Inverter fault diagnosis method and related device

Abstract

The invention provides an inverter fault diagnosis method and a related device. The inverter fault diagnosis method comprises the following specific steps: acquiring inverter alternating current side I V data; transmitting the inverter alternating current side I V data to the inverter fault diagnosis model to obtain an inverter fault diagnosis result; the inverter fault diagnosis model comprises a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module, the fault feature recognition module adopts a preliminary diagnosis module and an SVM module, and the preliminary diagnosis module is used for current sensor fault diagnosis; the SVM module is used for fault diagnosis of three-phase current imbalance, current THD abnormity and IGBT open circuit. According to the method, an inverter fault diagnosis module is used for extracting inverter system parameter fault features and carrying out fault identification and diagnosis, and accurate judgment of inverter faults is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of photovoltaic inverters, and in particular to an inverter fault diagnosis method and related devices. Background Art

[0002] As the core component of the photovoltaic power generation system, the stable and safe operation of the photovoltaic inverter plays a decisive role in the reliability of the entire photovoltaic station. During operation, the inverter needs to withstand high-intensity electrical and thermal stress from the power grid, and is also affected by various disturbances on the AC and DC sides. These factors together increase the failure risk of the inverter system. Once the inverter fails, if the fault location and cause cannot be quickly and accurately located and determined, the fault may persist and even trigger a chain reaction, seriously affecting the stable operation of the photovoltaic station, and further threatening the safety of personnel and the economic benefits of the photovoltaic station.

[0003] Traditional inverter fault diagnosis methods mainly rely on manual experience and simple instrument detection, which is not only inefficient but also cannot guarantee accuracy. With the rapid development of the photovoltaic industry and the continuous advancement of inverter technology, traditional fault diagnosis methods can no longer meet the high-precision and high-efficiency requirements of modern photovoltaic stations for inverter fault diagnosis. Therefore, it is urgent to develop a more efficient and accurate inverter fault diagnosis method to achieve real-time monitoring and rapid positioning of inverter faults, and improve the operational reliability and economic benefits of photovoltaic stations. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the present invention provides an inverter fault diagnosis method and related devices. The method uses an inverter fault diagnosis module to extract inverter system parameter fault characteristics and perform fault identification and diagnosis to achieve accurate judgment of inverter faults.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for diagnosing inverter faults, the specific steps are as follows: Get the IV data of the inverter AC side; Transmit the inverter AC side IV data to the inverter fault diagnosis model to obtain the inverter fault diagnosis result; The inverter fault diagnosis model includes a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module. The fault feature recognition module adopts a preliminary diagnosis module and an SVM module. The preliminary diagnosis module is used for current sensor fault diagnosis, and the SVM module is used for three-phase current imbalance, current THD abnormality and IGBT open circuit fault diagnosis.

[0006] Furthermore, the inverter AC side IV data are the three-phase AC voltage and current parameters on the output side.

[0007] Furthermore, the fault feature extraction module uses FFT analysis to periodically filter and intercept the IV data on the inverter AC side to obtain the fault features.

[0008] Furthermore, the preliminary diagnosis module obtains fault characteristics, calculates the absolute value of the sum of the three-phase currents using the fault characteristics, and calculates the product or mean within a period. If it exceeds a set threshold δ, it is determined that the current sensor is faulty.

[0009] Furthermore, if the set threshold δ is not exceeded, the IV data on the AC side of the inverter is Fourier transformed and then input into the SVM model to obtain the fault diagnosis result.

[0010] Furthermore, the SVM model uses fault feature data for supervised training.

[0011] The present invention also provides an inverter fault diagnosis system, comprising: A data acquisition module is used to obtain the IV data of the inverter AC side; A fault diagnosis module is used to transmit the inverter AC side IV data to the inverter fault diagnosis model to obtain the inverter fault diagnosis result; The inverter fault diagnosis model includes a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module. The fault feature recognition module adopts a preliminary diagnosis module and an SVM module. The preliminary diagnosis module is used for current sensor fault diagnosis, and the SVM module is used for three-phase current imbalance, current THD abnormality and IGBT open circuit fault diagnosis.

[0012] The present invention also provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned inverter fault diagnosis method when executing the computer program.

[0013] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned inverter fault diagnosis method are implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the above-mentioned inverter fault diagnosis method are implemented.

[0015] Compared with the prior art, the present invention has at least the following beneficial effects: The present invention provides an inverter fault diagnosis method, which combines signal processing and artificial intelligence technology to establish an inverter fault diagnosis model, thereby achieving accurate extraction and classification identification of inverter fault features. Traditional fault diagnosis methods often rely on manual experience and simple threshold judgments, and are difficult to cope with complex and changeable fault conditions. The advanced technologies such as the SVM model adopted by the present invention can more deeply mine the fault information of the inverter system and improve the accuracy and reliability of fault diagnosis. This not only provides strong support for the rapid positioning and processing of inverter faults, but also provides a solid guarantee for the stable operation of photovoltaic systems.

[0016] Traditional inverter fault diagnosis requires on-site inspection and analysis by maintenance personnel, which is not only time-consuming and labor-intensive, but also easily affected by human factors. However, the present invention realizes remote real-time monitoring and rapid diagnosis of inverter faults through the inverter fault diagnosis model, greatly reducing the need for manual intervention. This not only improves diagnostic efficiency and reduces maintenance costs, but also enables maintenance personnel to focus more on other important tasks, improving the overall maintenance level.

[0017] In summary, the inverter fault diagnosis method provided by the present invention not only improves the reliability and stability of the inverter, but also reduces the power loss and safety hazards caused by faults. This helps to promote the sustainable development of the photovoltaic industry and improve the overall competitiveness of the photovoltaic system. At the same time, the present invention also provides new ideas and methods for the intelligent operation and maintenance of photovoltaic systems, injecting new vitality into the transformation and upgrading of the photovoltaic industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of inverter fault diagnosis process; Figure 2 Schematic diagram of inverter fault diagnosis model; Figure 3 Schematic diagram of the inverter Simulink simulation model; Figure 4 Inverter simulation fault current waveform; Figure 5 FFT transformation result diagram; Figure 6 SVM classification effect diagram; Figure 7 Flowchart of inverter fault diagnosis algorithm. DETAILED DESCRIPTION

[0019] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0020] like Figure 1 As shown, the present invention provides an inverter fault diagnosis method, the specific steps are as follows: Step 1: Obtain DC parameters, AC parameters and thermal parameters of the inverter system; The DC parameters of the inverter system are the DC voltage and current on the input side; the AC parameters are the three-phase AC voltage and current parameters on the output side; the thermal parameters are the temperature parameters inside the inverter; Preferably, the present invention selects AC parameters to perform inverter fault diagnosis.

[0021] Step 2: Establish an inverter fault diagnosis network, such as Figure 2 As shown, the inverter fault diagnosis network includes a fault feature extraction module, a fault feature identification module and a fault diagnosis result output module, wherein: The fault feature extraction module can extract each fault feature by using signal processing methods such as effective value analysis, amplitude analysis, wavelet analysis or FFT analysis, and simultaneously save the corresponding fault features in the historical database.

[0022] Preferably, the fault feature extraction module uses FFT analysis to pre-process the data and obtain the fault features by periodic screening and interception; The fault feature recognition module is used to recognize the current fault feature extracted by the fault feature extraction module to obtain the current fault feature diagnosis result; Preferably, Figure 7 As shown, the fault feature recognition module includes a preliminary diagnosis module and an SVM module; the preliminary diagnosis module is used to calculate the absolute value of the sum of the three-phase currents using the fault features within the cycle and to obtain the product or mean. If it exceeds the set threshold δ, it is determined that the current sensor is faulty; if it does not exceed the set threshold δ, the data is Fourier transformed for feature extraction, and then input into the SVM for supervised training, and then the feature extraction results of the measured data are substituted into the trained SVM model to obtain the fault diagnosis result.

[0023] The fault diagnosis result output module is used to output the typical fault or abnormal data of the inverter identified by the fault feature identification module.

[0024] Step 3: Train the inverter fault diagnosis network to obtain the inverter fault diagnosis model The present invention specifically trains the inverter fault diagnosis model corresponding to the inverter of each photovoltaic array. Specifically, in the task list module of the data mining toolbox, an inverter fault diagnosis network training task is created, the data of the corresponding inverter is selected or accessed, the parameters of the inverter fault diagnosis network are configured, and the training task can be created by clicking "Complete creation". The model generated by the corresponding task is found in the model list, and an API is generated to realize the deployment of the corresponding inverter fault diagnosis network and obtain a trained inverter fault diagnosis model.

[0025] Step 4: Perform inverter fault diagnosis The application system calls the corresponding API, inputs the latest inverter AC side IV data into the inverter fault diagnosis model, and outputs whether the inverter is faulty and what fault has occurred through model diagnosis. If the inverter fails, the application system will call the photovoltaic equipment fault measure recommendation model API to obtain the disposal measures of the corresponding model, and at the same time display or notify the relevant person in charge through the system interface, email, SMS, etc., to realize real-time monitoring and alarm of the inverter.

[0026] The inverter fault diagnosis method of the present invention can diagnose 4 types of inverter faults and 15 sub-types, as shown in the following table:

[0027] The accuracy of the inverter fault diagnosis model in the inverter fault diagnosis method of the present invention is tested. First, an inverter Simulink simulation model is built to analyze the fault characteristics under different faults, such as Figure 3 As shown. Through the built Simulink inverter simulation model, the normal and fault conditions were simulated, and the current waveforms of the NPC three-level inverter under different faults were analyzed to provide guidance for subsequent fault diagnosis. Figure 4 As shown, (a) is the current waveform in normal state, (b) is the current waveform when the three phases are unbalanced, and (c)-(e) are the current waveforms when different IGBTs of phase A are open. As can be seen from the figure, when different faults occur, the time domain signals of the three-phase current measured by AC are different and there are large differences. When the three phases are unbalanced, it is manifested as a certain difference in the amplitude of the three-phase currents A, B, and C of the AC measured current. When the IGBT is open, the current waveform changes from a single peak to multiple peaks or a platform appears within one cycle. The differences in the current waveforms corresponding to different faults provide the possibility for subsequent feature extraction and fault diagnosis.

[0028] Since the inverter current and voltage data simulated by the Simulink model is in .mat file format, it needs to be converted to facilitate merging with the measured data. It is temporarily converted to Excel for storage. Since the subsequent diagnostic operator uses this format to read data for diagnosis, the measured data needs to be stored in this Excel file data storage method, that is, the header is the feature type and fault type, and one type of feature data is stored in a cell in the form of a list. One line is the inverter AC side data measured in a certain period of time.

[0029] For different fault current waveforms, FFT transformation is performed, and the amplitudes corresponding to different frequency components from 0 to 10 times the frequency are extracted as feature data, such as Figure 5 shown.

[0030] The SVM training and testing procedures were written, and the extracted training set feature data was used for SVM training. The actual classification and diagnosis results of the test set are shown in Figure 6 As shown, the accuracy is 96.89%, which illustrates the feasibility of the inverter fault diagnosis method of the present invention.

[0031] The following are device embodiments of the present invention, which can be used to perform method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0032] In another embodiment of the present invention, there is also provided an inverter fault diagnosis system, comprising: a data acquisition module and a fault diagnosis module, wherein the data acquisition module is used to acquire the IV data of the inverter AC side; the fault diagnosis module is used to transmit the IV data of the inverter AC side to the inverter fault diagnosis model to obtain the inverter fault diagnosis result; The inverter fault diagnosis model includes a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module. The fault feature recognition module adopts a preliminary diagnosis module and an SVM module. The preliminary diagnosis module is used for current sensor fault diagnosis, and the SVM module is used for three-phase current imbalance, current THD abnormality and IGBT open circuit fault diagnosis.

[0033] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the Internet advertising false traffic identification method.

[0034] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for identifying false traffic of Internet advertisements in the above embodiment.

[0035] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0036] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0037] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0038] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for diagnosing inverter faults, characterized in that: The specific steps are as follows: Get the IV data of the inverter AC side; Transmit the inverter AC side IV data to the inverter fault diagnosis model to obtain the inverter fault diagnosis result; The inverter fault diagnosis model includes a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module. The fault feature recognition module adopts a preliminary diagnosis module and an SVM module. The preliminary diagnosis module is used for current sensor fault diagnosis, and the SVM module is used for three-phase current imbalance, current THD abnormality and IGBT open circuit fault diagnosis.

2. The inverter fault diagnosis method according to claim 1, characterized in that: The IV data on the inverter AC side are the three-phase AC voltage and current parameters on the output side.

3. The inverter fault diagnosis method according to claim 1, characterized in that: The fault feature extraction module uses FFT analysis to periodically filter and intercept the IV data on the inverter AC side to obtain the fault features.

4. The inverter fault diagnosis method according to claim 3, characterized in that: The preliminary diagnosis module obtains the fault characteristics, calculates the absolute value of the sum of the three-phase currents using the fault characteristics, and calculates the product or mean within the cycle. If it exceeds the set threshold δ, it is determined that the current sensor is faulty.

5. The inverter fault diagnosis method according to claim 4, characterized in that: If it does not exceed the set threshold δ, the IV data on the AC side of the inverter is Fourier transformed and then input into the SVM model to obtain the fault diagnosis result.

6. The inverter fault diagnosis method according to claim 1, characterized in that: The SVM model is trained in a supervised manner using fault feature data.

7. An inverter fault diagnosis system, characterized in that: include: A data acquisition module is used to obtain the IV data of the inverter AC side; A fault diagnosis module is used to transmit the inverter AC side IV data to the inverter fault diagnosis model to obtain the inverter fault diagnosis result; The inverter fault diagnosis model includes a fault feature extraction module, a fault feature recognition module and a fault diagnosis result output module. The fault feature recognition module adopts a preliminary diagnosis module and an SVM module. The preliminary diagnosis module is used for current sensor fault diagnosis, and the SVM module is used for three-phase current imbalance, current THD abnormality and IGBT open circuit fault diagnosis.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of an inverter fault diagnosis method as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of an inverter fault diagnosis method as described in any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of an inverter fault diagnosis method according to any one of claims 1 to 7 are implemented.

Images