Series fault detection method and device for load lines of three-phase motor and frequency converter

Abstract

The embodiment of the invention provides a series fault detection method and device for a three-phase motor and frequency converter load circuit, and the method comprises the steps: collecting a current signal, an environment temperature signal and an arc light signal of a loop during the load operation period of a three-phase motor and a frequency converter; performing median filtering on the current signal to generate a filtering signal; inputting the filtering signal into a pre-trained fault arc identification model, and outputting a prediction result of the current signal; and obtaining a final identification result according to a prediction result of the current signal, the environment temperature signal and the arc light signal. In this way, multi-feature fusion fault arc detection of series arc faults in a three-phase motor and frequency converter load circuit can be achieved, and the universal applicability of the detection method and the accuracy of the detection result are improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of fault detection related to electric motors, and in particular to a method and device for detecting series faults in a three-phase motor and an inverter load line. Background Art

[0002] In order to achieve efficient operation and improve the performance of three-phase motors, inverters have been widely used in industrial fields such as mines, machining, and metallurgy. However, in the power supply line of a three-phase inverter driving a motor, series arc faults may be caused due to problems such as loose wiring, cable aging, core breakage, or damaged insulation layer. Such faults not only cause abnormal operation of the equipment but may also lead to serious safety accidents such as electrical fires, threatening industrial production safety.

[0003] Currently, there are mainly three mainstream methods for identifying series arc faults at home and abroad: One is to identify based on the physical properties of fault arcs. Since strong arc light, arc sound, electromagnetic radiation, temperature changes and other physical effects will occur when a fault arc occurs, physical information such as arc sound and arc light of the fault arc can be collected by sensors to extract the physical characteristics of the fault arc. This method can only detect the occurrence of fault arcs at fixed detection points through sensors and cannot identify fault arcs for the entire line. The second is to use deep learning algorithms for fault arc identification. This identification method does not need to extract feature quantities by itself, but uses learning algorithms to extract fault features and classify samples, exploring the potential features of signals to a greater extent. Due to the complexity of neural networks and the heavy computational workload, such algorithms are currently difficult to transplant to embedded devices with weak computing power. The third is to identify based on the current and voltage signals of the loop. This method is easy to obtain and the waveform contains more information. The fault arc characteristics can be obtained by analyzing the waveform in the time domain, frequency domain, and time-frequency domain, and the characteristics are input into a machine learning model for identification, which is currently a research hotspot for fault arc detection and processing.

[0004] There have been many studies on fault arcs at home and abroad, which have greatly improved the detection speed and accuracy of fault arcs. However, most studies mainly focus on the detection of fault arcs in household loads, and there are few detections for three-phase AC motors and inverter loads. Moreover, most of the current embedded devices for identifying series fault arcs are based on current signal detection, and there is less research on multi-information fusion detection methods and lack of comprehensive analysis of arc information. Summary of the Invention

[0005] In view of this, embodiments of the present application provide a scheme for detecting series faults in a three-phase motor and an inverter load line, which can perform fault arc detection with multi-feature fusion of series arc faults in a three-phase motor and an inverter load line.

[0006] In the first aspect of the present application, a method for detecting series faults in a three-phase motor and a frequency converter load line is provided, including:

[0007] During the operation of the three-phase motor and the frequency converter load, collect the current signal, ambient temperature signal, and arc light signal of the loop;

[0008] Perform median filtering on the current signal to generate a filtered signal;

[0009] Input the filtered signal into a pre-trained fault arc recognition model to output the prediction result of the current signal;

[0010] Obtain the final recognition result according to the prediction result of the current signal, the ambient temperature signal, and the arc light signal.

[0011] In some embodiments, the fault arc recognition model is trained in the following manner:

[0012] Collect historical current signal samples of a series circuit of a preset number of three-phase motors and frequency converter load lines;

[0013] Divide the historical current signal samples into a training set and a test set according to a preset ratio, and construct input matrices for the data samples in the training set and the test set;

[0014] Use the training set and the test set constructed as input matrices to train and test a kernel extreme learning machine fault arc recognition model optimized by the dung beetle algorithm;

[0015] Obtain a trained arc fault recognition model.

[0016] In some embodiments, the collecting the current signal, ambient temperature signal, and arc light signal of the loop includes:

[0017] Use a current transformer to collect the loop current signal during the operation of the three-phase motor and the frequency converter load line, convert the loop current signal into a voltage signal, and use a data acquisition card to convert the voltage signal into a digital current signal;

[0018] Use an arc light sensor to obtain the light intensity at the location of the fault arc and convert it into a voltage signal;

[0019] Use a temperature sensor to obtain the ambient temperature and convert it into a voltage signal.

[0020] In some embodiments, the performing median filtering on the current signal to generate a filtered signal includes:

[0021] Define a long window with a length of 5;

[0022] At a certain moment, the signal samples within the window are x(i - 2), x(i - 1), x(i), x(i + 1), x(i + 2), where x(i) is the signal sample value located at the center of the window;

[0023] After arranging these 5 signal sample values in ascending order, the median is defined as the output value of the median filter Y(i) = Mid[x(i - 2), x(i - 1), x(i), x(i + 1), x(i + 2)], and the value of x(i) in the middle of the original window is replaced with the sorted median Y(i).

[0024] In some embodiments, the dung beetle algorithm - optimized kernel extreme learning machine fault arc recognition model is obtained through the following training:

[0025] Build a series - fault arc recognition model of the kernel extreme learning machine optimized by the dung beetle algorithm, and introduce the dung beetle algorithm to optimize the regularization coefficient c and kernel function parameter s of the model. Divide the entire dung beetle population into rolling dung beetles, egg - laying dung beetles, small dung beetles, and stealing dung beetles, and their proportions in the population are 1:2:1:1 respectively. Set the number of the dung beetle population to 20 and the maximum number of iterations to 20. Update and iterate the positions of different - role dung beetles to finally find the optimal solution. When the maximum number of iterations is reached or the optimal fitness does not change under a certain number of iterations, output the position of the current optimal fitness, and establish a fault arc recognition model for the three - phase motor and frequency - converter load.

[0026] In some embodiments, constructing the input matrix from the data samples in the training set and the test set includes:

[0027] Calculate the optimal number K of intrinsic mode function components for variational mode decomposition based on the mean difference of the instantaneous frequencies of the intrinsic mode components, and decompose the current signal based on this K value;

[0028] Select IMF4 obtained after variational mode decomposition as the component for time - frequency domain feature calculation, and calculate the square Euclidean distance between the permutation entropy and the approximate entropy of IMF4;

[0029] Transmit the calculated square Euclidean distance between the permutation entropy and the approximate entropy of IMF4 as the input feature vector to the series - fault arc recognition model.

[0030] In some embodiments, obtaining the final recognition result according to the prediction result of the current signal, the ambient temperature signal, and the arc light signal includes:

[0031] If it is determined as a fault feature according to one of the prediction result of the current signal, the ambient temperature signal, and the arc light signal, then determine the series fault of the three - phase motor and the frequency - converter load line.

[0032] In a second aspect of the present application, a series fault detection device for a three-phase motor and a frequency converter load line is provided, including:

[0033] A signal acquisition module, configured to acquire the current signal, the ambient temperature signal, and the arc light signal of the loop during the operation of the three-phase motor and the frequency converter load;

[0034] A filtering module, configured to perform median filtering on the current signal to generate a filtered signal;

[0035] A current signal prediction module, configured to input the filtered signal into a pre-trained fault arc recognition model and output a prediction result of the current signal;

[0036] An identification result generation module, configured to obtain a final identification result according to the prediction result of the current signal, the ambient temperature signal, and the arc light signal.

[0037] In a third aspect of the present application, an electronic device is provided. The electronic device includes: a memory and a processor, and a computer program is stored on the memory. When the processor executes the program, the method as described above is implemented.

[0038] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect of the present application is implemented.

[0039] The series fault detection method for a three-phase motor and a frequency converter load line provided by the embodiments of the present application collects the current signal, the ambient temperature signal, and the arc light signal of the loop during the operation of the three-phase motor and the frequency converter load; performs median filtering on the current signal among them to generate a filtered signal; inputs the filtered signal into a pre-trained fault arc recognition model and outputs a prediction result of the current signal; and comprehensively obtains a final identification result based on the prediction result of the current signal, the ambient temperature signal, and the arc light signal, so as to be able to perform multi-feature fusion fault arc detection on the series arc fault in the three-phase motor and the frequency converter load line, improving the general applicability of the detection method and the accuracy of the detection result.

[0040] It should be understood that the content described in the summary of the invention section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Combined with the drawings and referring to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present application will become more obvious. In the drawings, the same or similar reference numerals represent the same or similar elements, where:

[0042] Figure 1 The system architecture diagram related to the method provided in the embodiments of the present application.

[0043] Figure 2 The flowchart of the series fault detection method for a three-phase motor and a frequency converter load line according to the embodiments of the present application;

[0044] Figure 3 The block diagram of the series fault detection device for a three-phase motor and a frequency converter load line according to the embodiments of the present application;

[0045] Figure 4 The structural schematic diagram of a terminal device or a server suitable for implementing the embodiments of the present application;

[0046] Figure 5 The flow schematic diagram of the dung beetle algorithm applied in the embodiments of the present application;

[0047] Figure 6 The circuit structural schematic diagram of a specific application example of the series fault detection device for a three-phase motor and a frequency converter load line. Detailed implementation manners

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some but not all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0049] In addition, the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after.

[0050] Figure 1 The schematic diagram shows an exemplary operating environment 100 in which the embodiments of the present disclosure can be implemented. The operating environment 100 includes a client 110, a communication module 120, a server 130, and a device 140.

[0051] Among them, the client 110 can be the current user terminal and is used to report instructions to the server 130;

[0052] The server 130 can be a cloud server, which is used to maintain the information of currently connected devices in the cloud, such as the online / offline status and device locking status of the devices. When a device goes online or offline, it updates the online / offline status of the device and maintains the locking status information of the device, etc.;

[0053] Furthermore, the server 130 further includes:

[0054] A device locking module, which is used to send locking / unlocking tasks to the device 140 to ensure the consistency between the status of the device 140 and that in the server 130. When the device 140 is offline, it synchronizes the locking status of the device 140 to the server 130, and at the same time creates a locking task. When the device 140 goes online, it sends the locking task. The locking task is completed until the device 140 returns a locking success status.

[0055] The device 140 can be a target user terminal, which is used to receive instructions sent by the server 130, perform corresponding operations according to the instructions, and report operation result information to the server 130.

[0056] A communication module 120, which is used to maintain the communication link between the device 140 and the server 130, and report callback information to the server 130 when the device 140 goes online or offline. That is, the server 130 can be connected to the device 140 through the communication module 120.

[0057] Figure 2 The flowchart of the series fault detection method for a three-phase motor and a frequency converter load line according to an embodiment of the present disclosure is shown. The method can be executed by Figure 1 the server 130 therein. The method includes the following steps:

[0058] S201: During the operation of the three-phase motor and the frequency converter load, collect the current signal, ambient temperature signal, and arc light signal of the loop.

[0059] Specifically, a current transformer can be used to collect the loop current signal during the operation of the three-phase motor and the frequency converter load line, convert the loop current signal into a voltage signal, and use a data acquisition card to convert the voltage signal into a digital current signal; an arc light sensor is used to obtain the light intensity at the location of the fault arc and convert it into a voltage signal; a temperature sensor is used to obtain the ambient temperature and convert it into a voltage signal.

[0060] S202: Perform median filtering on the current signal to generate a filtered signal.

[0061] Specifically, a long window with a length of 5 can be defined; at a certain moment, the signal samples within the window are x(i - 2), x(i - 1), x(i), x(i + 1), x(i + 2), where x(i) is the signal sample value located at the center of the window; after arranging these 5 signal sample values in ascending order, the median value is defined as the output value of the median filter Y(i) = Mid[x(i - 2), x(i - 1), x(i), x(i + 1), x(i + 2)], and the value of x(i) in the middle of the original window is replaced with the sorted median Y(i).

[0062] S203: Input the filtered signal into a pre-trained fault arc recognition model to output the prediction result of the current signal.

[0063] Among them, the fault arc recognition model is trained in the following way: collect historical current signal samples of a series circuit of a preset number of three-phase motors and frequency converter load lines; divide the historical current signal samples into a training set and a test set according to a preset ratio, and construct input matrices for the data samples in the training set and the test set. Specifically, the optimal number of intrinsic mode function (IMF) components K for variational mode decomposition can be calculated based on the mean difference of the instantaneous frequencies of the intrinsic mode components, and the current signal is decomposed based on this K value; select IMF4 obtained after variational mode decomposition as the component for time-frequency domain feature calculation, and calculate the squared Euclidean distance between the permutation entropy and the approximate entropy of IMF4; transmit the calculated squared Euclidean distance between the permutation entropy and the approximate entropy of IMF4 as an input feature vector to the series fault arc recognition model.

[0064] Use the training set and the test set constructed as input matrices to train and test a pre-built kernel extreme learning machine fault arc recognition model optimized by the dung beetle algorithm; obtain the trained arc fault recognition model.

[0065] The dung beetle algorithm-optimized kernel extreme learning machine fault arc recognition model is obtained through the following training: build a series fault arc recognition model based on the dung beetle algorithm-optimized kernel extreme learning machine, and introduce the dung beetle algorithm to optimize the regularization coefficient c and the kernel function parameter s of the model. Divide the entire dung beetle population into rolling dung beetles, egg-laying dung beetles, small dung beetles, and stealing dung beetles, and their proportions in the population are 1:2:1:1 respectively. The number of the dung beetle population is set to 20, and the maximum number of iterations is set to 20. The positions of different roles of dung beetles are updated iteratively to finally find the optimal solution. When the maximum number of iterations is reached or the optimal fitness does not change under a certain number of iterations, output the position of the current optimal fitness, and establish a fault arc recognition model for three-phase motors and frequency converter loads.

[0066] S204: Obtain the final recognition result based on the prediction result of the current signal, the environmental temperature signal, and the arc light signal.

[0067] Specifically, if a fault feature is determined according to one of the predicted result of the current signal, the ambient temperature signal, and the arc light signal, a series fault of the three-phase motor and the inverter load line is determined.

[0068] The series fault detection method for a three-phase motor and an inverter load line provided by the embodiments of the present application collects the current signal, the ambient temperature signal, and the arc light signal of the acquisition loop during the operation of the three-phase motor and the inverter load; performs median filtering on the current signal therein to generate a filtered signal; inputs the filtered signal into a pre-trained fault arc recognition model to output the predicted result of the current signal; and obtains the final recognition result by synthesizing the predicted result of the current signal, the ambient temperature signal, and the arc light signal, so as to be able to perform multi-feature fusion fault arc detection on the series arc fault in the three-phase motor and the inverter load line, improving the general applicability of the detection method and the accuracy of the detection result.

[0069] The technical solution of the present application will be described in detail below with specific examples.

[0070] The series fault detection method for a three-phase motor and an inverter load line provided by the embodiments of the present application is implemented based on a signal acquisition unit, a data processing unit, a model construction unit, and a fault detection unit. Among them,

[0071] The signal acquisition unit is configured to collect the current signal, the ambient temperature signal, and the arc light signal of the fault point during the operation of the three-phase motor and the inverter load, and synchronously transmit the signal data to the data processing unit.

[0072] The data processing unit is configured to perform median filtering on the current signal obtained by the signal acquisition unit, divide the filtered data into normal-class and fault-class data samples, add labels to the data samples of different classes respectively, calculate the feature vectors of each sample, obtain a series fault arc data set, and divide it into a training set and a test set of the model according to a certain ratio.

[0073] The model construction unit is configured to construct an input matrix from the data samples in the training set and the test set of the model, and build a dung beetle algorithm optimized kernel extreme learning machine (DBO-KELM) fault arc recognition model. Use the training set and the test set of the model constructed as the input matrix to train and test the series arc fault recognition model, and obtain the trained series arc fault recognition model.

[0074] The fault detection unit is configured to input the features of each sample into the series fault arc recognition model for result prediction, and output the final recognition result of the recognition model.

[0075] In the embodiment of the present application, the signal acquisition unit includes a current transformer, an arc sensor, a temperature sensor, a data acquisition card, and a DC power supply; wherein,

[0076] The current transformer is used to convert the loop current signal into a voltage signal during the operation of the three-phase motor and the frequency converter load line.

[0077] The arc sensor is used to obtain the light intensity at the location of the fault arc and convert it into a voltage signal.

[0078] The temperature sensor is used to obtain the ambient temperature and convert it into a voltage signal.

[0079] The data acquisition card is used to perform analog-to-digital conversion processing on the voltage signal.

[0080] The DC power supply is used to provide power for the current transformer and the data acquisition card.

[0081] In the embodiment of the present application, the data processing unit is implemented using Matlab. The sampling frequency of the signal acquisition unit is 10KHz, and the number of sampling points in one cycle is 200 points. Median filtering preprocessing is performed on the collected current waveform. The steps of the median filtering algorithm are as follows:

[0082] Step 1: First, define a long window with a length of 5.

[0083] Step 2: Suppose that at a certain moment, the signal samples within the window are x(i - 2), x(i - 1), x(i),

[0084] x(i + 1), x(i + 2), where x(i) is the signal sample value located at the center of the window.

[0085] Step 3: After arranging these 5 signal sample values in ascending order, the median among them is defined as the output value of the median filtering, Y(i) = Mid[x(i - 2), x(i - 1), x(i), x(i + 1), x(i + 2)]. Replace the original x(i) value in the middle of the window with the sorted median Y(i).

[0086] The loop current signal is divided into a data sample set at intervals of 2 current cycle signal lengths, and labels are added to the data samples. Calculate the squared Euclidean distance feature of the approximate entropy and permutation entropy features of the IMF4 component of each sample as the input of the model detection unit.

[0087] The calculation steps of the sample features are as follows:

[0088] Step 1: Perform variational mode decomposition on the preprocessed current data samples, and select an appropriate decomposition layer number K based on the mean difference of the instantaneous frequencies of the intrinsic mode components;

[0089] Step 2: Calculate the square Euclidean distance between the permutation entropy and approximate entropy features of the IMF4 component as the time-frequency domain features of the sample data, and use it as the input of the model construction unit;

[0090] Calculate the optimal number of intrinsic mode function (IMF) components K for variational mode decomposition (VMD) based on the mean difference of the instantaneous frequencies of the intrinsic mode components. The process is as follows:

[0091] (1) Initialize the parameters of the VMD algorithm, set the number of decomposition modes K to 2, and perform VMD on the signal;

[0092] (2) Calculate the mean of the instantaneous frequencies of each IMF mode of the decomposed signal. The mean of the instantaneous frequencies can be obtained as follows:

[0093]

[0094] where N is the number of instantaneous frequencies of the m-th mode, and the instantaneous frequency at the n-th sampling point is f mn .

[0095] (3) Calculate the difference between the mean values of the instantaneous frequencies of the last two IMF components, and set the threshold to 140 Hz. If the mean difference of the instantaneous frequencies of the last two IMF components is lower than the threshold, it indicates the existence of mode mixing, and then select K - 1 as the optimal K value; if the mean difference of the instantaneous frequencies of the last two IMF components is higher than the threshold, it means that the optimal K value has not been reached, then let K + 1 and continue to iterate to find the optimal value.

[0096] In the embodiment of the present application, the model construction unit is implemented using Matlab.

[0097] The model construction unit optimizes the kernel extreme learning machine model through the dung beetle algorithm. The specific optimization process can be seen in Figure 5 . Optimize the regularization coefficient and kernel function parameters of the model as the position coordinates through the dung beetle algorithm, and use the obtained optimal position information as the optimal regularization coefficient and kernel function parameters of the model. Divide the feature vector obtained by the data processing unit into a training set and a test set, and the ratio is 1:2. Input the training set and the test set into the optimized kernel extreme learning machine for training to obtain a series fault arc recognition model for the three-phase motor and the frequency converter load line.

[0098] The fault detection unit is used to determine according to the series fault arc recognition model established by the model construction unit and the threshold method. The current signal characteristics are judged according to the recognition model in the model construction unit, and the temperature and arc light signal characteristics are judged according to the threshold method. If any signal is recognized as the series fault arc characteristic, it is judged that a series fault arc occurs in the loop, and finally the recognition result is output.

[0099] In an embodiment of the present invention, a series fault arc detection device for a three-phase motor and a frequency converter load line is provided. The specific structure is shown in Figure 6 . The device includes a data acquisition module, a communication module, an upper computer UI, a data analysis module, and a series fault arc identification module.

[0100] The data acquisition module is used to obtain current signals, temperature signals, and arc light signals during the operation of the three-phase motor and the frequency converter load, and perform median filtering preprocessing on the current signals in the main control MCU.

[0101] The communication module is used to upload the signals collected by the data acquisition module to the upper computer.

[0102] The upper computer UI is used to realize the real-time display and storage of signals, and the current signal is plotted in real time.

[0103] The data analysis module calculates the squared Euclidean distance feature of the entropy feature of the processed current signal and inputs it into the recognition model.

[0104] The series fault arc identification module is used to judge faults on the current signal features input by the data analysis module. And analyze whether the temperature and arc light signals exceed the threshold. If the signal is judged to be a fault signal, the fault information is printed on the upper computer UI3 and a flag signal is sent to the main control MCU to drive the fault alarm circuit to act.

[0105] In an embodiment of the present application, the data acquisition module includes a current transformer, an arc light sensor, a temperature sensor, a DC power supply, and an embedded device; among them,

[0106] The current transformer is used to convert the loop current signal into a voltage signal during the operation of the three-phase motor and the frequency converter load line.

[0107] The arc light sensor is used to obtain the light intensity at the location where the fault arc occurs and convert it into a voltage signal.

[0108] The temperature sensor is used to obtain the ambient temperature and convert it into a voltage signal.

[0109] The DC power supply is used to supply power to the sensors and the embedded device;

[0110] The embedded device is used to obtain current, arc light, and temperature signals in real time; and perform median filtering processing on the current signals. The embedded device converts the collected analog signals into digital signals through the ADC channel and transmits them to the upper computer using the communication module.

[0111] In an embodiment of the present application, the communication module includes a LoRa module and a serial port module.

[0112] The LoRa module is a wireless communication module that can achieve wireless communication between the data acquisition module 1 and the host computer through the UART interface of the main control MCU.

[0113] The serial port module is a wired transmission module that can achieve wired data exchange between the data acquisition module and the host computer through this module.

[0114] In the embodiment of the present invention, the host computer UI is built using Matlab App Designer and is used to achieve real-time display and storage of current, temperature, and arc light signals, where the current signal is plotted in real time.

[0115] In the embodiment of the present invention, the data analysis module calculates and processes the squared Euclidean distance feature of the entropy feature of the current signal and inputs it into the series fault arc identification module.

[0116] In the embodiment of the present invention, the series fault arc identification module is used to perform fault judgment on the current signal features input by the data analysis module. And analyze whether the temperature and arc light signals exceed the threshold. If the signal is judged to be a fault signal, the fault information is printed on the host computer UI and a flag signal is sent to the main control MCU to drive the fault alarm circuit to act.

[0117] Implementing the embodiments of the present application has the following beneficial effects:

[0118] The present invention can accurately detect series arc faults in the three-phase motor and frequency converter load line by identifying series fault arcs through multi-feature fusion of current, arc light, and temperature, and has a good identification effect. The squared Euclidean distance feature of the approximate entropy and permutation entropy features of the IMF4 component after variational mode decomposition of the current signal can accurately and effectively identify series arc faults in the three-phase motor and frequency converter load line. The proposed series arc fault identification model optimizes the kernel extreme learning machine model using the dung beetle algorithm, with fast identification speed and high accuracy.

[0119] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0120] The above is the introduction of the method embodiments. The following further illustrates the solution of the present application through device embodiments.

[0121] Figure 3A block diagram of a series fault detection device for a three-phase motor and a frequency converter load line according to an embodiment of the present application is shown. The device includes:

[0122] A signal acquisition module 301, configured to acquire current signals, ambient temperature signals, and arc light signals of a loop during the operation of a three-phase motor and a frequency converter load.

[0123] A filtering module 302, configured to perform median filtering on the current signal to generate a filtered signal.

[0124] A current signal prediction module 303, configured to input the filtered signal into a pre-trained fault arc recognition model and output a prediction result of the current signal.

[0125] An identification result generation module 304, configured to obtain a final identification result according to the prediction result of the current signal, the ambient temperature signal, and the arc light signal.

[0126] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the described modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0127] Figure 4 A schematic structural diagram of a terminal device or a server suitable for implementing the embodiments of the present application is shown.

[0128] As Figure 4 shown, the terminal device or the server includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 into the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the terminal device or the server are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0129] The following components are connected to the I / O interface 405: an input part 406 including a keyboard, a mouse, etc.; an output part 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part 408 including a hard disk, etc.; and a communication part 409 including a network interface card such as a LAN card, a modem, etc. The communication part 409 performs communication processing via a network such as the Internet. The drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage part 408 as needed.

[0130] In particular, according to the embodiments of the present application, the above method flow steps can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the system of the present application are executed.

[0131] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. And in the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0133] The units or modules involved in the embodiments described in the present application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. Among them, the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0134] On the other hand, the present application also provides a computer-readable storage medium, which can be included in the electronic device described in the above embodiments; or can exist separately and not be assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the foregoing programs are executed by one or more processors, they implement the methods described in the present application.

[0135] The above description is only a preferred embodiment of the present application and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, technical solutions formed by mutually replacing the above features with (but not limited to) technical features having similar functions in the present application.

Claims

1. A method for detecting series faults of a three-phase motor and a frequency converter load line, characterized in that: include: During the operation of the three-phase motor and inverter load, the current signal, ambient temperature signal and arc signal of the circuit are collected; Performing median filtering on the current signal to generate a filtered signal; Inputting the filtered signal into a pre-trained fault arc identification model and outputting a prediction result of a current signal; A final recognition result is obtained according to the prediction result of the current signal, the ambient temperature signal and the arc signal.

2. The method according to claim 1, characterized in that The arc fault identification model is trained in the following way: Collecting a preset number of historical current signal samples of a series circuit of a three-phase motor and a frequency converter load circuit; Dividing the historical current signal samples into a training set and a test set according to a preset ratio, and constructing an input matrix with the data samples in the training set and the test set; The pre-built nuclear extreme learning machine fault arc identification model optimized by the dung beetle algorithm is trained and tested using the training set and test set constructed as input matrices; The trained arc fault recognition model is obtained.

3. The method according to claim 1, characterized in that The current signal, ambient temperature signal and arc signal of the acquisition circuit include: A current transformer is used to collect the loop current signal of the three-phase motor and the inverter load line during operation, the loop current signal is converted into a voltage signal, and a data acquisition card is used to convert the voltage signal into a digital current signal; An arc sensor is used to obtain the light intensity at the location where the fault arc occurs and convert it into a voltage signal; A temperature sensor is used to obtain the ambient temperature and convert it into a voltage signal.

4. The method according to claim 1, characterized in that: The performing median filtering on the current signal to generate a filtered signal includes: Define a long window of length 5; At a certain moment, the signal samples in the window are x(i-2), x(i-1), x(i), x(i+1), x(i+2), where x(i) is the signal sample value at the center of the window; After arranging these 5 signal sample values ​​in ascending order, the median value is defined as the output value of the median filter Y(i) = Mid[x(i-2), x(i-1), x(i), x(i+1), x(i+2)], and the value of x(i) in the middle of the original window is replaced by the sorted median Y(i).

5. The method according to claim 2, characterized in that: The nuclear extreme learning machine fault arc recognition model optimized by the dung beetle algorithm is obtained through the following training: A series fault arc recognition model of the nuclear extreme learning machine based on the dung beetle algorithm optimization is built, and the dung beetle algorithm is introduced to optimize the regularization coefficient c and kernel function parameter s of the model. The entire dung beetle population is divided into rolling dung beetles, egg-laying dung beetles, small dung beetles and stealing dung beetles, and the proportions of the population are 1:2:1:1 respectively. The number of dung beetle populations is set to 20, and the maximum number of iterations is set to 20. The positions of dung beetles with different roles are updated and iterated to finally find the optimal solution. When the maximum number of iterations is reached or the optimal fitness does not change under a certain number of iterations, the position of the current optimal fitness is output, and a fault arc recognition model of three-phase motor and inverter load is established.

6. The method according to claim 2, characterized in that The step of constructing an input matrix from the data samples in the training set and the test set includes: The optimal number of intrinsic mode component decompositions K of variational mode decomposition is calculated based on the instantaneous frequency mean difference of the intrinsic mode component, and the current signal is decomposed based on the K value; IMF4 obtained after variational mode decomposition is selected as the component for time-frequency domain feature calculation, and the squared Euclidean distance between the permutation entropy and the approximate entropy of IMF4 is calculated; The calculated squared Euclidean distance between the permutation entropy and the approximate entropy of IMF4 is transmitted as the input feature vector to the series fault arc recognition model.

7. The method according to claim 6, characterized in that The final recognition result is obtained according to the prediction result of the current signal, the ambient temperature signal and the arc signal, including: If a fault feature is determined based on the prediction result of the current signal, the ambient temperature signal, and the arc signal, a series fault between the three-phase motor and the inverter load line is determined.

8. A series fault detection device for a three-phase motor and a frequency converter load circuit, characterized in that: include: A signal acquisition module is used to collect the current signal, ambient temperature signal and arc signal of the circuit during the operation of the three-phase motor and the inverter load; A filtering module, used for performing median filtering on the current signal to generate a filtered signal; A current signal prediction module, used for inputting the filtered signal into a pre-trained fault arc recognition model and outputting a prediction result of the current signal; The recognition result generating module is used to obtain the final recognition result according to the prediction result of the current signal, the ambient temperature signal and the arc signal.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is 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 method according to any one of claims 1 to 7 is implemented.

Images