CN118582662A - Air storage tank intelligent management method and system based on air pressure monitoring - Google Patents
Air storage tank intelligent management method and system based on air pressure monitoring Download PDFInfo
- Publication number
- CN118582662A CN118582662A CN202411073926.3A CN202411073926A CN118582662A CN 118582662 A CN118582662 A CN 118582662A CN 202411073926 A CN202411073926 A CN 202411073926A CN 118582662 A CN118582662 A CN 118582662A
- Authority
- CN
- China
- Prior art keywords
- air pressure
- data
- pressure data
- storage tank
- air
- 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.)
- Granted
Links
- 238000003860 storage Methods 0.000 title claims abstract description 57
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000007726 management method Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 50
- 230000008569 process Effects 0.000 claims description 32
- 230000008859 change Effects 0.000 claims description 24
- 230000003044 adaptive effect Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 15
- 238000009499 grossing Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 8
- 230000001629 suppression Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 7
- 230000003247 decreasing effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 239000007789 gas Substances 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
Landscapes
- Control Of Fluid Pressure (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an intelligent management method and system for an air storage tank based on air pressure monitoring, which relate to the technical field of automatic control of air storage tank valves and comprise the following steps: s1, presetting an air pressure acquisition period T, and acquiring air pressure data of an air storage tank in the period T in real time; s2, preprocessing the collected air pressure data to obtain denoised air pressure data; s3, establishing a multidimensional fuzzy logic control algorithm model aiming at the denoised air pressure data, and obtaining an actual control instruction of an air storage tank valve by using the algorithm model; and S4, adjusting a valve of the air storage tank according to the actual control instruction, and repeating the step S1. The beneficial effects are that: according to the air pressure data denoising method and device, the collected air pressure data are denoised through preprocessing, the accuracy of the data is improved, the actual control quantity of the valve is obtained based on intelligent control of the monitored air pressure data, accurate control of the valve is achieved, and the operation stability of the air storage tank system is ensured.
Description
Technical Field
The invention relates to the technical field of automatic control of air storage tank valves, in particular to an air storage tank intelligent management method and system based on air pressure monitoring.
Background
The gas storage tank is used as an important storage device in industrial production and storage processes, and is widely applied to storage and conveying systems of various gases. The pressure within the reservoir is an important parameter for reservoir safety. Air pressure management of air tanks is also an important means for industrial production and storage safety operations, for example, during natural gas transportation, the air pressure within the air tanks must be maintained within a certain range to ensure proper operation of the transportation piping and to prevent gas leakage.
With the development of industrial automation and intellectualization, the requirements for monitoring and managing the air pressure of the air storage tank are also higher and higher. Traditional manual monitoring and adjustment methods have failed to meet the needs of the modern industry. In order to improve the safety, reliability and efficiency of the system, an intelligent system capable of monitoring the air pressure in the air storage tank in real time and performing automatic management according to the monitored data is urgently needed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an intelligent management method and system for an air storage tank based on air pressure monitoring, which denoise collected air pressure data through preprocessing, the accuracy of the data is improved, the actual control quantity of the valve is obtained by intelligent control based on the monitored air pressure data, the accurate control of the valve is realized, and the operation stability of the air storage tank system is ensured.
The aim of the invention is achieved by the following technical measures: an intelligent management method of an air storage tank based on air pressure monitoring comprises the following steps:
S1, presetting an air pressure acquisition period T, and acquiring air pressure data of an air storage tank in the period T in real time;
s2, preprocessing the collected air pressure data to obtain denoised air pressure data;
S3, establishing a multidimensional fuzzy logic control algorithm model aiming at the denoised air pressure data, and obtaining an actual control instruction of the air storage tank valve by utilizing the algorithm model, wherein the multidimensional fuzzy logic control algorithm model comprises a multidimensional fuzzification process, a multidimensional fuzzification process and a multidimensional defuzzification process, the multidimensional fuzzification process is used for converting the air pressure data and the change trend data of the air pressure data into a fuzzy set, the multidimensional fuzzification process is used for realizing reasoning according to a fuzzy rule base based on the fuzzy set so as to generate an intermediate control instruction, and the multidimensional defuzzification process is used for converting the intermediate control instruction into the actual control instruction;
and S4, adjusting a valve of the air storage tank according to the actual control instruction, and repeating the step S1.
Further, in S2, the collected air pressure data is preprocessed by using a multi-layer dynamic adaptive filtering algorithm model, where the multi-layer dynamic adaptive filtering algorithm model includes a frequency domain processing layer, a time domain processing layer and an adaptive adjustment layer, the frequency domain processing layer is configured to convert a time domain signal of the collected air pressure data into a frequency domain signal to remove high frequency noise, the frequency domain signal processed by the frequency domain processing layer is transformed into a time domain signal by inverse transformation and then enters the time domain processing layer, the time domain processing layer is configured to smooth the time domain signal to reduce random noise, and the adaptive adjustment layer is configured to dynamically adjust the time domain signal processed by the time domain processing layer to obtain the air pressure data.
Further, the frequency domain processing layer converts the time domain signal into the frequency domain signal by adopting a complex waveform transformation algorithm model, wherein the complex waveform transformation algorithm model is thatWherein, the method comprises the steps of, wherein,Is a frequency domain signal of the air pressure data,As a function of the frequency variation,Is a time domain signal, inThe start-up sub-data of the moment,Is the time domain sample point, the kth time point,In order to be able to take time,The number of total samples for the time domain signal,Is a complex exponential function of the number,In units of imaginary numbers,Is a waveform functionAs a gaussian function or a wavelet function,Is an integral variable, andRelated variables.
Further, the time domain processing layer adopts a time-varying weighted smoothing algorithm model to carry out smoothing processing on the time domain signals, and the time-varying weighted smoothing algorithm model is thatWherein, the method comprises the steps of, wherein,For the smoothed barometric pressure estimate,For time-varying weighting coefficients, at time t and window positionWeights at the positions satisfy,Is the smooth window length, and the weight is set according to the distance from the center point.
Further, the adaptive adjustment layer adopts an adaptive noise suppression algorithm model to dynamically adjust the time domain signal processed by the time domain processing layer, and the adaptive noise suppression algorithm model is thatWherein, the method comprises the steps of, wherein,For the adaptive noise suppressed barometric pressure data,The adaptive weight is dynamically adjusted along with time, and the adaptive weight dynamic adjustment mode adopts the ratio of the noise variance to the sum of the noise variance and the signal variance.
Further, the multidimensional blurring process includes dividing barometric data and change trend data of the barometric data into three data sets respectively, and converting an actual data set into a blurred set by adopting a membership function model for each data set, wherein the membership function model is as followsWherein, the method comprises the steps of, wherein,As a function of the degree of membership,In order to adjust the parameters of the device,For input barometric dataOr trend data of air pressure data,The center value represents the middle position of the fuzzy set.
Further, the multidimensional fuzzy reasoning process comprises the steps of establishing a fuzzy rule base between the air pressure data and the change trend data of the air pressure data and the opening degree of the valve of the air storage tank, obtaining an intermediate control instruction based on the fuzzy rule base,Wherein, the method comprises the steps of, wherein,In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of the membership function calculated based on the membership function model,For the weight of the air storage tank valve control action based on the fuzzy rule base,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.
Further, the multi-dimensional defuzzification process converts intermediate control commands into actual control commands by means of weighted averaging,Wherein, the method comprises the steps of, wherein,In order to actually control the amount of the liquid,In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of the membership function calculated based on the membership function model,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.
The air storage tank intelligent management system based on air pressure monitoring comprises an air pressure acquisition module, a data processing module, an intelligent control module and a communication module, wherein the air pressure acquisition module is used for acquiring air pressure data and transmitting the air pressure data to the data processing module, the data processing module is used for preprocessing the air pressure data and transmitting the processed air pressure data to the intelligent control module and the communication module, the intelligent control module is used for calculating the actual control quantity of the air storage tank, and the communication module is used for realizing communication of all modules in the air storage tank intelligent management system and realizing communication with a remote monitoring platform.
Further, the alarm device also comprises an alarm module, wherein the alarm module is connected with the data processing module and is used for sending alarm information.
Compared with the prior art, the invention has the beneficial effects that:
1. The multi-layer dynamic self-adaptive filtering algorithm model is utilized to preprocess the air pressure data through the frequency domain processing layer, the time domain processing layer and the self-adaptive adjusting layer, so that high-frequency noise and random noise can be effectively eliminated; the frequency domain processing layer converts the time domain signal into the frequency domain by using a complex waveform transformation algorithm model, and removes high-frequency components; the time domain processing layer uses a time-varying weighted smoothing algorithm model to carry out smoothing processing on the signals, so that random noise is reduced; the self-adaptive adjusting layer uses the self-adaptive noise suppression algorithm model to dynamically adjust the data, so that the accuracy of the data is further improved.
2. Automatically adjusting the inlet and outlet valve of the air storage tank by using a multidimensional fuzzy logic control algorithm model; the multidimensional fuzzy logic control algorithm model comprises a multidimensional fuzzification process, a multidimensional fuzzy reasoning process and a multidimensional defuzzification process; the air pressure data and the change trend data of the air pressure data after the self-adaptive noise suppression are converted into fuzzy sets, reasoning is carried out according to a fuzzy rule base, an intermediate control instruction is generated, and a specific actual control quantity is obtained through a defuzzification process, so that accurate control of a valve is realized, and the stable operation of an air storage tank system is ensured.
3. When the air pressure exceeds the preset safety range, the alarm module of the system can timely inform related personnel to process in various modes such as audible and visual alarm, short message notification, remote monitoring platform alarm and the like, so that the safe operation of the system is ensured.
The invention is described in detail below with reference to the drawings and the detailed description.
Drawings
Fig. 1 is a schematic structural view of the present invention.
Detailed Description
S1, presetting an air pressure acquisition period T, and acquiring air pressure data of an air storage tank in the period T in real time. The pressure sensor is arranged in the air storage tank and used for collecting air pressure data in real time, and the sensor can collect the air pressure data in microsecond level, so that the accuracy and the instantaneity of the data are ensured.
S2, preprocessing the collected air pressure data by adopting a multi-layer dynamic self-adaptive filtering algorithm model, wherein the multi-layer dynamic self-adaptive filtering algorithm model comprises a frequency domain processing layer, a time domain processing layer and a self-adaptive adjusting layer, and the frequency domain processing layer is used for converting time domain signals of the collected air pressure data into frequency domain signals so as to remove high-frequency noise.
The method comprises the steps of converting a time domain signal into a frequency domain signal by adopting a complex waveform transformation algorithm model at a frequency domain processing layer, wherein the complex waveform transformation algorithm model is as follows:
,
wherein, Is a frequency domain signal of the air pressure data,As a function of the frequency variation,Is a time domain signal, inThe start-up sub-data of the moment,Is the time domain sample point, the kth time point,In order to be able to take time,The number of total samples for the time domain signal,Is a complex exponential function, converts a time domain signal into a frequency domain signal,In units of imaginary numbers,Is a waveform function representing a function of smoothing and filtering a time domain signal, the waveform functionAs a gaussian function or a wavelet function,Is an integral variable, andRelated variables. The high frequency component is removed by setting the frequency threshold value, so that noise interference is reduced.
In the frequency domain processing, the appropriate waveform function is first selectedSuch as a gaussian function or a wavelet function. The time domain signal is converted into a frequency domain signal using numerical integration and complex exponential operations. By setting the frequency threshold, high frequency components in the frequency domain are removed. The signal component above the threshold frequency will be set to zero resulting in a filtered frequency domain signal.
The frequency domain signal processed by the frequency domain processing layer is converted into a time domain signal by inverse transformation and then enters the time domain processing layer, and the frequency domain signal processed by the inverse transformation is usedConverting back to the time domain signal to obtain a preliminarily filtered time domain signal. The inverse transform formula is:
。
after the inverse transformation, the time domain signal is transmitted to a time domain processing layer, and the time domain signal is smoothed by the time domain processing layer to reduce random noise. The time-varying weighted smoothing algorithm model is as follows:
,
wherein, For the smoothed barometric pressure estimate,For time-varying weighting coefficients, at time t and window positionWeights at the positions satisfy,The smoothed window length determines the range of the weighted average. The weights are set according to distance from the center point, such as with a Gaussian distribution. And smoothing the data through time-varying weighted smoothing, so as to reduce random noise.
And the self-adaptive adjusting layer adopts a self-adaptive noise suppression algorithm model to dynamically adjust the time domain signal processed by the time domain processing layer so as to obtain air pressure data. The adaptive noise suppression algorithm model is as follows:
,
wherein, For the adaptive noise suppressed barometric pressure data,The adaptive weight is dynamically adjusted along with time, and the adaptive weight dynamic adjustment mode adopts the ratio of the noise variance to the sum of the noise variance and the signal variance.
S3, establishing a multidimensional fuzzy logic control algorithm model aiming at the denoised air pressure data, and obtaining an actual control instruction of an air storage tank valve by utilizing the algorithm model, wherein the multidimensional fuzzy logic control algorithm model comprises a multidimensional fuzzification process, a multidimensional fuzzification process and a multidimensional defuzzification process, the multidimensional fuzzification process is used for converting the air pressure data and the change trend data of the air pressure data into fuzzy sets, and the multidimensional fuzzification process comprises dividing the air pressure data and the change trend data of the air pressure data into three data sets respectively, for example, dividing the air pressure data into three data sets: three data sets of Low (Low), medium (Medium), and High (High) divide the trend data of the air pressure data into: three data sets, e.g., barometric data, for Descent (DECREASING), plateau (Stable), ascent (INCREASING): low (Low) of 0-30 kPa, medium (Medium) of 20-50 kPa, and High (High) of 40-70 kPa. Similarly, when defining a fuzzy set of trend data, the following boundaries may be selected: the Drop (DECREASING) is-10-2 kPa/s, the Stable (Stable) is-3-3 kPa/s, and the rise (INCREASING) is 2-10 kPa/s.
The change data of the air pressure data is the change rate corresponding to the air pressure data acquired at the time t, specifically, the air pressure data can be drawn into an air pressure curve, and the slope of a tangent line of a point on the curve corresponding to the time t can be used as the change trend data of the air pressure data. And converting the actual data set into a fuzzy set by adopting a membership function model aiming at each data set, wherein the membership function model is as follows:
,
wherein, As a function of the degree of membership,In order to adjust the parameters of the device,For input barometric dataOr trend data of air pressure data,The center value represents the middle position of the fuzzy set.
Calculating the membership degree of each input data belonging to each fuzzy set by using a membership function model, and regarding the air pressure dataAnd trend data of change in air pressure dataThe membership degree is calculated as:
,
,
wherein, AndMembership degrees of the air pressure data and the change trend data of the air pressure data respectively,AndIn order to adjust the parameters of the device,AndIs the center value of the air pressure data and the change trend data of the air pressure data.
Adjusting parametersAndThe determination method of (2) is as follows:
Given empirically AndThe initial value may be chosen to be a small positive number, for example 0.1, the choice of initial value need not be particularly accurate but should be small enough to avoid excessive initial errors. Calculating preliminary membership function by using initial value, and observing air pressure dataTrend data of air pressure dataIs a blurring effect of (a). Adjustment using optimization algorithmAndTo minimize control errors and system response times. Common optimization algorithms include Genetic Algorithm (GA), particle Swarm Optimization (PSO), and gradient descent. The optimization steps are as follows:
Defining an objective function: the objective function may be the sum of squares of the control errors or the system response time. For example:
,
wherein, Is a function of the object to be measured,AndIs the air pressure data and the set value of the change trend data of the air pressure data,AndIs the actual output value of the air pressure data and the variation trend data of the air pressure data,Is a weight factor.
Selecting a suitable optimization algorithm, such as a genetic algorithm, initializing a population, setting a crossover rate and a mutation rate, and running the algorithm until the objective function converges. Adjusting according to the optimized resultAndAnd (3) recalculating the membership function and verifying the fuzzy control effect.
Optimized parametersAndVerification in an actual system is needed, and the influence of the verification on the control effect is observed. If the control effect is not ideal, secondary optimization can be performed, and parameters are further adjusted, for example, after optimization, the obtained adjustment parameters are:,。
The multidimensional fuzzy reasoning process is used for realizing reasoning according to a fuzzy rule base based on a fuzzy set to generate an intermediate control instruction, and comprises the steps of establishing the fuzzy rule base between air pressure data and change trend data of the air pressure data and the opening degree of a valve of the air storage tank, for example, establishing the fuzzy rule base according to experience or experimental data:
rule 1: if it is Low andWhen descending, the valve is opened. When the air pressure data is low and the trend of change is decreasing, it means that the air pressure is highly likely to further decrease, so that a rapid increase in air pressure is required and the valve should be opened.
Rule 2: if it isLow andAt steady, the valve is opened. When the air pressure data is low and the variation trend is stable, although the air pressure is low, there is no significant decrease trend, so the valve should still be opened to raise the air pressure.
Rule 3: if it isLow andWhen the valve is lifted, the valve is opened. When the air pressure data is low and the variation trend is rising, the air pressure is low but the air pressure has a rising trend, so the valve can be properly opened to smoothly increase the air pressure.
Rule 4: if it isMiddle and (C)When descending, the valve is opened. When the air pressure data and the change trend are decreasing, the air pressure is decreasing, the air pressure needs to be properly increased, and the valve is opened.
Rule 5: if it isMiddle and (C)At steady state, the valve is open. When the air pressure data is in the air pressure data and the change trend is stable, the current air pressure is kept, and the valve is opened.
Rule 6: if it isMiddle and (C)When the valve is lifted, the valve is closed. When the air pressure data and the change trend are increased, the air pressure is increased, and the valve is closed to prevent the air pressure from being too high.
Rule 7: if it isHigh and highWhen the valve descends, the valve opens. When the air pressure data is high and the variation trend is descending, the air pressure is high but the air pressure has a descending trend, and the valve is opened to properly reduce the air pressure.
Rule 8: if it isHigh and highAt steady, the valve is closed. When the air pressure data is high and the change trend is stable, the current air pressure is kept, and the valve is closed.
Rule 9: if it isHigh and highWhen the valve is lifted, the valve is closed. When the air pressure data is high and the change trend is rising, the air pressure is high and continues to rise, and the valve is closed to prevent the overpressure.
Obtaining an intermediate control instruction based on a fuzzy rule base:
,
wherein, In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of membership functions calculated based on membership function model, i.eWherein, the method comprises the steps of, wherein,Is the air pressure data and the membership degree of the change trend data of the air pressure data,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.For the weight of the control action of the air storage tank valve based on the fuzzy rule base, each rule corresponds to one control action, such as opening, closing and the like in the rule, the control action corresponds to a specific control quantity, and the weight of the control action is set based on the specific control quantity, for example:
Full-open: ;
opening: ;
and (3) opening: ;
Closing: ;
Closing: 。
and mapping the input multidimensional fuzzy set to the intermediate control output through a multidimensional fuzzy rule base to realize multidimensional fuzzy reasoning.
The multidimensional defuzzification process converts an intermediate control instruction into an actual control instruction in a weighted average mode:
,
wherein, In order to actually control the amount of the liquid,In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of the membership function calculated based on the membership function model,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.
And converting the multidimensional fuzzy control instruction into an actual operation amount by a multidimensional weighted average mode, so as to realize accurate control of the valve.
And S4, adjusting a valve of the air storage tank according to the actual control instruction, and repeating the step S1.
As shown in FIG. 1, the air storage tank intelligent management system based on air pressure monitoring is based on the air storage tank intelligent management method based on air pressure monitoring, and comprises an air pressure acquisition module, a data processing module, an intelligent control module and a communication module, wherein the air pressure acquisition module is used for acquiring air pressure data and transmitting the air pressure data to the data processing module, the data processing module is used for preprocessing the air pressure data and transmitting the processed air pressure data to the intelligent control module and the communication module, the intelligent control module is used for calculating the actual control quantity of the air storage tank, and the communication module is used for realizing the communication of each module in the air storage tank intelligent management system and realizing the communication with a remote monitoring platform.
The alarm device also comprises an alarm module, wherein the alarm module is connected with the data processing module and is used for sending alarm information. Triggering an alarm when the air pressure exceeds a preset safety range; the alarm module timely informs related personnel to process through various modes such as audible and visual alarm, short message notification, remote monitoring platform alarm and the like.
In the description of the present invention, it should be understood that the terms "upper," "middle," "outer," "inner," and the like indicate an orientation or a positional relationship, and are merely for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The intelligent management method of the air storage tank based on the air pressure monitoring is characterized by comprising the following steps of:
S1, presetting an air pressure acquisition period T, and acquiring air pressure data of an air storage tank in the period T in real time;
s2, preprocessing the collected air pressure data to obtain denoised air pressure data;
S3, establishing a multidimensional fuzzy logic control algorithm model aiming at the denoised air pressure data, and obtaining an actual control instruction of the air storage tank valve by utilizing the algorithm model, wherein the multidimensional fuzzy logic control algorithm model comprises a multidimensional fuzzification process, a multidimensional fuzzification process and a multidimensional defuzzification process, the multidimensional fuzzification process is used for converting the air pressure data and the change trend data of the air pressure data into a fuzzy set, the multidimensional fuzzification process is used for realizing reasoning according to a fuzzy rule base based on the fuzzy set so as to generate an intermediate control instruction, and the multidimensional defuzzification process is used for converting the intermediate control instruction into the actual control instruction;
and S4, adjusting a valve of the air storage tank according to the actual control instruction, and repeating the step S1.
2. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 1, wherein the method comprises the following steps: s2, preprocessing the acquired air pressure data by adopting a multi-layer dynamic self-adaptive filtering algorithm model, wherein the multi-layer dynamic self-adaptive filtering algorithm model comprises a frequency domain processing layer, a time domain processing layer and a self-adaptive adjusting layer, the frequency domain processing layer is used for converting a time domain signal of the acquired air pressure data into a frequency domain signal to remove high-frequency noise, the frequency domain signal processed by the frequency domain processing layer is converted into a time domain signal through inverse transformation and then enters the time domain processing layer, the time domain processing layer is used for carrying out smoothing processing on the time domain signal to reduce random noise, and the self-adaptive adjusting layer is used for carrying out dynamic adjustment on the time domain signal processed by the time domain processing layer to obtain the denoised air pressure data.
3. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 2, wherein the method comprises the following steps: the frequency domain processing layer converts the time domain signal into the frequency domain signal by adopting a complex waveform transformation algorithm model, wherein the complex waveform transformation algorithm model is thatWherein, the method comprises the steps of, wherein,Is a frequency domain signal of the air pressure data,As a function of the frequency variation,Is a time domain signal, inThe start-up sub-data of the moment,Is the time domain sample point, the kth time point,In order to be able to take time,The number of total samples for the time domain signal,Is a complex exponential function of the number,In units of imaginary numbers,Is a waveform functionAs a gaussian function or a wavelet function,Is an integral variable, andRelated variables.
4. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 2, wherein the method comprises the following steps: the time domain processing layer adopts a time-varying weighted smoothing algorithm model to carry out smoothing processing on the time domain signals, and the time-varying weighted smoothing algorithm model is thatWherein, the method comprises the steps of, wherein,For the smoothed barometric pressure estimate,For time-varying weighting coefficients, at time t and window positionWeights at the positions satisfy,Is the smooth window length, and the weight is set according to the distance from the center point.
5. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 2, wherein the method comprises the following steps: the self-adaptive adjustment layer adopts a self-adaptive noise suppression algorithm model to dynamically adjust the time domain signal processed by the time domain processing layer, and the self-adaptive noise suppression algorithm model is thatWherein, the method comprises the steps of, wherein,For the adaptive noise suppressed barometric pressure data,The adaptive weight is dynamically adjusted along with time, and the adaptive weight dynamic adjustment mode adopts the ratio of the noise variance to the sum of the noise variance and the signal variance.
6. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 1, wherein the method comprises the following steps: the multidimensional blurring process comprises the steps of dividing air pressure data and change trend data of the air pressure data into three data sets respectively, and converting an actual data set into a fuzzy set by adopting a membership function model aiming at each data set, wherein the membership function model is as followsWherein, the method comprises the steps of, wherein,As a function of the degree of membership,In order to adjust the parameters of the device,For input barometric dataOr trend data of air pressure data,The center value represents the middle position of the fuzzy set.
7. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 1, wherein the method comprises the following steps: the multidimensional fuzzy reasoning process comprises the steps of establishing a fuzzy rule base between the air pressure data and the change trend data of the air pressure data and the opening of the valve of the air storage tank, obtaining an intermediate control instruction based on the fuzzy rule base,Wherein, the method comprises the steps of, wherein,In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of the membership function calculated based on the membership function model,For the weight of the air storage tank valve control action based on the fuzzy rule base,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.
8. The intelligent management method for the air storage tank based on air pressure monitoring according to claim 1, wherein the method comprises the following steps: the multi-dimensional defuzzification process converts intermediate control commands into actual control commands by means of weighted averaging,Wherein, the method comprises the steps of, wherein,In order to actually control the amount of the liquid,In the event of an intermediate control instruction,Is air pressure dataOr trend data of air pressure dataThe minimum value of the membership function calculated based on the membership function model,Representing a fuzzy set of barometric pressure data,A fuzzy set of trend data representing barometric pressure data.
9. An air storage tank intelligent management system based on air pressure monitoring, based on the air storage tank intelligent management method based on air pressure monitoring as set forth in any one of claims 1-8, characterized in that: the intelligent control system comprises an air pressure acquisition module, a data processing module, an intelligent control module and a communication module, wherein the air pressure acquisition module is used for acquiring air pressure data and transmitting the air pressure data to the data processing module, the data processing module is used for preprocessing the air pressure data and transmitting the processed air pressure data to the intelligent control module and the communication module, the intelligent control module is used for calculating the actual control quantity of an air storage tank, and the communication module is used for realizing the communication of each module in the intelligent management system of the air storage tank and realizing the communication with a remote monitoring platform.
10. The air reservoir intelligent management system based on air pressure monitoring of claim 9, wherein: the alarm device also comprises an alarm module, wherein the alarm module is connected with the data processing module and is used for sending alarm information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202411073926.3A CN118582662B (en) | 2024-08-07 | 2024-08-07 | Air storage tank intelligent management method and system based on air pressure monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202411073926.3A CN118582662B (en) | 2024-08-07 | 2024-08-07 | Air storage tank intelligent management method and system based on air pressure monitoring |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118582662A true CN118582662A (en) | 2024-09-03 |
CN118582662B CN118582662B (en) | 2024-10-29 |
Family
ID=92533709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202411073926.3A Active CN118582662B (en) | 2024-08-07 | 2024-08-07 | Air storage tank intelligent management method and system based on air pressure monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118582662B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5067374A (en) * | 1988-11-18 | 1991-11-26 | Honda Giken Kogyo Kabushiki Kaisha | Vehicle automatic transmission control system |
WO1999060247A1 (en) * | 1998-05-15 | 1999-11-25 | Baker Hughes Incorporated | Automatic hydrocarbon production management system |
CN107523491A (en) * | 2016-06-21 | 2017-12-29 | 祁艳 | A kind of biogas concentrates gas storage and feeder and control system |
CN108875710A (en) * | 2018-07-24 | 2018-11-23 | 杭州电子科技大学 | Elevator door speed of service estimation method based on energy threshold algorithm |
CN111901279A (en) * | 2020-07-07 | 2020-11-06 | 中兴通讯股份有限公司 | Data transmission method, device, equipment and storage medium |
US20210020158A1 (en) * | 2019-07-19 | 2021-01-21 | Cirrus Logic International Semiconductor Ltd. | Input signal-based frequency domain adaptive filter stability control |
EP3771957A1 (en) * | 2019-07-30 | 2021-02-03 | Vemmio Spólka Z Ograniczona Odpowiedzialnoscia | Method and system for controlling of heating, ventilation and air conditioning |
CN112954977A (en) * | 2021-02-18 | 2021-06-11 | 财拓云计算(上海)有限公司 | System and method for realizing energy-saving temperature control of data center based on artificial intelligence |
CN116612290A (en) * | 2023-06-12 | 2023-08-18 | 广东工业大学 | Source camera identification method based on small-size image |
CN117724348A (en) * | 2024-02-06 | 2024-03-19 | 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 |
CN118336036A (en) * | 2024-04-29 | 2024-07-12 | 中汽创智科技有限公司 | Intake state response processing method and device |
-
2024
- 2024-08-07 CN CN202411073926.3A patent/CN118582662B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5067374A (en) * | 1988-11-18 | 1991-11-26 | Honda Giken Kogyo Kabushiki Kaisha | Vehicle automatic transmission control system |
WO1999060247A1 (en) * | 1998-05-15 | 1999-11-25 | Baker Hughes Incorporated | Automatic hydrocarbon production management system |
CN107523491A (en) * | 2016-06-21 | 2017-12-29 | 祁艳 | A kind of biogas concentrates gas storage and feeder and control system |
CN108875710A (en) * | 2018-07-24 | 2018-11-23 | 杭州电子科技大学 | Elevator door speed of service estimation method based on energy threshold algorithm |
US20210020158A1 (en) * | 2019-07-19 | 2021-01-21 | Cirrus Logic International Semiconductor Ltd. | Input signal-based frequency domain adaptive filter stability control |
EP3771957A1 (en) * | 2019-07-30 | 2021-02-03 | Vemmio Spólka Z Ograniczona Odpowiedzialnoscia | Method and system for controlling of heating, ventilation and air conditioning |
CN111901279A (en) * | 2020-07-07 | 2020-11-06 | 中兴通讯股份有限公司 | Data transmission method, device, equipment and storage medium |
CN112954977A (en) * | 2021-02-18 | 2021-06-11 | 财拓云计算(上海)有限公司 | System and method for realizing energy-saving temperature control of data center based on artificial intelligence |
CN116612290A (en) * | 2023-06-12 | 2023-08-18 | 广东工业大学 | Source camera identification method based on small-size image |
CN117724348A (en) * | 2024-02-06 | 2024-03-19 | 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 |
CN118336036A (en) * | 2024-04-29 | 2024-07-12 | 中汽创智科技有限公司 | Intake state response processing method and device |
Non-Patent Citations (5)
Title |
---|
刘晓燕;: "智能电气阀门系统控制优化方法研究", 科学技术与工程, no. 24, 28 August 2013 (2013-08-28), pages 189 - 193 * |
吴洁: "《预测模型的优化及应用》", vol. 1, 31 August 2022, 中国科学技术出版社, pages: 40 - 44 * |
张敬信: "《数学建模:算法与编程实现》", vol. 1, 31 July 2022, 机械工业出版社, pages: 179 - 184 * |
张立红: "《单片微型计算机原理与应用》", vol. 2, 31 May 2000, 中国劳动社会保障出版社, pages: 164 - 169 * |
金伟: "《现代检测技术》", vol. 3, 31 January 2012, 北京邮电大学出版社, pages: 286 - 291 * |
Also Published As
Publication number | Publication date |
---|---|
CN118582662B (en) | 2024-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117807382B (en) | Intelligent processing method for pollution monitoring data of drainage pipe network based on intelligent Internet of things | |
CN109597315B (en) | Method, equipment and system for identifying health degradation state of mechanical equipment | |
CN112965548A (en) | Automatic control method for temperature of reaction kettle, and upper and lower limit controllers and system for opening degree of valve | |
CN111582406A (en) | Power equipment state monitoring data clustering method and system | |
CN118582662B (en) | Air storage tank intelligent management method and system based on air pressure monitoring | |
CN116906821A (en) | 5G-based gas transmission and distribution pipe network monitoring and early warning management system | |
CN115962551A (en) | Intelligent air conditioner control system and method for building automatic control | |
CN110657864B (en) | Sensor response time measuring method | |
CN110687791B (en) | Nonlinear oscillation detection method based on improved adaptive frequency modulation modal decomposition | |
CN116561535B (en) | Individualized building interaction design processing method | |
CN115862301B (en) | Remote intelligent communication system for pressure transmitter | |
CN117666406A (en) | Multi-parameter synchronous dynamic signal acquisition method and system based on edge calculation | |
CN118013197A (en) | Torch flow monitoring emergency system and method based on deep learning algorithm | |
CN115202190B (en) | Working condition dividing and identifying method for adjusting potential based on process index | |
CN117273207A (en) | Method for predicting permanganate index of ozone biological active carbon process effluent of water works | |
CN113885371A (en) | Mixed variable process monitoring method based on health state data | |
CN117408440B (en) | River drain sewage intelligent treatment method and system based on multidimensional sensor | |
CN117407728B (en) | Storage environment real-time monitoring method and system for stem cells | |
CN118245959B (en) | Intelligent water meter operation monitoring method based on Internet of things | |
CN117250871B (en) | Man-machine cooperation safety assessment method and device based on decentralised federal learning | |
CN118959694A (en) | Flow self-adaptive adjusting method and system based on electromagnetic valve | |
CN118521144B (en) | Boiler waste heat recovery energy scheduling management method and system | |
CN118442219B (en) | Methanol fuel supply system | |
CN114873665B (en) | Condensate polishing regeneration automatic control system based on computer vision technology | |
Tang | Research on intelligent decision-making mechanism of the elderly care system based on fuzzy neural network |
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 |