CN118444200B - Flyback chip loss state monitoring method and system - Google Patents
Flyback chip loss state monitoring method and system Download PDFInfo
- Publication number
- CN118444200B CN118444200B CN202410903409.8A CN202410903409A CN118444200B CN 118444200 B CN118444200 B CN 118444200B CN 202410903409 A CN202410903409 A CN 202410903409A CN 118444200 B CN118444200 B CN 118444200B
- Authority
- CN
- China
- Prior art keywords
- voltage drop
- threshold
- comparator
- change
- voltage
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000008859 change Effects 0.000 claims abstract description 127
- 230000007306 turnover Effects 0.000 claims abstract description 36
- 230000035945 sensitivity Effects 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 74
- 238000012549 training Methods 0.000 claims description 29
- 238000011156 evaluation Methods 0.000 claims description 24
- 230000004044 response Effects 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000011084 recovery Methods 0.000 claims description 6
- 238000011217 control strategy Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 7
- 238000012423 maintenance Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 238000002405 diagnostic procedure Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/40—Testing power supplies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/12—Measuring rate of change
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Current Or Voltage (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to a flyback chip loss state monitoring method and a flyback chip loss state monitoring system, wherein the method comprises the following steps: detecting the voltage drop change of the output voltage of the flyback chip, and judging whether the voltage drop change exceeds a preset threshold change rate; detecting whether the voltage drop of the output voltage of the flyback chip exceeds a first threshold voltage drop by using a first comparator, and outputting a turnover signal if the voltage drop exceeds the first threshold voltage drop; detecting whether the voltage drop of the output voltage of the flyback chip exceeds a second threshold voltage drop by using a second comparator, and outputting a turnover signal if the voltage drop exceeds the second threshold voltage drop, wherein the first threshold voltage drop is smaller than the second threshold voltage drop; starting to count at the output turning moment of the first comparator by using a timer so as to determine whether the pressure drop change exceeds a threshold change rate within a preset count time T; and judging whether the loss state of the flyback chip is normal or not according to the output overturning signals of the first comparator and the second comparator and the timing result of the timer. The voltage abnormality can be identified in time, and the sensitivity and the adaptability of the monitoring system are enhanced.
Description
Technical Field
The embodiment of the invention relates to the field of power supply monitoring, in particular to a method and a system for monitoring a loss state of a flyback chip.
Background
Existing flyback chip loss monitoring techniques typically rely on simple threshold comparison and timing mechanisms, which have limitations in terms of real-time and accuracy. The technical principle is based on direct comparison of voltage values, and lack of in-depth analysis of voltage change trend and mode. In implementing the embodiments of the present invention, the inventors have found that at least the following problems or disadvantages exist in the prior art: 1. the prior art cannot accurately identify whether the voltage drop variation exceeds the normal fluctuation range. 2. There is a lack of efficient algorithms for deep analysis and pattern recognition of voltage drop changes. 3. The existing monitoring system has long response time and cannot realize quick and accurate loss state evaluation.
The embodiment of the invention is an improvement for solving the problems.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a system for monitoring the loss state of a flyback chip, wherein the method can accurately monitor and evaluate the loss state of the flyback chip in real time. By implementing the embodiment of the invention, the accuracy and the response speed of loss monitoring can be effectively improved, and the stable operation of the flyback chip is ensured.
A first aspect of an embodiment of the present invention relates to a method for monitoring a loss state of a flyback chip, where the method includes:
detecting the voltage drop change of the output voltage of the flyback chip, and judging whether the voltage drop change exceeds a preset threshold change rate;
detecting whether the voltage drop of the output voltage of the flyback chip exceeds a first threshold voltage drop by using a first comparator, and outputting a turnover signal if the voltage drop exceeds the first threshold voltage drop;
Detecting whether the voltage drop of the output voltage of the flyback chip exceeds a second threshold voltage drop by using a second comparator, and outputting a turnover signal if the voltage drop exceeds the second threshold voltage drop, wherein the first threshold voltage drop is smaller than the second threshold voltage drop;
starting to count at the output turning moment of the first comparator by using a timer so as to determine whether the pressure drop change exceeds a threshold change rate within a preset count time T;
and judging whether the loss state of the flyback chip is normal or not according to the output overturning signals of the first comparator and the second comparator and the timing result of the timer.
Further, the method further comprises the steps of:
Collecting and setting an initial voltage value of the flyback chip under normal working conditions as a reference point;
monitoring the output voltage of the flyback chip in real time, and continuously recording voltage data;
identifying a falling trend of the voltage level by comparing the continuous voltage data;
the occurrence of a voltage drop is determined and the time point and duration of the voltage drop are recorded.
Further, the method further comprises the steps of:
setting a first threshold voltage drop for identifying an initial anomaly of the voltage drop, the first threshold being determined based on the flyback chip design parameters and historical operating data;
Continuously monitoring the output voltage of the flyback chip, and immediately outputting a turnover signal by the first comparator corresponding to the detection that the voltage drop exceeds a first threshold voltage drop;
In response to the output toggle signal, analyzing a pressure drop event including an amplitude, a duration, and a frequency of occurrence of the pressure drop;
and recording a voltage drop event corresponding to the inversion signal.
Further, the method further comprises the steps of:
setting a second threshold voltage drop for identifying an initial anomaly of the voltage drop, the second threshold being higher than the first threshold voltage drop;
when the output voltage drop of the flyback chip continuously exceeds a second threshold voltage drop, the second comparator outputs a turnover signal to indicate that the voltage drop reaches an abnormal state of a higher level;
Each event that the output voltage drop exceeds the second threshold drop is recorded, including a time stamp and a drop magnitude.
Further, the method further comprises the steps of:
Starting a timer while the first comparator outputs the flipping signal to capture a starting point of the voltage drop change;
setting preset time T of a timer, wherein the preset time T is determined based on normal response time and voltage recovery characteristics of a flyback chip;
continuously monitoring the output voltage of the flyback chip during the running period of the timer, and recording each change of the voltage value;
stopping timing and evaluating the total variation of the voltage drop in the time when the timer reaches the preset time T;
Comparing the evaluation result with a preset threshold change rate to determine whether the voltage drop change is abnormal;
if the voltage drop change does not exceed the threshold change rate within the preset time T, resetting the monitoring flow, and continuing to monitor the voltage state in real time.
Further, the method further comprises the steps of:
Collecting all the turnover signals output by the first comparator and the second comparator and corresponding timer records;
Clearing the turnover signal data, and removing abnormal values and noise interference through filtering and abnormal value removal;
calculating the statistical characteristics of voltage drop change in preset time T, wherein the statistical characteristics comprise average voltage drop value, standard deviation and change rate;
determining whether the voltage drop variation is within a normal range by comparing with an expected pattern under normal operating conditions;
based on the preprocessed overturn signals, evaluating the current loss state by analyzing and comparing historical data;
Based on the evaluation results, the loss state is classified as "normal" or "abnormal", where "normal" means that the voltage drop change conforms to the expected pattern, and "abnormal" means that there is an unexpected loss.
Further, the method further comprises the steps of:
Defining and marking voltage drop change events in the historical data set, and classifying the voltage drop change events into two types of normal and abnormal;
Training an SVM model by utilizing normal and abnormal events in the historical data set, and determining a classification boundary of the SVM model;
Taking the cleaned overturn signal data and statistical characteristics as inputs, and applying a trained SVM model to evaluate the current loss state;
classifying the input feature vectors according to the learned mode through an SVM model, and outputting a prediction result of the loss state;
the loss state of the flyback chip is classified as "normal" or "abnormal" according to the output of the SVM model.
Further, the method further comprises the steps of:
setting a training data set, wherein the training data set comprises voltage drop characteristics recorded by a flyback chip in different working states, and each characteristic sample is marked as a normal or abnormal loss type;
Performing standardized processing on the voltage drop characteristics in the training data set to eliminate the influence of dimensions under different working conditions;
Selecting an RBF function as a kernel function of the SVM, wherein a parameter gamma of the RBF kernel is determined according to the voltage stability and the sensitivity of the voltage drop change of the flyback chip, and optimizing on a verification set through grid search and cross verification;
Determining a regularization parameter C of an SVM model, wherein the regularization parameter C controls regularization strength of the model for classifying the loss state of the flyback chip;
and training an SVM model by using the optimized parameters C and gamma, and determining a classification boundary for distinguishing the normal loss state and the abnormal loss state of the flyback chip.
Further, the method further comprises the steps of:
Constructing an objective function of the SVM model, wherein the function is a convex quadratic programming problem and is used for minimizing regularization errors of the model;
Solving the objective function to obtain a weight vector and a bias term of the SVM model;
Determining a classification boundary by using the weight vector and the bias term obtained by solving, wherein the boundary can divide the voltage drop characteristic space into a normal loss state area and an abnormal loss state area;
classifying and predicting a new voltage drop characteristic sample by using the determined classification boundary, if the sample meets the condition of the classification boundary, predicting the sample as a normal loss state, otherwise, predicting the sample as an abnormal loss state;
and integrating the prediction result into a flyback chip loss monitoring system to realize real-time loss state evaluation and classification.
A second aspect of an embodiment of the present invention relates to a flyback chip loss state monitoring system, including:
the voltage drop detection unit is used for monitoring the output voltage of the flyback chip in real time, detecting voltage drop change and judging whether the voltage drop change exceeds a preset threshold change rate or not;
The first comparator unit is used for receiving the output of the voltage drop detection unit, detecting whether the voltage drop exceeds a first threshold voltage drop, and generating a turnover signal if the voltage drop exceeds the first threshold voltage drop;
The second comparator unit is used for receiving the turnover signal of the first comparator unit and further detecting whether the voltage drop exceeds a second threshold voltage drop, and if so, generating a corresponding turnover signal, wherein the first threshold voltage drop is set to be smaller than the second threshold voltage drop;
A timer unit, synchronized with the output of the first comparator unit, started when the flip signal is generated, for determining whether the voltage drop change exceeds a threshold change rate within a preset timing time T;
the loss state judging unit is used for receiving the overturning signals of the first comparator unit and the second comparator unit and the timing result of the timer unit, and analyzing and judging whether the loss state of the flyback chip is normal or not;
and the control unit is used for executing a corresponding control strategy according to the analysis result of the loss state judging unit.
The other technical scheme has the following advantages or beneficial effects:
By monitoring the output voltage of the flyback chip in real time and detecting the voltage drop change by using the double comparators (the first comparator and the second comparator), the invention effectively solves the problem of insufficient response to the voltage change in the prior art, thereby realizing the rapid identification and response to the voltage abnormality; the invention solves the problem that the persistence and the severity of the voltage change are difficult to accurately judge in the prior art by using a timer to accurately record the generation moment of the turnover signal and combining the change rate evaluation within the preset time T, thereby improving the accuracy and the reliability of a monitoring system; the invention solves the problem of insufficient noise and abnormal value processing in the prior art by adopting a data preprocessing and statistical analysis method to clean and analyze the overturn signal data, thereby ensuring the accuracy of the data analysis result.
Drawings
In order to more clearly describe the embodiments of the present invention or the technical solutions in the background art, the following description will describe the drawings that are required to be used in the embodiments of the present invention or the background art.
FIG. 1 is a schematic flow diagram of a method in one embodiment of the invention;
Fig. 2 is a schematic diagram of the system in one embodiment of the invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement of the purpose and the effect achieved by the embodiments of the present invention easy to understand, the embodiments of the present invention are further described below with reference to the drawings and the specific embodiments, and it should be understood that the specific embodiments described herein are only for explaining the embodiments of the present invention and are not limiting the embodiments of the present invention.
In describing embodiments of the present application, it should be noted that, unless explicitly stated or limited otherwise, the terms "mounted," "connected," and "coupled" should be construed broadly, and may be, for example, fixedly coupled, indirectly coupled through an intermediary, in communication between two elements, or in an interaction relationship between two elements. The specific meaning of the above terms in the embodiments of the present application will be understood by those of ordinary skill in the art according to specific circumstances. The terms "first," "second," "third," "fourth," and the like, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
Furthermore, the terms "first," "second," "third," "fourth," and the like, if any, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "first," "second," "third," "fourth," etc. (if present) may explicitly or implicitly include at least one such feature. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless explicitly defined otherwise; the terms "comprises," "comprising," and any variations thereof, in the description and claims, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In describing embodiments of the present invention, it should be noted that, for directional words such as "center", "lateral", "longitudinal", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., the directional and positional relationships are based on the directional or positional relationships shown in the drawings, merely for convenience in describing the embodiments of the present invention and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and should not be construed as limiting the specific scope of the embodiments of the present invention.
It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The following detailed description of preferred embodiments of the application is made in connection with the accompanying drawings, which form a part hereof, and together with the description of the embodiments of the application, are used to explain the principles of the application and are not intended to limit the scope of the application.
In one embodiment of the present invention, a method for monitoring a loss state of a flyback chip is disclosed, as shown in fig. 1, the method S100 includes the following steps:
S101, detecting the voltage drop change of the output voltage of the flyback chip, and judging whether the voltage drop change exceeds a preset threshold change rate;
The inversion signal is a signal that changes the state of the output signal when the comparator detects that the voltage drop exceeds the threshold value, and is used to indicate an abnormal change in the voltage state. And the loss state refers to a state that the flyback chip is reduced in performance due to various reasons (such as overheating, aging and the like) during operation. By the method provided by the embodiment of the invention, the loss state of the flyback chip can be effectively monitored and evaluated in real time, so that the reliability and the safety of the system are improved.
In some embodiments, first, the output voltage signal of the flyback chip is acquired using a high-precision voltage sensor. This step involves the necessary pre-processing of the original voltage signal to eliminate noise and interference, ensuring the accuracy of the signal. The preprocessing operation typically involves filtering, wherein a bandpass filter is used to screen out the effective signal components that are consistent with the operating frequency of the flyback chip, while suppressing noise at other frequencies.
S102, detecting whether the voltage drop of the output voltage of the flyback chip exceeds a first threshold voltage drop by using a first comparator, and outputting a turnover signal if the voltage drop exceeds the first threshold voltage drop;
And monitoring the preprocessed voltage signal through a first comparator so as to judge whether the voltage drop reaches or exceeds a preset first threshold voltage drop. The first threshold voltage drop is a small value that identifies small changes in voltage that may be early signals of loss state changes. Upon detecting a voltage drop exceeding this threshold, the first comparator then outputs a toggle signal indicating a possible loss state change.
S103, detecting whether the voltage drop of the output voltage of the flyback chip exceeds a second threshold voltage drop by using a second comparator, and outputting a turnover signal if the voltage drop exceeds the second threshold voltage drop, wherein the first threshold voltage drop is smaller than the second threshold voltage drop;
the second comparator is used for further monitoring the voltage drop and judging whether the voltage drop reaches or exceeds a second higher threshold voltage drop. This threshold is set to identify a more severe voltage drop condition, and if an excess is detected, the second comparator likewise outputs a toggle signal. Here, the first threshold voltage drop is set to be smaller than the second threshold voltage drop, and a hierarchical voltage drop detection mechanism is formed to distinguish between different loss states.
S104, starting timing at the output turning moment of the first comparator by using a timer so as to determine whether the pressure drop change exceeds a threshold change rate within a preset timing time T;
In some embodiments, the timer unit is started to start timing the voltage drop change at the instant the first comparator outputs the toggle signal. The preset time T of the timer unit is determined according to the expected response time of the flyback chip and the voltage recovery characteristics to ensure that the change in voltage drop is evaluated in a reasonable time.
S105, judging whether the loss state of the flyback chip is normal or not according to the output overturning signals of the first comparator and the second comparator and the timing result of the timer.
In some embodiments, the loss state determining unit integrates the flip signals of the first comparator and the second comparator and the timing result of the timer unit to evaluate the loss state of the flyback chip. If the voltage drop change does not exceed the threshold change rate within the preset timing time T, judging that the loss state is normal; if the loss state is exceeded, the abnormal loss state is judged, and corresponding alarm or protection measures are triggered to prevent further loss or damage.
Further, the flyback chip loss state monitoring method comprises the steps of collecting and setting an initial voltage value of the flyback chip under a normal working condition as a reference point; monitoring the output voltage of the flyback chip in real time, and continuously recording voltage data; identifying a falling trend of the voltage level by comparing the continuous voltage data; the occurrence of a voltage drop is determined and the time point and duration of the voltage drop are recorded.
Under the normal working condition of the flyback chip, the output voltage of the chip is acquired by using high-precision voltage measurement equipment. This initial voltage value reflects the performance index of the chip in the no-loss or minimal-loss state, and is set as the reference point. This step is the basis for all subsequent monitoring and comparison work. Meanwhile, the output voltage of the chip can be monitored in real time through a voltage sensor connected to the output end of the flyback chip. The sensor needs to have a high sampling rate and accuracy to ensure the accuracy of the monitored data. And continuously recording the voltage data obtained by real-time monitoring in a data recording system. These data will be used in subsequent comparisons and analysis to identify any voltage changes. And carrying out real-time or near real-time comparison analysis on the recorded voltage data by utilizing a data processing algorithm. By calculating the difference between successive data points, it can be identified whether the voltage has a decreasing trend.
In the voltage data, if a consecutive plurality of data points are found to exhibit a decrease relative to a previous data point, this may indicate the onset of a chip loss state. Statistical methods or machine learning algorithms are used to improve the accuracy and reliability of the identification.
When the voltage drop is determined to occur, the specific point in time at which the voltage drop occurs and the duration of the voltage drop are recorded. These data are critical to analyzing the wear state of the chip and predicting its remaining useful life. Through the steps, the invention provides a systematic method for monitoring the loss state of the flyback chip, and potential loss problems can be found and processed in time by monitoring and analyzing the voltage drop change in real time, so that the reliability and the safety of the system are improved.
Further, the detecting the voltage drop of the flyback chip output voltage using the first comparator includes: setting a first threshold voltage drop for identifying an initial anomaly of the voltage drop, the first threshold being determined based on the flyback chip design parameters and historical operating data; continuously monitoring the output voltage of the flyback chip, and immediately outputting a turnover signal by the first comparator corresponding to the detection that the voltage drop exceeds a first threshold voltage drop; in response to the output toggle signal, analyzing a pressure drop event including an amplitude, a duration, and a frequency of occurrence of the pressure drop; and recording a voltage drop event corresponding to the inversion signal.
A first threshold for voltage drop is determined and set based on design parameters and historical operating data of the flyback chip. This threshold is used to identify an initial anomaly in the voltage drop and is a key reference indicator in the monitoring process. The output voltage of the flyback chip is continuously monitored by the first comparator. The comparator is configured to compare the output voltage of the chip with a preset reference voltage or initial voltage value in real time. When the monitored output voltage drops below a preset first threshold voltage drop, the first comparator immediately outputs a flipping signal. This flip signal indicates that the voltage drop has exceeded the normal fluctuation range and may indicate the onset of chip loss.
After receiving the flipping signal, the system automatically starts an analysis flow of the pressure drop event. The analysis includes the magnitude, duration, and frequency of occurrence of the pressure drop, which are critical to assessing the loss state of the chip. Each detected voltage drop event and its associated information are recorded. The recorded information includes the point in time of the flipping signal, the magnitude of the voltage drop, the duration period, the frequency of occurrence, etc. The recorded voltage drop events and analysis results are stored in a database or data log to facilitate historical data analysis and trend prediction. At the same time, corresponding reports are generated for technicians to review and take necessary maintenance measures. And supporting maintenance decision of the flyback chip by utilizing the collected and analyzed data. If the data shows accelerated wear or potential failure risk, maintenance or replacement can be performed in time to avoid unexpected downtime or performance degradation.
Through the steps, the flyback chip loss state monitoring method can detect and respond to voltage drop abnormality in real time, and can also provide deep analysis and record, so that effective technical support is provided for health management and predictive maintenance of the chip.
Further, the detecting the voltage drop of the flyback chip output voltage using the second comparator includes: setting a second threshold voltage drop for identifying an initial anomaly of the voltage drop, the second threshold being higher than the first threshold voltage drop; when the output voltage drop of the flyback chip continuously exceeds a second threshold voltage drop, the second comparator outputs a turnover signal to indicate that the voltage drop reaches an abnormal state of a higher level; each event that the output voltage drop exceeds the second threshold drop is recorded, including a time stamp and a drop magnitude.
A second threshold pressure drop is added to the monitoring system, the threshold being higher than the first threshold pressure drop. The second threshold is set based on the more stringent monitoring requirements for flyback chip performance for identifying more severe anomalies in voltage drop. And continuously monitoring the output voltage of the flyback chip by using a second comparator, and comparing the output voltage with a second threshold voltage drop. The sensitivity and response speed of the second comparator need to meet the requirement of real-time monitoring. When the output voltage drop of the flyback chip continuously exceeds the second threshold voltage drop, the second comparator immediately outputs a flip signal. This toggle signal indicates that the voltage drop has reached a higher level of anomaly, requiring immediate attention.
In some embodiments, upon receiving the toggle signal from the second comparator, the system automatically initiates a higher level exception handling flow. This may include alerting a technician, adjusting system operating parameters, or preparing for further diagnostic testing. The events, including the time stamp and the voltage drop amplitude, are recorded in detail for each output voltage drop exceeding the second threshold voltage drop. The time stamp is accurate to the order of seconds or milliseconds, ensuring that the exact time at which the event occurred can be traced. The recorded pressure drop event data is analyzed to determine the severity and possible cause of the abnormal condition. Based on the analysis results, a detailed report is generated that includes critical information such as the frequency, amplitude, and duration of the pressure drop event.
And supporting maintenance and replacement decisions of the flyback chip by using the recorded and analyzed data. If the data display loss accelerates or there is a risk of failure, maintenance or replacement measures can be taken in time to avoid potential system failure.
And feeding back the monitoring result and maintenance experience to the system for optimizing the threshold setting and monitoring strategy. Through continuous data accumulation and experience learning, the accuracy and efficiency of the monitoring system are improved.
Through the steps, the flyback chip loss state monitoring method disclosed by the invention not only can detect voltage drop abnormality in real time, but also can distinguish and respond abnormal states of different levels, and provides finer monitoring and maintenance support for the health state of the chip.
Further, the determining, using the timer, whether the pressure drop change exceeds the threshold change rate within the preset timing time T includes: starting a timer while the first comparator outputs the flipping signal to capture a starting point of the voltage drop change; setting preset time T of a timer, wherein the preset time T is determined based on normal response time and voltage recovery characteristics of a flyback chip; continuously monitoring the output voltage of the flyback chip during the running period of the timer, and recording each change of the voltage value; stopping timing and evaluating the total variation of the voltage drop in the time when the timer reaches the preset time T; comparing the evaluation result with a preset threshold change rate to determine whether the voltage drop change is abnormal; if the voltage drop change does not exceed the threshold change rate within the preset time T, resetting the monitoring flow, and continuing to monitor the voltage state in real time.
In some embodiments, the timer is started while the first comparator detects the voltage drop and outputs the toggle signal. This step is used to capture the starting point of the voltage drop change, ensuring the accuracy of the timing. The preset time T of the timer is set, which is determined based on the normal response time of the flyback chip and the voltage recovery characteristics. The preset time T should be set to ensure that it is sufficient to cover the potential period of variation of the voltage drop. During the operation of the timer, the output voltage of the flyback chip is continuously monitored by a voltage monitoring device, and each change of the voltage value is recorded. These data will be used for subsequent evaluation and analysis. Once the timer reaches the preset time T, the timing is stopped immediately and the recording of the voltage change is stopped. At this time, all voltage data for a preset time have been collected. And evaluating the voltage value recorded in the preset time T, and calculating the total variation of the voltage drop in the time period. This evaluation will be used to compare with a preset threshold rate of change. And comparing the estimated total change amount of the voltage drop with a preset threshold change rate. If the amount of change exceeds the threshold rate of change, the voltage drop is considered abnormal, requiring further diagnostics and possible maintenance.
And if the voltage drop change does not exceed the threshold change rate within the preset time T, the voltage state is considered to be normal. At this time, the monitoring flow is reset, the voltage state is continuously monitored in real time, and the working state of the flyback chip is ensured to be continuously monitored. According to the monitoring result, if the voltage drop change trend or abnormality is found, the system can automatically adjust the working parameters or give out an alarm so as to prevent potential loss problems.
For any abnormal situation indicated by the evaluation result, corresponding maintenance measures are taken, such as replacing components, adjusting system configuration or performing further diagnostic tests.
Through the steps, the flyback chip loss state monitoring method can effectively use the timer to determine whether the voltage drop change is abnormal, so that measures are taken in time, and the stable operation and the reliability of the system are ensured.
Further, the judging whether the loss state of the flyback chip is normal according to the output overturn signals of the first comparator and the second comparator and the timing result of the timer comprises: collecting all the turnover signals output by the first comparator and the second comparator and corresponding timer records; clearing the turnover signal data, and removing abnormal values and noise interference through filtering and abnormal value removal; calculating the statistical characteristics of voltage drop change in preset time T, wherein the statistical characteristics comprise average voltage drop value, standard deviation and change rate;
Determining whether the voltage drop variation is within a normal range by comparing with an expected pattern under normal operating conditions; based on the preprocessed overturn signals, evaluating the current loss state by analyzing and comparing historical data; based on the evaluation results, the loss state is classified as "normal" or "abnormal", where "normal" means that the voltage drop change conforms to the expected pattern, and "abnormal" means that there is an unexpected loss.
In some embodiments, all output roll-over signals are collected from the first comparator and the second comparator, while records of the corresponding timers are collected. These data provide the original material for subsequent analysis. And cleaning the collected turnover signal data, removing noise interference by a filtering technology, and removing abnormal values in the data by an abnormal value detection method so as to ensure the accuracy of analysis.
And in the preset time T, carrying out statistical analysis on the voltage drop change, and calculating statistical characteristics including average voltage drop value, standard deviation and change rate. These statistical features provide a quantitative indicator for assessing whether the voltage change is normal. The calculated statistical features are compared to expected patterns under normal operating conditions. The expected mode is based on historical data and standard parameters of the flyback chip in a lossless or normal loss state.
Based on the preprocessed turnover signals, the current loss state is comprehensively evaluated by combining historical data. And analyzing the trend and mode of voltage drop change, and comparing the trend and mode with data of historical normal states and abnormal states. And classifying the loss state of the flyback chip as normal or abnormal according to the evaluation result. A voltage drop change is classified as "normal" if it meets the expected pattern, i.e. is within the tolerance of normal operating conditions. An "anomaly" is classified if there is an unexpected loss or a change in voltage drop that deviates significantly from the expected pattern.
In some embodiments, the results of the assessment of the wear state are fed back to a system administrator or an automated control system, providing support for further decisions. For the case that the evaluation result is abnormal, the system can automatically trigger an early warning mechanism or a maintenance flow. For the loss state determined as "abnormal", corresponding maintenance measures such as further diagnostic tests, chip repair or replacement, etc. are performed to ensure the reliability and stability of the system.
After the maintenance measures are executed, continuously monitoring the flyback chip, collecting new data, continuously optimizing the loss state monitoring method according to new running conditions, and improving the accuracy and response speed of the monitoring system.
Through the steps, the flyback chip loss state monitoring method disclosed by the invention can comprehensively evaluate the loss state of the chip and timely discover and process abnormal conditions, so that the service life of the chip is effectively prolonged and the stable operation of a system is ensured.
Further, evaluating the current loss state includes: defining and marking voltage drop change events in the historical data set, and classifying the voltage drop change events into two types of normal and abnormal; training an SVM model by utilizing normal and abnormal events in the historical data set, and determining a classification boundary of the SVM model; taking the cleaned overturn signal data and statistical characteristics as inputs, and applying a trained SVM model to evaluate the current loss state; classifying the input feature vectors according to the learned mode through an SVM model, and outputting a prediction result of the loss state; the loss state of the flyback chip is classified as "normal" or "abnormal" according to the output of the SVM model.
Voltage drop change events are defined and marked from the historical dataset, and the events are explicitly classified into two categories of normal and abnormal according to expert knowledge or preset rules. These data will serve as the basis for training the model. Features are extracted using the labeled historical dataset and a training set of support vector machine SVM models for training is constructed. Features may include statistical features of the amplitude, frequency, duration, etc. of the voltage drops.
In some embodiments, the SVM model is trained using the training set data by selecting appropriate kernel functions and parameters. By determining classification boundaries, the model learns the ability to distinguish between normal and abnormal voltage drop changes. And cleaning the collected turnover signal data, including filtering and outlier rejection, so as to eliminate noise and outlier interference and ensure the quality of input data.
And constructing the cleaned overturn signal data and the calculated statistical characteristics into feature vectors, wherein the feature vectors are used as the input of the SVM model for evaluating the current loss state.
In some embodiments, feature vectors are input into a trained SVM model, which classifies the input feature vectors according to a learned pattern, outputting a prediction of the loss state. And classifying the loss state of the flyback chip as normal or abnormal according to the output result of the SVM model. The decision boundary of the model will determine this classification.
And verifying the prediction result of the SVM model, and comparing the prediction result with an actual maintenance record or manual auditing. And feeding back the result to a system administrator, and providing basis for further decision-making. Based on the classification result of the SVM model, the system can automatically trigger corresponding response measures. If the loss state is classified as "abnormal," further diagnostic or maintenance work may be required.
New data is continually collected and used to periodically retrain and optimize the SVM model to accommodate possible variations and to improve model accuracy.
Through the steps, the flyback chip loss state monitoring method provided by the invention provides an automatic and high-accuracy assessment means by utilizing an advanced machine learning technology, and the intelligent level and the response capability of a monitoring system are effectively improved.
Further, training the SVM model to determine its classification boundaries includes: setting a training data set, wherein the training data set comprises voltage drop characteristics recorded by a flyback chip in different working states, and each characteristic sample is marked as a normal or abnormal loss type; performing standardized processing on the voltage drop characteristics in the training data set to eliminate the influence of dimensions under different working conditions; selecting an RBF function as a kernel function of the SVM, wherein a parameter gamma of the RBF kernel is determined according to the voltage stability and the sensitivity of the voltage drop change of the flyback chip, and optimizing on a verification set through grid search and cross verification; determining a regularization parameter C of an SVM model, wherein the regularization parameter C controls regularization strength of the model for classifying the loss state of the flyback chip; and training an SVM model by using the optimized parameters C and gamma, and determining a classification boundary for distinguishing the normal loss state and the abnormal loss state of the flyback chip.
In some embodiments, a training data set is prepared and set up that includes voltage drop characteristics recorded by the flyback chip under different operating conditions. Each feature sample has been labeled as "normal" or "abnormal" loss category based on historical performance and expert knowledge.
A normalization process is performed on the voltage drop characteristics in the training dataset. This step is to eliminate the influence of the dimensions under different working conditions, and ensure that model training will not deviate due to the different dimensions. The radial basis function RBF is chosen as the kernel function of the SVM. RBFs are widely used because of their effectiveness in addressing non-linearity problems. The parameter gamma of the RBF core is determined according to the voltage stability of the flyback chip and the sensitivity of the voltage drop variation. Optimization is performed on the validation set by grid search and cross validation to find the most appropriate parameter values.
And determining a regularization parameter C of the SVM model, wherein the regularization parameter controls regularization strength of the model for classifying the loss state of the flyback chip. Regularization parameter C helps prevent model overfitting. And training an SVM model by using the optimized parameters C and gamma. During training, patterns distinguishing between "normal" and "abnormal" loss states are learned using a training data set, and classification boundaries are determined. The performance of the SVM model is tested on an independent verification set, and the accuracy and generalization capability of the model are verified. And further adjusting and optimizing model parameters according to the verification result.
In some embodiments, classification effects of the SVM model, including indexes such as precision, recall, F1 score, etc., are evaluated, ensuring that the model is able to accurately distinguish between loss states of the flyback chip. And applying the trained and optimized SVM model to a real-time monitoring system, and carrying out real-time evaluation and classification on the loss state of the flyback chip.
New voltage drop profile data is continuously collected as the system operates and data accumulates, and is used periodically to retrain and parameter optimize the SVM model to accommodate possible data drift and conceptual changes.
Through the steps, the flyback chip loss state monitoring method can accurately evaluate and classify the loss state of the flyback chip by utilizing the SVM model, and provides scientific and reliable basis for maintenance and replacement of the chip.
Further, the specific steps for solving the convex quadratic programming problem include: constructing an objective function of the SVM model, wherein the function is a convex quadratic programming problem and is used for minimizing regularization errors of the model; solving the objective function to obtain a weight vector and a bias term of the SVM model; determining a classification boundary by using the weight vector and the bias term obtained by solving, wherein the boundary can divide the voltage drop characteristic space into a normal loss state area and an abnormal loss state area; classifying and predicting a new voltage drop characteristic sample by using the determined classification boundary, if the sample meets the condition of the classification boundary, predicting the sample as a normal loss state, otherwise, predicting the sample as an abnormal loss state; and integrating the prediction result into a flyback chip loss monitoring system to realize real-time loss state evaluation and classification.
In some embodiments, an objective function of the SVM model is constructed that is a convex quadratic programming problem, expressed formally generally as minimizing regularization errors of the model while maximizing spacing. This objective function ensures that the model finds a balance between errors in the training data and model complexity. And solving the objective function by using a numerical optimization method. This typically involves the Lagrangian multiplier method and the conversion of the dual problem. The solving process will obtain the weight vector and bias term of the SVM model. And determining the classification boundary of the SVM by using the weight vector and the bias term obtained by solving. This boundary divides the feature space into "normal" and "abnormal" loss state regions such that the separation between the two classes is maximized.
And monitoring the new voltage drop characteristic sample in real time, acquiring data of the new voltage drop characteristic sample and constructing a characteristic vector. And performing classification prediction on the new characteristic sample by using the determined classification boundary. If the sample meets the conditions of the classification boundary (i.e., is located on the side of the "normal" region), then a "normal" loss state is predicted; if the condition is not met (i.e., located on the "abnormal" region side), an "abnormal" loss state is predicted.
In some embodiments, the prediction results are integrated into a flyback chip loss monitoring system. The system will update the loss state evaluation of the chip in real time according to the prediction result. The system can evaluate and classify the loss state of the flyback chip in real time, and can respond in time when the loss state changes. The evaluation results are provided to a system administrator or an automated control system to take necessary maintenance or adjustment actions upon detection of an "abnormal" loss condition.
The system will continually monitor the voltage drop characteristics and periodically review and optimize the SVM model to accommodate possible new loss patterns or changes. Based on feedback of the monitoring system, regular maintenance and system updating are executed, and accuracy and effectiveness of the flyback chip loss monitoring method are ensured.
The above embodiments of the present disclosure have the following advantageous effects:
by monitoring the output voltage of the flyback chip in real time and detecting the voltage drop change, the method can timely identify voltage abnormality and provide real-time data support for chip maintenance and fault prevention; by setting the first threshold voltage drop and the second threshold voltage drop, the method can identify voltage anomalies at different levels, provide a multi-level early warning mechanism and enhance the sensitivity and adaptability of the monitoring system; the voltage drop change is evaluated by using the timer within the preset time, and whether the voltage abnormality is in the normal fluctuation range or not can be more accurately judged by the method, so that the judgment accuracy is improved; by collecting the turnover signals and timing data and combining statistical analysis, the method can evaluate the chip loss state based on actual data, and improves the objectivity and reliability of evaluation.
With further reference to fig. 2, as an implementation of the method shown in the foregoing figures, the present disclosure provides some embodiments of a flyback chip loss state monitoring system, which apparatus embodiments correspond to the method embodiments shown in fig. 2, and the state monitoring system is particularly applicable to various electronic devices. As shown in fig. 2, a flyback chip loss state monitoring system 200 of some embodiments, the system 200 comprising:
The voltage drop detection unit 201 is configured to monitor an output voltage of the flyback chip in real time, detect a voltage drop change, and determine whether the voltage drop change exceeds a preset threshold change rate;
A first comparator unit 202 for receiving the output of the voltage drop detection unit and detecting whether the voltage drop exceeds a first threshold voltage drop, and if so, generating a flip signal;
A second comparator unit 203, configured to receive the toggling signal of the first comparator unit and further detect whether the voltage drop exceeds a second threshold voltage drop, and if so, generate a corresponding toggling signal, where the first threshold voltage drop is set to be less than the second threshold voltage drop;
A timer unit 204, synchronized with the output of the first comparator unit, started when the flip signal is generated, for determining whether the voltage drop change exceeds the threshold change rate within a preset timing time T;
A loss state judging unit 205, configured to receive the flip signals of the first comparator unit and the second comparator unit and the timing result of the timer unit, and analyze and judge whether the loss state of the flyback chip is normal;
and the control unit 206 is configured to execute a corresponding control policy according to the analysis result of the loss state judging unit.
The voltage drop detection unit 201 is designed to continuously monitor the output voltage of the flyback chip in real time. The unit digitizes the voltage signal using a high precision analog to digital converter ADC and analyzes the voltage level using a software algorithm to detect if there is a voltage drop change.
In some embodiments, the first comparator unit 202 receives the digitized voltage signal from the voltage drop detection unit. The unit is internally provided with a preset first threshold voltage drop which is used for judging whether the voltage drop exceeds a normal fluctuation range. If the voltage drop is detected to exceed the threshold value, the first comparator unit generates a flip signal.
The second comparator unit 203 receives the flip signal of the first comparator unit and compares it with a second threshold voltage drop. The second threshold voltage drop is set higher than the first threshold voltage drop to trigger when the voltage drop change is more pronounced. If the voltage drop exceeds the second threshold voltage drop, the second comparator unit generates a corresponding flip signal.
The timer unit 204 operates in synchronization with the output of the first comparator unit 202. Upon detection of the roll-over signal, the timer unit starts and begins to count to determine whether the pressure drop change exceeds a threshold rate of change within a preset count time T.
The loss state judgment unit 205 receives the flip signals from the first comparator unit 202 and the second comparator unit 203 and the timing result of the timer unit. The unit utilizes the data, combines the historical data and a preset evaluation standard to analyze and judge whether the loss state of the flyback chip is normal.
The control unit 206 executes a corresponding control strategy according to the analysis result of the loss state judgment unit. These strategies may include, but are not limited to: raising warnings, adjusting operating parameters, reducing load, starting maintenance procedures or shutting down the system to prevent further wear. The control unit feeds back the execution result to the system to make necessary adjustment. If the loss status is assessed as "abnormal", the system may automatically enter a maintenance mode, awaiting inspection and repair by technicians.
All detected voltage drop events, roll-over signals, timing results, and loss state evaluation results are recorded in the system. These data can be used to generate reports for analysis and auditing by technicians. The system will be optimized and updated periodically to accommodate new operating conditions and voltage characteristics. This includes updating the threshold voltage drop, timing time T, loss assessment criteria, and control strategy.
In some embodiments, the system also provides a user interface that allows an operator to monitor system status, view loss assessment results and historical data, and manually adjust control strategies.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (4)
1. The method for monitoring the loss state of the flyback chip is characterized by comprising the following steps of:
detecting the voltage drop change of the output voltage of the flyback chip, and judging whether the voltage drop change exceeds a preset threshold change rate;
the detecting the output voltage drop change of the flyback chip comprises:
Collecting and setting an initial voltage value of the flyback chip under normal working conditions as a reference point;
monitoring the output voltage of the flyback chip in real time, and continuously recording voltage data;
identifying a falling trend of the voltage level by comparing the continuous voltage data;
Determining occurrence of voltage drop, and recording time points and duration periods of the voltage drop;
detecting whether the voltage drop of the output voltage of the flyback chip exceeds a first threshold voltage drop by using a first comparator, and outputting a turnover signal if the voltage drop exceeds the first threshold voltage drop;
the detecting a voltage drop of the flyback chip output voltage using a first comparator includes:
setting a first threshold voltage drop for identifying an initial anomaly of the voltage drop, the first threshold being determined based on the flyback chip design parameters and historical operating data;
Continuously monitoring the output voltage of the flyback chip, and immediately outputting a turnover signal by the first comparator corresponding to the detection that the voltage drop exceeds a first threshold voltage drop;
In response to the output toggle signal, analyzing a pressure drop event including an amplitude, a duration, and a frequency of occurrence of the pressure drop;
Recording a voltage drop event corresponding to the overturn signal;
Detecting whether the voltage drop of the output voltage of the flyback chip exceeds a second threshold voltage drop by using a second comparator, and outputting a turnover signal if the voltage drop exceeds the second threshold voltage drop, wherein the first threshold voltage drop is smaller than the second threshold voltage drop;
the detecting the voltage drop of the flyback chip output voltage by using the second comparator comprises:
setting a second threshold voltage drop for identifying an initial anomaly of the voltage drop, the second threshold being higher than the first threshold voltage drop;
when the output voltage drop of the flyback chip continuously exceeds a second threshold voltage drop, the second comparator outputs a turnover signal to indicate that the voltage drop reaches an abnormal state of a higher level;
Recording events of each output voltage drop exceeding a second threshold drop, including a time stamp and a drop amplitude;
starting to count at the output turning moment of the first comparator by using a timer so as to determine whether the pressure drop change exceeds a threshold change rate within a preset count time T;
the determining, using a timer, whether the pressure drop change exceeds a threshold rate of change within a preset timing time T includes:
Starting a timer while the first comparator outputs the flipping signal to capture a starting point of the voltage drop change;
setting preset time T of a timer, wherein the preset time T is determined based on normal response time and voltage recovery characteristics of a flyback chip;
continuously monitoring the output voltage of the flyback chip during the running period of the timer, and recording each change of the voltage value;
stopping timing and evaluating the total variation of the voltage drop in the time when the timer reaches the preset time T;
Comparing the evaluation result with a preset threshold change rate to determine whether the voltage drop change is abnormal;
if the voltage drop change does not exceed the threshold change rate within the preset time T, resetting the monitoring flow, and continuously monitoring the voltage state in real time;
Judging whether the loss state of the flyback chip is normal or not according to the output overturning signals of the first comparator and the second comparator and the timing result of the timer;
the judging whether the loss state of the flyback chip is normal or not according to the output turnover signals of the first comparator and the second comparator and the timing result of the timer comprises:
Collecting all the turnover signals output by the first comparator and the second comparator and corresponding timer records;
Clearing the turnover signal data, and removing abnormal values and noise interference through filtering and abnormal value removal;
calculating the statistical characteristics of voltage drop change in preset time T, wherein the statistical characteristics comprise average voltage drop value, standard deviation and change rate;
determining whether the voltage drop variation is within a normal range by comparing with an expected pattern under normal operating conditions;
based on the preprocessed overturn signals, evaluating the current loss state by analyzing and comparing historical data;
classifying the loss state as "normal" or "abnormal" according to the evaluation result, wherein "normal" means that the voltage drop change conforms to the expected mode, and "abnormal" means that there is an unexpected loss;
Evaluating the current loss state includes:
Defining and marking voltage drop change events in the historical data set, and classifying the voltage drop change events into two types of normal and abnormal;
Training an SVM model by utilizing normal and abnormal events in the historical data set, and determining a classification boundary of the SVM model;
Taking the cleaned overturn signal data and statistical characteristics as inputs, and applying a trained SVM model to evaluate the current loss state;
classifying the input feature vectors according to the learned mode through an SVM model, and outputting a prediction result of the loss state;
the loss state of the flyback chip is classified as "normal" or "abnormal" according to the output of the SVM model.
2. The method of claim 1, wherein training the SVM model to determine its classification boundaries comprises:
setting a training data set, wherein the training data set comprises voltage drop characteristics recorded by a flyback chip in different working states, and each characteristic sample is marked as a normal or abnormal loss type;
Performing standardized processing on the voltage drop characteristics in the training data set to eliminate the influence of dimensions under different working conditions;
Selecting an RBF function as a kernel function of the SVM, wherein a parameter gamma of the RBF kernel is determined according to the voltage stability and the sensitivity of the voltage drop change of the flyback chip, and optimizing on a verification set through grid search and cross verification;
Determining a regularization parameter C of an SVM model, wherein the regularization parameter C controls regularization strength of the model for classifying the loss state of the flyback chip;
and training an SVM model by using the optimized parameters C and gamma, and determining a classification boundary for distinguishing the normal loss state and the abnormal loss state of the flyback chip.
3. The method for monitoring the loss state of a flyback chip according to claim 2, wherein the specific step of solving the convex quadratic programming problem comprises the steps of:
Constructing an objective function of the SVM model, wherein the function is a convex quadratic programming problem and is used for minimizing regularization errors of the model;
Solving the objective function to obtain a weight vector and a bias term of the SVM model;
Determining a classification boundary by using the weight vector and the bias term obtained by solving, wherein the boundary can divide the voltage drop characteristic space into a normal loss state area and an abnormal loss state area;
classifying and predicting a new voltage drop characteristic sample by using the determined classification boundary, if the sample meets the condition of the classification boundary, predicting the sample as a normal loss state, otherwise, predicting the sample as an abnormal loss state;
and integrating the prediction result into a flyback chip loss monitoring system to realize real-time loss state evaluation and classification.
4. A flyback chip loss state monitoring system, the system comprising:
the voltage drop detection unit is used for monitoring the output voltage of the flyback chip in real time, detecting voltage drop change and judging whether the voltage drop change exceeds a preset threshold change rate or not;
detecting the output voltage drop change of the flyback chip comprises:
Collecting and setting an initial voltage value of the flyback chip under normal working conditions as a reference point;
monitoring the output voltage of the flyback chip in real time, and continuously recording voltage data;
identifying a falling trend of the voltage level by comparing the continuous voltage data;
Determining occurrence of voltage drop, and recording time points and duration periods of the voltage drop;
The first comparator unit is used for receiving the output of the voltage drop detection unit, detecting whether the voltage drop exceeds a first threshold voltage drop, and generating a turnover signal if the voltage drop exceeds the first threshold voltage drop;
detecting a voltage drop of the flyback chip output voltage using a first comparator, comprising:
setting a first threshold voltage drop for identifying an initial anomaly of the voltage drop, the first threshold being determined based on the flyback chip design parameters and historical operating data;
Continuously monitoring the output voltage of the flyback chip, and immediately outputting a turnover signal by the first comparator corresponding to the detection that the voltage drop exceeds a first threshold voltage drop;
In response to the output toggle signal, analyzing a pressure drop event including an amplitude, a duration, and a frequency of occurrence of the pressure drop;
Recording a voltage drop event corresponding to the overturn signal;
The second comparator unit is used for receiving the turnover signal of the first comparator unit and further detecting whether the voltage drop exceeds a second threshold voltage drop, and if so, generating a corresponding turnover signal, wherein the first threshold voltage drop is set to be smaller than the second threshold voltage drop;
detecting a voltage drop of the flyback chip output voltage using a second comparator, comprising:
setting a second threshold voltage drop for identifying an initial anomaly of the voltage drop, the second threshold being higher than the first threshold voltage drop;
when the output voltage drop of the flyback chip continuously exceeds a second threshold voltage drop, the second comparator outputs a turnover signal to indicate that the voltage drop reaches an abnormal state of a higher level;
Recording events of each output voltage drop exceeding a second threshold drop, including a time stamp and a drop amplitude;
A timer unit, synchronized with the output of the first comparator unit, started when the flip signal is generated, for determining whether the voltage drop change exceeds a threshold change rate within a preset timing time T;
determining whether the pressure drop change exceeds a threshold rate of change within a preset timer time T using a timer, comprising:
Starting a timer while the first comparator outputs the flipping signal to capture a starting point of the voltage drop change;
setting preset time T of a timer, wherein the preset time T is determined based on normal response time and voltage recovery characteristics of a flyback chip;
continuously monitoring the output voltage of the flyback chip during the running period of the timer, and recording each change of the voltage value;
stopping timing and evaluating the total variation of the voltage drop in the time when the timer reaches the preset time T;
Comparing the evaluation result with a preset threshold change rate to determine whether the voltage drop change is abnormal;
if the voltage drop change does not exceed the threshold change rate within the preset time T, resetting the monitoring flow, and continuously monitoring the voltage state in real time;
the loss state judging unit is used for receiving the overturning signals of the first comparator unit and the second comparator unit and the timing result of the timer unit, and analyzing and judging whether the loss state of the flyback chip is normal or not;
Judging whether the loss state of the flyback chip is normal or not according to the output overturning signals of the first comparator and the second comparator and the timing result of the timer comprises:
Collecting all the turnover signals output by the first comparator and the second comparator and corresponding timer records;
Clearing the turnover signal data, and removing abnormal values and noise interference through filtering and abnormal value removal;
calculating the statistical characteristics of voltage drop change in preset time T, wherein the statistical characteristics comprise average voltage drop value, standard deviation and change rate;
determining whether the voltage drop variation is within a normal range by comparing with an expected pattern under normal operating conditions;
based on the preprocessed overturn signals, evaluating the current loss state by analyzing and comparing historical data;
classifying the loss state as "normal" or "abnormal" according to the evaluation result, wherein "normal" means that the voltage drop change conforms to the expected mode, and "abnormal" means that there is an unexpected loss;
Evaluating the current loss state includes:
Defining and marking voltage drop change events in the historical data set, and classifying the voltage drop change events into two types of normal and abnormal;
Training an SVM model by utilizing normal and abnormal events in the historical data set, and determining a classification boundary of the SVM model;
Taking the cleaned overturn signal data and statistical characteristics as inputs, and applying a trained SVM model to evaluate the current loss state;
classifying the input feature vectors according to the learned mode through an SVM model, and outputting a prediction result of the loss state;
Classifying the loss state of the flyback chip as normal or abnormal according to the output of the SVM model;
and the control unit is used for executing a corresponding control strategy according to the analysis result of the loss state judging unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903409.8A CN118444200B (en) | 2024-07-08 | 2024-07-08 | Flyback chip loss state monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903409.8A CN118444200B (en) | 2024-07-08 | 2024-07-08 | Flyback chip loss state monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118444200A CN118444200A (en) | 2024-08-06 |
| CN118444200B true CN118444200B (en) | 2024-09-24 |
Family
ID=92309215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410903409.8A Active CN118444200B (en) | 2024-07-08 | 2024-07-08 | Flyback chip loss state monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118444200B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104578850A (en) * | 2015-01-15 | 2015-04-29 | 东南大学 | Constant voltage control method and circuit for AC-DC converter output voltages |
| CN112615529A (en) * | 2020-11-26 | 2021-04-06 | 苏州美思迪赛半导体技术有限公司 | Output voltage state detection method of switching power supply system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5098169A (en) * | 1990-10-22 | 1992-03-24 | Westinghouse Air Brake Company | Magnet valve safety check and fault indication integrator |
| KR200209176Y1 (en) * | 2000-07-27 | 2001-01-15 | 주식회사유진전자 | Induction Voltage Monitoring System |
| EP2509201B1 (en) * | 2011-04-04 | 2016-03-30 | Nxp B.V. | Controller for a quasi-resonant switch mode power supply |
| CN110855151B (en) * | 2019-11-26 | 2020-12-18 | 广州金升阳科技有限公司 | Positive and negative excitation type switching power supply circuit and control method thereof |
| CN114785147A (en) * | 2022-05-13 | 2022-07-22 | 杭州得明电子有限公司 | Flyback circuit system without input electrolytic capacitor |
| CN115173863A (en) * | 2022-06-27 | 2022-10-11 | 电子科技大学 | Knee point detection circuit based on slope detection |
| KR102618023B1 (en) * | 2022-12-23 | 2023-12-27 | 앤츠이엔씨 주식회사 | Failure prediction diagnosis system and method through pattern analysis according to failure type |
| CN118213936A (en) * | 2024-02-23 | 2024-06-18 | 王鼎 | Voltage monitoring and voltage protecting system and method |
| CN118300422A (en) * | 2024-04-17 | 2024-07-05 | 成都利普芯微电子有限公司 | Secondary control circuit, chip and switching power supply |
| CN118091490B (en) * | 2024-04-28 | 2024-07-30 | 国网辽宁省电力有限公司辽阳供电公司 | Overhead high-voltage cable line current detection method |
-
2024
- 2024-07-08 CN CN202410903409.8A patent/CN118444200B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104578850A (en) * | 2015-01-15 | 2015-04-29 | 东南大学 | Constant voltage control method and circuit for AC-DC converter output voltages |
| CN112615529A (en) * | 2020-11-26 | 2021-04-06 | 苏州美思迪赛半导体技术有限公司 | Output voltage state detection method of switching power supply system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118444200A (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11403160B2 (en) | Fault predicting system and fault prediction method | |
| KR102618023B1 (en) | Failure prediction diagnosis system and method through pattern analysis according to failure type | |
| EP2015186B1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| KR102249113B1 (en) | Automatic equipment failure prediction system in smart factory | |
| EP3105644B1 (en) | Method of identifying anomalies | |
| CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
| CN110366031A (en) | A kind of monitoring abnormal state and method for diagnosing faults digitizing workshop MES system view-based access control model | |
| CN118014341A (en) | Chemical industry garden safety risk assessment system and device | |
| CN118376936B (en) | Intelligent diagnosis method and system for lithium battery state | |
| KR102351538B1 (en) | System and method for predicting failure of automated facilities using and algorithm that learns and diagnoses patterns | |
| CN118030409A (en) | Method and system for detecting abnormal operation performance of fan unit | |
| KR20090061856A (en) | A system and method for statistical process control enabling process quality rules to be changed | |
| CN118444200B (en) | Flyback chip loss state monitoring method and system | |
| CN117520999B (en) | Intelligent operation and maintenance method and system for edge data center equipment | |
| CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
| CN117932268A (en) | Nuclear power equipment intelligent operation monitoring and fault diagnosis system | |
| CN118130927A (en) | Automatic fault detection method and system for charging pile equipment | |
| CN107533572B (en) | Process tool monitoring | |
| US11573153B2 (en) | Prediction of machine failure based on vibration trend information | |
| CN118224156B (en) | Hydraulic system abnormality monitoring method and system | |
| CN113454553A (en) | System and method for detecting and measuring anomalies in signaling originating from components used in industrial processes | |
| CN118503769B (en) | Automatic diagnosis system for operation faults of packaging and dotter | |
| CN117145753B (en) | Working quality testing method and device for air compressor | |
| CN117493129B (en) | Operating power monitoring system of computer control equipment | |
| CN117521478A (en) | Cloud computing out-of-band management equipment auxiliary alarm method based on machine learning |
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 |