A Data-Driven Intermittent Fault Detection Method for Three-Phase PFC Converters

Abstract

The present invention is a method for intermittent fault detection of a three-phase PFC converter based on data-driven. The present invention relates to the technical field of electronic measurement. The present invention collects the output x(t) of the three-phase PFC converter for a duration of 4 ms; decomposes x(t) based on the empirical mode decomposition (EMD) method to obtain n intrinsic mode functions (IMFs); selects m IMFs that are most relevant to the original output data and least relevant to each other among the n IMFs for statistical eigenvalue extraction; performs statistical feature extraction on the selected specific IMF; trains a convolutional neural network; collects the output data of the three-phase PFC to be measured, uses the obtained eigenvalues as the input of the trained convolutional neural network, obtains the output of the neural network, and determines whether the three-phase PFC converter has a fault.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic measurement, and is a method for detecting intermittent faults of a three-phase PFC converter based on data driving. Background Art

[0002] Three-phase power factor correction (PFC) converters are widely used in AC-DC conversion devices, and can achieve high power factor and low harmonic distortion. Due to the importance of three-phase PFC converters in today's industry, it is necessary to ensure the continuous and safe operation of three-phase PFC converters. However, due to reasons such as long-term use of components, intermittent faults may occur in three-phase PFC converters. Although the duration of intermittent faults is short, if not detected and measures are not taken in time, it will lead to catastrophic consequences.

[0003] Existing fault detection methods for three-phase PFC converters can detect open-circuit faults of switching tubes. There are also methods that can observe the parameters of capacitors in PFC converters. However, existing methods all target permanent faults. Therefore, a method for detecting intermittent faults of a three-phase PFC converter based on data driving has been proposed. Summary of the Invention

[0004] In order to overcome the deficiencies of the prior art, in view of the fact that existing fault detection methods for three-phase PFC converters can detect open-circuit faults of switching tubes. There are also methods that can observe the parameters of capacitors in PFC converters. However, existing methods all target permanent faults, the present invention provides a method for detecting intermittent faults of a three-phase PFC converter based on data driving.

[0005] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0006] A method for detecting intermittent faults of a three-phase PFC converter based on data driving, the method includes the following steps:

[0007] A method for detecting intermittent faults of a three-phase PFC converter based on data driving, the method includes the following steps:

[0008] Step 1: Collect the output x(t) of the three-phase PFC converter, with a sampling frequency of 100 kHz and a duration of 4 ms;

[0009] Step 2: Decompose x(t) based on the Empirical Mode Decomposition (EMD) method to obtain n Intrinsic Mode Functions (IMFs).

[0010] Step 3: Select m IMFs from the n IMFs that are most relevant to the original output data and least relevant to each other, and extract statistical eigenvalues.

[0011] Step 4: Extract statistical features from the selected specific IMF.

[0012] Step 5: Train a convolutional neural network.

[0013] Step 6: Collect the output data of the three-phase PFC to be measured. Use the obtained eigenvalues as the input of the trained convolutional neural network to get the output of the neural network, and determine whether the three-phase PFC converter fails.

[0014] Preferably, Step 3 is specifically as follows:

[0015] To select IMFs, introduce a correlation relationship evaluation index W. Let the Pearson correlation coefficient between each IMF and the original output signal x(t) be p i , where i = 1, 2, …, n;

[0016] Let the Pearson correlation coefficient between two IMFs be q ij , i = 1, 2, …, n, j = 1, 2, …, n, and i ≠ j;

[0017] The set of the selected IMF layer numbers is M. Then the correlation relationship evaluation index W is expressed by the following formula:

[0018]

[0019] Among them, k1 is the coefficient of the correlation between the IMF and the original output signal, and k2 is the coefficient of the correlation between two IMFs. Finally, select the combination of IMF layer numbers with the largest W value.

[0020] Preferably, the features extracted in Step 4 include mean, variance, standard deviation, peak value, root mean square, peak index, kurtosis index, impulse index, and shape index.

[0021] Preferably, the neural network in Step 5 is specifically:

[0022] The deep learning neural network has a convolutional layer, a pooling layer, and a fully connected layer. The parameter settings of the convolutional neural network are as follows: the convolutional kernel size is 3, the number of convolutional kernels is 16, the relu activation function is used, and finally there are two fully connected layers, and the number of neurons is set to 384 for both.

[0023] Preferably, the input data for the training process is the output data of N sets of three-phase PFCs in the normal state, and the eigenvalues obtained through Steps 1 to 4. The output data of the training process are all 0.

[0024] Preferably, the judgment process in Step 6 is specifically as follows:

[0025] Set a positive threshold ε. When the absolute value of the output is greater than this threshold, it is determined that the three-phase PFC converter is in a faulty state; otherwise, it is in a normal state.

[0026] A data-driven intermittent fault detection system for a three-phase PFC converter, the system comprising:

[0027] An acquisition module, which acquires the output x(t) of the three-phase PFC converter, with a sampling frequency of 100 kHz and a duration of 4 ms;

[0028] A decomposition module, which decomposes x(t) based on the empirical mode decomposition (EMD) method to obtain n intrinsic mode functions (IMFs);

[0029] A statistical eigenvalue extraction module, which selects m IMFs that are most relevant to the original output data and least correlated with each other among the n IMFs for statistical eigenvalue extraction;

[0030] A feature extraction module, which performs statistical feature extraction on the selected specific IMF;

[0031] A neural network module, which trains a convolutional neural network.

[0032] Preferably, the system further includes a judgment module, which acquires the output data of the three-phase PFC to be measured, uses the obtained eigenvalue as the input of the trained convolutional neural network, obtains the output of the neural network, and judges whether the three-phase PFC converter has a fault.

[0033] A computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement a data-driven intermittent fault detection method for a three-phase PFC converter.

[0034] A computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program stored in the memory, the processor executes a data-driven intermittent fault detection method for a three-phase PFC converter.

[0035] The present invention has the following beneficial effects:

[0036] Through simulation, it can be verified that this method can achieve the detection of intermittent faults in three-phase PFC converters. Existing fault detection methods are aimed at permanent faults, and it is difficult to detect intermittent faults. However, due to the production process of electronic components, fault degradation characteristics, and external environmental stress, intermittent faults are likely to occur in the circuit. Different from permanent faults, intermittent faults are a special form of fault manifestation, with characteristics such as randomness, periodicity, sometimes present and sometimes absent, and can recover by themselves. Due to the above characteristics, it is difficult to extract the characteristics of intermittent faults, and their existence has a serious impact on complex electronic equipment systems. The proposed method uses EMD for feature extraction, which can extract the fault characteristics of intermittent faults with short duration; uses CNN for fault detection, and obtains a high fault detection rate. Brief Description of the Drawings

[0037] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is the structure diagram of a three-phase PFC converter. Specific Embodiments

[0039] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0040] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0041] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0042] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0043] The following is a detailed description of the present invention in conjunction with specific embodiments. Specific Embodiment 1:

[0045] According to Figure 1 As shown, the specific optimized technical solution adopted by the present invention to solve the above technical problems is: the present invention relates to a method for intermittent fault detection of a three-phase PFC converter based on data driving.

[0046] A method for intermittent fault detection of a three-phase PFC converter based on data driving, the method comprising the following steps:

[0047] The method comprises the following steps:

[0048] Step 1: Collect the output x(t) of the three-phase PFC converter, with a sampling frequency of 100 kHz and a duration of 4 ms;

[0049] Step 2: Decompose x(t) based on the empirical mode decomposition (EMD) method to obtain n intrinsic mode functions (IMFs);

[0050] Step 3: Select m IMFs that are most relevant to the original output data and least relevant to each other among the n IMFs for statistical eigenvalue extraction;

[0051] Step 4: Extract statistical features of the selected specific IMF;

[0052] Step 5: Train a convolutional neural network;

[0053] Step 6: Collect the output data of the three-phase PFC to be measured, use the obtained eigenvalues as the input of the trained convolutional neural network, obtain the output of the neural network, and determine whether the three-phase PFC converter has a fault. Specific Embodiment 2:

[0055] The difference between the second embodiment and the first embodiment of this application is only that:

[0056] Specifically, step 3 is:

[0057] To select IMFs, a correlation evaluation index W is introduced. Let the Pearson correlation coefficient between each IMF and the original output signal x(t) be p i , where i = 1, 2, …, n;

[0058] Let the Pearson correlation coefficient between two IMFs be q ij , i = 1, 2, …, n, j = 1, 2, …, n, and i ≠ j;

[0059] The set of the finally selected IMF layer numbers is M. Then the correlation evaluation index W is expressed by the following formula:

[0060]

[0061] where k1 is the coefficient of the correlation between the IMF and the original output signal, and k2 is the coefficient of the correlation between two IMFs. Finally, the combination of IMF layer numbers with the largest W value is selected. Specific Embodiment Three:

[0063] The difference between Embodiment Three and Embodiment Two of this application is only that:

[0064] The features extracted in Step 4 are mean, variance, standard deviation, peak value, root mean square, peak index, kurtosis index, impulse index, and shape index. Specific Embodiment Four:

[0066] The difference between Embodiment Four and Embodiment Three of this application is only that:

[0067] The neural network in Step 5 is specifically:

[0068] The deep learning neural network has a convolutional layer, a pooling layer, and a fully connected layer. The parameter settings of the convolutional neural network are as follows: the convolutional kernel size is 3, the number of convolutional kernels is 16, the relu activation function is used, and finally there are two fully connected layers, and the number of neurons is set to 384 for both. Specific Embodiment Five:

[0070] The difference between Embodiment Five and Embodiment Four of this application is only that:

[0071] The input data in the training process is the output data of N groups of three-phase PFCs in the normal state and the feature values obtained through Steps 1 to 4. The output data in the training process is all 0. Specific Embodiment Six:

[0073] The difference between Embodiment Six and Embodiment Five of this application is only that:

[0074] The judgment process in Step 6 is specifically:

[0075] Set a positive threshold ε. When the absolute value of the output is greater than this threshold, it is determined that the three-phase PFC converter is in a fault state; otherwise, it is in a normal state. Specific Embodiment Seven:

[0077] The difference between the seventh embodiment of this application and the sixth embodiment is only that:

[0078] The present invention provides a data-driven intermittent fault detection system for a three-phase PFC converter. The system includes:

[0079] An acquisition module that acquires the output x(t) of the three-phase PFC converter with a sampling frequency of 100 kHz and a duration of 4 ms;

[0080] A decomposition module that decomposes x(t) based on the Empirical Mode Decomposition (EMD) method to obtain n Intrinsic Mode Functions (IMFs);

[0081] A statistical eigenvalue extraction module that selects m IMFs that are most relevant to the original output data and least relevant to each other among the n IMFs for statistical eigenvalue extraction;

[0082] A feature extraction module that performs statistical feature extraction on the selected specific IMF;

[0083] A neural network module that trains a convolutional neural network. Specific Embodiment Eight:

[0085] The difference between the eighth embodiment of this application and the seventh embodiment is only that:

[0086] The system further includes a judgment module that acquires the output data of the three-phase PFC to be measured, uses the obtained eigenvalue as the input of the trained convolutional neural network to obtain the output of the neural network, and determines whether the three-phase PFC converter has a fault. Specific Embodiment Nine:

[0088] The difference between the ninth embodiment of this application and the eighth embodiment is only that:

[0089] The present invention provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement a data-driven intermittent fault detection method for a three-phase PFC converter. Specific Embodiment Ten:

[0091] The difference between the tenth embodiment of this application and the ninth embodiment is only that:

[0092] The present invention provides a computer device, including a memory and a processor. A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a method for intermittent fault detection of a three-phase PFC converter based on data driving. Specific Embodiment XI:

[0094] The difference between Embodiment XI and Embodiment X of this application is only that:

[0095] Step 1: Collect the output x(t) of the three-phase PFC converter. The sampling frequency is 100 kHz and the duration is 4 ms.

[0096] Step 2: Decompose x(t) based on the empirical mode decomposition (EMD) method to obtain n IMFs.

[0097] Step 3: Select m IMFs that are most relevant to the original output data and least relevant to each other among the n IMFs for statistical eigenvalue extraction.

[0098] To select IMFs, a correlation relationship evaluation index W is introduced. Let the Pearson correlation coefficient between each IMF and the original output signal x(t) be p i , where i = 1, 2,..., n. Let the Pearson correlation coefficient between two IMFs be q ij , i = 1, 2,..., n, j = 1, 2,..., n, and i ≠ j. Assume that the set of IMF layer numbers finally selected is M. Then the correlation relationship evaluation index W can be expressed as:

[0099]

[0100] where k1 is the coefficient of the correlation between the IMF and the original output signal, and k2 is the coefficient of the correlation between two IMFs. Finally, select the combination of IMF layer numbers with the largest W value.

[0101] Step 4: Perform statistical feature extraction on the selected specific IMF. The extracted features include mean, variance, standard deviation, peak value, root mean square, peak index, kurtosis index, impulse index, and shape index. The specific calculation methods are shown in Table 1.

[0102] Table 1 Calculation Formulas of Eigenvalues

[0103]

[0104]

[0105] Step 5: Train the convolutional neural network. This deep learning network has convolutional layers, pooling layers, and fully connected layers. The parameter settings of the convolutional neural network are as follows: the convolutional kernel size is 3, the number of convolutional kernels is 16, the relu activation function is used, and finally there are two fully connected layers, with the number of neurons in both layers set to 384. The input data for the training process is the output data of N sets of three-phase PFCs in the normal state and the eigenvalue obtained through Steps 1 to 4. The output data during the training process is all 0.

[0106] Step 6: Collect the output data of the three-phase PFC to be measured and obtain the eigenvalue through Steps 1 to 4. Then use the eigenvalue as the input of the convolutional neural network trained in Step 5 to obtain the output of the neural network. Set a positive threshold ε. When the absolute value of the output is greater than this threshold, it is determined that the three-phase PFC converter is in a fault state; otherwise, it is in a normal state.

[0107] Among them, va, vb, and vc are the three-phase voltage sources input to the PFC converter, L1, L2, L3, L4, L5, and L6 are the inductors connected in series with the voltage sources, ia, ib, and ic are the currents at this position, and GA1, GA2, GB1, GB2, GC1, and GC2 are IGBTs. C is the capacitor, and uo is the output voltage.

[0108] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined. Any process or method description represented in a flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or more N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present invention belong. The logic and / or steps represented in a flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in connection with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM).In addition, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation or other appropriate processing when necessary, and then stored in a computer memory. It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0109] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments. In addition, in each embodiment of the present invention, the functional units can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0110] The above is only a preferred embodiment of a data-driven intermittent fault detection method for a three-phase PFC converter. The protection scope of a data-driven intermittent fault detection method for a three-phase PFC converter is not limited to the above embodiments. Any technical solution within this concept belongs to the protection scope of the present invention. It should be noted that for those skilled in the art, several improvements and changes made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A data-driven intermittent fault detection method for three-phase PFC converters, characterized in that: The method includes the following steps: Step 1: Collect the output x(t) of the three-phase PFC converter with a sampling frequency of 100 kHz and a duration of 4 ms; Step 2: Decompose x(t) based on the empirical mode decomposition (EMD) method to obtain n intrinsic mode functions (IMFs); Step 3: Select m IMFs from the n IMFs that are most relevant to the original output data and least relevant to each other to extract statistical eigenvalues; Specifically, Step 3 is as follows: To select IMFs, a correlation evaluation index W is introduced, and the Pearson correlation coefficient between each IMF and the original output signal x(t) is set as p i , where i = 1, 2, …, n; Let the Pearson correlation coefficient between any two IMFs be q ij , where \(i = 1, 2, \ldots, n\), \(j = 1, 2, \ldots, n\), and \(i \neq j\); If the set of the finally selected IMF layers is M, the correlation evaluation index W is expressed by the following formula: where k1 is the coefficient of the correlation between the IMF and the original output signal, and k2 is the coefficient of the correlation between two IMFs. Finally, select the combination of IMF layers with the largest W value; Step 4: Extract statistical features from the selected specific IMF; Step 5: Train a convolutional neural network; Step 6: Collect the output data of the three-phase PFC to be measured. Use the obtained eigenvalues as the input of the trained convolutional neural network to get the output of the neural network, and determine whether the three-phase PFC converter has a fault.

2. A data-driven intermittent fault detection method for a three-phase PFC converter according to claim 1, characterized in that: The features extracted in Step 4 include mean, variance, standard deviation, peak value, root mean square, peak index, kurtosis index, impulse index, and shape index.

3. A data-driven intermittent fault detection method for a three-phase PFC converter according to claim 2, characterized in that: Specifically, the neural network in Step 5 is: The deep learning neural network has a convolutional layer, a pooling layer, and a fully connected layer. The parameters of the convolutional neural network are set as follows: the convolutional kernel size is 3, the number of convolutional kernels is 16, the relu activation function is used, and finally there are two fully connected layers with the number of neurons set to 384 each.

4. A data-driven intermittent fault detection method for a three-phase PFC converter according to claim 3, characterized in that: The input data during the training process is the output data of N groups of three-phase PFCs in the normal state and the eigenvalues obtained through Steps 1 to 4. The output data during the training process is all 0.

5. A data-driven intermittent fault detection method for a three-phase PFC converter according to claim 4, characterized in that: Specifically, the judgment process in Step 6 is: Set a positive threshold ε. When the absolute value of the output is greater than this threshold, it is determined that the three-phase PFC converter is in a fault state; otherwise, it is in a normal state.

6. A data-driven intermittent fault detection system for three-phase PFC converters, characterized in that: The system includes: A collection module that collects the output x(t) of the three-phase PFC converter with a sampling frequency of 100 kHz and a duration of 4 ms; A decomposition module that decomposes x(t) based on the empirical mode decomposition (EMD) method to obtain n intrinsic mode functions (IMFs); A statistical eigenvalue extraction module that selects m IMFs from the n IMFs that are most relevant to the original output data and least relevant to each other to extract statistical eigenvalues; To select IMFs, a correlation evaluation index W is introduced, and the Pearson correlation coefficient between each IMF and the original output signal x(t) is set as p i , where i = 1, 2, …, n; Let the Pearson correlation coefficient between any two IMFs be q ij , where i = 1, 2, …, n, j = 1, 2, …, n, and i ≠ j; If the set of the finally selected IMF layers is M, the correlation evaluation index W is expressed by the following formula: where k1 is the coefficient of the correlation between the IMF and the original output signal, and k2 is the coefficient of the correlation between two IMFs. Finally, select the combination of IMF layers with the largest W value; A feature extraction module that extracts statistical features from the selected specific IMF; A neural network module that trains a convolutional neural network.

7. An intermittent fault detection system for a three-phase PFC converter based on data driving according to claim 6, characterized in that: The system further includes a judgment module. The judgment module collects the output data of the three-phase PFC to be measured, uses the obtained eigenvalue as the input of a trained convolutional neural network, obtains the output of the neural network, and judges whether a fault occurs in the three-phase PFC converter.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement a data-driven intermittent fault detection method for a three-phase PFC converter as described in any one of claims 1-5.

9. A computer device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a data-driven intermittent fault detection method for a three-phase PFC converter as described in any one of claims 1-5.

Images