Electrical performance testing methods for industrial equipment

Abstract

The present invention discloses an electrical performance detection method for industrial equipment, and relates to the technical field of electrical performance detection. The method comprises: determining an electrical performance detection target according to application environment parameters and operating parameters; performing test parameter analysis to obtain environment detection configuration parameters and electrical detection configuration parameters; constructing a simulation detection space; performing parameter configuration, simulating operating parameters through the simulation detection space to perform simulation detection on industrial equipment, and obtaining simulation detection data; and performing electrical performance evaluation on industrial equipment to obtain performance evaluation results. The method solves the technical problem that it is difficult to flexibly match electrical performance detection content according to the real-time operating parameters and states of different industrial equipment in the existing electrical performance detection, thereby resulting in low immediacy and accuracy of electrical performance detection results, and achieves the technical effect of improving the accuracy and immediacy of electrical performance detection of industrial equipment.

Description

Technical Field

[0001] The present application relates to the technical field of electrical performance testing, and in particular to an electrical performance testing method for industrial equipment. Background Art

[0002] With the rapid development of modern industrial technology, the stability and reliability of electrical performance have become crucial for industrial equipment. Electrical performance is not only directly related to the operating efficiency of the equipment, but also involves production safety, product quality and the economic benefits of the enterprise. In industrial environments, equipment usually needs to operate under complex and changeable working conditions, such as high temperature, high humidity, strong electromagnetic interference, etc. The harsh environmental conditions pose severe challenges to the electrical performance of the equipment. Once there is a problem with the electrical performance of the equipment, it may cause equipment shutdown, production interruption, and even cause safety accidents, bringing huge economic losses and reputation risks to the enterprise. With the continuous advancement of industrial automation and intelligence, the functions and complexity of industrial equipment are also increasing. The electrical performance of various electrical components and control systems influence and restrict each other, making electrical performance testing more complicated and difficult.

[0003] Therefore, in the current technologies related to electrical performance testing of industrial equipment, there is a technical problem that it is difficult to flexibly match the electrical performance testing content according to the real-time operating parameters and status of different industrial equipment, which leads to the low timeliness and accuracy of the electrical performance testing results. Summary of the invention

[0004] The present application provides an electrical performance testing method for industrial equipment, thereby solving the technical problem of the existing electrical performance testing that it is difficult to flexibly match the electrical performance testing content according to the real-time operating parameters and status of different industrial equipment, which in turn leads to the low timeliness and accuracy of the electrical performance testing results, thereby achieving the technical effect of improving the accuracy and timeliness of electrical performance testing of industrial equipment.

[0005] The present application provides an electrical performance detection method for industrial equipment, the method comprising: collecting application environment parameters and operating parameters of industrial equipment, and determining electrical performance detection targets according to the application environment parameters and operating parameters; performing test parameter analysis according to the electrical performance detection targets, application environment parameters, and operating parameters to obtain environmental detection configuration parameters and electrical detection configuration parameters; constructing a simulation detection space, the simulation detection space comprising a front-end scenario module and a rear-end electrical performance detection module; performing parameter configuration on the front-end scenario module and the rear-end electrical performance detection module according to the environmental detection configuration parameters and the electrical detection configuration parameters, performing simulation detection on the industrial equipment by simulating the operating parameters through the simulation detection space, and obtaining simulation detection data; performing electrical performance evaluation on the industrial equipment according to the simulation detection data to obtain performance evaluation results, wherein the electrical performance evaluation comprises an instant evaluation and a predictive evaluation.

[0006] In a possible implementation, the electrical performance detection target is determined according to the application environment parameters and the operating parameters, and the following processing is performed: according to the application environment parameters and the operating parameters, a correlation analysis is performed through a sample data set to obtain a first correlation, a second correlation, and a third correlation, wherein the sample data set includes the application environment parameters, the operating parameters and their electrical performance status, the first correlation is the correlation between the application environment parameters and the operating parameters, the second correlation is the correlation between the application environment parameters and the electrical performance status, and the third correlation is the correlation between the operating parameters and the electrical performance status; according to the first correlation, the second correlation, and the third correlation, a fusion calculation is performed with the electrical performance status as the target to determine the electrical performance correlation influence coefficient; according to the electrical performance correlation influence coefficient, the detection target is screened to obtain the electrical performance detection target, and the electrical performance detection target is an electrical performance detection item whose electrical performance correlation influence coefficient reaches a preset threshold.

[0007] In a possible implementation, according to the application environment parameters and operating parameters, correlation analysis is performed through a sample data set, and the following processing is performed: according to the sample data set, an abnormal sample set is screened; according to the abnormal sample set, a transaction data set is configured, wherein a transaction in the transaction data set is an abnormal sample case, and the items in the transaction are the application environment parameters, operating parameters and electrical performance failures in the sample case; the transaction data sets are aligned and compared to determine the data discreteness, and when the data discreteness does not meet the requirements, the data in the transaction data set is discretized, including conversion into discrete intervals or random screening of data intervals; the transaction data set after discretization is correlated through a correlation calculation module to obtain association rules; according to the association rules, the correlation calculation of each item is performed separately to obtain the correlation between the application environment parameters, operating parameters and electrical performance failure parameters.

[0008] In a possible implementation, test parameter analysis is performed according to the electrical performance detection target, application environment parameters, and operating parameters to obtain environmental detection configuration parameters and electrical detection configuration parameters, and the following processing is also performed: obtaining the active impact interval and the stable impact interval of the application environment parameters and the operating parameters; configuring the sample ratio of the active impact interval and the stable impact interval, and performing configuration parameter screening on the active impact interval and the stable impact interval based on the sample ratio to obtain the environmental detection configuration parameters, wherein the configuration parameter screening includes at least boundary values ​​and intermediate values; obtaining the electrical performance detection target, determining the electrical detection configuration parameters, and the electrical detection configuration parameters are the calculation variables of the electrical performance detection target.

[0009] In a possible implementation, the operating parameters are simulated through the simulation detection space to perform simulation detection on the industrial equipment, and simulation detection data is obtained. The following processing is also performed: the application environment parameters are switched according to the environment detection configuration parameters, and the simulation environment of the simulation detection space is configured; the operating parameters are simulated through the simulation detection space, and the electrical detection parameters of the industrial equipment are identified and extracted by the post-electrical performance detection module based on the electrical detection configuration parameters to obtain electrical detection information; a mapping relationship between the application environment parameters and the electrical detection information is established to obtain the simulation detection data.

[0010] In a possible implementation, based on the first correlation, the second correlation, and the third correlation, a fusion calculation is performed with the electrical performance state as the target to determine the electrical performance correlation influence coefficient, and the following processing is also performed: based on the first correlation and the third correlation, a series relationship is established with the electrical performance state as the target, and the first coefficient is obtained by using correlation overlapping calculation; based on the second correlation and the third correlation, a parallel relationship is established with the electrical performance state as the target, and a weighted average calculation is performed using correlation to obtain the second coefficient; based on the first coefficient and the second coefficient, a fusion is performed to obtain the electrical performance correlation influence coefficient.

[0011] In a possible implementation, the electrical performance of the industrial equipment is evaluated based on the simulation detection data to obtain a performance evaluation result, and the following processing is also performed: based on the industrial equipment, a normal performance feature is obtained, and the normal performance feature is the minimum limit for normal performance; based on the electrical detection information, an electrical detection feature is obtained; the normal performance feature is aligned with the electrical detection feature to construct a feature pair; the feature distance of the feature pair is calculated, and a distance matrix is ​​constructed based on the feature distance; a minimum cumulative distance search is performed based on the distance matrix, and feature similarity is obtained based on the minimum cumulative distance; electrical performance evaluation is performed based on the feature similarity to obtain the performance evaluation result.

[0012] In a possible implementation, the performance evaluation result is obtained and the following processing is also performed: using historical data to fit the abnormal feature timing chain of the electrical performance detection target, wherein the abnormal feature timing chain includes feature similarity and its corresponding fault probability; using the feature similarity to match the feature similarity in the abnormal feature timing chain to determine the fault probability, and when the fault probability reaches a preset probability, generating fault manifestation information; when the preset probability is not reached, extracting continuous feature similarity based on the simulation detection data, predicting the abnormal probability through the abnormal feature timing chain according to the continuous feature similarity, and performing fusion evaluation according to the predicted fault node distance and the current feature similarity to obtain the performance evaluation result.

[0013] The electrical performance detection method for industrial equipment proposed in this application is proposed to collect application environment parameters and operating parameters of industrial equipment, determine the electrical performance detection target according to the application environment parameters and operating parameters; perform test parameter analysis according to the electrical performance detection target, application environment parameters, and operating parameters to obtain environmental detection configuration parameters and electrical detection configuration parameters; construct a simulation detection space, which includes a front scene module and a rear electrical performance detection module; configure parameters of the front scene module and the rear electrical performance detection module according to the environmental detection configuration parameters and the electrical detection configuration parameters, simulate the operating parameters of the industrial equipment through the simulation detection space, and obtain simulation detection data; perform electrical performance evaluation on the industrial equipment according to the simulation detection data, and obtain performance evaluation results, wherein the electrical performance evaluation includes instant evaluation and predictive evaluation. The technical problem that it is difficult to flexibly match the electrical performance detection content according to the real-time operating parameters and states of different industrial equipment in the existing electrical performance detection is solved, and the immediacy and accuracy of the electrical performance detection results are low, and the technical effect of improving the accuracy and immediacy of electrical performance detection of industrial equipment is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a flow chart of an electrical performance testing method for industrial equipment provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of a flow chart for performing correlation analysis in an electrical performance detection method for industrial equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application provides an electrical performance detection method for industrial equipment, such as Figure 1 As shown, the method includes:

[0021] Step S100, collect application environment parameters and operating parameters of industrial equipment, and determine electrical performance test targets based on the application environment parameters and operating parameters. In the electrical performance test of industrial equipment, application environment parameters and operating parameters are collected, and electrical performance test targets are determined based on these parameters. Specifically, application environment parameters refer to various conditions and factors in the actual working environment of the equipment. These factors may directly affect the electrical performance of the equipment, help to understand the working status of the equipment, and evaluate the stability of its electrical performance. Application environment parameters may include the temperature range of the equipment's working environment, such as high temperature, low temperature, or temperature fluctuations; the humidity level of the equipment's working environment. Too high or too low humidity may affect electrical performance; whether there are electromagnetic interference sources around the equipment, and the intensity of the interference; the composition and pollution level of the air in the equipment's working environment, such as dust, corrosive gases, etc.; operating parameters refer to various data generated by the equipment during operation, reflecting the actual operation of the equipment. Actual working status and performance. These parameters can understand whether the electrical performance of the equipment meets the design requirements and whether there are potential problems. Specific operating parameters may include the current and voltage values ​​of the equipment under different working conditions, which are important indicators for evaluating the electrical performance of the equipment; power factor, which reflects the efficiency of the equipment in utilizing electric energy; the temperature of key components inside the equipment. Excessive temperature may lead to a decrease in electrical performance; the speed and vibration of rotating equipment; the electrical performance test target refers to the test and analysis of industrial electrical equipment to evaluate its electrical characteristics and capabilities. The electrical performance test target is determined according to the application environment parameters and operating parameters, that is, the performance parameters with greater influence are analyzed and matched with the corresponding electrical performance test content, such as dielectric strength, arc resistance, insulation resistance and electrical strength.

[0022] In a possible implementation, step S100 further includes step S110, performing correlation analysis through a sample data set according to the application environment parameters and the operating parameters to obtain a first correlation, a second correlation, and a third correlation, wherein the sample data set includes the application environment parameters, the operating parameters, and their electrical performance status, the first correlation is the correlation between the application environment parameters and the operating parameters, the second correlation is the correlation between the application environment parameters and the electrical performance status, and the third correlation is the correlation between the operating parameters and the electrical performance status. The sample data set is a data set containing application environment parameters, operating parameters and their corresponding electrical performance states. Correlation analysis usually uses statistical methods to calculate the correlation coefficients between variables (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.) to quantify the strength of association between variables. When detecting the electrical performance of industrial equipment, correlation analysis refers to analyzing the correlation between application environment parameters (such as temperature, humidity, pressure, etc.), operating parameters (such as voltage, current, speed, etc.) and electrical performance states (such as power output, efficiency, failure rate, etc.). The first correlation refers to the correlation between application environment parameters and operating parameters, that is, how application environment parameters (such as ambient temperature, humidity, etc.) affect the operating parameters of the equipment (such as current, voltage, etc.). For example, at higher temperatures, the equipment may require higher current to maintain its normal operation; the second correlation refers to the correlation between application environment parameters and electrical performance states, that is, how application environment parameters directly affect the electrical performance state of the equipment. For example, a high humidity environment may cause corrosion of internal components of the equipment, thereby affecting its electrical performance; the third correlation refers to the correlation between operating parameters and electrical performance states, that is, how the operating parameters of the equipment directly affect its electrical performance state. For example, excessive current may cause the equipment to overheat, thereby affecting its power output and efficiency.

[0023] Step S100 also includes step S120, according to the first correlation, the second correlation, and the third correlation, the electrical performance state is taken as the target to perform fusion calculation to determine the electrical performance correlation influence coefficient. Based on the absolute value of the correlation coefficient, a weight is assigned to each pair of correlations. For example, if the absolute value of the correlation coefficient of the second correlation is the largest, then its influence on the electrical performance state may be the most significant, so a higher weight is assigned, and the weighted correlation information is fused and calculated. The result of the fusion calculation is the electrical performance correlation influence coefficient, which quantifies the influence of different factors (environmental parameters and operating parameters) on the electrical performance state. It also includes step S130, according to the electrical performance correlation influence coefficient, the detection target is screened to obtain the electrical performance detection target, and the electrical performance detection target is the electrical performance detection item whose electrical performance correlation influence coefficient reaches the preset threshold. The preset threshold is a judgment standard set according to the specific requirements of the equipment and historical data, which is used to screen out the detection items that have a significant impact on the electrical performance, and compare the correlation influence coefficient of each electrical performance detection item with the preset threshold. If the correlation influence coefficient of a detection item reaches or exceeds the preset threshold, it is regarded as an electrical performance detection target. After screening, a group of electrical performance detection targets are obtained.

[0024] In one possible implementation, Figure 2As shown, step S110 further includes step S111, screening the abnormal sample set according to the sample data set. It also includes step S112, configuring the transaction data set according to the abnormal sample set, wherein one transaction in the transaction data set is an abnormal sample case, and the items in the transaction are the application environment parameters, operating parameters and electrical performance failures in the sample case. The transaction data set is a data set containing multiple transactions, each transaction represents a complete database operation sequence, and is used to describe the abnormal sample case; the items in the transaction are the application environment parameters, operating parameters and electrical performance failures in the sample case, and the electrical performance failure is the most critical item in the transaction data set, which describes the electrical performance failure of the system or equipment under specific environment and operating parameters, which may include but is not limited to voltage fluctuations, current anomalies, power loss, etc. It also includes step S113, aligning and comparing the transaction data set to determine the data discreteness, and when the data discreteness does not meet the requirements, discretizing the data in the transaction data set, including converting to discrete intervals or performing random screening of data intervals. Data discreteness refers to the degree of difference between each data point in a data set. It is used to measure the dispersion of data, that is, whether the data points are concentrated around a central value or whether they are dispersed in a larger range. Conversion to discrete intervals refers to converting continuous values ​​in a data set into discrete intervals or categories. For example, temperature data can be divided into several fixed intervals (such as low temperature, medium temperature, high temperature), or power data can be divided into different levels (such as low power, medium power, high power). Data interval random screening refers to randomly selecting certain data intervals or subsets in a data set to reduce the number of data points and reduce the degree of data discreteness.

[0025] Step S110 also includes step S114, in which a correlation calculation module is used to perform correlation calculation on the discretized transaction data set to obtain association rules. The correlation calculation module can calculate the correlation between the variables in the discretized transaction data set based on different correlation analysis methods (such as Pearson correlation coefficient, Spearman correlation coefficient, etc.), that is, according to the selected correlation analysis method, the correlation coefficient between the variables is calculated, which reflects the strength and direction of the association between the variables. According to the calculated correlation coefficient, the association rules that meet the threshold conditions are extracted, and the significant association relationship between different variables is described. For example, when the application environment parameter A is in a certain interval, the probability of occurrence of electrical performance failure B will increase. It also includes step S115, according to the association rule, the correlation calculation of each item is performed separately to obtain the correlation between the application environment parameters, the operating parameters, and the electrical performance failure parameters. The correlation between application environment parameters, operating parameters and electrical performance failures is calculated according to association rules. That is, for each pair of application environment parameters, operating parameters and electrical performance failures, the selected correlation calculation method is applied to calculate the correlation between them. For example, it is found that there is a strong positive correlation between a specific application environment parameter (such as temperature) and a certain electrical performance failure (such as overheating), which means that as the temperature increases, the incidence of overheating failures also increases.

[0026] In a possible implementation, step S120 further includes step S121, establishing a relational series relationship based on the first correlation and the third correlation with the electrical performance state as the target, and obtaining a first coefficient by using correlation overlap calculation. Establishing a relational series relationship based on the first correlation and the third correlation with the electrical performance state as the target refers to establishing a series relationship of application environment parameters-operating parameters-electrical performance, adding or multiplying the corresponding influence coefficients to obtain the first coefficient. It also includes step S122, establishing a relational parallel relationship based on the second correlation and the third correlation with the electrical performance state as the target, and obtaining a second coefficient by using correlation for weighted average calculation. Establishing a relational parallel relationship based on the second correlation and the third correlation with the electrical performance state as the target refers to performing a weighted average calculation on the correlation to obtain the second coefficients that affect the electrical performance respectively. It also includes step S123, fusing the first coefficient and the second coefficient to obtain the electrical performance association influence coefficient. The first coefficient and the second coefficient are combined by weighted average or linear combination to obtain a comprehensive electrical performance correlation influence coefficient. For example, if the first coefficient is the influence of temperature on resistance, and the second coefficient is the influence of humidity on resistance, they are combined by linear combination to obtain a resistance correlation influence coefficient that takes both temperature and humidity into account. The final electrical performance correlation influence coefficient reflects the comprehensive influence of multiple factors on electrical performance and is used to predict, evaluate or optimize the performance of electrical equipment.

[0027] Step S200, according to the electrical performance test target, application environment parameters, and operating parameters, test parameter parsing is performed to obtain environmental test configuration parameters and electrical test configuration parameters. Test parameter parsing refers to setting and parsing specific parameters required in the test process according to the determined electrical performance test target, combined with application environment parameters and operating parameters, to obtain environmental test configuration parameters and electrical test configuration parameters. Specifically, the environmental test configuration parameters include temperature configuration, humidity configuration, vibration and shock configuration, and electromagnetic interference configuration, wherein temperature configuration refers to setting the temperature conditions of the test environment according to the temperature range in the application environment parameters, for example, if the operating temperature range of the device is -20°C to +60°C, the temperature of the test environment should be within this range; humidity configuration refers to setting the humidity conditions of the test environment according to the humidity level in the application environment parameters, for example, if the device is running in a humid environment, the humidity of the test environment should simulate humid conditions; vibration and shock configuration refers to setting the vibration and shock conditions of the test environment according to the vibration and shock levels in the application environment parameters; electromagnetic interference configuration refers to setting the electromagnetic interference conditions of the test environment according to the electromagnetic interference level in the application environment parameters, for example, using an electromagnetic interference source to simulate the working state of the device in an electromagnetic interference environment. The electrical testing configuration parameters include test instrument configuration, test point setting, test time configuration, data recording and analysis configuration, etc. Among them, test instrument configuration refers to selecting appropriate test instruments, such as voltmeters, ammeters, power analyzers, etc., according to the electrical performance testing objectives to ensure that the accuracy of the test instruments meets the test requirements; test point setting refers to setting multiple test points according to operating parameters and electrical performance testing objectives, and each test point should cover different load conditions and electrical performance parameters; test time configuration refers to setting the test time according to the complexity of the test items and the test requirements; data recording and analysis configuration refers to configuring the data recording system to ensure that the data during the test process can be recorded accurately and completely.

[0028] Step S200 further includes step S210, obtaining the active influence interval and the stable influence interval of the application environment parameters and the operating parameters. The active influence interval refers to the parameter value range that can significantly affect the electrical performance or the device state when the application environment parameters or the operating parameters change. In this interval, the change of the parameters is more sensitive to the electrical performance. Specifically, based on the results of the correlation analysis, the parameter value range that can significantly affect the electrical performance is identified, that is, the active influence interval. This interval can be determined by setting a threshold value of the correlation coefficient, for example, the parameter value range with a correlation coefficient greater than 0.8 is selected as the active interval; the stable influence interval refers to the parameter value range that the electrical performance or the device state remains relatively stable when the application environment parameters or the operating parameters remain relatively stable. In this interval, the small fluctuation of the parameters has little effect on the electrical performance, and the device state is relatively stable. Specifically, based on the analysis results of the electrical performance, the parameter value range that can keep the electrical performance stable is determined, that is, the stable influence interval, for example, the data segment with parameter values ​​within the range of mean ± standard deviation is selected as the stable interval.

[0029] Step S200 further includes step S220, configuring the sample ratios of the active interval and the stable interval, and filtering the configuration parameters of the active interval and the stable interval based on the sample ratios to obtain the environmental detection configuration parameters, wherein the configuration parameter filtering includes at least boundary values ​​and intermediate values. Based on historical data analysis and business needs, determine the sample ratios used to analyze and define the active interval and the stable interval. For example, you can select parameter value ranges that cause significant changes in electrical performance. These ranges may account for 20% to 40% of the entire parameter value range, and the parameter value ranges where the electrical performance remains stable account for 60% to 80% of the entire parameter value range. The configuration parameter filtering includes at least boundary values ​​and intermediate values, and finally obtains the environmental detection configuration parameters. It also includes step S230, obtaining the electrical performance detection target, determining the electrical detection configuration parameters, and the electrical detection configuration parameters are the calculation variables of the electrical performance detection target. The electrical detection configuration parameters are determined according to the electrical performance detection target. The electrical detection configuration parameters are the calculation variables of the electrical performance detection target. Specifically, by measuring and collecting data of these parameters, the actual value of the electrical performance detection target can be calculated and compared and evaluated with the predetermined target value. For example, if the electrical performance detection target is voltage stability, the actual value of the voltage stability can be calculated by measuring the two configuration parameters of the output voltage and voltage fluctuation range of the equipment, and compared with the predetermined target value.

[0030] Step S300, constructing a simulation detection space, the simulation detection space includes a front scene module and a rear electrical performance detection module. Constructing a simulation detection space, including a front scene module and a rear electrical performance detection module, specifically, the front scene module is mainly responsible for simulating the scene conditions of the electrical equipment in the actual working environment, including environmental parameters such as temperature, humidity, vibration, electromagnetic interference, and the operating parameters of the equipment, such as load conditions, input voltage, etc. For example, by simulating different environmental conditions, such as temperature variation range (-20°C to +60°C), humidity level (such as relative humidity 30% to 90%), etc., to evaluate the performance of the equipment in different environments, set the operating parameters of the equipment, such as input voltage, current, frequency, etc., to simulate the working state of the equipment under different load conditions, and control the start, pause, continue and end of the simulation scene, so as to perform accurate testing and data analysis; the rear electrical performance detection module is mainly responsible for detecting and evaluating the electrical performance of the electrical equipment, receiving the simulation signal from the front scene module, and processing and analyzing it to obtain the electrical performance parameters of the equipment. In general, the front scene module and the rear electrical performance detection module are connected through a data interface to realize real-time transmission and sharing of information. The front scene module provides analog signals to the rear electrical performance detection module, and the rear electrical performance detection module processes and analyzes the received signals to obtain the electrical performance parameters of the equipment. The scene parameters and operating parameters can be customized as needed to simulate different working environments and load conditions. Then, by running the simulation detection space, the electrical performance parameters and performance evaluation results of the equipment can be obtained to understand the performance of the equipment under different conditions.

[0031] Step S400, according to the environmental detection configuration parameters and the electrical detection configuration parameters, respectively configure the parameters of the front scene module and the rear electrical performance detection module, simulate the operating parameters through the simulation detection space to simulate the industrial equipment, and obtain simulation detection data. Configuring the parameters of the front scene module and the rear electrical performance detection module according to the environmental detection configuration parameters and the electrical detection configuration parameters refers to setting the environmental parameters such as temperature, humidity, vibration, etc. in the simulation detection space according to the environmental detection configuration parameters, considering the environmental factors such as electromagnetic interference that may affect the performance of the equipment, and simulating these interferences in the simulation detection space, setting the corresponding parameter values ​​in the simulation detection space according to the actual operating parameters of the industrial equipment, such as input voltage, current, frequency, etc., considering the performance of the equipment under different load conditions, and setting multiple load points for testing, and selecting appropriate test instruments such as voltmeters, ammeters, and power analyzers according to the electrical detection configuration parameters. Analyzers, etc., set test parameters such as test range, test accuracy, sampling frequency, etc. according to the electrical performance detection objectives. For specific electrical performance parameters (such as voltage, current, power, etc.), set corresponding test conditions and thresholds. Simulation detection refers to starting the simulation detection space, simulating the actual working environment and operating conditions of industrial equipment according to the parameter configuration of the front-end scenario module, monitoring the operating status of the simulation detection space, ensuring the stability and accuracy of environmental parameters and operating parameters, using the test instruments in the rear electrical performance detection module to monitor and collect data on the electrical performance of industrial equipment in the simulation detection space in real time, and record key data in the test process, namely, simulation detection data.

[0032] In a possible implementation, step S400 further includes step S410, switching the application environment parameters according to the environment detection configuration parameters, and configuring the simulation environment of the simulation detection space. Application environment parameter switching refers to adjusting or simulating different combinations of environment parameters in the actual environment according to the environment detection configuration parameters, so as to test in the simulation environment, and configuring the simulation environment of the simulation detection space according to the conversion results. It also includes step S420, simulating the operation parameters through the simulation detection space, and using the post-electrical performance detection module to identify and extract the electrical detection parameters of the industrial equipment based on the electrical detection configuration parameters to obtain electrical detection information. In the simulation detection space, according to the actual operation of the industrial equipment and the test requirements, the operation parameters of the equipment are set or adjusted, and the post-electrical performance detection module receives the electrical signal simulated by the simulation detection space as input. According to the electrical detection configuration parameters, the module identifies the electrical signal, extracts the features or data related to the electrical performance detection target, and processes and analyzes the extracted data to evaluate whether the electrical performance of the industrial equipment meets the requirements. The test results or data obtained about the electrical performance of the industrial equipment may include voltage fluctuation range, current stability, power factor, etc. It also includes step S430, establishing a mapping relationship between the application environment parameters and the electrical detection information, and obtaining the simulation detection data. The mapping relationship refers to the corresponding relationship between the application environment parameters (such as temperature, humidity, air pressure, etc.) and the electrical detection information (such as voltage, current, power factor, etc.), which describes the change trend of the electrical performance of industrial equipment under different environmental parameters. Specifically, the operation of industrial equipment under different application environment parameters is simulated by the simulation detection space, and the corresponding electrical detection information is recorded to find the correlation between the application environment parameters and the electrical detection information. Based on the results of data analysis, a mapping model between the application environment parameters and the electrical detection information is established to obtain the mapping relationship between the two. The simulation detection data refers to the electrical performance data of industrial equipment simulated in the simulation environment according to the mapping relationship between the application environment parameters and the electrical detection information.

[0033] Step S500, the electrical performance of the industrial equipment is evaluated according to the simulation detection data to obtain a performance evaluation result, wherein the electrical performance evaluation includes instant evaluation and predictive evaluation. The electrical performance of the industrial equipment is evaluated using the acquired simulation detection data, including instant evaluation and predictive evaluation. Specifically, the instant evaluation refers to the real-time evaluation and analysis of the electrical performance of the industrial equipment during the simulation detection process, focusing on the performance of the equipment in the current state, including basic electrical parameter evaluation, power and efficiency evaluation, and safety performance evaluation. The basic electrical parameter evaluation refers to the instant evaluation of whether the basic electrical parameters such as voltage, current, resistance, capacitance, and inductance of the industrial equipment meet the preset standards or requirements according to the simulation detection data. For example, the voltage stability and fluctuation range of the equipment under different load conditions can be checked to ensure that it can work normally under normal and overload conditions; power and efficiency evaluation refers to calculating the performance indicators such as active power, reactive power, and efficiency of the equipment during the simulation detection process, evaluating its energy utilization efficiency and operation stability, and judging whether the power output and efficiency of the equipment meet the requirements by comparing the simulation detection data with the preset standards; safety performance evaluation refers to the evaluation of the equipment under voltage withstand test, insulation resistance test, etc. according to the simulation detection data. For example, the insulation performance of the equipment under high voltage conditions can be checked to avoid safety accidents such as breakdown. Predictive evaluation is to predict and evaluate the future performance of industrial equipment based on simulation test data, focusing on the performance stability and reliability of the equipment under long-term operation or different working conditions, including long-term performance prediction, fault prediction and diagnosis, and optimization suggestions. Among them, long-term performance prediction refers to predicting the performance changes of the equipment during long-term operation by analyzing the trends and rules in the simulation test data. For example, the electrical performance stability of the equipment under different environmental conditions such as temperature and humidity can be predicted. Fault prediction and diagnosis refers to using the abnormal information in the simulation test data to predict the possible fault type and occurrence time of the equipment, and diagnose and analyze the cause of the fault in combination with the structure, working principle and historical fault data of the equipment. According to the prediction and evaluation results, optimization suggestions for the electrical performance of industrial equipment are put forward, such as adjusting the operating parameters of the equipment, improving the heat dissipation conditions, replacing key components, etc., to improve the electrical performance and reliability of the equipment.

[0034] In a possible implementation, step S500 further includes step S510, based on the industrial equipment, obtaining a normal performance feature, the normal performance feature is the minimum limit of normal performance. Under the normal operating state of the equipment, a set of minimum performance indicators or standards that should be achieved or maintained ensures that the equipment can meet the predetermined production requirements, safety standards and quality standards under normal operating conditions. The normal performance feature means that when the industrial equipment is in normal operation, its various performance indicators should reach or remain within a predetermined and acceptable range. The minimum limit is the minimum performance standard that must be achieved to ensure that the equipment can operate continuously, stably and safely. It also includes step S520, obtaining electrical detection features based on the electrical detection information. The electrical detection data is further analyzed and processed to extract key features or parameters related to electrical performance, such as numerical (such as voltage, current, resistance value, etc.), or descriptive (such as equipment status, fault type, etc.). It also includes step S530, aligning the normal performance feature with the electrical detection feature to construct a feature pair. The features representing the normal performance state of the equipment (normal performance features) are matched and corresponded with the features extracted from the electrical detection information (electrical detection features) to form a series of feature pairs, which facilitates a better understanding of the performance of the equipment under different states and provides a basis for subsequent model training, fault diagnosis, performance evaluation, etc.

[0035] Step 500 also includes step S540, calculating the characteristic distance of the characteristic pair, and constructing a distance matrix based on the characteristic distance. The characteristic distance is a metric used to quantify the difference or similarity between two characteristic pairs, that is, to compare the difference between the electrical detection characteristics of different devices or the same device at different time points and the normal performance characteristics. The distance matrix is ​​a two-dimensional matrix, in which each element represents the distance between two characteristic pairs in the data set. For a data set of n characteristic pairs, the distance matrix will be an n×n symmetric matrix. Specifically, an n×n zero matrix is ​​created, where n is the number of characteristic pairs. The calculated characteristic distance values ​​are filled into the corresponding positions of the distance matrix in the order of the characteristic pairs. Since the distance matrix is ​​symmetrical, only the upper triangle or the lower triangle part needs to be filled, and then copied to the symmetric position. It also includes step S550, performing a minimum cumulative distance search based on the distance matrix, and obtaining the characteristic similarity based on the minimum cumulative distance. The minimum cumulative distance search is to find the minimum cumulative distance on the path from the starting point to the end point through dynamic programming under the given distance matrix, and obtain the characteristic similarity based on the minimum cumulative distance. A smaller cumulative distance usually indicates a higher characteristic similarity. The method further includes step S560, wherein the electrical performance is evaluated according to the feature similarity to obtain the performance evaluation result. The previously calculated feature similarity is used to evaluate the performance status of the electrical equipment or its degree of compliance with the expected performance standard. Specifically, the calculated feature similarity is compared with the set evaluation standard to determine whether the equipment performance meets the requirements. Based on the comparison result, the performance of the electrical equipment is evaluated and the meaning of the evaluation result is explained. For example, if the feature similarity is higher than the set threshold, the equipment performance can be considered good; if it is lower than the threshold, further inspection or maintenance may be required.

[0036] In a possible implementation, step S560 further includes step S561, using historical data to fit the abnormal feature timing chain of the electrical performance detection target, wherein the abnormal feature timing chain includes feature similarity and its corresponding fault probability. By analyzing the electrical performance detection data in the historical data, the feature timing pattern related to the equipment failure or abnormal state is identified, and a timing chain that can describe the change of these abnormal features over time is constructed, which not only includes feature similarity, but also corresponds to the probability of equipment failure under each feature similarity. Specifically, according to the fault records in the historical data and the abnormal feature timing chain, a corresponding fault probability is mapped for each feature similarity. It also includes step S562, using the feature similarity to match the feature similarity in the abnormal feature timing chain to determine the fault probability, and when the fault probability reaches the preset probability, the fault manifestation information is generated. By comparing the feature similarity of the current electrical performance test data with the feature similarity in the abnormal feature time series chain extracted from the historical data, the possibility of failure of the current equipment is estimated. The preset probability threshold refers to a fault probability threshold set by the system. When the matched fault probability exceeds this threshold, it means that the equipment has a high failure risk. Once the fault probability reaches or exceeds the preset threshold, the system will generate fault manifestation information, such as prediction of fault type, recommended maintenance measures, and possible location of the fault.

[0037] Step S560 also includes step S563, when the preset probability is not reached, extracting continuous feature similarity based on the simulation detection data, predicting abnormal probability through the abnormal feature time series chain according to the continuous feature similarity, and performing fusion evaluation according to the predicted fault node distance and current feature similarity, to obtain the performance evaluation result. Use a simulation tool or simulation environment to generate detection data of electrical equipment, calculate the feature similarity of the simulation detection data in a continuous time period, compare and match the calculated continuous feature similarity with the data in the abnormal feature time series chain, predict the probability of abnormality of the equipment at a certain time point in the current or future based on the information in the historical data and the abnormal feature time series chain, predict the time node (i.e., the fault node) where the fault may occur, and calculate the distance between the time node and the current time point, consider the feature similarity at the current moment, i.e., the similarity between the current performance state of the equipment and the normal state, use the predicted fault node distance and the current feature similarity as evaluation factors, and perform fusion through weighted average to obtain the performance evaluation result of the equipment.

[0038] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for detecting electrical properties of industrial equipment, characterized in that: The method comprises: Collect application environment parameters and operating parameters of industrial equipment, and determine electrical performance detection targets based on the application environment parameters and operating parameters; According to the electrical performance detection target, application environment parameters, and operation parameters, test parameter analysis is performed to obtain environmental detection configuration parameters and electrical detection configuration parameters; Constructing a simulation detection space, wherein the simulation detection space includes a front scene module and a rear electrical performance detection module; According to the environmental detection configuration parameters and the electrical detection configuration parameters, the parameters of the front scene module and the rear electrical performance detection module are configured respectively, and the operating parameters are simulated in the simulation detection space to perform simulation detection on the industrial equipment to obtain simulation detection data; Performing electrical performance evaluation on the industrial equipment according to the simulation detection data to obtain a performance evaluation result, wherein the electrical performance evaluation includes an instant evaluation and a predictive evaluation; Wherein, determining the electrical performance detection target according to the application environment parameters and the operation parameters includes: According to the application environment parameters and the operating parameters, a correlation analysis is performed through a sample data set to obtain a first correlation, a second correlation, and a third correlation, wherein the sample data set includes the application environment parameters, the operating parameters, and their electrical performance states, the first correlation is the correlation between the application environment parameters and the operating parameters, the second correlation is the correlation between the application environment parameters and the electrical performance state, and the third correlation is the correlation between the operating parameters and the electrical performance state; According to the first correlation, the second correlation, and the third correlation, a fusion calculation is performed with the electrical performance state as a target to determine the electrical performance correlation influence coefficient; The detection target is screened according to the electrical performance correlation influence coefficient to obtain the electrical performance detection target, and the electrical performance detection target is an electrical performance detection item whose electrical performance correlation influence coefficient reaches a preset threshold.

2. The electrical performance testing method for industrial equipment according to claim 1, characterized in that: According to the application environment parameters and operation parameters, correlation analysis is performed using the sample data set, including: According to the sample data set, screening abnormal sample sets; According to the abnormal sample set, a transaction data set is configured, wherein one transaction in the transaction data set is an abnormal sample case, and the items in the transaction are the application environment parameters, operation parameters and electrical performance failures in the sample case; Aligning and comparing the transaction data sets to determine data discreteness, and when the data discreteness does not meet the requirements, discretizing the data in the transaction data sets, including converting to discrete intervals or performing random screening of data intervals; The correlation calculation module is used to calculate the correlation of the transaction data set after discretization to obtain association rules; According to the association rules, the correlation calculations of each item are performed respectively to obtain the correlations among the application environment parameters, the operation parameters, and the electrical performance fault parameters.

3. The electrical performance testing method for industrial equipment according to claim 1, characterized in that: According to the electrical performance test target, application environment parameters, and operation parameters, test parameter analysis is performed to obtain environmental test configuration parameters and electrical test configuration parameters, including: Obtaining the active influence interval and the stable influence interval of the application environment parameters and the operation parameters; Configure the sample ratios of the active interval and the stable interval, and screen the configuration parameters of the active interval and the stable interval based on the sample ratios to obtain the environment detection configuration parameters, wherein the configuration parameter screening includes at least a boundary value and an intermediate value; The electrical performance detection target is acquired, and the electrical detection configuration parameters are determined, where the electrical detection configuration parameters are calculation variables of the electrical performance detection target.

4. The electrical performance testing method for industrial equipment according to claim 1, characterized in that: The simulation detection space simulates the operating parameters to perform simulation detection on the industrial equipment to obtain simulation detection data, including: Switching application environment parameters according to the environment detection configuration parameters to configure the simulation environment of the simulation detection space; The operation parameters are simulated by the simulation detection space, and based on the electrical detection configuration parameters, the electrical detection parameters of the industrial equipment are identified and extracted by using the post-electrical performance detection module to obtain electrical detection information; A mapping relationship between the application environment parameters and the electrical detection information is established to obtain the simulation detection data.

5. The electrical performance testing method for industrial equipment according to claim 1, characterized in that: According to the first correlation, the second correlation, and the third correlation, a fusion calculation is performed with the electrical performance state as a target to determine the electrical performance correlation influence coefficient, including: According to the first correlation and the third correlation, a relationship series relationship is established with the electrical performance state as a target, and a first coefficient is obtained by using correlation overlap calculation; According to the second correlation and the third correlation, a relational parallel relationship is established with the electrical performance state as a target, and a weighted average calculation is performed using the correlation to obtain a second coefficient; The electrical performance correlation influence coefficient is obtained by fusing the first coefficient and the second coefficient.

6. The electrical performance testing method for industrial equipment according to claim 4, characterized in that: The electrical performance of the industrial equipment is evaluated according to the simulation detection data to obtain a performance evaluation result, including: Based on the industrial equipment, obtaining a normal performance characteristic, wherein the normal performance characteristic is a minimum limit for normal performance; Acquiring electrical detection features according to the electrical detection information; Aligning the normal performance feature with the electrical detection feature to construct a feature pair; Calculating the feature distances of the feature pairs, and constructing a distance matrix based on the feature distances; Performing a minimum cumulative distance search based on the distance matrix, and obtaining feature similarity based on the minimum cumulative distance; The electrical performance is evaluated according to the feature similarity to obtain the performance evaluation result.

7. The electrical performance testing method for industrial equipment according to claim 6, characterized in that: The obtaining of the performance evaluation result further includes: Using historical data to fit the abnormal feature time series chain of the electrical performance detection target, wherein the abnormal feature time series chain includes feature similarity and its corresponding fault probability; The feature similarity is matched with the feature similarity in the abnormal feature time series chain to determine the fault probability, and when the fault probability reaches a preset probability, fault manifestation information is generated; When the preset probability is not reached, continuous feature similarity is extracted based on the simulation detection data, abnormal probability prediction is performed through the abnormal feature time series chain according to the continuous feature similarity, and fusion evaluation is performed according to the predicted fault node distance and current feature similarity to obtain the performance evaluation result.

Images