exploitation of the forward motion. Meanwhile, the signal conditioning module and the sensing task establish a closed-loop feedback loop through the updated state space and the updated action space. In this cycle, the performance of the conditioning action will affect the state and performance of the sensor, and the change in state and performance will trigger a new conditioning action, forming a continuous self-optimizing process. With continuous deep and experience continuous accumulation, the signal conditioning module can intelligently adjust conditioning strategies under various complex working conditions, and the adaptability and performance of the sensor are continuously improved.
The successful experience of the history conditioning example is fully used, and the continuous updating and perfecting can be realized according to the real-time feedback, so that the conditioning efficiency is improved, and the continuous optimization of the conditioning performance is ensured. In particular, by introducing the reward signal and the forward excitation mechanism, the conditioning action can be guided to develop towards the optimal direction, the convergence process is accelerated, and excellent robustness and adaptability are shown under the dynamically-changing working condition.
Further, the signal conditioning module further includes:
in the process of carrying out synchronous signal conditioning on the resonant pressure sensor, establishing data communication connection between the resonant pressure sensor and a cloud, and predicting signal quality by using a time sequence to obtain long-term memory degradation fluctuation; performing root cause analysis based on long-term memory degeneration fluctuation, and determining degeneration association factors; based on the degradation association factor, preventive adjustment is performed through fuzzy reasoning.
In one possible implementation, the signal conditioning module connects the sensor to the cloud platform via wired or wireless data communication technology, such as 5G, NB-IoT, while the sensor is operating. On the basis, the signal conditioning module uploads the original signal data acquired by the sensor to the cloud in real time, and a long-term signal quality tracking and predicting mechanism is constructed by utilizing the strong storage and computing capacity of the cloud. The historical signal quality data of the sensor is modeled and trend predicted by using time sequence analysis and machine learning algorithms such as ARIMA, LSTM and the like, and possible quality degradation problems are found in advance. Particularly, the long-term memory effect of the sensor, namely the gradual performance degradation phenomenon of the sensor caused by the factors such as material aging, structure loosening and the like in the long-term use process, is focused. By tracking and quantifying the long-term memory degradation fluctuation, the health state and the residual life of the sensor are accurately grasped, and a decision basis is provided for subsequent maintenance and replacement.
Then, the signal conditioning module carries out deep root cause analysis on the acquired long-term memory degradation fluctuation, and explores the intrinsic cause and key influence factors which lead to the degradation. The material characteristics, structural design, process quality, use environment and other factors of the sensor are comprehensively considered, and the most obvious degradation association factors are extracted from complex data relations by means of data mining and causal reasoning technologies such as association rules, bayesian networks and the like. For example, through correlation analysis of environmental factors such as temperature, humidity, vibration and the like and degradation rate, the high-temperature and high-humidity environment is found to significantly accelerate the aging process of the sensor; through the analysis of the corresponding relation between the internal stress distribution and the degradation part of the sensor, the weak area of the structure is found to be easier to generate microcracks and performance attenuation; by statistical analysis of production information and degradation frequency of batches, suppliers and the like, the process quality irregularity is found to be a main cause of early failure. Through systematic root cause analysis, the signal conditioning module accurately positions degradation influence factors and provides a clear optimization direction for subsequent preventive adjustment.
Then, the signal conditioning module performs preventive adjustment on the working parameters and conditioning strategies of the sensor by adopting a fuzzy reasoning method on the basis of definitely degrading the associated factors so as to delay the degradation process and improve the long-term reliability of the sensor. The fuzzy reasoning is an intelligent decision method based on fuzzy logic, and according to expert knowledge and experience, fuzzy rule mapping between degradation association factors and adjustment strategies is established, and the optimal adjustment strategy for the current degradation state is obtained through calculation and synthesis of fuzzy membership. For example, when the sensor is in a high-temperature and high-humidity environment, fuzzy reasoning dynamically adjusts the working current and sampling frequency of the sensor according to specific values of degradation related factors such as temperature and humidity so as to reduce power consumption and self-heating and delay aging; when microcracks appear in a certain structural weak area of the sensor, the fuzzy inference system properly adjusts the mounting mode and the protection measures of the sensor according to the size and the position of the cracks so as to slow down crack expansion and prevent fracture failure; when the batch quality analysis shows that the sensor performance of a certain batch is unstable, fuzzy reasoning dynamically adjusts the use intensity and maintenance period of the batch of sensors according to the degradation rule and the survival rate so as to balance the performance and the service life. Preventive adjustment realized through fuzzy reasoning, when the performance of the sensor is not obviously degraded, targeted countermeasures are adopted in advance, the service life of the sensor is prolonged to the maximum extent, and the long-term reliability and economy are improved.
The intelligent monitoring and prevention management of the signal quality and performance degradation are realized in the full life cycle of the sensor, the long-term memory degradation rule of the sensor is tracked by utilizing a cloud big data platform and a time sequence prediction technology, key degradation factors are determined through root cause analysis, on the basis, the preventive intelligent adjustment is performed by adopting a fuzzy reasoning technology, the degradation process can be effectively delayed, the quality accident is reduced, and solid guarantee is provided for the long-period stable operation of the sensor.
Further, the embodiment of the application further comprises:
Under extreme conditions, weak links are identified; extracting enhanced key features corresponding to the sensing task demands based on the weak links; and connecting an adjustable element, and carrying out hardware self-adaptive adjustment by combining the enhanced key characteristics corresponding to the sensing task requirements.
In a preferred embodiment, first, the various extreme conditions that the sensor may encounter, such as extreme conditions of ultra-high temperature, ultra-low temperature, strong vibration, strong electromagnetic interference, strong corrosive media, etc., are comprehensively analyzed and identified. After the extreme conditions are identified, the influence and the damage degree of the extreme conditions on each functional link of the sensor are evaluated, and the weakest link which is the weakest and most likely to fail is found. For example, in ultra-high temperature environments, the sensing elements and signal amplification circuitry of the sensor may be subject to failure risk; under a strong vibration environment, the mechanical connection structure and the lead interface of the sensor can be loosened or broken; under the strong electromagnetic interference environment, the signal conditioning circuit of the sensor may be severely polluted and distorted by noise. Through weak link identification, protection and compensation strategies can be formulated in a targeted manner, the weakest and most critical functional links of resource guarantee are concentrated, and the survivability and measurement reliability under extreme conditions are improved.
And then, on the basis of identifying weak links, further analyzing key requirements and characteristic parameters for guaranteeing the normal operation of the sensor under extreme conditions to obtain enhanced key characteristics. The enhanced key features are closely related to specific sensing tasks, and various constraint conditions such as measurement indexes, precision requirements, response time and the like need to be comprehensively considered. For example, in a high temperature environment, in order to ensure the measurement accuracy of the sensor, the temperature drift characteristics and the nonlinear compensation characteristics need to be focused on; in a strong vibration environment, in order to ensure the dynamic response performance of the sensor, the electromechanical coupling characteristic and the vibration compensation characteristic need to be focused; in a strong electromagnetic interference environment, in order to ensure the anti-interference capability of the sensor, important attention is required to be paid to shielding characteristics and filtering characteristics. By analyzing the requirements of sensing tasks and the characteristics of weak links, targeted enhancement key characteristics are extracted, and an optimization target and an evaluation basis are provided for subsequent hardware self-adaptive adjustment.
Then, on the basis of the original signal conditioning circuit of the sensor, an adjustable element such as a variable capacitor, a variable inductor, a variable resistor and the like is additionally connected to form a flexible and controllable parameter adjusting network. On the basis, the extreme environment state and the current enhancement key characteristics of the sensor are comprehensively analyzed, the optimal parameter values of all the adjustable elements are calculated in real time, and the self-adaptive adjustment is carried out, so that the performance state of the sensor is dynamically matched with the enhancement requirements all the time. For example, in a high-temperature environment, the temperature drift of the sensitive element is automatically compensated by adjusting a temperature compensation resistor in the bridge circuit; in a strong vibration environment, the influence of vibration noise is reduced in a self-adaptive manner by adjusting the cut-off frequency of the low-pass filter; in a strong electromagnetic interference environment, the common mode rejection ratio of the amplifier is adjusted, so that the anti-interference capability of the circuit is adaptively improved. Through flexible connection and intelligent self-adaptive adjustment of the adjustable element, accurate reinforcement can be implemented on weak links of the sensor according to different extreme working conditions, the environmental adaptability and the robustness of the sensor are obviously improved from a hardware level, and the measurement performance and the reliability of the sensor under severe conditions are ensured.
In summary, the resonant pressure sensor detection system for auxiliary signal conditioning provided by the embodiment of the application has the following technical effects:
The basic information acquisition module is used for being connected with the resonance pressure sensor to acquire basic information of equipment, wherein the basic information of the equipment comprises a resonance type and a resonance frequency range, and necessary preconditions are provided for subsequent signal conditioning. The model construction module is used for acquiring detection precision information, designing a signal conditioning circuit by combining the equipment basic information, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity, and a model foundation is laid for follow-up fine conditioning. And the drift characteristic analysis module is used for reading the sensing task, analyzing a network layer by combining the drift characteristic in the signal conditioning model framework, and determining a first conditioning characteristic so as to pertinently inhibit precision drift caused by environmental interference. And the performance optimization module is used for determining a second conditioning characteristic based on the historical signal conditioning example defined by the detection precision information and combining with a performance optimization network layer in the signal conditioning model framework, and is used for guiding conditioning strategy formulation for improving the performance. And the performance feedback verification module is used for setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit based on the first conditioning characteristic and the second conditioning characteristic, carrying out performance feedback verification by combining the sensing task, recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter, dynamically evaluating and improving the conditioning effect through closed-loop feedback of the actual sensing task, and obtaining a refined stability parameter index. The state recognition module is used for setting a signal state recognition model based on the signal conditioning circuit and combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter, evaluating the signal quality in real time, and timely discriminating abnormal fluctuation and early warning the performance degradation problem possibly occurring. And the signal conditioning module is used for connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining the optimal conditioning parameter combination, and carrying out signal conditioning on the resonant pressure sensor by combining the signal state identification model so as to improve the detection precision and stability of the resonant pressure sensor.
Example two
Based on the same inventive concept as the resonant pressure sensor detection system for auxiliary signal conditioning in the foregoing embodiment, as shown in fig. 2, an embodiment of the present application provides a method for detecting a resonant pressure sensor for auxiliary signal conditioning, including:
Connecting a resonance pressure sensor, and acquiring equipment basic information, wherein the equipment basic information comprises a resonance type and a resonance frequency range;
Acquiring detection precision information, designing a signal conditioning circuit by combining the basic information of the equipment, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity;
reading a sensing task, analyzing a network layer by combining drift characteristics in the signal conditioning model framework, and determining a first conditioning characteristic;
Determining a second conditioning characteristic based on the historical signal conditioning example limited by the detection precision information and combining with a performance optimization network layer in the signal conditioning model architecture;
Based on the first conditioning characteristic and the second conditioning characteristic, setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit, performing performance feedback verification in combination with the sensing task, and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter;
setting a signal state identification model based on the signal conditioning circuit by combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter;
and connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining an optimal conditioning parameter combination, and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
Further, the embodiment of the application further comprises:
Analyzing signal interference characteristics based on the detection precision information to acquire signal interference characteristics;
setting a minimized linear error and an allowable error range by combining physical characteristics of linearity error characteristic information in the detection precision information through the signal interference characteristics;
And adding the minimized linear error and the allowable error range to the signal conditioning model architecture as constraint information.
Further, the embodiment of the application further comprises:
generating an initial solution set based on the minimized linear error and the allowable error range;
Based on the initial solution set, calculating fitness according to an objective function corresponding to the signal conditioning model architecture, and obtaining a fitness sequence according to the sequence of the fitness values from large to small;
And carrying out self-adaptive iteration according to the adaptability sequence based on the initial solution set.
Further, the embodiment of the application further comprises:
Based on the matching degree of the sensing task, extracting key features corresponding to the sensing task requirements;
Updating the signal conditioning circuit through key features corresponding to the sensing task demands to obtain an updated signal conditioning circuit;
And based on the updated signal conditioning circuit, performing synchronous signal conditioning on the resonant pressure sensor.
Further, the embodiment of the application further comprises:
Comparing the historical signal conditioning examples defined by the detection precision information to define a state space, an action space and a reward signal;
acquiring sensing task feedback information, and updating the state space and the action space;
Based on the reward signal, analyzing the feedback information of the sensing task, extracting forward excitation, and establishing a feedback loop through the updated state space and action space.
Further, the embodiment of the application further comprises:
in the process of carrying out synchronous signal conditioning on the resonant pressure sensor, establishing data communication connection between the resonant pressure sensor and a cloud, and predicting signal quality by using a time sequence to obtain long-term memory degradation fluctuation;
Performing root cause analysis based on long-term memory degeneration fluctuation, and determining degeneration association factors;
Based on the degradation association factor, preventive adjustment is performed through fuzzy reasoning.
Further, the embodiment of the application further comprises:
Under extreme conditions, weak links are identified;
Extracting enhanced key features corresponding to the sensing task demands based on the weak links;
And connecting an adjustable element, and carrying out hardware self-adaptive adjustment by combining the enhanced key characteristics corresponding to the sensing task requirements.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. A resonant pressure sensor detection system for auxiliary signal conditioning, comprising:
The basic information acquisition module is used for connecting the resonance pressure sensor and acquiring basic information of equipment, wherein the basic information of the equipment comprises a resonance type and a resonance frequency range;
The model construction module is used for acquiring detection precision information, designing a signal conditioning circuit by combining the equipment basic information, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity;
The drift characteristic analysis module is used for reading the sensing task and combining the drift characteristic analysis network layer in the signal conditioning model framework to determine a first conditioning characteristic;
the performance optimization module is used for determining a second conditioning characteristic based on the historical signal conditioning example limited by the detection precision information and combining with a performance optimization network layer in the signal conditioning model architecture;
The performance feedback verification module is used for setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit based on the first conditioning characteristic and the second conditioning characteristic, carrying out performance feedback verification by combining the sensing task, and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter;
The state identification module is used for setting a signal state identification model based on the signal conditioning circuit and combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter;
And the signal conditioning module is used for connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining an optimal conditioning parameter combination, and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
2. The auxiliary signal conditioning resonant pressure sensor detection system of claim 1, wherein the model building module comprises:
Analyzing signal interference characteristics based on the detection precision information to acquire signal interference characteristics;
setting a minimized linear error and an allowable error range by combining physical characteristics of linearity error characteristic information in the detection precision information through the signal interference characteristics;
And adding the minimized linear error and the allowable error range to the signal conditioning model architecture as constraint information.
3. The auxiliary signal conditioning resonant pressure sensor detection system of claim 2, wherein the model building module further comprises:
generating an initial solution set based on the minimized linear error and the allowable error range;
Based on the initial solution set, calculating fitness according to an objective function corresponding to the signal conditioning model architecture, and obtaining a fitness sequence according to the sequence of the fitness values from large to small;
And carrying out self-adaptive iteration according to the adaptability sequence based on the initial solution set.
4. The auxiliary signal conditioning resonant pressure sensor detection system of claim 2, wherein the signal conditioning module further comprises:
Based on the matching degree of the sensing task, extracting key features corresponding to the sensing task requirements;
Updating the signal conditioning circuit through key features corresponding to the sensing task demands to obtain an updated signal conditioning circuit;
And based on the updated signal conditioning circuit, performing synchronous signal conditioning on the resonant pressure sensor.
5. The auxiliary signal conditioning resonant pressure sensor detection system of claim 4, wherein the signal conditioning module further comprises:
Comparing the historical signal conditioning examples defined by the detection precision information to define a state space, an action space and a reward signal;
acquiring sensing task feedback information, and updating the state space and the action space;
Based on the reward signal, analyzing the feedback information of the sensing task, extracting forward excitation, and establishing a feedback loop through the updated state space and action space.
6. The auxiliary signal conditioning resonant pressure sensor detection system of claim 5, wherein the signal conditioning module further comprises:
in the process of carrying out synchronous signal conditioning on the resonant pressure sensor, establishing data communication connection between the resonant pressure sensor and a cloud, and predicting signal quality by using a time sequence to obtain long-term memory degradation fluctuation;
Performing root cause analysis based on long-term memory degeneration fluctuation, and determining degeneration association factors;
Based on the degradation association factor, preventive adjustment is performed through fuzzy reasoning.
7. The auxiliary signal conditioning resonant pressure sensor detection system of claim 4, wherein weak links are identified under extreme conditions;
Extracting enhanced key features corresponding to the sensing task demands based on the weak links;
And connecting an adjustable element, and carrying out hardware self-adaptive adjustment by combining the enhanced key characteristics corresponding to the sensing task requirements.
8. A method of detecting a resonant pressure sensor for auxiliary signal conditioning, the method comprising:
Connecting a resonance pressure sensor, and acquiring equipment basic information, wherein the equipment basic information comprises a resonance type and a resonance frequency range;
Acquiring detection precision information, designing a signal conditioning circuit by combining the basic information of the equipment, and constructing a signal conditioning model framework, wherein the detection precision information comprises linearity error characteristic information and drift characteristic information corresponding to temperature and humidity;
reading a sensing task, analyzing a network layer by combining drift characteristics in the signal conditioning model framework, and determining a first conditioning characteristic;
Determining a second conditioning characteristic based on the historical signal conditioning example limited by the detection precision information and combining with a performance optimization network layer in the signal conditioning model architecture;
Based on the first conditioning characteristic and the second conditioning characteristic, setting an adaptive correction conditioning layer corresponding to the signal conditioning circuit, performing performance feedback verification in combination with the sensing task, and recording an anti-interference stability parameter, a linearity stability parameter and a resolution stability parameter;
setting a signal state identification model based on the signal conditioning circuit by combining the anti-interference stability parameter, the linearity stability parameter and the resolution stability parameter;
and connecting the signal conditioning model framework with the adaptive correction conditioning layer, determining an optimal conditioning parameter combination, and performing signal conditioning on the resonant pressure sensor by combining the signal state identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410773910.7A CN118332484B (en) | 2024-06-17 | 2024-06-17 | Resonance pressure sensor detection system and method for auxiliary signal conditioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410773910.7A CN118332484B (en) | 2024-06-17 | 2024-06-17 | Resonance pressure sensor detection system and method for auxiliary signal conditioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118332484A CN118332484A (en) | 2024-07-12 |
| CN118332484B true CN118332484B (en) | 2024-08-09 |
Family
ID=91770505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410773910.7A Active CN118332484B (en) | 2024-06-17 | 2024-06-17 | Resonance pressure sensor detection system and method for auxiliary signal conditioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118332484B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109073381A (en) * | 2016-05-11 | 2018-12-21 | 株式会社村田制作所 | Secondary sensing loop with force feedback ability |
| CN114459338A (en) * | 2022-01-05 | 2022-05-10 | 中国船舶重工集团公司七五0试验场 | Underwater vehicle depth sensing signal self-adaptive control system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3635865A1 (en) * | 2017-05-24 | 2020-04-15 | Anlotek Limited | Apparatus and method for controlling a resonator |
| CN117724348B (en) * | 2024-02-06 | 2024-04-16 | 深圳市万斯得自动化设备有限公司 | Accurate pressure regulation and control system based on explosion testing machine |
| CN118090030A (en) * | 2024-02-29 | 2024-05-28 | 江苏无线电厂有限公司 | High-precision silicon resonance barometer for dynamic measurement |
-
2024
- 2024-06-17 CN CN202410773910.7A patent/CN118332484B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109073381A (en) * | 2016-05-11 | 2018-12-21 | 株式会社村田制作所 | Secondary sensing loop with force feedback ability |
| CN114459338A (en) * | 2022-01-05 | 2022-05-10 | 中国船舶重工集团公司七五0试验场 | Underwater vehicle depth sensing signal self-adaptive control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118332484A (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117798744B (en) | Method for monitoring running state of numerical control machine tool | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN110717543B (en) | Double window concept drift detection method based on sample distribution statistical test | |
| CN110109441B (en) | Laser inertial measurement unit fault prediction method and system | |
| CN113325721B (en) | Model-free adaptive control method and system for industrial system | |
| KR20210024106A (en) | Controller for controlling the technical system and method for configuring the controller | |
| CN117473411A (en) | Bearing life prediction method based on improved transducer model | |
| CN116629136A (en) | Method, device, equipment and storage medium for updating digital twin model | |
| CN118332484B (en) | Resonance pressure sensor detection system and method for auxiliary signal conditioning | |
| CN115616163A (en) | Gas accurate preparation and concentration measurement system | |
| CN118330447B (en) | Semiconductor integrated circuit test system | |
| CN117369349B (en) | Management system of remote monitoring intelligent robot | |
| CN118536082A (en) | Inverter fault prediction method and device based on artificial intelligence, terminal equipment and storage medium | |
| CN115659201A (en) | Gas concentration detection method and monitoring system for Internet of things | |
| CN118249810B (en) | Method and system for testing multichannel AD/DA (analog to digital) chip | |
| CN111784010B (en) | Method and system for predicting residual service life of electric gate valve | |
| Zheng et al. | Research on predicting remaining useful life of equipment based on health index | |
| CN118707888B (en) | Multi-data fusion control method of temperature, pressure, flow and humidity integrated monitor | |
| CN118329128B (en) | Method for monitoring running state of electromechanical equipment for remote intelligent processing | |
| CN118091522B (en) | Testing and checking system and method for transformer substation | |
| CN118550202B (en) | Welding control method, electronic device, and computer-readable storage medium | |
| KR102572628B1 (en) | Integrated management system for production facilities | |
| CN118448182B (en) | Balanced heating method for chip capacitor processing | |
| CN118464164B (en) | Petroleum and petrochemical flowmeter calibration method based on Coriolis force | |
| CN118449984A (en) | Sparse point location association sensing method suitable for building monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |