A method and apparatus for detecting the status of a solenoid valve

Abstract

This invention relates to the field of solenoid valve condition detection technology, and discloses a method and apparatus for solenoid valve condition detection. The method involves: acquiring historical and current data on potential difference changes over time; filtering the current data using a preset filter to plot a potential difference change curve; extracting geometric features of the switching action and performing consistency evaluation to obtain the switching state; determining the coil's fault state based on the potential difference change curve and geometric features; analyzing the response time and assessing the coil's aging degree based on the potential difference change curve; fitting an aging index using a linear regression algorithm based on historical data to predict the coil's lifespan and generating a maintenance recommendation report; integrating the above data into a health status report; and classifying the health status report using a clustering algorithm to obtain optimized maintenance strategies. This invention improves the accuracy of determining the correspondence between potential difference changes and solenoid valve conditions.

Description

Technical Field

[0001] This invention relates to the field of solenoid valve condition detection technology, and in particular to a solenoid valve condition detection method and apparatus. Background Technology

[0002] Currently, in modern industrial production, solenoid valves, as key components for controlling pneumatic and hydraulic devices, are widely used in various industrial scenarios, such as factory automated production lines, energy management devices, and fluid control. The performance and reliability of solenoid valves directly determine the normal operation of equipment and the quality of products. However, during long-term use, the insulation performance of the solenoid valve coil gradually deteriorates, leading to problems such as coil damage or poor contact. These problems not only affect the normal switching function of the solenoid valve but may also cause equipment downtime, thereby impacting production efficiency and product quality.

[0003] Currently, most enterprises still rely primarily on manual inspections for solenoid valve condition monitoring. This method has several problems, such as untimely and inaccurate monitoring, and the potential for missing potential faults. Although some solenoid valve condition monitoring devices are available on the market, most of these devices can only detect the on / off state of the solenoid valve and cannot monitor the health status of the solenoid valve coil in real time. For example, some devices only determine whether the solenoid valve is in an on / off state through simple current or voltage detection, but cannot deeply monitor changes in the coil insulation performance. Therefore, developing a technology that can monitor the health status of solenoid valve coils in real time is of great significance for improving equipment reliability and production efficiency.

[0004] In the existing technology, due to the complex working environment of the solenoid valve, the change of potential difference may be affected by a variety of factors, resulting in a high misjudgment rate and a problem of poor accuracy in judging the correspondence between the change of potential difference and the state of the solenoid valve. Summary of the Invention

[0005] This invention provides a method and apparatus for detecting the state of a solenoid valve, thereby improving the accuracy of determining the correspondence between changes in potential difference and the state of the solenoid valve.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a method for detecting the state of a solenoid valve, comprising: Acquire historical and current data on the change of potential difference over time; The current data is filtered according to a preset filter, and the potential difference change curve is plotted. Based on the potential difference change curve, the geometric features of the switching action are extracted, and the consistency of the geometric features is evaluated to obtain the switching state of the solenoid valve. Based on the potential difference change curve and the geometric features, the fault state of the coil is obtained. If a fault occurs, a fault alarm signal is generated. Based on the potential difference change curve, the response time is analyzed, and the aging degree of the coil is evaluated based on the response time. Based on the historical data, the potential difference change curve and the degree of aging are fitted using a linear regression algorithm to obtain the predicted value of the aging index. Based on the predicted aging index value, the remaining service life of the coil is predicted, and a maintenance recommendation report is generated based on the remaining service life. The historical data, current data, switch status, fault alarm signal, aging level, and maintenance suggestions are integrated into a health status report, which is then transmitted to the monitoring device through the industrial IoT platform. Clustering algorithms are used to classify the health status reports to obtain optimized maintenance strategies.

[0007] In one optional implementation, the step of filtering the current data according to a preset filter to obtain a potential difference change curve includes: Based on the noise characteristics of the solenoid valve's working environment, select a suitable type and order of filter, and design the cutoff frequency of the filter to obtain a preset filter. The current data is filtered using the preset filter to remove high-frequency noise and low-frequency interference, resulting in processed data. Based on the processed data, a smooth potential difference change curve is plotted.

[0008] In one optional implementation, the step of extracting geometric features of the switching action based on the potential difference change curve, and performing a consistency evaluation on the geometric features to obtain the switching state of the solenoid valve includes: Based on the potential difference change curve, a potential difference time series is constructed; Feature extraction is performed on the potential difference time series to obtain the rising edge slope and falling edge slope of each switching action, which are used as geometric features; The slope range of normal switching actions is obtained by clustering the geometric features of multiple switching actions using a clustering algorithm. Based on the slope range, determine whether the geometric feature is within the slope range. If it is not within the slope range, determine that the switching action is abnormal. If it is within the slope range, determine that the switching action is normal. The number of abnormal switching actions is counted. If the number of abnormal actions exceeds a preset threshold, the switching action of the solenoid valve is determined to be abnormal. If the number of abnormal actions does not exceed the preset threshold, the switching action of the solenoid valve is determined to be normal.

[0009] In one optional implementation, the step of obtaining the coil's fault state based on the potential difference change curve and the geometric features, and generating a fault alarm signal if a fault occurs, includes: Based on the potential difference change curve, noise reduction and smoothing operations are performed to obtain the optimized potential difference change curve. Based on the geometric features and the optimized potential difference change curve, the switching action time data and the steady-state potential difference value data are obtained. The optimized potential difference change curve is judged. If the optimized potential difference change curve has missing data, it is judged as an abnormal potential difference. Based on the switch action time data, it is compared with a preset action time threshold. If it exceeds the threshold, it is determined that the switch action time is abnormal. Based on the steady-state potential difference data, it is compared with a preset normal range. If it exceeds the normal range, it is determined that the steady-state potential difference is abnormal. Based on the judgment results of the abnormal potential difference, the abnormal switching action time, and the abnormal steady-state value of the potential difference, a preset decision tree algorithm model is used to determine whether there is a fault in the coil. If there is a fault in the coil, a fault alarm signal is generated.

[0010] In one optional implementation, the step of analyzing the response time based on the potential difference change curve and assessing the aging degree of the coil based on the response time includes: Based on the potential difference change curve, extract the time points of the on and off states; Based on the stated time point, calculate the time difference between the opening and closing states of the solenoid valve to obtain the response time; Based on the response time, the input is fed into a preset support vector machine regression algorithm to obtain the aging degree of the coil.

[0011] In one optional implementation, the step of fitting the aging index prediction value to the potential difference change curve and the aging degree using a linear regression algorithm based on the historical data includes: Based on the historical data and the degree of aging, a training dataset is constructed; The training dataset is preprocessed to remove outliers and noisy data, resulting in preprocessed data. Based on the preprocessed data, the least squares method was used to perform linear regression fitting to obtain a linear relationship between the change in potential difference and the degree of aging. The current data is input into the linear relationship to calculate the corresponding aging index prediction value.

[0012] In one optional implementation, the step of predicting the remaining service life of the coil based on the aging index prediction value, and generating a maintenance recommendation report based on the remaining service life, includes: Based on the predicted aging index value, the remaining service life of the coil is predicted using a preset support vector machine regression model; Determine the optimal maintenance time based on the remaining service life. Based on the optimal maintenance time point, an association rule mining algorithm is used to obtain frequent itemsets; Association rules are generated based on the frequent itemsets, and a maintenance suggestion report is obtained.

[0013] In one optional implementation, the step of integrating the historical data, the current data, the switch status, the fault alarm signal, the aging level, and the maintenance recommendations into a health status report, and transmitting it to the monitoring device via an industrial IoT platform, includes: Based on the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions, the data is cleaned and transformed using data preprocessing and feature extraction methods to obtain a standardized feature vector; Based on the pre-established equipment health status assessment model, the support vector machine algorithm is used to classify the feature vectors and determine the current health status level of the equipment. Based on the health status level, and in conjunction with the maintenance suggestion knowledge base, equipment maintenance suggestions are generated. Based on the health status level and the equipment maintenance recommendations, the two are integrated into an equipment health status report and transmitted to the monitoring device through an industrial IoT platform.

[0014] In one optional implementation, the step of classifying the health status reports using a clustering algorithm to obtain an optimized maintenance strategy includes: Based on the health status report, the data portion is preprocessed and normalized to obtain feature data; The K-means clustering algorithm was used to perform cluster analysis on the extracted feature data to obtain cluster centers; Calculate the equipment's failure risk score based on the cluster centers and the feature data; Based on the aforementioned fault risk score, an optimized maintenance strategy is obtained.

[0015] In a second aspect, the present invention provides a solenoid valve status detection device, comprising: The data acquisition module is used to acquire historical and current data on the change of potential difference over time. The data processing module is used to filter the current data according to a preset filter and plot the potential difference change curve. The state detection module is used to extract the geometric features of the switching action based on the potential difference change curve, perform a consistency evaluation on the geometric features, and obtain the switching state of the solenoid valve. The fault detection module is used to determine the fault state of the coil based on the potential difference change curve and the geometric features. If a fault occurs, a fault alarm signal is generated. An aging detection module is used to analyze the response time based on the potential difference change curve and to evaluate the degree of aging of the coil based on the response time. An alarm module is used to obtain a predicted aging index value by fitting the historical data, the potential difference change curve and the degree of aging using a linear regression algorithm. The recommended report generation module is used to predict the remaining service life of the coil based on the aging index prediction value, and generate a maintenance recommendation report based on the remaining service life. The health status generation module is used to integrate the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions into a health status report, which is then transmitted to the monitoring device through the industrial Internet of Things platform. The optimization strategy generation module is used to classify the health status report using a clustering algorithm to obtain an optimization maintenance strategy.

[0016] Thirdly, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the solenoid valve state detection method described in any one of the above.

[0017] Fourthly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the solenoid valve status detection method described in any one of the above.

[0018] Compared with the prior art, the present invention has the following beneficial effects: This invention relates to the field of solenoid valve condition detection technology, and discloses a method and apparatus for solenoid valve condition detection. The method involves: acquiring historical and current data on potential difference changes over time; filtering the current data using a preset filter to plot a potential difference change curve; extracting geometric features of the switching action and performing consistency evaluation to obtain the switching state; determining the coil's fault state based on the potential difference change curve and geometric features; analyzing the response time and assessing the coil's aging degree based on the potential difference change curve; fitting an aging index using a linear regression algorithm based on historical data to predict the coil's lifespan and generating a maintenance recommendation report; integrating the above data into a health status report; and classifying the health status report using a clustering algorithm to obtain optimized maintenance strategies. This method can improve the accuracy of determining the correspondence between potential difference changes and solenoid valve states.

[0019] This invention acquires historical and current data on potential difference changes over time, and processes the data using a preset filter to accurately plot the potential difference change curve, providing a reliable data foundation for subsequent feature extraction and consistency assessment of switching actions. Through feature extraction and consistency assessment, the switching status and operating condition of the solenoid valve can be determined more accurately, thereby effectively identifying the solenoid valve's fault state, such as coil failure or aging. Using a linear regression algorithm to fit the aging index and predict the coil's lifespan provides a scientific basis for equipment maintenance, offering early warnings of potential faults and preventing production line shutdowns or equipment damage due to sudden equipment failures. This invention, through cluster analysis of health status reports, can automatically classify different maintenance needs, optimize maintenance strategies, and help equipment managers develop more accurate and efficient maintenance plans, reducing maintenance costs and improving equipment lifespan and production efficiency. This intelligent and automated solenoid valve status detection method significantly improves the accuracy of solenoid valve fault diagnosis, and this invention can improve the accuracy of determining the correspondence between potential difference changes and solenoid valve status. Attached Figure Description

[0020] Figure 1 This is a schematic flowchart of a solenoid valve status detection method provided in the first embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a solenoid valve status detection device provided in the second embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Reference Figure 1 The first embodiment of the present invention provides a method for detecting the state of a solenoid valve, comprising the following steps: S11, acquire historical and current data on the change of potential difference over time; S12, The current data is filtered according to a preset filter to obtain a potential difference change curve; S13, Based on the potential difference change curve, the geometric features of the switching action are extracted, and the consistency of the geometric features is evaluated to obtain the switching state of the solenoid valve. S14. Based on the potential difference change curve and the geometric features, the fault state of the coil is obtained. If a fault occurs, a fault alarm signal is generated. S15, Based on the potential difference change curve, the response time is analyzed, and the aging degree of the coil is evaluated based on the response time; S16. Based on the historical data, the potential difference change curve and the degree of aging are fitted with a linear regression algorithm to obtain the predicted value of the aging index. S17, Based on the predicted aging index value, predict the remaining service life of the coil, and generate a maintenance recommendation report based on the remaining service life; S18, integrate the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions into a health status report, and transmit it to the monitoring device through the industrial Internet of Things platform; S19, use a clustering algorithm to classify the health status reports to obtain an optimized maintenance strategy.

[0023] In step S11, historical data and current data of potential difference changes over time are obtained.

[0024] It's important to note that potential difference is the voltage change generated when current flows through a solenoid valve coil after it's energized, reflecting the coil's electrical characteristics and operating state. Historical data refers to recorded potential difference changes over a period of time, used to capture the long-term behavior of the solenoid valve. Current data, on the other hand, is potential difference data acquired during real-time monitoring, reflecting the solenoid valve's current state. This data allows for comprehensive analysis of the solenoid valve's performance, identification of potential problems, and provides a foundation for subsequent fault diagnosis and health assessment. Data acquisition requires real-time collection using high-precision sensors, and the data acquisition frequency must be sufficiently high to capture potential difference changes in different operating states of the solenoid valve.

[0025] In step S12, the current data is filtered according to a preset filter to obtain a potential difference change curve.

[0026] In one implementation, the step of filtering the current data according to a preset filter to plot the potential difference change curve includes: Based on the noise characteristics of the solenoid valve's working environment, select a suitable type and order of filter, and design the cutoff frequency of the filter to obtain a preset filter. The current data is filtered using the preset filter to remove high-frequency noise and low-frequency interference, resulting in processed data. Based on the processed data, a smooth potential difference change curve is plotted.

[0027] It is important to note that the selection and design of the filter are crucial to the accuracy and reliability of the potential difference curve. First, the type and order of the filter should be determined based on the noise characteristics of the solenoid valve's operating environment to ensure effective filtering of environmental noise without losing important signal characteristics. The solenoid valve's operating environment includes various electrical noises and mechanical vibration interferences, which affect the accuracy of the potential difference data. By selecting an appropriate filter type (such as a low-pass filter, high-pass filter, or band-pass filter), unwanted frequency components can be precisely removed. For example, in an environment with high-frequency noise interference, a second-order low-pass filter with a cutoff frequency of 100Hz can be selected to effectively filter out high-frequency noise and retain low-frequency signals. In scenarios requiring the removal of low-frequency interference, such as ECG signal processing, a high-pass filter can be used to filter out low-frequency drift and retain high-frequency ECG signals. For applications requiring the extraction of signals within a specific frequency range, such as RF antennas in wireless communication, a band-pass filter can be designed to allow signals in that specific frequency band to pass through while suppressing signals in other frequency bands.

[0028] It should be noted that the cutoff frequency of the filter needs to be set according to the actual frequency range of the potential difference signal and the characteristics of the noise. A reasonable cutoff frequency can effectively isolate high-frequency noise and low-frequency interference in the signal, ensuring that the filtered data more accurately reflects the actual working state of the solenoid valve.

[0029] In step S13, based on the potential difference change curve, the geometric features of the switching action are extracted, and the consistency of the geometric features is evaluated to obtain the switching state of the solenoid valve.

[0030] In one implementation, the step of extracting geometric features of the switching action based on the potential difference change curve, and performing a consistency evaluation on the geometric features to obtain the switching state of the solenoid valve includes: Based on the potential difference change curve, a potential difference time series is constructed; Feature extraction is performed on the potential difference time series to obtain the rising edge slope and falling edge slope of each switching action, which are used as geometric features; The slope range of normal switching actions is obtained by clustering the geometric features of multiple switching actions using a clustering algorithm. Based on the slope range, determine whether the geometric feature is within the slope range. If it is not within the slope range, determine that the switching action is abnormal. If it is within the slope range, determine that the switching action is normal. The number of abnormal switching actions is counted. If the number of abnormal actions exceeds a preset threshold, the switching action of the solenoid valve is determined to be abnormal. If the number of abnormal actions does not exceed the preset threshold, the switching action of the solenoid valve is determined to be normal.

[0031] It should be noted that clustering algorithms are unsupervised learning methods that aim to divide samples in a dataset into multiple groups (clusters) based on a certain similarity metric. Data points within each cluster should be as similar as possible, while data points between different clusters should be as dissimilar as possible. In this implementation, the clustering algorithm performs cluster analysis on the geometric features of multiple switching actions (such as rising and falling edge slopes), grouping similar slope values ​​into one category, thereby determining the slope range of normal switching actions. The clustering algorithm used in this invention is K-Means, which iteratively divides data points into K clusters, minimizing the sum of the distances from each data point to the center of its cluster.

[0032] It should be noted that the slope range is obtained through cluster analysis of the geometric features of multiple switching actions. Specifically, the clustering algorithm uses the rising and falling edge slopes of multiple switching actions as feature vectors, and groups them according to the similarity of these feature vectors, classifying similar slope values ​​into one category, thereby determining the slope range of normal switching actions. This range reflects the switching action characteristics of the solenoid valve under normal operating conditions. By comparing the slope of each switching action with this range, it is possible to determine whether the switching action is abnormal.

[0033] It should be noted that the threshold number is a preset standard value used to determine whether the solenoid valve's switching status is normal when counting the number of abnormal switching actions. For example, if the threshold number is set to 3, then if the number of abnormal actions exceeds 3 in 100 consecutive switching actions, the solenoid valve's switching action is determined to be abnormal, and further inspection and maintenance are required.

[0034] It is worth noting that during feature extraction, the potential difference change curve reflects the electrical characteristics of the solenoid valve during switching. By constructing a potential difference time series, the relationship between potential difference changes and time can be presented, providing data for subsequent feature extraction. For example, the construction of the potential difference time series can extract the potential difference value at each time point from the potential difference change curve. If the curve is discrete, the recorded data points are directly extracted; if the curve is continuous, more potential difference values ​​at different time points can be obtained through curve fitting or interpolation methods. The extracted potential difference values ​​are then arranged in chronological order to form a time series. The rising edge slope and falling edge slope in the potential difference time series are key geometric features in the solenoid valve's switching action. They directly reflect the rate of current change during the opening and closing of the solenoid valve and can reveal the performance of the solenoid valve. The rising edge and falling edge slope values ​​are affected by factors such as the quality of the solenoid valve coil and the switching response speed; therefore, abnormal changes in the slope values ​​are an indication of a solenoid valve malfunction.

[0035] In step S14, the fault state of the coil is obtained based on the potential difference change curve and the geometric features. If a fault occurs, a fault alarm signal is generated.

[0036] In one implementation, the step of obtaining the coil's fault state based on the potential difference change curve and the geometric characteristics, and generating a fault alarm signal if a fault occurs, includes: Based on the potential difference change curve, noise reduction and smoothing operations are performed to obtain the optimized potential difference change curve. Based on the geometric features and the optimized potential difference change curve, the switching action time data and the steady-state potential difference value data are obtained. The optimized potential difference change curve is judged. If the optimized potential difference change curve has missing data, it is judged as an abnormal potential difference. Based on the switch action time data, it is compared with a preset action time threshold. If it exceeds the threshold, it is determined that the switch action time is abnormal. Based on the steady-state potential difference data, it is compared with a preset normal range. If it exceeds the normal range, it is determined that the steady-state potential difference is abnormal. Based on the judgment results of the abnormal potential difference, the abnormal switching action time, and the abnormal steady-state value of the potential difference, a preset decision tree algorithm model is used to determine whether there is a fault in the coil. If there is a fault in the coil, a fault alarm signal is generated.

[0037] It should be noted that, based on the geometric features and the optimized potential difference change curve, the switching action time data is determined by identifying the rising and falling edges of the curve, i.e., the time difference from the opening to the closing of the solenoid valve; the steady-state potential difference value data is extracted by analyzing the stable region of the curve when the solenoid valve is operating stably, and this invention takes the average value of this region as the steady-state value. The geometric features provide physical background information about the solenoid valve, which helps to more accurately identify and interpret the curve features, thereby ensuring more reliable extraction of the switching action time and the steady-state potential difference value.

[0038] It should be noted that coil fault detection relies on a comprehensive analysis of the potential difference change curve and geometric characteristics. First, denoising and smoothing operations yield an optimized potential difference change curve, effectively removing noise and unnecessary interference signals, making subsequent data analysis more accurate. The optimized potential difference change curve accurately reflects the solenoid valve's operating state and is the basis for determining whether the coil has malfunctioned.

[0039] It's worth noting that during the judgment process, the first step is to check for missing data based on the optimized potential difference change curve. If there are significant data gaps in the potential difference curve, it indicates abnormal signal acquisition or an interruption fault in the solenoid valve, which is marked as an abnormal potential difference. Next, the switching action time data is compared with the preset action time threshold. If the switching action time exceeds the threshold, it indicates a delay in the solenoid valve's response time, leading to abnormal switching action, which is judged as an abnormal switching action time. Finally, the steady-state potential difference value is the stable value of the potential difference during long-term operation of the solenoid valve. If this value exceeds the preset normal range, it means that the electrical performance of the coil has deteriorated or there is a fault.

[0040] In step S15, the response time is obtained by analyzing the potential difference change curve, and the aging degree of the coil is evaluated based on the response time.

[0041] In one implementation, the step of analyzing the response time based on the potential difference change curve and assessing the aging degree of the coil based on the response time includes: Based on the potential difference change curve, extract the time points of the on and off states; Based on the stated time point, calculate the time difference between the opening and closing states of the solenoid valve to obtain the response time; Based on the response time, the input is fed into a preset support vector machine regression algorithm to obtain the aging degree of the coil.

[0042] It should be noted that in step S15, the response time is analyzed based on the potential difference change curve, and the aging degree of the coil is assessed based on the response time. Specifically, the time points for the open and closed states are extracted by analyzing the potential difference change curve. First, the transition time of the solenoid valve from the open to the closed state is determined based on the characteristic points (inflection points) of the curve. For example, the moment when the potential difference rises from low to high and exceeds a certain threshold is defined as the open time point, and the moment when the potential difference falls from high to low and falls below the threshold is defined as the close time point. By accurately extracting these time points, the response time of the solenoid valve can be accurately calculated, thus providing key data support for assessing the aging degree of the coil.

[0043] It is important to note that response time is a crucial indicator for assessing the aging of a solenoid valve coil. By analyzing the opening and closing time points in the potential difference change curve, the response time of the solenoid valve—that is, the time difference between opening and closing—can be accurately calculated. The physical mechanism by which response time relates to coil aging is primarily that increased resistance in an aging coil slows down the rate of current change, prolonging the opening and closing action time of the solenoid valve; short circuits between coil turns or degradation of the magnetic core performance alter the inductance value, affecting the dynamic response of the magnetic field and thus extending the response time. Therefore, response time (i.e., the time difference between opening and closing) can serve as a direct indicator of the degree of coil aging. This response time reflects the speed of the solenoid valve's switching action; as the coil ages, its response time increases, making changes in response time a key basis for assessing the degree of coil aging.

[0044] It should be noted that the preset Support Vector Machine (SVR) regression algorithm uses response time as an input feature and leverages the nonlinear mapping learned during its training phase to predict the aging degree of the coil. The core idea of ​​SVR is to find a regression function in a high-dimensional space that can fit the data points as accurately as possible within an acceptable error range. By minimizing the combined objectives of prediction error and model complexity, SVR can effectively handle problems such as small sample sizes and nonlinearity.

[0045] For example, a regression model is constructed based on historical data to establish a mapping relationship between response time and known aging level. The input of the regression model is the response time, and the output is the aging level (0-100%). Support Vector Machine (SVR) regression is used, with Radial Basis Function (RBF) selected as the kernel function. Hyperparameters (such as penalty coefficient and kernel width) are optimized to minimize prediction error. Furthermore, model validation can be performed, and model accuracy can be evaluated through cross-validation to ensure that the mean absolute error (MAE) is <5%. For example, the aging level can be set to 0% (new), 20% (mildly aged), 50% (moderately aged), 80% (severely aged), and 100% (completely failed).

[0046] In step S16, based on the historical data, the potential difference change curve and the degree of aging are fitted using a linear regression algorithm to obtain the predicted value of the aging index.

[0047] In one implementation, the step of using a linear regression algorithm to fit the potential difference change curve with the aging degree based on the historical data to obtain a predicted aging index includes: Based on the historical data and the degree of aging, a training dataset is constructed; The training dataset is preprocessed to remove outliers and noisy data, resulting in preprocessed data. Based on the preprocessed data, the least squares method was used to perform linear regression fitting to obtain a linear relationship between the change in potential difference and the degree of aging. The current data is input into the linear relationship to calculate the corresponding aging index prediction value.

[0048] It's important to note that the least squares method determines the optimal linear relationship by minimizing the sum of the squared differences between the observed aging index and the model's predicted value. The change in the current potential difference is substituted into the above formula to predict the coil's aging index. The core of this method lies in finding the best-fit line among numerous data points, minimizing the overall difference between the predicted and actual observations. By establishing this linear model, we can accurately estimate the coil's aging degree, thereby effectively assessing and managing its maintenance needs.

[0049] It should be noted that the core of the linear regression algorithm is to construct a mathematical model (linear relationship) by analyzing the relationship between the potential difference change curve and the aging degree of the coil in historical data, and then use this model to predict the aging index of the coil at the current moment. Through linear regression, the potential linear relationship between potential difference change and aging degree can be revealed, thereby predicting the aging of the coil.

[0050] In step S17, the remaining service life of the coil is predicted based on the aging index prediction value, and a maintenance recommendation report is generated based on the remaining service life.

[0051] In one implementation, the step of predicting the remaining service life of the coil based on the aging index prediction value, and generating a maintenance recommendation report based on the remaining service life, includes: Based on the predicted aging index value, the remaining service life of the coil is predicted using a preset support vector machine regression model; Determine the optimal maintenance time based on the remaining service life. Based on the optimal maintenance time point, an association rule mining algorithm is used to obtain frequent itemsets; Association rules are generated based on the frequent itemsets, and a maintenance suggestion report is obtained.

[0052] It's important to note that association rule mining algorithms are data mining techniques used to find relationships between items in large-scale datasets. Their core principle is to generate association rules by analyzing frequent itemsets in the dataset. For example, in market basket analysis, this algorithm can discover potential associations between customer purchases, such as "customers who buy milk also buy bread." The algorithm measures the strength and reliability of rules based on metrics like support and confidence. Support represents the frequency with which a given itemset appears in all transactions, while confidence represents the probability that a transaction containing the preceding item also contains the following item.

[0053] It is important to note that remaining service life prediction is a crucial aspect of equipment maintenance management. Accurately predicting the remaining service life of coils provides a scientific basis for maintenance decisions, thereby optimizing the allocation of maintenance resources and preventing equipment failures. The optimal maintenance balance point is found by analyzing the aging index prediction value and the remaining service life, combined with the equipment's condition. This step uses the aging index prediction value to determine the remaining service life of the coils and generate a maintenance recommendation report, ensuring more efficient and stable equipment operation.

[0054] It should be noted that Support Vector Machine (SVM) regression is a machine learning method commonly used to handle nonlinear regression problems. It builds a regression model to predict the remaining lifespan of a coil based on the aging index prediction. SVM regression effectively captures the complex relationships in the input data, ensuring the accuracy of the prediction between the aging index and the remaining lifespan.

[0055] In step S18, the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions are integrated into a health status report, which is then transmitted to the monitoring device through the industrial Internet of Things platform.

[0056] In one implementation, integrating the historical data, the current data, the switch status, the fault alarm signal, the aging level, and the maintenance recommendations into a health status report, and transmitting it to the monitoring device via an industrial IoT platform, includes: Based on the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions, the data is cleaned and transformed using data preprocessing and feature extraction methods to obtain a standardized feature vector; Based on the pre-established equipment health status assessment model, the support vector machine algorithm is used to classify the feature vectors and determine the current health status level of the equipment. Based on the health status level, and in conjunction with the maintenance suggestion knowledge base, equipment maintenance suggestions are generated. Based on the health status level and the equipment maintenance recommendations, the two are integrated into an equipment health status report and transmitted to the monitoring device through an industrial IoT platform.

[0057] It should be noted that the generation and transmission of health status reports are crucial steps in achieving intelligent equipment management and maintenance. By integrating and transmitting key data from the solenoid valve equipment to the monitoring device, the equipment's health status can be monitored in real time, and necessary maintenance measures can be taken promptly, thereby ensuring the long-term stable operation of the equipment. This step involves several key stages, including data preprocessing, feature extraction, health status assessment, and maintenance recommendation generation.

[0058] In step S19, a clustering algorithm is used to classify the health status reports to obtain an optimized maintenance strategy.

[0059] In one implementation, the step of classifying the health status reports using a clustering algorithm to obtain an optimized maintenance strategy includes: Based on the health status report, the data portion is preprocessed and normalized to obtain feature data; The K-means clustering algorithm was used to perform cluster analysis on the extracted feature data to obtain cluster centers; Calculate the equipment's failure risk score based on the cluster centers and the feature data; Based on the aforementioned fault risk score, an optimized maintenance strategy is obtained.

[0060] It should be noted that the preprocessing operations include handling missing values, denoising, and outlier handling; the normalization operation uses min-max normalization to eliminate the influence of different magnitudes on the analysis. The K-means clustering algorithm divides the equipment feature data into multiple groups to identify different operating states. Based on the cluster centers and the feature data, the fault risk score of the equipment is calculated by evaluating the distance between the feature data and the cluster centers. Specifically, firstly, the Euclidean distance from the feature data of each device to its respective cluster center is calculated, which reflects the degree of deviation of the equipment's health status from the typical health status. Then, a fault risk score is assigned according to the distance; the larger the distance, the more the equipment's health status deviates from the normal state, and the higher the fault risk; in this embodiment of the invention, the range of distance is not limited. The optimized maintenance strategy first arranges the equipment maintenance order from high to low according to the risk score, dynamically adjusts the maintenance cycle, and allocates resources according to the risk score.

[0061] In summary, this invention discloses a method for detecting the status of a solenoid valve, comprising: acquiring historical and current data on the change of potential difference over time; filtering the current data according to a preset filter to plot a potential difference change curve; extracting geometric features of the switching action and performing consistency evaluation to obtain the switching status; determining the fault status of the coil based on the potential difference change curve and geometric features; analyzing the response time and evaluating the aging degree of the coil based on the potential difference change curve; fitting the aging index using a linear regression algorithm based on historical data and predicting the service life of the coil to generate a maintenance recommendation report; integrating the above data into a health status report; and classifying the health status report using a clustering algorithm to obtain an optimized maintenance strategy. This method can improve the accuracy of determining the correspondence between potential difference changes and the solenoid valve status.

[0062] This invention acquires historical and current data on potential difference changes over time, and processes the data using a preset filter to accurately plot the potential difference change curve, providing a reliable data foundation for subsequent feature extraction and consistency assessment of switching actions. Through feature extraction and consistency assessment, the switching status and operating condition of the solenoid valve can be determined more accurately, thereby effectively identifying the solenoid valve's fault state, such as coil failure or aging. Using a linear regression algorithm to fit the aging index and predict the coil's lifespan provides a scientific basis for equipment maintenance, offering early warnings of potential faults and preventing production line shutdowns or equipment damage due to sudden equipment failures. This invention, through cluster analysis of health status reports, can automatically classify different maintenance needs, optimize maintenance strategies, and help equipment managers develop more accurate and efficient maintenance plans, reducing maintenance costs and improving equipment lifespan and production efficiency. This intelligent and automated solenoid valve status detection method significantly improves the accuracy of solenoid valve fault diagnosis, and this invention can improve the accuracy of determining the correspondence between potential difference changes and solenoid valve status.

[0063] Reference Figure 2 The second embodiment of the present invention provides a solenoid valve status detection device, comprising: The data acquisition module is used to acquire historical and current data on the change of potential difference over time. The data processing module is used to filter the current data according to a preset filter and plot the potential difference change curve. The state detection module is used to extract the geometric features of the switching action based on the potential difference change curve, perform a consistency evaluation on the geometric features, and obtain the switching state of the solenoid valve. The fault detection module is used to determine the fault state of the coil based on the potential difference change curve and the geometric features. If a fault occurs, a fault alarm signal is generated. An aging detection module is used to analyze the response time based on the potential difference change curve and to evaluate the degree of aging of the coil based on the response time. An alarm module is used to obtain a predicted aging index value by fitting the historical data, the potential difference change curve and the degree of aging using a linear regression algorithm. The recommended report generation module is used to predict the remaining service life of the coil based on the aging index prediction value, and generate a maintenance recommendation report based on the remaining service life. The health status generation module is used to integrate the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions into a health status report, which is then transmitted to the monitoring device through the industrial Internet of Things platform. The optimization strategy generation module is used to classify the health status report using a clustering algorithm to obtain an optimization maintenance strategy.

[0064] It should be noted that the solenoid valve status detection device provided in this embodiment of the invention is used to execute all the process steps of the solenoid valve status detection method in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0065] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a suggestion report generation program. When the processor executes the computer program, it implements the steps in the various embodiments of the solenoid valve state detection methods described above, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the suggestion report generation module.

[0066] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0067] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0068] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0069] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating device and applications required for at least one function (such as sound playback function, image playback function, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory and non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0070] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0071] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0072] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for detecting the status of a solenoid valve, characterized in that, Executed by a computer, including: Acquire historical and current data on the change of potential difference over time; The current data is filtered according to a preset filter, and the potential difference change curve is plotted. Based on the potential difference change curve, the geometric features of the switching action are extracted, and the consistency of the geometric features is evaluated to obtain the switching state of the solenoid valve. Based on the potential difference change curve and the geometric features, the fault state of the coil is obtained. If a fault occurs, a fault alarm signal is generated. Based on the potential difference change curve, the response time is analyzed, and the aging degree of the coil is evaluated based on the response time. Based on the historical data, the potential difference change curve and the degree of aging are fitted using a linear regression algorithm to obtain the predicted value of the aging index. Based on the predicted aging index value, the remaining service life of the coil is predicted, and a maintenance recommendation report is generated based on the remaining service life. The historical data, current data, switch status, fault alarm signal, aging level, and maintenance suggestions are integrated into a health status report, which is then transmitted to the monitoring device through the industrial IoT platform. Clustering algorithms are used to classify the health status reports to obtain optimized maintenance strategies; The step of extracting the geometric features of the switching action based on the potential difference change curve includes: Based on the potential difference change curve, a potential difference time series is constructed; Feature extraction is performed on the potential difference time series to obtain the rising edge slope and falling edge slope of each switching action, which are used as geometric features; The step of obtaining the coil's fault state based on the potential difference change curve and the geometric characteristics, and generating a fault alarm signal if a fault occurs, includes: Based on the potential difference change curve, noise reduction and smoothing operations are performed to obtain the optimized potential difference change curve. Based on the geometric features and the optimized potential difference change curve, the switching action time data and the steady-state potential difference value data are obtained. The optimized potential difference change curve is judged. If the optimized potential difference change curve has missing data, it is judged as an abnormal potential difference. Based on the switch action time data, it is compared with a preset action time threshold. If it exceeds the threshold, it is determined that the switch action time is abnormal. Based on the steady-state potential difference data, it is compared with a preset normal range. If it exceeds the normal range, it is determined that the steady-state potential difference is abnormal. Based on the judgment results of the abnormal potential difference, the abnormal switching action time, and the abnormal steady-state value of the potential difference, a preset decision tree algorithm model is used to determine whether there is a fault in the coil. If there is a fault in the coil, a fault alarm signal is generated.

2. The solenoid valve status detection method according to claim 1, characterized in that, The step of filtering the current data according to a preset filter and plotting the potential difference change curve includes: Based on the noise characteristics of the solenoid valve's working environment, select a suitable type and order of filter, and design the cutoff frequency of the filter to obtain a preset filter. The current data is filtered using the preset filter to remove high-frequency noise and low-frequency interference, resulting in processed data. Based on the processed data, a smooth potential difference change curve is plotted.

3. The solenoid valve status detection method according to claim 1, characterized in that, The process of performing a consistency evaluation on the geometric features to obtain the on / off state of the solenoid valve includes: The slope range of normal switching actions is obtained by clustering the geometric features of multiple switching actions using a clustering algorithm. Based on the slope range, determine whether the geometric feature is within the slope range. If it is not within the slope range, determine that the switching action is abnormal. If it is within the slope range, determine that the switching action is normal. The number of abnormal switching actions is counted. If the number of abnormal actions exceeds a preset threshold, the switching action of the solenoid valve is determined to be abnormal. If the number of abnormal actions does not exceed the preset threshold, the switching action of the solenoid valve is determined to be normal.

4. The solenoid valve status detection method according to claim 1, characterized in that, The step of analyzing the response time based on the potential difference change curve and assessing the aging degree of the coil based on the response time includes: Based on the potential difference change curve, extract the time points of the on and off states; Based on the stated time point, calculate the time difference between the opening and closing states of the solenoid valve to obtain the response time; Based on the response time, the input is fed into a preset support vector machine regression algorithm to obtain the aging degree of the coil.

5. The solenoid valve status detection method according to claim 1, characterized in that, The step of fitting the aging index prediction value to the potential difference change curve and the aging degree using a linear regression algorithm based on the historical data includes: Based on the historical data and the degree of aging, a training dataset is constructed; The training dataset is preprocessed to remove outliers and noisy data, resulting in preprocessed data. Based on the preprocessed data, the least squares method was used to perform linear regression fitting to obtain a linear relationship between the change in potential difference and the degree of aging. The current data is input into the linear relationship to calculate the corresponding aging index prediction value.

6. The solenoid valve status detection method according to claim 1, characterized in that, The process of predicting the remaining service life of the coil based on the aging index prediction value and generating a maintenance recommendation report based on the remaining service life includes: Based on the predicted aging index value, the remaining service life of the coil is predicted using a preset support vector machine regression model; Determine the optimal maintenance time based on the remaining service life. Based on the optimal maintenance time point, an association rule mining algorithm is used to obtain frequent itemsets; Association rules are generated based on the frequent itemsets, and a maintenance suggestion report is obtained.

7. The solenoid valve status detection method according to claim 1, characterized in that, The process of integrating the historical data, current data, switch status, fault alarm signal, aging level, and maintenance recommendations into a health status report, and transmitting it to the monitoring device via an industrial IoT platform, includes: Based on the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions, the data is cleaned and transformed using data preprocessing and feature extraction methods to obtain a standardized feature vector; Based on the pre-established equipment health status assessment model, the support vector machine algorithm is used to classify the feature vectors and determine the current health status level of the equipment. Based on the health status level, and in conjunction with the maintenance suggestion knowledge base, equipment maintenance suggestions are generated. Based on the health status level and the equipment maintenance recommendations, the two are integrated into an equipment health status report and transmitted to the monitoring device through an industrial IoT platform.

8. The solenoid valve status detection method according to claim 1, characterized in that, The step of classifying the health status reports using a clustering algorithm to obtain optimized maintenance strategies includes: Based on the health status report, the data portion is preprocessed and normalized to obtain feature data; The K-means clustering algorithm was used to perform cluster analysis on the extracted feature data to obtain cluster centers; Calculate the equipment's failure risk score based on the cluster centers and the feature data; Based on the aforementioned fault risk score, an optimized maintenance strategy is obtained.

9. A solenoid valve status detection device, characterized in that, A method for implementing the solenoid valve status detection method as described in any one of claims 1 to 8, comprising: The data acquisition module is used to acquire historical and current data on the change of potential difference over time. The data processing module is used to filter the current data according to a preset filter and plot the potential difference change curve. The state detection module is used to extract the geometric features of the switching action based on the potential difference change curve, perform a consistency evaluation on the geometric features, and obtain the switching state of the solenoid valve. The fault detection module is used to determine the fault state of the coil based on the potential difference change curve and the geometric features. If a fault occurs, a fault alarm signal is generated. An aging detection module is used to analyze the response time based on the potential difference change curve and to evaluate the degree of aging of the coil based on the response time. An alarm module is used to obtain a predicted aging index value by fitting the historical data, the potential difference change curve and the degree of aging using a linear regression algorithm. The recommended report generation module is used to predict the remaining service life of the coil based on the aging index prediction value, and generate a maintenance recommendation report based on the remaining service life. The health status generation module is used to integrate the historical data, the current data, the switch status, the fault alarm signal, the aging degree, and the maintenance suggestions into a health status report, which is then transmitted to the monitoring device through the industrial Internet of Things platform. The optimization strategy generation module is used to classify the health status report using a clustering algorithm to obtain an optimization maintenance strategy.

Images