Frequency converter remote fault diagnosis method and system combined with Internet of Things

Abstract

The invention discloses a frequency converter remote fault diagnosis method and system combined with the Internet of Things, and relates to the field of electrical measurement. The method comprises the following steps: receiving a frequency converter control mode for calibration, and obtaining reference current fluctuation information and reference voltage fluctuation information; performing dimension reduction reconstruction on the reference current fluctuation information and the reference voltage fluctuation information to generate a reference current characteristic matrix and a reference voltage characteristic matrix; obtaining a comparison current characteristic matrix and a comparison voltage characteristic matrix; obtaining a fault prediction probability through a fault probability prediction component; and when the fault prediction probability is greater than or equal to a fault probability threshold, generating a fault early warning signal and sending the fault early warning signal to a user side. By adopting the method, the technical problem that in the prior art, fault analysis needs to be carried out according to complex semantic monitoring data of the frequency converter, more layering is carried out, complexity is large, and the analysis calculation amount is large is solved, and the technical effects that the calculation amount is reduced, and frequency converter fault diagnosis is efficiently and rapidly completed are achieved.

Description

Technical Field

[0001] The present application relates to the field of electrical measurement technology, and in particular to the field of electrical measurement diagnosis, and specifically to a method and system for remote fault diagnosis of a frequency converter in combination with the Internet of Things. Background Art

[0002] As the core equipment in industrial production, the stability and reliability of the inverter are directly related to the operating efficiency and product quality of the production line. Therefore, the inverter remote fault diagnosis method combined with the Internet of Things has important application value. The traditional inverter fault diagnosis method mainly relies on the experience and technical level of the on-site personnel to discover potential faults through manual inspections and regular maintenance. However, this method has many shortcomings, such as low diagnostic efficiency, low accuracy, and slow response speed.

[0003] In summary, the prior art has the technical problem that fault analysis needs to be performed based on the complex semantic monitoring data of the inverter, which is highly layered and complicated, resulting in a large amount of analysis calculation. Summary of the invention

[0004] Based on this, it is necessary to provide a method and system for remote fault diagnosis of inverter combined with the Internet of Things, which can reduce the amount of calculation and complete inverter fault diagnosis efficiently and quickly, in response to the above technical problems.

[0005] In the first aspect, a method for remote fault diagnosis of an inverter combined with the Internet of Things is provided, including: receiving an inverter control mode; calibrating the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; performing dimensionality reduction reconstruction on the reference current fluctuation information to generate a reference current feature matrix; performing dimensionality reduction reconstruction on the reference voltage fluctuation information to generate a reference voltage feature matrix; receiving monitoring current fluctuation information and monitoring voltage fluctuation information to perform dimensionality reduction reconstruction to obtain a comparison current feature matrix and a comparison voltage feature matrix; analyzing the reference current feature matrix, the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix through a fault probability prediction component to obtain a fault prediction probability; when the fault prediction probability is greater than or equal to a fault probability threshold, generating a fault warning signal and sending it to a user end.

[0006] In the second aspect, a frequency converter remote fault diagnosis system combined with the Internet of Things is provided, including: a frequency converter control mode receiving module, the frequency converter control mode receiving module is used to receive the frequency converter control mode; a calibration module, the calibration module is used to calibrate the frequency converter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; a reference current feature matrix generation module, the reference current feature matrix generation module is used to reduce the dimension of the reference current fluctuation information and reconstruct it to generate a reference current feature matrix; a reference voltage feature matrix generation module, the reference voltage feature matrix generation module is used to reduce the dimension of the reference voltage fluctuation information and reconstruct it to generate a reference voltage feature matrix. A quasi-voltage characteristic matrix; a dimensionality reduction and reconstruction module, the dimensionality reduction and reconstruction module is used to receive the monitoring current fluctuation information and the monitoring voltage fluctuation information for dimensionality reduction and reconstruction, and obtain a comparison current characteristic matrix and a comparison voltage characteristic matrix; a fault prediction probability module, the fault prediction probability module is used to analyze the reference current characteristic matrix, the comparison current characteristic matrix, the reference voltage characteristic matrix and the comparison voltage characteristic matrix through a fault probability prediction component to obtain a fault prediction probability; a fault warning signal generation module, the fault warning signal generation module is used to generate a fault warning signal and send it to the user end when the fault prediction probability is greater than or equal to the fault probability threshold.

[0007] According to a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps according to the first aspect when executing the computer program.

[0008] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps described in the first aspect are implemented.

[0009] The above-mentioned inverter remote fault diagnosis method and system combined with the Internet of Things adopts this method to solve the technical problem that in the prior art, fault analysis needs to be performed based on the complex semantic monitoring data of the inverter, which is highly layered and complicated, resulting in a large amount of analysis calculation. This method achieves the technical effect of reducing the amount of calculation and completing the inverter fault diagnosis efficiently and quickly.

[0010] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flowchart of a method for remote fault diagnosis of a frequency converter in combination with the Internet of Things in one embodiment; Figure 2A schematic diagram of a flow chart of obtaining reference current fluctuation information and reference voltage fluctuation information in a method for remote fault diagnosis of a frequency converter in combination with the Internet of Things in one embodiment; Figure 3 A structural block diagram of a frequency converter remote fault diagnosis system combined with the Internet of Things in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0012] Explanation of the reference numerals: inverter control mode receiving module 11, calibration module 12, reference current characteristic matrix generating module 13, reference voltage characteristic matrix generating module 14, dimensionality reduction and reconstruction module 15, fault prediction probability module 16, fault warning signal generating module 17. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] like Figure 1 As shown, the present application provides a method for remote fault diagnosis of a frequency converter in combination with the Internet of Things, including: Receive inverter control mode; Traditional inverter fault analysis requires fault analysis based on the complex semantic monitoring data of the inverter. It is highly layered and complex, resulting in a large amount of analysis and calculation. This application provides an inverter remote fault diagnosis method combined with the Internet of Things, which combines the Internet of Things with the inverter remote fault diagnosis method to achieve remote monitoring and fault diagnosis of the inverter operating status. The Internet of Things uses sensor technology to obtain various operating parameters of the inverter in real time, such as voltage, current, temperature, vibration, etc. These data are sent to the control center after being processed by the transmission layer. In the control center, through big data analysis and fault diagnosis algorithms, the operating status of the inverter can be monitored in real time, and an alarm can be issued in time when an abnormality is found, so as to achieve efficient and accurate analysis of inverter faults, reduce the amount of analysis and calculation, and improve the efficiency and accuracy of fault diagnosis.

[0015] The frequency converter is a power control device that controls the speed, torque or other process parameters of the motor by changing the frequency and voltage of the power supply. According to the control mode of the frequency converter, the corresponding input parameters are configured, and one control mode corresponds to a group of control parameters, including voltage range, signal type, etc., that is, the preset control parameters of the frequency converter are obtained. By receiving the frequency converter control mode, a basis is provided for the subsequent frequency converter remote fault diagnosis method.

[0016] Calibrate the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; Select a suitable calibration environment to ensure that external factors such as ambient temperature and humidity do not affect the calibration results. Determine the load type and load conditions for calibration, such as using a standard motor or simulated load. According to the characteristics of the control mode, set the corresponding operating parameters, such as frequency, voltage, current, etc. For current and voltage, set reasonable reference values ​​according to the working principle and application requirements of the inverter. Operate the inverter in the control mode and record the current and voltage fluctuation data in real time. Perform statistical analysis on the collected current and voltage fluctuation data, extract key features, identify and exclude abnormal data, ensure the reliability of the calibration results, and obtain reference current fluctuation information and reference voltage fluctuation information. Reference current fluctuation information refers to the stable fluctuation range of the output current of the inverter when it is operating normally under specific conditions. The range is usually determined through the calibration process to ensure that the inverter can output a stable and expected current under normal working conditions; reference voltage fluctuation information refers to the stable fluctuation range of the output voltage of the inverter when it is operating normally under specific working conditions. The information is obtained through the calibration and analysis process to ensure that the inverter can provide a stable and required output voltage under the predetermined working mode. By calibrating the inverter control mode, reference current fluctuation information and reference voltage fluctuation information of the inverter under a specific control mode can be obtained, thereby ensuring stable operation of the inverter, optimizing performance, and laying the foundation for subsequent fault diagnosis.

[0017] like Figure 2 As shown, positive sample backtracking is performed according to the inverter control mode to obtain a current fluctuation record information set and a voltage fluctuation record information set, wherein the positive sample refers to a fault-free sample of the same inverter control mode; Performing feature-level aggregation on the current fluctuation record information set to obtain the reference current fluctuation information; The voltage fluctuation record information set is aggregated at a feature level to obtain the reference voltage fluctuation information.

[0018] Positive sample backtracking refers to collecting current and voltage fluctuation record information of fault-free samples under the same inverter control mode to form a current fluctuation record information set and a voltage fluctuation record information set, ensuring that the collected data comes from the inverter of the same model and is in the same control mode, verifying that these data come from the inverter operation record under a fault-free state, and using a current measuring device to record the output current change in real time during the normal operation of the inverter. Based on the output current change, a current fluctuation record information set is generated, wherein the current fluctuation record information set includes the current value at each time point and the corresponding timestamp; as in the above method, during the normal operation of the inverter, a voltage measuring device is used to record the output voltage change in real time. Based on the output voltage change, a voltage fluctuation record information set is integrated to generate the voltage value at each time point and the corresponding timestamp. Feature hierarchical aggregation includes feature extraction and feature fusion. By aggregating at different levels, we can better understand and describe the intrinsic structure and pattern of the data, pre-process the current fluctuation record information set, such as removing outliers and smoothing, extract the key features of the current fluctuation, such as the average value, standard deviation, peak value, etc. For each feature, feature aggregation is performed to describe the shape and characteristics of the current distribution and obtain the reference current fluctuation information; the reference voltage fluctuation information is obtained in the same way as above. Obtaining accurate reference current fluctuation information and reference voltage fluctuation information provides basic support for subsequent inverter performance evaluation, fault diagnosis and optimization.

[0019] According to the first current fluctuation record information of the current fluctuation record information set, extracting the amplitude record information set, frequency record information set, phase record information set, kurtosis record information set, skewness record information set, year-on-year change rate record information set and month-on-month change rate record information set of the first current fluctuation record information, wherein the year-on-year change rate represents the current amplitude change rate within one cycle, and the month-on-month change rate represents the adjacent current amplitude change rate in the same cycle; Traversing the amplitude record information set, the frequency record information set, the phase record information set, and the kurtosis record information set to perform first type feature hierarchical aggregation to obtain a reference current amplitude, a reference current frequency, a reference current phase, and a reference current kurtosis; Traversing the skewness record information set, the year-on-year change rate record information set and the quarter-on-quarter change rate record information set to perform second type feature hierarchical aggregation to obtain a reference current skewness, a reference current year-on-year change rate and a reference current quarter-on-quarter change rate; The reference current amplitude, the reference current frequency, the reference current phase, the reference current kurtosis, the reference current skewness, the reference current year-on-year change rate and the reference current quarter-on-quarter change rate are added to the reference current fluctuation information.

[0020] The amplitude data of the current is extracted from the first current fluctuation recording information, wherein the first current fluctuation recording information refers to the first current fluctuation recording information randomly selected from the current fluctuation recording information set and recorded as the first current fluctuation recording information; according to the amplitude recording information set, frequency recording information set, phase recording information set, kurtosis recording information set, skewness recording information set, year-on-year change rate recording information set and month-on-month change rate recording information set of the first current fluctuation recording information, the amplitude data of the current is extracted from the first current fluctuation recording information to form an amplitude recording information set, the amplitude reflects the size of the current; the frequency data of the current is extracted to form a frequency recording information set. The frequency indicates how fast the current changes. The phase data of the current is extracted to form a phase record information set. The phase reflects the time offset between the current and the reference signal. The kurtosis of the current is calculated to form a kurtosis record information set. The kurtosis describes the sharpness of the current distribution shape. The skewness of the current is calculated to form a skewness record information set. The skewness describes the degree of skewness of the current distribution shape. The current amplitude change rate within one cycle is calculated to form a year-on-year change rate record information set. The year-on-year change rate is used to compare current changes in different cycles. The adjacent current amplitude change rates of the same cycle are calculated to form a month-on-month change rate record information set. The month-on-month change rate is used to compare current changes in adjacent cycles. Among them, the year-on-year change rate represents the current amplitude change rate within one cycle. The current amplitude change rate of the period, the year-on-year change rate characterizes the adjacent current amplitude change rate of the same period, and the amplitude record information set, the frequency record information set, the phase record information set, and the kurtosis record information set are traversed to perform the first type of feature hierarchical aggregation. The first type of feature hierarchical aggregation refers to the traditional feature information, that is, the basic features, such as amplitude, frequency, phase, etc., for feature hierarchical aggregation, including calculating the average, median, mode or other statistics to reflect the overall situation of these features. The results after aggregation include the reference current amplitude, reference current frequency, reference current phase and reference current kurtosis. The first type of feature hierarchical aggregation focuses on the feature hierarchical aggregation of basic features. The skewness record information set, the year-on-year change rate record information set and the year-on-year change rate record information set are traversed to perform the second type of feature hierarchical aggregation. The second type of feature hierarchical aggregation focuses on capturing the complex relationship between the distribution and change trend of these features. The results after aggregation are the reference current skewness, the year-on-year change rate of the reference current and the year-on-year change rate of the reference current. Compared with the first type of feature hierarchical aggregation, the year-on-year change rate and the month-on-month change rate are added, which can analyze the refined amplitude change state of the current, which is conducive to improving the accuracy of fault analysis. All the above-mentioned benchmark characteristic values, including benchmark current amplitude, benchmark current frequency, benchmark current phase, benchmark current kurtosis, benchmark current skewness, benchmark current year-on-year change rate and benchmark current month-on-month change rate, are integrated into the benchmark current fluctuation information. A comprehensive description of the current fluctuation characteristics is provided for subsequent performance evaluation, fault diagnosis and optimization of control strategies.

[0021] Performing cluster analysis on the amplitude record information set based on the amplitude deviation threshold to obtain multiple clusters of amplitude record information, wherein the multiple clusters of amplitude record information have multiple first intra-cluster trigger frequencies; Based on the multiple first intra-cluster trigger frequencies, average the intra-cluster amplitude record information whose first intra-cluster trigger frequency is greater than or equal to the first intra-cluster trigger frequency threshold, obtain a plurality of intra-cluster amplitude feature values, and add them into the reference current amplitude; The calculation process of the frequency record information set, the phase record information set, and the kurtosis record information set is the same as that of the amplitude record information set.

[0022] According to the actual application requirements and the characteristics of current fluctuations, an amplitude deviation threshold is set, which is set by the technicians in this field, and is used to determine which amplitude records belong to the same cluster, that is, have similar amplitude ranges; the amplitude record information set is clustered using a hierarchical clustering algorithm. During the clustering process, similar amplitude records are grouped into a cluster according to the amplitude deviation threshold, and multiple clusters of amplitude record information are obtained, each cluster represents a specific amplitude range, and the multiple clusters of amplitude record information have multiple first intra-cluster trigger frequencies; for each cluster of amplitude record information, its intra-cluster trigger frequency is calculated, and the trigger frequency can be defined as the number of times the amplitude record appears in the cluster. It is used to identify which clusters are the main and frequent amplitude fluctuation patterns; a cluster trigger frequency threshold is set, which is set by the technicians in this field, and only clusters with intra-cluster trigger frequencies greater than or equal to this threshold will be further processed. For clusters that meet the intra-cluster trigger frequency threshold, the mean of the intra-cluster amplitude is calculated, which represents the typical value of the current amplitude in the cluster, and can be used as the intra-cluster amplitude feature value and added to the reference current amplitude. For the frequency record information set, phase record information set and kurtosis record information set, the same processing process as the amplitude record information set can be used, that is, first perform cluster analysis based on the corresponding deviation threshold, and then extract eigenvalues ​​based on the trigger frequency within the cluster. These eigenvalues ​​will be added to the reference current frequency, reference current phase and reference current kurtosis respectively. Since amplitude, frequency, phase and kurtosis are the most basic features, all eigenvalues ​​with a frequency higher than a certain threshold are statistically analyzed as the evaluation benchmark. All extracted benchmark eigenvalues, including eigenvalues ​​of amplitude, frequency, phase and kurtosis, are integrated together to form complete benchmark current fluctuation information for subsequent performance evaluation, fault diagnosis or optimization of control strategies. Through this method based on cluster analysis and trigger frequency within the cluster, representative eigenvalues ​​can be more effectively extracted from a large number of current fluctuation records, providing strong support for the performance analysis and optimization of the inverter.

[0023] Performing a central tendency analysis on the skewness record information set to obtain a central value of the skewness record information; Performing cluster analysis on the concentrated values ​​of the skewness record information according to a skewness deviation threshold to obtain multiple clusters of skewness record information; Traversing the multiple cluster skewness record information to calculate the intra-cluster mean, and obtaining multiple intra-cluster skewness characteristic values; Taking the maximum and minimum values ​​of the plurality of intra-cluster skewness characteristic values, constructing a skewness fluctuation constraint interval, and setting it as the reference current skewness; The calculation process of the year-on-year change rate of the reference current and the month-on-month change rate of the reference current is the same as that of the skewness record information set.

[0024] Central tendency analysis of skewness record information sets refers to calculating the mean, median and other statistics of skewness to understand the distribution of skewness data. The median can reflect the center position of the data set and is not affected by extreme values. According to the skewness deviation threshold, cluster analysis is performed on the concentrated values ​​of the skewness record information. The cluster analysis classifies similar skewness values ​​into one category to form multiple clusters of skewness record information, wherein the skewness deviation threshold is based on the actual situation of the data and the purpose of analysis to ensure that the skewness values ​​within the cluster have sufficient similarity, traverse each skewness cluster, calculate the mean of the skewness value within each cluster, the mean represents the typical value of the skewness within the cluster, and can be regarded as the skewness characteristic value within the cluster, and obtain multiple skewness characteristic values ​​within the cluster; according to all the skewness characteristic values ​​within the cluster, the maximum and minimum values ​​are taken to construct a skewness fluctuation constraint interval, the skewness fluctuation constraint interval reflects the fluctuation range of the skewness value in the entire data set, and the skewness fluctuation constraint interval is set as the reference current skewness; according to the above method, the reference current year-on-year change rate and the reference current month-on-month change rate are processed to obtain the reference current year-on-year change rate and the reference current month-on-month change rate respectively; the processed reference current skewness, the reference current year-on-year change rate and the reference current month-on-month change rate are integrated together, which can be used for subsequent comprehensive evaluation of inverter performance and fault prediction.

[0025] Reconstructing the reference current fluctuation information by dimensionality reduction to generate a reference current characteristic matrix; Performing dimensionality reduction reconstruction on the reference voltage fluctuation information to generate a reference voltage feature matrix; The reference current fluctuation information includes the reference current amplitude, the reference current frequency, the reference current phase, the reference current kurtosis, the reference current skewness, the reference current year-on-year change rate and the reference current month-on-month change rate. The reference current fluctuation information is subjected to data preprocessing to eliminate the impact of the dimensions and ranges between different features so that each feature has the same unit during the dimensionality reduction process. The reference current fluctuation information is subjected to dimensionality reduction processing according to the dimensionality reduction reconstruction function to obtain the current feature vector after dimensionality reduction. The current feature vector after dimensionality reduction is integrated to obtain a matrix form, namely, a reference current feature matrix. According to the same method, the reference voltage fluctuation information is subjected to dimensionality reduction reconstruction to obtain a reference voltage feature matrix. After the dimensionality reduction reconstruction is completed, the reference current feature matrix and the reference voltage feature matrix will serve as the basis for subsequent analysis and modeling. The reference current feature matrix and the reference voltage feature matrix will be used to perform tasks such as fault prediction, performance evaluation, and anomaly detection.

[0026] Receiving monitoring current fluctuation information and monitoring voltage fluctuation information to perform dimensionality reduction reconstruction, and obtaining a comparison current feature matrix and a comparison voltage feature matrix; Receive real-time current fluctuation information and voltage fluctuation information from the monitoring system as monitoring current fluctuation information and monitoring voltage fluctuation information, that is, the current fluctuation information and voltage fluctuation information of the inverter obtained by the monitoring device, including real-time value, change rate, fluctuation range, etc., perform data preprocessing on the monitoring current fluctuation information and the monitoring voltage fluctuation information and extract key features, including the average value, standard deviation, peak value, skewness, kurtosis, etc. of current and voltage, perform dimension reduction processing on the monitoring current fluctuation information and the monitoring voltage fluctuation information according to the dimension reduction reconstruction function, obtain low-dimensional feature vectors, and integrate the reduced-dimensional current feature vectors and voltage feature vectors into a comparison current feature matrix and a comparison voltage feature matrix respectively. Each row of the matrix represents a sample, and each column represents a reduced-dimensional feature value, which is used to compare with the reference current feature matrix and the reference voltage feature matrix to perform tasks such as inverter fault prediction. Convert the high-dimensional monitoring current fluctuation information and the monitoring voltage fluctuation information into a low-dimensional comparison current feature matrix and a comparison voltage feature matrix, providing convenient and efficient data representation for subsequent analysis and comparison.

[0027] Receiving, via a user terminal, a feature multi-valued interval, wherein the feature multi-valued interval includes a current feature interval sequence; According to the current characteristic interval sequence, a dimension reduction reconstruction function is constructed: ; in, Characterize the dimensionality reduction and reconstruct the eigenvalues, Characterize the current characteristics of the jth attribute, , , , is the current characteristic interval sequence configured at the user end, N represents the interval counting symbol, N is an integer, N≥2; According to the dimensionality reduction and reconstruction function, the reference current fluctuation information is dimensionality reduced and reconstructed to generate the reference current characteristic matrix, wherein each column of the reference current characteristic matrix is ​​a dimensionality reduced and reconstructed characteristic value of the same attribute, and when an element is empty, it is supplemented with N+1.

[0028] The feature multi-value interval is received through the user end, and the user end refers to the port for the user to perform configuration and other operations. The feature multi-value interval refers to the feature value interval configured by the user, wherein multi-value refers to converting the feature at the user end, that is, converting the feature to 0, 1, 2, etc., and determining which interval the feature belongs to based on the number; wherein the feature multi-value interval includes a current feature interval sequence, and the current feature interval sequence refers to the user-defined upper and lower limits of the interval value; the received current feature interval sequence will be used in the subsequent dimensionality reduction and reconstruction process to convert the original current data into a series of labels or categories, each label or category corresponds to a specific interval; according to the current feature interval sequence, a dimensionality reduction and reconstruction function is constructed, wherein, Characterize the dimensionality reduction and reconstruct the eigenvalues, Characterize the current characteristics of the jth attribute, , , , The current characteristic interval sequence configured for the user side, N represents the interval counting symbol, N is an integer, N≥2; the reference current fluctuation information is converted using the defined dimensionality reduction reconstruction function, for each sample in the data set, its current characteristic value is compared with the current characteristic interval sequence defined by the user, and the dimensionality reduction reconstruction characteristic value is calculated based on the comparison result, and each sample in the data set is traversed. For each sample, all its current characteristic values ​​are traversed. For each current characteristic value, check whether it falls within the user-defined current characteristic interval. If the current characteristic value falls within a certain interval, the count corresponding to the interval is added to the accumulator of the dimensionality reduction reconstruction characteristic value. After completing the traversal of all current characteristic values, the value in the accumulator is the dimensionality reduction reconstruction characteristic value, converting the original high-dimensional current characteristic data into low-dimensional dimensionality reduction reconstruction characteristic values. Each eigenvalue represents the distribution of the sample in a specific current characteristic interval. The obtained dimensionality reduction reconstruction characteristic values ​​are organized into a matrix form, namely the reference current characteristic matrix. Each row of this matrix corresponds to a sample, and each column corresponds to a dimensionality reduction and reconstruction feature. If a sample is missing data on a certain feature, that is, the element is empty, it can be filled with N+1 according to regulations to ensure the integrity of the matrix and facilitate subsequent data analysis and processing. The reference current fluctuation information is reconstructed by dimensionality reduction, and a reference current feature matrix is ​​generated. The reference current feature matrix not only reduces the dimension of the data, but also retains the key information in the original data, which facilitates subsequent analysis and modeling.

[0029] By means of a fault probability prediction component, the reference current characteristic matrix, the comparison current characteristic matrix, the reference voltage characteristic matrix and the comparison voltage characteristic matrix are analyzed to obtain a fault prediction probability; Construct a fault probability prediction component, which is used to analyze the reference current feature matrix, the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix. For example, according to a neural network model, construct a fault probability prediction component, provide the reference current feature matrix, the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix as input data to the fault probability prediction component, analyze and process the reference current feature matrix and the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix, and output a fault prediction probability. The fault prediction probability refers to the possibility of failure of the reference current feature matrix and the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix determined based on historical data of the Internet of Things. The fault probability prediction component can effectively use the information in the reference and comparison feature matrices to predict and evaluate the failure risk of the equipment, and provide strong support for fault prevention and maintenance.

[0030] Comparing the reference current characteristic matrix with the comparison current characteristic matrix to obtain a current deviation reconstruction characteristic value; Perform frequency statistics on the monitored current fluctuation information according to the deviation reconstruction characteristic value to obtain a current deviation trigger frequency; Comparing the reference voltage characteristic matrix with the comparison voltage characteristic matrix to obtain voltage deviation reconstruction characteristic values; Perform frequency statistics on the monitored voltage fluctuation information according to the voltage deviation reconstruction characteristic value to obtain a voltage deviation trigger frequency; According to the current deviation reconstruction characteristic value, the current deviation trigger frequency, the voltage deviation reconstruction characteristic value, and the voltage deviation trigger frequency, historical operation record retrieval is performed based on the Internet of Things, and the fault detection ratio is counted and set as the fault prediction probability.

[0031] The reference current characteristic matrix and the comparison current characteristic matrix are compared to obtain the current deviation reconstruction eigenvalue, wherein the two matrices represent the current characteristics of the device during normal operation and the current characteristics of the device in the current operating state, respectively; the comparison process can be achieved by calculating the difference, ratio or other similarity measurement between the two, so as to obtain the current deviation reconstruction eigenvalue, which refers to the difference in eigenvalues ​​between the reference current characteristic matrix and the comparison current characteristic matrix, quantifies the degree of change of the current characteristic, and helps to identify potential faults. Frequency statistics are performed in the monitored current fluctuation information according to the current deviation reconstruction eigenvalue, and the number and frequency of occurrence of the current deviation eigenvalue in the monitoring data are analyzed. By counting the occurrence frequency of different deviation eigenvalues, it can be In order to understand the prevalence and severity of current deviation, and then evaluate its impact on the operating status of the equipment, the higher the frequency of occurrence of different deviation characteristic values, the larger the current deviation, and the more likely a fault will occur; according to the above method, the reference voltage characteristic matrix and the comparison voltage characteristic matrix are compared to obtain the voltage deviation reconstruction characteristic value, which reflects the change of voltage characteristics and is crucial for identifying voltage-related faults. According to the voltage deviation reconstruction characteristic value, the frequency statistics are performed in the monitored voltage fluctuation information to obtain the voltage deviation trigger frequency. According to the voltage deviation reconstruction characteristic value, the frequency statistics are performed in the monitored voltage fluctuation information. By analyzing the frequency of occurrence of voltage deviation, the voltage stability and its impact on equipment performance can be evaluated. After obtaining the current deviation reconstruction characteristic value, the current deviation trigger frequency, the voltage deviation reconstruction characteristic value and the voltage deviation trigger frequency, the Internet of Things technology is used to retrieve the historical operation record of the equipment. The historical operation record includes various data and events of the equipment in the past operation process. According to the retrieved historical operation records, the proportion of fault detections that match the current current and voltage deviation characteristics is counted. This ratio represents the possibility of equipment failure under the current operating status, so it can be used as a failure prediction probability. By combining real-time monitoring data with historical failure data, a quantitative assessment of equipment failure risk can be achieved.

[0032] When the fault prediction probability is greater than or equal to the fault probability threshold, a fault warning signal is generated and sent to the user end.

[0033] The fault probability threshold is set by the technicians in this field to determine whether the inverter fails. When the predicted fault probability meets the warning condition, that is, it is greater than or equal to the fault probability threshold, it means that the inverter fails and a fault warning signal is generated, such as generating a specific warning code, triggering an alarm sound or light prompt, etc. The content of the warning signal should contain enough information so that the user can quickly understand the nature and severity of the fault. By generating and sending the fault warning signal in a timely manner, the system can help users to timely discover and respond to potential faults of the equipment, thereby improving the operating safety and reliability of the equipment.

[0034] like Figure 3 As shown, the embodiment of the present application includes a frequency converter remote fault diagnosis system combined with the Internet of Things, including: A frequency converter control mode receiving module 11, wherein the frequency converter control mode receiving module 11 is used to receive the frequency converter control mode; A calibration module 12, the calibration module 12 is used to calibrate the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; A reference current characteristic matrix generating module 13, wherein the reference current characteristic matrix generating module 13 is used to perform dimension reduction reconstruction on the reference current fluctuation information to generate a reference current characteristic matrix; A reference voltage characteristic matrix generating module 14, wherein the reference voltage characteristic matrix generating module 14 is used to perform dimension reduction reconstruction on the reference voltage fluctuation information to generate a reference voltage characteristic matrix; A dimensionality reduction and reconstruction module 15, wherein the dimensionality reduction and reconstruction module 15 is used to receive the monitoring current fluctuation information and the monitoring voltage fluctuation information to perform dimensionality reduction and reconstruction, and obtain a comparison current feature matrix and a comparison voltage feature matrix; A fault prediction probability module 16, the fault prediction probability module 16 is used to analyze the reference current feature matrix, the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix through a fault probability prediction component to obtain a fault prediction probability; The fault warning signal generating module 17 is used to generate a fault warning signal and send it to the user end when the fault prediction probability is greater than or equal to the fault probability threshold.

[0035] Furthermore, the embodiment of the present application also includes: A positive sample backtracking module, which is used to perform positive sample backtracking according to the inverter control mode to obtain a current fluctuation record information set and a voltage fluctuation record information set, wherein the positive sample refers to a fault-free sample of the same inverter control mode; A feature level aggregation module, the feature level aggregation module is used to perform feature level aggregation on the current fluctuation record information set to obtain the reference current fluctuation information; A reference voltage fluctuation information acquisition module is used to perform feature-level aggregation on the voltage fluctuation record information set to obtain the reference voltage fluctuation information.

[0036] Furthermore, the embodiment of the present application also includes: A current fluctuation information extraction module, the current fluctuation information extraction module is used to extract the amplitude recording information set, frequency recording information set, phase recording information set, kurtosis recording information set, skewness recording information set, year-on-year change rate recording information set and month-on-month change rate recording information set of the first current fluctuation recording information set according to the first current fluctuation recording information of the current fluctuation recording information set, wherein the year-on-year change rate represents the current amplitude change rate within an interval of one cycle, and the month-on-month change rate represents the adjacent current amplitude change rate of the same cycle; A first type feature hierarchical aggregation module, the first type feature hierarchical aggregation module is used to traverse the amplitude record information set, the frequency record information set, the phase record information set, and the kurtosis record information set to perform first type feature hierarchical aggregation to obtain a reference current amplitude, a reference current frequency, a reference current phase, and a reference current kurtosis; A second type feature hierarchical aggregation module, the second type feature hierarchical aggregation module is used to traverse the skewness record information set, the year-on-year change rate record information set and the quarter-on-quarter change rate record information set to perform second type feature hierarchical aggregation to obtain the reference current skewness, the reference current year-on-year change rate and the reference current quarter-on-quarter change rate; A current information adding module, the current information adding module is used to add the reference current amplitude, the reference current frequency, the reference current phase, the reference current kurtosis, the reference current skewness, the reference current year-on-year change rate and the reference current quarter-on-quarter change rate into the reference current fluctuation information.

[0037] Furthermore, the embodiment of the present application also includes: A multi-cluster amplitude record information acquisition module, the multi-cluster amplitude record information acquisition module is used to perform cluster analysis on the amplitude record information set based on the amplitude deviation threshold to obtain multi-cluster amplitude record information, wherein the multi-cluster amplitude record information has a plurality of first intra-cluster trigger frequencies; An intra-cluster amplitude characteristic value adding module, the intra-cluster amplitude characteristic value adding module is used to calculate the average of the intra-cluster amplitude record information of the first intra-cluster trigger frequency greater than or equal to the first intra-cluster trigger frequency threshold based on the multiple first intra-cluster trigger frequencies, obtain a plurality of intra-cluster amplitude characteristic values, and add them into the reference current amplitude; A calculation module, wherein the calculation process of the frequency record information set, the phase record information set, and the kurtosis record information set is the same as that of the amplitude record information set.

[0038] Furthermore, the embodiment of the present application also includes: A central tendency analysis module, the central tendency analysis module is used to perform a central tendency analysis on the skewness record information set to obtain a central value of the skewness record information; A multi-cluster skewness record information acquisition module, the multi-cluster skewness record information acquisition module is used to perform cluster analysis on the skewness record information concentration value according to the skewness deviation threshold value to obtain multi-cluster skewness record information; A mean calculation module, wherein the mean calculation module is used to traverse the plurality of cluster skewness record information to perform intra-cluster mean calculation to obtain a plurality of intra-cluster skewness characteristic values; A reference current skewness setting module, the reference current skewness setting module is used to take the maximum value and the minimum value according to the plurality of intra-cluster skewness characteristic values, construct a skewness fluctuation constraint interval, and set it as the reference current skewness; A change rate calculation module, wherein the change rate calculation module is used in which the calculation process of the reference current year-on-year change rate and the reference current quarter-on-quarter change rate is the same as that of the skewness record information set.

[0039] Furthermore, the embodiment of the present application also includes: A feature multi-valued interval receiving module, the feature multi-valued interval receiving module is used to receive the feature multi-valued interval through the user end, wherein the feature multi-valued interval includes a current feature interval sequence; A dimension reduction and reconstruction function construction module, wherein the dimension reduction and reconstruction function construction module is used to construct a dimension reduction and reconstruction function according to the current characteristic interval sequence: ; in, Characterize the dimensionality reduction and reconstruct the eigenvalues, Characterize the current characteristics of the jth attribute, , , , is the current characteristic interval sequence configured at the user end, N represents the interval counting symbol, N is an integer, N≥2; A dimensionality reduction and reconstruction module is used to perform dimensionality reduction and reconstruction on the reference current fluctuation information according to the dimensionality reduction and reconstruction function to generate the reference current characteristic matrix, wherein each column of the reference current characteristic matrix is ​​a dimensionality reduction and reconstruction characteristic value of the same attribute, and when an element is empty, N+1 is added.

[0040] Furthermore, the embodiment of the present application also includes: A current deviation reconstruction eigenvalue obtaining module, wherein the current deviation reconstruction eigenvalue obtaining module is used to compare the reference current characteristic matrix with the comparison current characteristic matrix to obtain a current deviation reconstruction eigenvalue; A current deviation trigger frequency acquisition module, the current deviation trigger frequency acquisition module is used to perform frequency statistics on the monitored current fluctuation information according to the deviation reconstruction characteristic value to obtain the current deviation trigger frequency; A voltage deviation reconstruction eigenvalue obtaining module, wherein the voltage deviation reconstruction eigenvalue obtaining module is used to compare the reference voltage characteristic matrix with the comparison voltage characteristic matrix to obtain a voltage deviation reconstruction eigenvalue; A voltage deviation trigger frequency acquisition module, the voltage deviation trigger frequency acquisition module is used to perform frequency statistics on the monitored voltage fluctuation information according to the voltage deviation reconstruction characteristic value to obtain the voltage deviation trigger frequency; A fault detection ratio statistics module is used to perform historical operation record retrieval based on the Internet of Things according to the reconstructed characteristic value of the current deviation, the current deviation trigger frequency, the reconstructed characteristic value of the voltage deviation, and the voltage deviation trigger frequency, to count the fault detection ratio and set it as the fault prediction probability.

[0041] For the specific embodiments of the inverter remote fault diagnosis system combined with the Internet of Things, please refer to the embodiments of the inverter remote fault diagnosis method combined with the Internet of Things above, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0042] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time attenuation factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a remote fault diagnosis method for a frequency converter combined with the Internet of Things.

[0043] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0044] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, steps of a method for remote fault diagnosis of a frequency converter combined with the Internet of Things are implemented.

[0045] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for remote fault diagnosis of a frequency converter combined with the Internet of Things are implemented.

[0046] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0047] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for remote fault diagnosis of a frequency converter combined with the Internet of Things, characterized in that: include: Receive inverter control mode; Calibrate the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; Reconstructing the reference current fluctuation information by dimensionality reduction to generate a reference current characteristic matrix; Performing dimensionality reduction reconstruction on the reference voltage fluctuation information to generate a reference voltage feature matrix; Receiving monitoring current fluctuation information and monitoring voltage fluctuation information to perform dimensionality reduction reconstruction, and obtaining a comparison current feature matrix and a comparison voltage feature matrix; By means of a fault probability prediction component, the reference current characteristic matrix, the comparison current characteristic matrix, the reference voltage characteristic matrix and the comparison voltage characteristic matrix are analyzed to obtain a fault prediction probability; When the fault prediction probability is greater than or equal to the fault probability threshold, a fault warning signal is generated and sent to the user end.

2. The method according to claim 1, characterized in that Calibrate the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information, including: Perform positive sample backtracking according to the inverter control mode to obtain a current fluctuation record information set and a voltage fluctuation record information set, wherein the positive sample refers to a fault-free sample of the same inverter control mode; Performing feature-level aggregation on the current fluctuation record information set to obtain the reference current fluctuation information; The voltage fluctuation record information set is aggregated at a feature level to obtain the reference voltage fluctuation information.

3. The method according to claim 2, characterized in that Performing feature hierarchical aggregation on the current fluctuation record information set to obtain the reference current fluctuation information includes: According to the first current fluctuation record information of the current fluctuation record information set, extracting the amplitude record information set, frequency record information set, phase record information set, kurtosis record information set, skewness record information set, year-on-year change rate record information set and month-on-month change rate record information set of the first current fluctuation record information, wherein the year-on-year change rate represents the current amplitude change rate within one cycle, and the month-on-month change rate represents the adjacent current amplitude change rate in the same cycle; Traversing the amplitude record information set, the frequency record information set, the phase record information set, and the kurtosis record information set to perform first type feature hierarchical aggregation to obtain a reference current amplitude, a reference current frequency, a reference current phase, and a reference current kurtosis; Traversing the skewness record information set, the year-on-year change rate record information set and the quarter-on-quarter change rate record information set to perform second type feature hierarchical aggregation to obtain a reference current skewness, a reference current year-on-year change rate and a reference current quarter-on-quarter change rate; The reference current amplitude, the reference current frequency, the reference current phase, the reference current kurtosis, the reference current skewness, the reference current year-on-year change rate and the reference current quarter-on-quarter change rate are added to the reference current fluctuation information.

4. The method according to claim 3, characterized in that Traversing the amplitude record information set, the frequency record information set, the phase record information set, and the kurtosis record information set to perform first type feature hierarchical aggregation to obtain a reference current amplitude, a reference current frequency, a reference current phase, and a reference current kurtosis, including: Performing cluster analysis on the amplitude record information set based on the amplitude deviation threshold to obtain multiple clusters of amplitude record information, wherein the multiple clusters of amplitude record information have multiple first intra-cluster trigger frequencies; Based on the multiple first intra-cluster trigger frequencies, average the intra-cluster amplitude record information whose first intra-cluster trigger frequency is greater than or equal to the first intra-cluster trigger frequency threshold, obtain a plurality of intra-cluster amplitude feature values, and add them into the reference current amplitude; The calculation process of the frequency record information set, the phase record information set, and the kurtosis record information set is the same as that of the amplitude record information set.

5. The method according to claim 3, characterized in that Traversing the skewness record information set, the year-on-year change rate record information set, and the quarter-on-quarter change rate record information set to perform second-type feature hierarchical aggregation to obtain a reference current skewness, a reference current year-on-year change rate, and a reference current quarter-on-quarter change rate, including: Performing a central tendency analysis on the skewness record information set to obtain a central value of the skewness record information; Performing cluster analysis on the concentrated values ​​of the skewness record information according to a skewness deviation threshold to obtain multiple clusters of skewness record information; Traversing the plurality of cluster skewness record information to perform intra-cluster mean calculation to obtain a plurality of intra-cluster skewness characteristic values; Taking the maximum and minimum values ​​of the plurality of intra-cluster skewness characteristic values, constructing a skewness fluctuation constraint interval, and setting it as the reference current skewness; The calculation process of the year-on-year change rate of the reference current and the month-on-month change rate of the reference current is the same as that of the skewness record information set.

6. The method according to claim 1, characterized in that The reference current fluctuation information is reconstructed by dimensionality reduction to generate a reference current characteristic matrix, including: Receiving, via a user terminal, a feature multi-valued interval, wherein the feature multi-valued interval includes a current feature interval sequence; According to the current characteristic interval sequence, a dimension reduction reconstruction function is constructed: ； in, Characterize the dimensionality reduction and reconstruct the eigenvalues, Characterize the current characteristics of the jth attribute, , , , It is the current characteristic interval sequence configured at the user end, N represents the interval counting symbol, N is an integer, N≥2; According to the dimensionality reduction and reconstruction function, the reference current fluctuation information is dimensionality reduced and reconstructed to generate the reference current characteristic matrix, wherein each column of the reference current characteristic matrix is ​​a dimensionality reduced and reconstructed characteristic value of the same attribute, and when an element is empty, it is supplemented with N+1.

7. The method according to claim 1, characterized in that By means of a fault probability prediction component, the reference current characteristic matrix, the comparison current characteristic matrix, the reference voltage characteristic matrix and the comparison voltage characteristic matrix are analyzed to obtain a fault prediction probability, including: Comparing the reference current characteristic matrix with the comparison current characteristic matrix to obtain a current deviation reconstruction characteristic value; Perform frequency statistics on the monitored current fluctuation information according to the deviation reconstruction characteristic value to obtain a current deviation trigger frequency; Comparing the reference voltage characteristic matrix with the comparison voltage characteristic matrix to obtain voltage deviation reconstruction characteristic values; Perform frequency statistics on the monitored voltage fluctuation information according to the voltage deviation reconstruction characteristic value to obtain a voltage deviation trigger frequency; According to the current deviation reconstruction characteristic value, the current deviation trigger frequency, the voltage deviation reconstruction characteristic value, and the voltage deviation trigger frequency, historical operation record retrieval is performed based on the Internet of Things, and the fault detection ratio is counted and set as the fault prediction probability.

8. The inverter remote fault diagnosis system combined with the Internet of Things is characterized by: include: A frequency converter control mode receiving module, the frequency converter control mode receiving module is used to receive the frequency converter control mode; A calibration module, the calibration module is used to calibrate the inverter control mode to obtain reference current fluctuation information and reference voltage fluctuation information; A reference current characteristic matrix generation module, wherein the reference current characteristic matrix generation module is used to perform dimension reduction reconstruction on the reference current fluctuation information to generate a reference current characteristic matrix; A reference voltage characteristic matrix generation module, wherein the reference voltage characteristic matrix generation module is used to perform dimensionality reduction reconstruction on the reference voltage fluctuation information to generate a reference voltage characteristic matrix; A dimensionality reduction and reconstruction module, wherein the dimensionality reduction and reconstruction module is used to receive the monitoring current fluctuation information and the monitoring voltage fluctuation information to perform dimensionality reduction and reconstruction, and obtain a comparison current feature matrix and a comparison voltage feature matrix; A fault prediction probability module, the fault prediction probability module is used to analyze the reference current feature matrix, the comparison current feature matrix, the reference voltage feature matrix and the comparison voltage feature matrix through a fault probability prediction component to obtain a fault prediction probability; A fault warning signal generation module is used to generate a fault warning signal and send it to the user end when the fault prediction probability is greater than or equal to the fault probability threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images