Fault detection method, device, equipment, medium and program product

Abstract

The invention discloses a fault detection method, device and equipment, a medium and a program product, and relates to the technical field of fault diagnosis, and the method comprises the steps: obtaining a first voltage signal and a first current signal inputted to a converter, and a second voltage signal of a DC bus; judging whether the voltage variable quantity represented by the second voltage signal is greater than a preset variable quantity or not to obtain a first judgment result; if the first judgment result represents that the voltage variable quantity represented by the second voltage signal is not greater than the preset variable quantity, fusing the first voltage signal and the first current signal to obtain a fused signal; and processing the fusion signal to obtain the fault position of the converter. According to the method, multi-signal fusion analysis is carried out, the common problem that the current fault position and the voltage fault position are not corresponding in a traditional detection method is effectively avoided, and the fault position judgment efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault diagnosis, and in particular relates to a fault detection method, device, equipment, medium and program product. Background Art

[0002] In the field of wind power generation, wind turbine converters play a critical role in ensuring the stable and efficient operation of power generation systems. These converters are responsible for converting the variable-frequency and variable-voltage electrical energy generated by wind turbines into stable grid-connected power. However, due to the complex operating environment of wind turbines, wind turbine converters are prone to various faults. Timely and accurate detection of these faults is crucial to avoiding power outages, reducing maintenance costs, and improving the overall reliability of wind power generation systems. Traditional methods for fault detection in wind turbine converters typically rely on signal analysis techniques. With the recent development of artificial intelligence, the Transformer model has demonstrated great potential for processing sequential data. However, practical applications of wind turbine converter fault detection face significant challenges, primarily the difficulty of data integration. Wind turbine converters generate multiple types of signals, including voltage, current, and DC bus voltage. Previous applications of the Transformer model for fault detection often resulted in mismatches between current and voltage fault locations, making it impossible to accurately determine the fault location under these multiple signal types, severely impacting the ability to quickly respond to faults. Summary of the Invention

[0003] The present application provides a fault detection method, apparatus, device, medium and program product that can accurately and quickly confirm the fault location and further improve the ability to quickly respond to faults.

[0004] To achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides a fault detection method, comprising: Acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus; determining whether a voltage variation represented by the second voltage signal is greater than a preset variation, and obtaining a first determination result; If the first judgment result indicates that the voltage variation represented by the second voltage signal is not greater than a preset variation, fusing the first voltage signal and the first current signal to obtain a fused signal; The fused signal is processed to obtain the fault location of the converter. In some optional implementations, fusing the first voltage signal and the first current signal includes: Performing feature extraction on the first voltage signal to obtain a first voltage matrix; performing feature extraction on the first current signal to obtain a first current matrix; Determine a first voltage attention matrix based on the voltage weight matrix and the first voltage matrix, and determine a first current attention matrix based on the current weight matrix and the first current matrix; The first voltage attention matrix and the first current attention matrix are fused. In some optional implementations, determining the first voltage attention matrix according to the voltage weight matrix and the first voltage matrix includes: Determine a first voltage query matrix, a first voltage key matrix, and a first voltage value matrix according to the voltage weight matrix and the first voltage matrix; Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix; Determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix; Determining a first current attention matrix according to the current weight matrix and the first current matrix includes: Determine a first current query matrix, a first current key matrix, and a first current value matrix respectively according to the current weight matrix and the first current matrix; Determining a first current attention weight matrix according to the first current query matrix and the first current key matrix; A first current attention matrix is determined according to the first current attention weight matrix and the first current value matrix.

[0005] In some optional implementations, the voltage weight matrix includes a voltage query weight matrix, a voltage key weight matrix, and a voltage value weight matrix. Determining a first voltage query matrix, a first voltage key matrix, and a first voltage value matrix based on the voltage weight matrix and the first voltage matrix respectively includes:

[0006] in, is the first voltage query matrix, is the first voltage bond matrix, The first voltage value matrix, is the first voltage matrix, is the voltage query weight matrix, is the voltage bond weight matrix, is the voltage value weight matrix; Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix includes:

[0007] in,A V is the first voltage attention weight matrix, is the transpose of the first voltage matrix; Refers to the dimension of the key vector; Determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix includes:

[0008] in, is the first voltage attention matrix; The current weight matrix includes a current query weight matrix, a current key weight matrix, and a current value weight matrix. According to the current weight matrix and the first current matrix, respectively determining the first current query matrix, the first current key matrix, and the first current value matrix includes:

[0009] in, is the first current query matrix, is the first current bond matrix, The first current value matrix, is the first current matrix, is the current query weight matrix, is the current bond weight matrix, is the current value weight matrix; Determining a first current attention weight matrix according to the first current query matrix and the first current key matrix includes:

[0010] in, is the first voltage attention weight matrix, is the transpose of the first current matrix; Refers to the dimension of the key vector; Determining a first current attention matrix according to the first current attention weight matrix and the first current value matrix includes:

[0011] in, is the first current attention matrix.

[0012] In some optional implementations, performing feature extraction on the first voltage signal to obtain a first voltage matrix, and performing feature extraction on the first current signal to obtain a first current matrix, includes: Acquire a first voltage signal input to the converter; Obtaining a first voltage variation according to the first voltage signal; Determine whether the first voltage change is greater than a preset first voltage change, and obtain a second determination result; If the second judgment result indicates that the first voltage change is greater than the first voltage preset change, outputting a first voltage abnormality signal; obtaining a first voltage matrix according to the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal; Acquire a first current signal input to the converter; Obtaining a first current variation according to the first current signal; Determine whether the first current change is greater than a preset first current change, and obtain a third determination result; If the third judgment result indicates that the first current change is greater than the first current preset change, outputting a first current abnormality signal; A first current matrix is obtained according to the first abnormal current signal and the time corresponding to the first abnormal current signal.

[0013] In some optional implementations, if the first judgment result indicates that the voltage change represented by the second voltage signal is greater than a preset change, the process is stopped.

[0014] In a second aspect, the present application provides a fault detection device, comprising: an acquisition module, configured to acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus; a judgment module, configured to judge whether a voltage variation represented by the second voltage signal is greater than a preset variation, and obtain a first judgment result; a fusion module, configured to fuse the first voltage signal and the first current signal to obtain a fused signal if the first judgment result indicates that the voltage change represented by the second voltage signal is not greater than a preset change; The processing module is used to process the fused signal to obtain the fault location of the converter.

[0015] In a third aspect, the present application provides a computing device comprising one or more processors and a memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the fault detection method as described in any one of the first aspects are performed.

[0016] In a fourth aspect, the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the fault detection method as described in any one of the first aspects.

[0017] In a fifth aspect, the present application provides a computer program product, characterized in that the computer program product comprises one or more computer instructions, and when the computer instructions are executed by a computer, the computer executes the method as described in any one of the first aspects.

[0018] It can be seen from the above technical solution that this application has at least the following beneficial effects: In the present application, the first voltage signal and the first current signal input to the converter, as well as the second voltage signal of the DC bus are first obtained; then it is determined whether the voltage change represented by the second voltage signal is greater than the preset change, and a first judgment result is obtained; if the first judgment result indicates that the voltage change represented by the second voltage signal is not greater than the preset change, the first voltage signal and the first current signal are fused to obtain a fused signal; the fused signal is processed to obtain the fault location of the converter.

[0019] The fault corresponding to an abnormal change in the second voltage of the DC bus is extremely dangerous and requires a quick response. Therefore, prioritizing whether the voltage change represented by the second voltage signal of the DC bus is greater than a preset change can greatly improve the timeliness and accuracy of fault detection.

[0020] The fault detection method of this application not only reduces the amount of data calculation, but also effectively avoids the common problem of mismatch between current fault location and voltage fault location in traditional detection methods. By comprehensively utilizing voltage, current, and DC bus voltage signals, it ultimately outputs an accurate fault location, greatly improving the efficiency and accuracy of fault location determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a fault detection method provided in an embodiment of the present application; Figure 2 A schematic diagram of a fault detection device provided in an embodiment of the present application; Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The terms "first", "second" and "third" in this application specification and the accompanying drawings are used to distinguish different objects rather than to limit a specific order.

[0023] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0024] To make the description of the following embodiments clear and concise, a brief introduction to the related technologies is first given: Wind turbine converter fault detection currently relies on Transformer models for data processing. However, wind turbine converters generate multiple types of signals, including voltage, current, and DC bus voltage. Each Transformer model can only perform fault analysis for one type of signal. Analyzing both voltage and current signals simultaneously requires two Transformer models, which is computationally intensive. Furthermore, if both current and voltage Transformer models identify a fault but the fault locations they analyze are in different phases, a direct judgment cannot be made. A separate judgment process is required, significantly slowing down the speed and accuracy of the judgment.

[0025] In view of this, an embodiment of the present application provides a fault detection method, in which a first voltage signal and a first current signal input to the converter, as well as a second voltage signal of the DC bus, are first obtained; then, a determination is made as to whether the voltage variation represented by the second voltage signal is greater than a preset variation, to obtain a first judgment result; wherein, a fault corresponding to an abnormality in the second voltage variation of the DC bus is extremely dangerous and requires a rapid response. Therefore, prioritizing the determination as to whether the voltage variation represented by the second voltage signal of the DC bus is greater than a preset variation can greatly improve the timeliness and accuracy of fault detection. Once an abnormality in the second voltage variation of the DC bus is detected, the system can quickly trigger a protection mechanism, disconnecting the relevant circuits in a very short time, preventing serious faults of the converter and even the entire power system caused by a sudden change in the DC bus voltage, effectively avoiding catastrophic consequences such as equipment damage and fire, thereby ensuring the safe and stable operation of the entire power system, significantly improving the reliability and availability of the system, and reducing potential economic losses and safety risks.

[0026] If the first judgment result indicates that the voltage change represented by the second voltage signal is not greater than a preset change, the first voltage signal and the first current signal are fused to obtain a fused signal; the fused signal is processed to obtain the fault location of the converter.

[0027] The converter includes a wind power converter.

[0028] The first voltage signal and the first current signal input to the converter, as well as the second voltage signal of the DC bus are obtained by sampling at a preset sampling position through an acquisition module. Multiple samplings are evenly performed at set time intervals within each signal cycle to obtain the first voltage signal and the first current signal, as well as the second voltage signal of the DC bus.

[0029] The time interval is set according to the application scenario of the fault detection method described in this application.

[0030] The first voltage abnormality signal is a combination of the sampled voltage value within a signal cycle before the abnormal moment and the sampled voltage value within a signal cycle after the abnormal moment. The first current abnormality signal is a combination of the sampled current value within a signal cycle before the abnormal moment and the sampled current value within a signal cycle after the abnormal moment.

[0031] Compared with the traditional method of performing complex calculations and independent analysis on multiple signals separately, this method of comprehensively using voltage, current and DC bus voltage signals during fault detection greatly reduces the amount of data calculation. The system does not need to perform lengthy and tedious calculations on each type of signal one by one. Instead, it cleverly uses signal fusion to simplify the data processing process and save a lot of computing resources and time costs. Most importantly, the multi-signal fusion analysis effectively circumvents the common problem of mismatch between the current fault location and the voltage fault location in traditional detection methods. By fusing multiple signals, this method comprehensively considers the system operating status and performs fault analysis from multiple dimensions, greatly improving the efficiency and accuracy of fault location judgment, making fault troubleshooting more efficient and accurate, and providing a more reliable guarantee for the stable operation of the power system. In order to make the technical solution of this application clearer and easier to understand, a fault detection method provided by an embodiment of this application is introduced below. Figure 1 As shown in the figure, this figure is a flowchart of a fault detection method provided in an embodiment of the present application.

[0032] In an embodiment of the present application, the fault detection method includes: S1. Acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus.

[0033] wherein, a low-pass filter is used to filter the acquired first voltage signal, the first current signal, and the second voltage signal of the DC bus to eliminate signal distortion caused by electromagnetic interference or transmission errors, thereby obtaining filtered first voltage signal, first current signal, and the second voltage signal of the DC bus for subsequent data processing; The frequency response of the low-pass filter H( f ) formula is:

[0034] Where H is the frequency response function of the filter, which represents the gain of the filter for signals of different frequencies; j is an imaginary unit, satisfying j 2 =−1; R is the resistance value in the filter, in ohms (Ω); C is the capacitance value in the filter, measured in Farads (F).

[0035] The cutoff frequency is:

[0036] Where fc is the cutoff frequency in Hertz (Hz); R is the resistance value in the filter, in ohms (Ω); C is the capacitance value in the filter, measured in Farads (F); R and C determine the filter's cutoff frequency.

[0037] A simple RC filter is used, which has a simple structure and a fast response speed and is fully applicable to the frequency range of the wind power converter.

[0038] S2. Determine whether the voltage variation represented by the second voltage signal is greater than a preset variation, and obtain a first determination result.

[0039] The calculation method of the preset change amount is: The second voltage signal in the sample data is split into the first order, that is, the difference between the second voltage signals of adjacent sampling points is calculated to obtain the second voltage change .

[0040] Then according to the second voltage change Calculate the average value of the second voltage change and the standard deviation of the second voltage variation , according to the mean and standard deviation Calculate preset changes ,include:

[0041] Here, K is a preset constant that will change in real time according to the speed of the wind turbine to adapt to different means and standard deviations at different speeds.

[0042] The sample data is a data set of the second voltage signal of the DC bus without abnormality.

[0043] The voltage variation represented by the second voltage signal is the absolute value of the second voltage variation obtained by first-order decomposition of the second voltage signal obtained during the fault detection process. .

[0044] Determining whether the voltage variation represented by the second voltage signal is greater than a preset variation is: Determine whether > .

[0045] S3. If the first judgment result indicates that the voltage variation represented by the second voltage signal is not greater than the preset variation, the first voltage signal is first-order split to obtain the first voltage variation. .

[0046] include 、 and ; Among them, a represents phase a, b represents phase b, and c represents phase c.

[0047] Determine whether the first voltage change is greater than the first voltage preset change ,Right now 、 or Whether one or more of the above is true, if true, it means that the first voltage change is greater than the first voltage preset change , and obtain the second judgment result.

[0048] If the second judgment result indicates that the first voltage change is greater than the first voltage preset change, a first voltage abnormality signal is output, and the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal are spliced to obtain a first voltage matrix , =

[0049] Wherein, a represents phase a, b represents phase b, c represents phase c, and t represents time.

[0050] For example, the signal cycle is 10 seconds, 100 points are sampled in each signal cycle, the first voltage change is greater than the first voltage preset change at the 10th second, and the output first voltage abnormality signal is the voltage signal of 200 points sampled within 1 to 20 seconds.

[0051] The first voltage matrix is obtained by splicing the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal. for: =

[0052] Perform first-order decomposition on the first current signal to obtain the first current change , include 、 and ; Among them, a represents phase a, b represents phase b, and c represents phase c.

[0053] Determine whether the first current change is greater than the first current preset change ,Right now 、 or Whether one or more of the above is true, if true, it means that the first current change is greater than the first current preset change , and obtain the third judgment result.

[0054] If the third judgment result indicates that the first current change is greater than the first current preset change, a first current abnormality signal is output, and the first current abnormality signal and the time corresponding to the first current abnormality signal are spliced to obtain a first current matrix , =

[0055] Wherein, a represents phase a, b represents phase b, c represents phase c, and t represents time.

[0056] For example, the signal cycle is 10 seconds, 100 points are sampled in each signal cycle, the first current change is greater than the first current preset change at the 10th second, and the output first voltage abnormality signal is the voltage signal of 200 points sampled within 1 to 20 seconds.

[0057] The first current matrix is obtained by splicing the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal. for: =

[0058] The voltage weight matrix includes a voltage query weight matrix, a voltage key weight matrix, and a voltage value weight matrix.

[0059] Determining a first voltage query matrix, a first voltage key matrix, and a first voltage value matrix respectively according to the voltage weight matrix and the first voltage matrix includes:

[0060] in, is the first voltage query matrix, is the first voltage bond matrix, The first voltage value matrix, is the first voltage matrix, is the voltage query weight matrix, is the voltage bond weight matrix, is the voltage value weight matrix.

[0061] Among them, the first voltage preset change amount The calculation method is: The first voltage signal in the sample data is split into the first order, that is, the difference between the first voltage signals of adjacent sampling points in the sample data is calculated to obtain the first voltage change of the sample ; Then the first voltage change of the sample Calculate the mean of the first voltage change of the sample and the standard deviation of the first voltage change of the sample , according to the mean and standard deviation Calculate the first voltage preset change ,include:

[0062] Here, K is a preset constant, which will change in real time according to the speed of the wind turbine to adapt to different means and standard deviations at different speeds.

[0063] The sample data is a data set of a first voltage signal without abnormality input to the converter.

[0064] The calculation method of the first current preset change amount is: The first current signal in the sample data is split into the first order, that is, the difference between the first current signals of adjacent sampling points in the sample data is calculated to obtain the first current variation of the sample ; Then the first current change of the sample Calculate the mean of the first current change of the sample and the standard deviation of the first current change of the sample , according to the mean and standard deviation Calculate the first current preset change ,include:

[0065] Here, K is a preset constant that will change in real time according to the speed of the wind turbine to adapt to different means and standard deviations at different speeds.

[0066] The sample data is a data set of a first current signal without abnormality input to the converter.

[0067] Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix includes:

[0068] in, A Vis the first voltage attention weight matrix, is the transpose of the first voltage matrix; Refers to the dimension of the key vector; The determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix includes:

[0069] in, is the first voltage attention matrix; The current weight matrix includes a current query weight matrix, a current key weight matrix, and a current value weight matrix. According to the current weight matrix and the first current matrix, respectively determining the first current query matrix, the first current key matrix, and the first current value matrix includes:

[0070] in, is the first current query matrix, is the first current bond matrix, The first current value matrix, is the first current matrix, is the current query weight matrix, is the current bond weight matrix, is the current value weight matrix; Determining a first current attention weight matrix according to the first current query matrix and the first current key matrix includes:

[0071] in, is the first voltage attention weight matrix, is the transpose of the first current matrix; Refers to the dimension of the key vector; Determining a first current attention matrix according to the first current attention weight matrix and the first current value matrix includes:

[0072] in, is the first current attention matrix.

[0073] The first voltage attention matrix and the first current attention matrix are fused by element-wise multiplication to obtain a fused signal matrix C, including: ⊙

[0074] Furthermore, if there are two identical data in the same column of the obtained matrix C, that is, the weights of two different phases in the same time step are the same, this means that an error occurred in the fusion process of the previous step. When fault diagnosis is performed, it is impossible to confirm which phase has failed and the specific fault location cannot be obtained. In this case, S3 needs to be repeated until a fusion signal matrix with no identical data in the same column is obtained. .

[0075] S4 will fuse the signal matrix or fusion signal matrix Input into the Transformer model to obtain the fault location of the converter.

[0076] In some possible implementations, if the first judgment result indicates that the voltage variation represented by the second voltage signal is greater than a preset variation, the process is stopped.

[0077] In the present invention, the fault corresponding to an abnormal change in the second voltage of the DC bus is extremely dangerous and requires a rapid response. Therefore, prioritizing the determination of whether the voltage change represented by the second voltage signal of the DC bus is greater than a preset change can greatly improve the timeliness and accuracy of fault detection. Once an abnormal change in the second voltage of the DC bus is detected, the system can quickly trigger a protection mechanism, disconnecting the relevant circuits in a very short time, preventing serious faults of the converter and even the entire power system caused by sudden changes in the DC bus voltage, effectively avoiding catastrophic consequences such as equipment damage and fire, thereby ensuring the safe and stable operation of the entire power system, significantly improving the reliability and availability of the system, and reducing potential economic losses and safety risks.

[0078] The present application also provides a fault detection device, such as Figure 2 As shown in FIG, this figure is a schematic diagram of a wind power converter fault detection device 200 provided in an embodiment of the present application, the device comprising: An acquisition module 201 is configured to acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus; A judgment module 202 is configured to judge whether a voltage variation represented by the second voltage signal is greater than a preset variation, and obtain a first judgment result; A fusion module 203 is configured to fuse the first voltage signal and the first current signal to obtain a fused signal; The processing module 204 is configured to process the fused signal to obtain a fault location of the converter.

[0079] Optionally, the fusion module 203 is specifically used to perform feature extraction on the first voltage signal to obtain a first voltage matrix, and to perform feature extraction on the first current signal to obtain a first current matrix; determine the first voltage attention matrix based on the voltage weight matrix and the first voltage matrix, and determine the first current attention matrix based on the current weight matrix and the first current matrix; and fuse the first voltage attention matrix and the first current attention matrix.

[0080] Optionally, the fusion module 203 is specifically configured to determine the first voltage query matrix, the first voltage key matrix, and the first voltage value matrix according to the voltage weight matrix and the first voltage matrix, including:

[0081] in, is the first voltage query matrix, is the first voltage bond matrix, The first voltage value matrix, is the first voltage matrix, is the voltage query weight matrix, is the voltage bond weight matrix, is a voltage value weight matrix; the voltage weight matrix includes a voltage query weight matrix, a voltage key weight matrix, and a voltage value weight matrix; Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix includes:

[0082] in, A V is the first voltage attention weight matrix, is the transpose of the first voltage matrix; Refers to the dimension of the key vector; Determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix includes:

[0083] in, is the first voltage attention matrix; Determining the first current query matrix, the first current key matrix, and the first current value matrix respectively according to the current weight matrix and the first current matrix includes:

[0084] in, is the first current query matrix, is the first current bond matrix, The first current value matrix, is the first current matrix, is the current query weight matrix, is the current bond weight matrix, is the current value weight matrix; Determining a first current attention weight matrix according to the first current query matrix and the first current key matrix includes:

[0085] in, is the first voltage attention weight matrix, is the transpose of the first current matrix; Refers to the dimension of the key vector; Determining a first current attention matrix according to the first current attention weight matrix and the first current value matrix includes:

[0086] in, is the first current attention matrix.

[0087] Optionally, the fusion module 203 is specifically configured to obtain a first voltage signal input to the converter; Obtaining a first voltage variation according to the first voltage signal; Determine whether the first voltage change is greater than a preset first voltage change, and obtain a second determination result; If the second judgment result indicates that the first voltage change is greater than the first voltage preset change, outputting a first voltage abnormality signal; obtaining a first voltage matrix according to the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal; Acquire a first current signal input to the converter; Obtaining a first current variation according to the first current signal; Determine whether the first current change is greater than a preset first current change, and obtain a third determination result; If the third judgment result indicates that the first current change is greater than the first current preset change, outputting a first current abnormality signal; A first current matrix is obtained according to the first abnormal current signal and the time corresponding to the first abnormal current signal.

[0088] The fault detection device further includes a control execution module, which is specifically configured to shut down the machine if the first judgment result indicates that the voltage variation represented by the second voltage signal is greater than a preset variation.

[0089] The present application also provides a computing device. Figure 3As shown, this figure is a schematic diagram of a computing device provided in an embodiment of the present application, wherein the computing device 300 includes a bus 301, a processor 302, a communication interface 303, and a memory 304. The processor 302, the memory 304, and the communication interface 303 communicate with each other via the bus 301.

[0090] The bus 301 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0091] The processor 302 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0092] The communication interface 303 is used for communicating with the outside.

[0093] The memory 304 may include volatile memory, such as random access memory (RAM). The memory 304 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0094] The memory 304 stores executable codes, and the processor 302 executes the executable codes to perform the aforementioned fault detection method.

[0095] Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of storing data on a computing device, or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the above method.

[0096] The present application also provides a computer program product comprising one or more computer instructions that, when loaded and executed on a computing device, fully or partially generate the process or function described in the present application.

[0097] The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0098] When the computer program product is executed by a computer, the computer performs any of the aforementioned fault detection methods. The computer program product may be a software installation package, and when any of the aforementioned fault detection methods is needed, the computer program product may be downloaded and executed on the computer.

[0099] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0100] The above description is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A fault detection method, characterized in that: The method comprises: Acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus; determining whether a voltage variation represented by the second voltage signal is greater than a preset variation, and obtaining a first determination result; If the first judgment result indicates that the voltage variation represented by the second voltage signal is not greater than a preset variation, fusing the first voltage signal and the first current signal to obtain a fused signal; The fused signal is processed to obtain a fault location of the converter.

2. The method according to claim 1, characterized in that The fusing the first voltage signal and the first current signal includes: Performing feature extraction on the first voltage signal to obtain a first voltage matrix, and performing feature extraction on the first current signal to obtain a first current matrix; Determine a first voltage attention matrix based on a voltage weight matrix and the first voltage matrix, and determine a first current attention matrix based on a current weight matrix and the first current matrix; The first voltage attention matrix and the first current attention matrix are fused.

3. The method according to claim 2, characterized in that The determining of a first voltage attention matrix according to the voltage weight matrix and the first voltage matrix includes: Determine a first voltage query matrix, a first voltage key matrix, and a first voltage value matrix respectively according to the voltage weight matrix and the first voltage matrix; Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix; Determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix; The determining a first current attention matrix according to the current weight matrix and the first current matrix includes: Determine a first current query matrix, a first current key matrix, and a first current value matrix respectively according to the current weight matrix and the first current matrix; determining a first current attention weight matrix according to the first current query matrix and the first current key matrix; A first current attention matrix is determined according to the first current attention weight matrix and the first current value matrix.

4. The method according to claim 3, characterized in that The voltage weight matrix includes a voltage query weight matrix, a voltage key weight matrix, and a voltage value weight matrix. Determining the first voltage query matrix, the first voltage key matrix, and the first voltage value matrix respectively according to the voltage weight matrix and the first voltage matrix includes: in, is the first voltage query matrix, is the first voltage bond matrix, The first voltage value matrix, is the first voltage matrix, is the voltage query weight matrix, is the voltage bond weight matrix, is the voltage value weight matrix; Determining a first voltage attention weight matrix according to the first voltage query matrix and the first voltage key matrix includes: in, A V is the first voltage attention weight matrix, is the transpose of the first voltage matrix; Refers to the dimension of the key vector; The determining a first voltage attention matrix according to the first voltage attention weight matrix and the first voltage value matrix includes: in, is the first voltage attention matrix; The current weight matrix includes a current query weight matrix, a current key weight matrix, and a current value weight matrix. Determining the first current query matrix, the first current key matrix, and the first current value matrix respectively according to the current weight matrix and the first current matrix includes: in, is the first current query matrix, is the first current bond matrix, The first current value matrix, is the first current matrix, is the current query weight matrix, is the current bond weight matrix, is the current value weight matrix; Determining a first current attention weight matrix according to the first current query matrix and the first current key matrix includes: in, is the first voltage attention weight matrix, is the transpose of the first current matrix; Refers to the dimension of the key vector; The determining a first current attention matrix according to the first current attention weight matrix and the first current value matrix includes: in, is the first current attention matrix.

5. The method according to claim 2, characterized in that The step of extracting features from the first voltage signal to obtain a first voltage matrix and extracting features from the first current signal to obtain a first current matrix includes: Acquire a first voltage signal input to the converter; Obtaining a first voltage variation according to the first voltage signal; Determine whether the first voltage change is greater than a preset first voltage change, and obtain a second determination result; If the second judgment result indicates that the first voltage change is greater than the first voltage preset change, outputting a first voltage abnormality signal; obtaining a first voltage matrix according to the first voltage abnormality signal and the time corresponding to the first voltage abnormality signal; Acquire a first current signal input to the converter; Obtaining a first current variation according to the first current signal; Determine whether the first current change is greater than a preset first current change, and obtain a third determination result; If the third judgment result indicates that the first current change is greater than the first current preset change, outputting a first current abnormality signal; A first current matrix is obtained according to the first abnormal current signal and the time corresponding to the first abnormal current signal.

6. The method according to claim 1, characterized in that The method further comprises: If the first judgment result indicates that the voltage variation represented by the second voltage signal is greater than a preset variation, the process is stopped.

7. A fault detection device, characterized in that: The device comprises: an acquisition module, configured to acquire a first voltage signal and a first current signal input to the converter, and a second voltage signal of the DC bus; a judgment module, configured to judge whether a voltage variation represented by the second voltage signal is greater than a preset variation, and obtain a first judgment result; a fusion module, configured to fuse the first voltage signal and the first current signal to obtain a fused signal if the first judgment result indicates that the voltage change represented by the second voltage signal is not greater than a preset change; The processing module is used to process the fused signal to obtain the fault location of the converter.

8. A computing device, characterized in that including one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the fault detection method according to any one of claims 1 to 6 are performed.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the fault detection method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes one or more computer instructions. When the computer instructions are executed by a computer, the computer performs the method according to any one of claims 1 to 6.

Images