A capacitor fault recognition method and related device

Abstract

The application discloses a capacitor fault identification method and related device, and the method comprises the following steps: acquiring an original running voltage signal in the running process of a capacitor; identifying a fault phase of the capacitor running according to the original running voltage signal through a preset wavelet transform method; inputting the original running voltage signal into a preset multi-core SVM model to perform signal decoupling operation, and obtaining a voltage positive sequence transient component and a voltage negative sequence transient component; after extracting a voltage instantaneous value in the voltage positive sequence transient component, calculating an identification parameter according to the voltage instantaneous value and a preset steady-state voltage value; judging a capacitor fault category according to the identification parameter and a parameter threshold value, wherein the capacitor fault category comprises thermal breakdown and electric breakdown. The application can solve the technical problem of poor capacitor fault identification effect caused by the defects of low efficiency and poor reliability in the prior art.

Description

Technical Field

[0001] This application relates to the field of capacitors, and more particularly to a capacitor fault identification method and related apparatus. Background Technology

[0002] DC support capacitors are widely used as power switching devices in fields such as wind power, photovoltaics, aerospace and electric vehicles. However, frequent component failures, easy damage, cluster failures and high failure rates seriously affect the operating performance of the capacitors. In order to ensure the reliability of capacitor operation, it is necessary to accurately identify the faults of the support capacitors.

[0003] Existing fault identification technologies are complex to operate, inefficient, computationally intensive, and unreliable, resulting in poor capacitor fault identification performance during real-time monitoring. Summary of the Invention

[0004] This application provides a capacitor fault identification method and related apparatus to solve the technical problem that the prior art has low efficiency and poor reliability, resulting in poor capacitor fault identification effect.

[0005] In view of the above, the first aspect of this application provides a capacitor fault identification method, comprising:

[0006] Acquire the original operating voltage signal of the capacitor during operation;

[0007] The fault phase of the capacitor operation is identified based on the original operating voltage signal using a preset wavelet transform method.

[0008] The original operating voltage signal is input into a preset multi-core SVM model for signal decoupling to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0009] After extracting the instantaneous voltage value from the positive sequence transient voltage component, identification parameters are calculated based on the instantaneous voltage value and the preset steady-state voltage value.

[0010] The capacitor fault category is determined based on the identification parameters and parameter thresholds, and the capacitor fault category includes thermal breakdown and electrical breakdown.

[0011] Preferably, the step of identifying the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform method includes:

[0012] Extract the voltage transient signal from the original operating voltage signal;

[0013] The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

[0014] Preferably, the step of inputting the original operating voltage signal into a preset multi-core SVM model for signal decoupling to obtain positive-sequence transient voltage components and negative-sequence transient voltage components includes:

[0015] The linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space by the preset multi-core SVM model to obtain the mapped linearly separable signal;

[0016] The optimal hyperplane optimization process is performed based on the linearly separable signal in the mapped signal and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0017] Preferably, the step of extracting the instantaneous voltage value from the positive-sequence transient voltage component and calculating the identification parameters based on the instantaneous voltage value and a preset steady-state voltage value includes:

[0018] Extract the instantaneous voltage value from the positive-sequence transient component of the voltage;

[0019] The identification parameter is calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value, and the ratio is expressed as:

[0020]

[0021] Where, r U For the identification parameters, U BD U is the instantaneous value of the voltage. FP This is a preset steady-state voltage value.

[0022] A second aspect of this application provides a capacitor fault identification device, comprising:

[0023] The data acquisition module is used to acquire the original operating voltage signal of the capacitor during operation.

[0024] The fault location module is used to identify the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform method.

[0025] The signal decoupling module is used to input the original operating voltage signal into a preset multi-core SVM model for signal decoupling operation to obtain the positive-sequence transient component and the negative-sequence transient component of voltage;

[0026] The parameter calculation module is used to extract the instantaneous voltage value from the positive sequence transient component of the voltage and then calculate the identification parameters based on the instantaneous voltage value and the preset steady-state voltage value.

[0027] The fault identification module is used to determine the capacitor fault category based on the identification parameters and parameter thresholds, wherein the capacitor fault category includes thermal breakdown and electrical breakdown.

[0028] Preferably, the fault location module is specifically used for:

[0029] Extract the voltage transient signal from the original operating voltage signal;

[0030] The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

[0031] Preferably, the signal decoupling module is specifically used for:

[0032] The linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space by the preset multi-core SVM model to obtain the mapped linearly separable signal;

[0033] The optimal hyperplane optimization process is performed based on the linearly separable signal in the mapped signal and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0034] Preferably, the parameter calculation module is specifically used for:

[0035] Extract the instantaneous voltage value from the positive-sequence transient component of the voltage;

[0036] The identification parameter is calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value, and the ratio is expressed as:

[0037]

[0038] Where, r U For the identification parameters, U BD U is the instantaneous value of the voltage. FP This is a preset steady-state voltage value.

[0039] A third aspect of this application provides a capacitor fault identification device, the device including a processor and a memory;

[0040] The memory is used to store program code and transmit the program code to the processor;

[0041] The processor is used to execute the capacitor fault identification method described in the first aspect according to the instructions in the program code.

[0042] A fourth aspect of this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code for executing the capacitor fault identification method described in the first aspect.

[0043] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0044] This application provides a capacitor fault identification method, comprising: acquiring the original operating voltage signal during capacitor operation; identifying the faulty phase of capacitor operation based on the original operating voltage signal using a preset wavelet transform method; inputting the original operating voltage signal into a preset multi-core SVM model for signal decoupling to obtain a positive-sequence transient voltage component and a negative-sequence transient voltage component; extracting the instantaneous voltage value from the positive-sequence transient voltage component and calculating identification parameters based on the instantaneous voltage value and a preset steady-state voltage value; and determining the capacitor fault category based on the identification parameters and parameter thresholds, wherein the capacitor fault category includes thermal breakdown and electrical breakdown.

[0045] The capacitor fault identification method provided in this application performs fault location and identification operations based on the original operating voltage signal during capacitor operation. To improve identification reliability, it adopts a two-part identification approach, identifying both the fault phase and the fault category, and uses a pre-set multi-core SVM model that is a trained classification model, which can be applied efficiently in specific scenarios with high signal processing efficiency. Furthermore, the two progressive fault identification methods further ensure the reliability of the identification results. Therefore, this application can solve the technical problems of low efficiency and poor reliability in existing technologies, leading to poor capacitor fault identification performance. Attached Figure Description

[0046] Figure 1 A schematic flowchart illustrating a capacitor fault identification method provided in an embodiment of this application;

[0047] Figure 2 This is a schematic diagram of the structure of a capacitor fault identification device provided in an embodiment of this application;

[0048] Figure 3 A schematic diagram of a capacitor system structure provided for application examples of this application. Detailed Implementation

[0049] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0050] For easier understanding, please refer to Figure 1 An embodiment of a capacitor fault identification method provided in this application includes:

[0051] Step 101: Obtain the original operating voltage signal during the operation of the capacitor.

[0052] Parameters such as current, voltage, and impedance during capacitor operation are crucial for fault identification. Monitoring changes in these parameters helps determine the location and nature of the fault, i.e., the fault category. To accurately acquire these parameters, an RS-485 data receiver can be installed on the capacitor. A data acquisition unit, voltage sensor, current sensor, and TSG2-3kVA voltage regulating transformer are used to collect the capacitor's voltage, current, and impedance parameters. These parameters are uploaded to the data aggregator every 1ms. The collected data can undergo basic preprocessing to facilitate subsequent analysis. In this embodiment, only voltage analysis is performed, i.e., acquiring the raw operating voltage signal.

[0053] Step 102: Identify the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform method.

[0054] Further, step 102 includes:

[0055] Extract the voltage transient signal from the original operating voltage signal;

[0056] The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

[0057] The preset wavelet transform method uses discrete wavelet transform to process signals that are not the original operating voltage signals, but rather the voltage transient signals extracted from the original operating voltage signals. After multi-scale decomposition, wavelet coefficients at different levels can be obtained, and then the specific fault phases (A, B, and C phases) can be determined based on the decomposed signals. The decomposition process based on wavelet transform is expressed as follows:

[0058]

[0059] Where c0(k) are the wavelet coefficients of the original signal, h n (k) represents the wavelet coefficients of the noise signal, and n represents the number of decomposition levels or the order. Furthermore, after eliminating fault singularities, the time of fault occurrence can be determined based on different fault numbers and time sequences.

[0060] Step 103: Input the original operating voltage signal into the preset multi-core SVM model to perform signal decoupling operation, and obtain the positive sequence transient component and the negative sequence transient component of voltage.

[0061] Further, step 103 includes:

[0062] By using a pre-set multi-core SVM model, the linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space to obtain the mapped linearly separable signal;

[0063] The optimal hyperplane optimization process is performed based on the linearly separable signal mapped and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0064] A pre-built multi-core SVM model can perform hyperplane optimization on linearly separable samples to achieve sample classification. In this embodiment, the samples are the original operating voltage signals, which contain linearly inseparable sample signals. It is necessary to first map the linearly inseparable signals to a high-dimensional space to approximate them as linearly separable samples. Then, together with the original linearly separable signals, a hyperplane optimization operation is performed to complete the decoupling of the signals and obtain the positive-sequence transient components and negative-sequence transient components of the voltage.

[0065] If x is adopted n Let y represent the feature vector of the nth sample. n The table shows the class labels for the nth sample, α. n For Lagrange multipliers, the hyperplane formula can be expressed as:

[0066] G(X n )=Z·x n +b

[0067] Among them, Z * and b * Let be the optimal hyperplane normal vector and offset, respectively. The optimization formula is:

[0068]

[0069] y n ·z·x n +y n ·b≥1

[0070] A pre-built multi-kernel SVM model can address the issue of discrepancies in the distance between samples mapped to different dimensional spaces, thus improving signal classification accuracy. The linear weighted sum formula for multiple single-kernel functions is:

[0071]

[0072] Where, N K K1 represents the number of kernel functions, where K1 is the first kernel function, w1 is the weight of the first kernel function, and so on.

[0073] Step 104: After extracting the instantaneous voltage value from the positive sequence transient component of the voltage, calculate the identification parameters based on the instantaneous voltage value and the preset steady-state voltage value.

[0074] Further, step 104 includes:

[0075] Extract the instantaneous voltage value from the positive sequence transient component of voltage;

[0076] The identification parameters are calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value. The ratio is expressed as:

[0077]

[0078] Where, r U To identify parameters, U BD U is the instantaneous voltage value. FP This is a preset steady-state voltage value.

[0079] Since the network containing the negative-sequence transient voltage component has no power source and the initial values ​​of the inductor and capacitor are 0, there is no negative-sequence transient voltage component. The identification parameter calculation is only for the positive-sequence transient voltage component; the instantaneous voltage value is extracted from it, and the ratio of the instantaneous voltage value to the preset steady-state voltage value is used as the identification parameter.

[0080] Step 105: Determine the capacitor fault type based on the identification parameters and parameter thresholds. The capacitor fault types include thermal breakdown and electrical breakdown.

[0081] In this embodiment, the parameter threshold is 1, and the identification parameter r U If the value is less than 1, it indicates that the instantaneous voltage value U BD Less than the preset steady-state voltage value U FP If it is determined to be thermal breakdown; if the identification parameter r U If the value is greater than 1, it indicates that the instantaneous voltage value U BD Greater than the preset steady-state voltage value U FP It was determined to be an electrical breakdown.

[0082] When this embodiment is applied to a specific scenario, the system deployment for capacitor operation is as follows: Figure 3 This includes a voltage transformer TV1, a circuit breaker, a reactor, a grounding switch, a discharge coil, and a capacitor bank. The solution used in this embodiment for capacitor operation fault identification is more efficient and reliable, and has practical operational significance.

[0083] The capacitor fault identification method provided in this application performs fault location and identification operations based on the original operating voltage signal during capacitor operation. To improve identification reliability, it adopts a two-part identification approach, identifying both the fault phase and the fault category, and uses a pre-set multi-core SVM model that is a trained classification model, which can be applied efficiently in specific scenarios with high signal processing efficiency. Furthermore, the two progressive fault identification methods further ensure the reliability of the identification results. Therefore, this application embodiment can solve the technical problems of low efficiency and poor reliability in existing technologies, leading to poor capacitor fault identification performance.

[0084] For easier understanding, please refer to Figure 2This application provides an embodiment of a capacitor fault identification device, comprising:

[0085] The data acquisition module 201 is used to acquire the original operating voltage signal during the operation of the capacitor;

[0086] Fault location module 202 is used to identify the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform method;

[0087] The signal decoupling module 203 is used to input the original operating voltage signal into a preset multi-core SVM model for signal decoupling operation to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0088] The parameter calculation module 204 is used to calculate identification parameters based on the instantaneous voltage value and the preset steady-state voltage value after extracting the instantaneous voltage value from the positive sequence transient component of the voltage.

[0089] The fault identification module 205 is used to determine the capacitor fault type based on the identification parameters and parameter thresholds. The capacitor fault types include thermal breakdown and electrical breakdown.

[0090] Furthermore, the fault location module 202 is specifically used for:

[0091] Extract the voltage transient signal from the original operating voltage signal;

[0092] The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

[0093] Furthermore, the signal decoupling module 203 is specifically used for:

[0094] By using a pre-set multi-core SVM model, the linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space to obtain the mapped linearly separable signal;

[0095] The optimal hyperplane optimization process is performed based on the linearly separable signal mapped and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

[0096] Furthermore, the parameter calculation module 204 is specifically used for:

[0097] Extract the instantaneous voltage value from the positive sequence transient component of voltage;

[0098] The identification parameters are calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value. The ratio is expressed as:

[0099]

[0100] Where, r U To identify parameters, UBD U is the instantaneous voltage value. FP This is a preset steady-state voltage value.

[0101] This application also provides a capacitor fault identification device, the device including a processor and a memory;

[0102] The memory is used to store program code and transfer the program code to the processor;

[0103] The processor is used to execute the capacitor fault identification method in the above method embodiments according to the instructions in the program code.

[0104] This application also provides a computer-readable storage medium for storing program code for executing the capacitor fault identification method in the above method embodiments.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0106] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0108] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of this application through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0109] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A capacitor fault identification method, characterized in that, include: Acquire the original operating voltage signal of the capacitor during operation; The fault phase of the capacitor operation is identified based on the original operating voltage signal using a preset wavelet transform method. The original operating voltage signal is input into a preset multi-core SVM model for signal decoupling to obtain the positive-sequence transient component and the negative-sequence transient component of voltage. After extracting the instantaneous voltage value from the positive sequence transient voltage component, identification parameters are calculated based on the instantaneous voltage value and the preset steady-state voltage value. The capacitor fault category is determined based on the identification parameters and parameter thresholds, and the capacitor fault category includes thermal breakdown and electrical breakdown.

2. The capacitor fault identification method according to claim 1, characterized in that, The method of identifying the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform includes: Extract the voltage transient signal from the original operating voltage signal; The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

3. The capacitor fault identification method according to claim 1, characterized in that, The step of inputting the original operating voltage signal into a preset multi-core SVM model for signal decoupling to obtain positive-sequence transient voltage components and negative-sequence transient voltage components includes: The linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space by the preset multi-core SVM model to obtain the mapped linearly separable signal; The optimal hyperplane optimization process is performed based on the linearly separable signal in the mapped signal and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

4. The capacitor fault identification method according to claim 1, characterized in that, After extracting the instantaneous voltage value from the positive-sequence transient component of the voltage, the identification parameters are calculated based on the instantaneous voltage value and a preset steady-state voltage value, including: Extract the instantaneous voltage value from the positive-sequence transient component of the voltage; The identification parameter is calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value, and the ratio is expressed as: Where, r U For the identification parameters, U BD U is the instantaneous value of the voltage. FP This is a preset steady-state voltage value.

5. A capacitor fault identification device, characterized in that, include: The data acquisition module is used to acquire the original operating voltage signal of the capacitor during operation. The fault location module is used to identify the faulty phase of the capacitor operation based on the original operating voltage signal using a preset wavelet transform method. The signal decoupling module is used to input the original operating voltage signal into a preset multi-core SVM model for signal decoupling operation to obtain the positive-sequence transient component and the negative-sequence transient component of voltage; The parameter calculation module is used to extract the instantaneous voltage value from the positive sequence transient component of the voltage and then calculate the identification parameters based on the instantaneous voltage value and the preset steady-state voltage value. The fault identification module is used to determine the capacitor fault category based on the identification parameters and parameter thresholds, wherein the capacitor fault category includes thermal breakdown and electrical breakdown.

6. The capacitor fault identification device according to claim 5, characterized in that, The fault location module is specifically used for: Extract the voltage transient signal from the original operating voltage signal; The fault phase of capacitor operation is identified based on the voltage transient signal using a preset wavelet transform method.

7. The capacitor fault identification device according to claim 5, characterized in that, The signal decoupling module is specifically used for: The linearly inseparable signal in the original operating voltage signal is mapped to a high-dimensional space by the preset multi-core SVM model to obtain the mapped linearly separable signal; The optimal hyperplane optimization process is performed based on the linearly separable signal in the mapped signal and the linearly separable signal in the original operating voltage signal, and the signal decoupling operation is completed to obtain the positive-sequence transient component and the negative-sequence transient component of voltage.

8. The capacitor fault identification device according to claim 5, characterized in that, The parameter calculation module is specifically used for: Extract the instantaneous voltage value from the positive-sequence transient component of the voltage; The identification parameter is calculated by the ratio between the instantaneous voltage value and the preset steady-state voltage value, and the ratio is expressed as: Where, r U For the identification parameters, U BD U is the instantaneous value of the voltage. FP This is a preset steady-state voltage value.

9. A capacitor fault identification device, characterized in that, The device includes a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the capacitor fault identification method according to any one of claims 1-4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the capacitor fault identification method according to any one of claims 1-4.

Images