GIL equipment fault detection method, system and equipment based on voiceprint dynamic coupling model, and storage medium

Abstract

The invention discloses a GIL equipment fault detection method, system and equipment based on a voiceprint dynamic coupling model and a storage medium, and relates to the technical field of power system equipment monitoring and operation and maintaining.The method comprises the steps that sound signals in GIL equipment are collected in real time, feature parameters are extracted, and feature vectors are obtained; establishing a Gaussian mixture model by using the normal working condition data, and training the Gaussian mixture model based on the feature vector to obtain an anomaly detection model; carrying out feature parameter extraction on a real-time signal to be detected, and calculating an estimated value and a residual error of an extracted feature on the anomaly detection model; and based on the calculated estimated value and the residual error, calculating an abnormal score and outputting corresponding early warning information and a fault positioning result. According to the method, the whole process from data acquisition to fault diagnosis is optimized, the accuracy, timeliness and intelligent level of GIL equipment voiceprint monitoring are effectively improved, and a powerful guarantee is provided for safe and stable operation of equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of power system equipment monitoring and operation and maintenance, and in particular to a GIL equipment fault detection method, system, equipment and storage medium based on a voiceprint dynamic coupling model. Background Art

[0002] Gas-insulated metal-enclosed transmission lines (GILs) require complex manufacturing and installation processes, requiring meticulous maintenance procedures. Even the slightest negligence can lead to quality issues. Partial discharge (PD) is a common GIL failure. While rare, once it occurs, the consequences can be severe, impacting both the equipment itself and surrounding equipment, ultimately impacting the overall safe operation of the power network.

[0003] Existing GIL status monitoring devices primarily employ pressure monitoring and ultra-high frequency partial discharge (PD) signal monitoring. These devices offer limited functionality, are installed in limited locations, and are unable to fully monitor the operating status of the GIL system in real time. When gas-insulated transmission lines are located in high-drop shafts, daily equipment operation is difficult to monitor. Furthermore, after a fault, the fault can only be located by monitoring changes in gas composition in each chamber, which is time-consuming and labor-intensive. There is also a lack of real-time monitoring for potential temperature rises, abnormal PD noise, and changes in SF6 meter readings. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing GIL system monitoring device has a single function, few installation locations, cannot monitor the operating status in all directions, has a large inspection workload and poses safety risks, and lacks real-time detection of various physical indicators and unified analysis, modeling and early warning means.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a GIL equipment fault detection method based on a voiceprint dynamic coupling model, comprising:

[0008] Collect the sound signals inside the GIL device in real time, extract the characteristic parameters, and obtain the characteristic vector;

[0009] Use normal operating data to establish a Gaussian mixture model, train the Gaussian mixture model based on the feature vector, and obtain an anomaly detection model;

[0010] Extract feature parameters of the real-time signal to be detected, and calculate the estimated value and residual of the extracted features on the anomaly detection model;

[0011] Based on the calculated estimated value and residual, the anomaly score is calculated and the corresponding warning information and fault location results are output.

[0012] As a preferred solution for GIL equipment fault detection method based on the voiceprint dynamic coupling model,

[0013] The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector include:

[0014] The collected sound signal is decomposed into effective signal and noise components, and a wavelet basis is selected to perform wavelet decomposition on the sound signal to obtain a series of wavelet coefficients.

[0015] As a preferred solution for GIL equipment fault detection method based on the voiceprint dynamic coupling model,

[0016] The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes:

[0017] Different processing is performed based on the relationship between the absolute value of the wavelet coefficient and the preset threshold: when the absolute value of the wavelet coefficient is greater than or equal to the threshold, it is transformed with a specific function; when it is less than the threshold, it is directly set to zero; the preset threshold is calculated based on the standard deviation of the noise and the signal length.

[0018] The beneficial effect of this preferred technical solution is that this wavelet coefficient processing method based on a preset threshold can effectively remove noise interference from sound signals. The threshold is calculated based on the standard deviation of the noise and the signal length, making the threshold setting more scientific and reasonable. While retaining the effective signal characteristics, it also minimizes the impact of noise on subsequent analysis.

[0019] As a preferred solution for GIL equipment fault detection method based on the voiceprint dynamic coupling model,

[0020] The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes:

[0021] The transform coefficients determined to be noise after processing are discarded, and an inverse wavelet transform is performed to obtain the signal after noise removal;

[0022] The denoised sound signal is pre-emphasized and divided into frames. The frame length is between 20ms and 30ms, and the overlap time between different frames is 10ms.

[0023] The beneficial effects of the preferred technical solutions are: discarding the transform coefficients corresponding to the noise and performing inverse wavelet transform can obtain the pure effective signal. The pre-emphasis processing can enhance the energy of the high frequency part of the signal and highlight the characteristics of the sound signal. The frame division and the setting of the overlap time can capture the local characteristic changes of the signal and ensure the continuity of the information between the frames when analyzing the signal, thereby improving the accuracy of feature extraction.

[0024] As a preferred scheme of the GIL equipment fault detection method based on the voiceprint dynamic coupling model, wherein:

[0025] The real-time acquisition of the sound signal inside the GIL equipment and the extraction of the characteristic parameters to obtain the characteristic vector further include:

[0026] The windowing operation is performed on the sound signal after the frame division, and the window function is used to perform the weighting processing on each frame signal.

[0027] The windowed sound signal is converted from the time domain to the frequency domain, and the amplitude of each point in the frequency domain is calculated to obtain the amplitude spectrum of the sound signal.

[0028] As a preferred scheme of the GIL equipment fault detection method based on the voiceprint dynamic coupling model, wherein:

[0029] The real-time acquisition of the sound signal inside the GIL equipment and the extraction of the characteristic parameters to obtain the characteristic vector further include:

[0030] The triangular band-pass filter bank is used to convert the sound amplitude spectrum, the amplitude spectrum is multiplied by the triangular filter bank to obtain the smoothed sound amplitude spectrum, and the discrete cosine transform is performed on the signal after the frequency spectrum smoothing processing to extract the mel frequency cepstrum coefficient feature vector.

[0031] As a preferred scheme of the GIL equipment fault detection method based on the voiceprint dynamic coupling model, wherein:

[0032] The use of normal working condition data to establish a Gaussian mixture model, and the training of the Gaussian mixture model based on the characteristic vector to obtain an anomaly detection model includes:

[0033] The characteristic vector extracted from the related data under the normal running state of the equipment is used as the input data of the Gaussian mixture model, the expectation maximization algorithm is used to calculate and optimize the parameters of the Gaussian mixture model, the model training is completed, and the anomaly detection model is obtained.

[0034] The beneficial effects of the preferred technical solutions are that the Gaussian mixture model is trained by using the feature vector in the normal running state of the equipment, so that the feature distribution of the equipment in the normal running state can be accurately described, the expectation maximization algorithm can effectively calculate and optimize the model parameters, the model can better fit the normal data, and the accuracy and reliability of the abnormality detection are improved.

[0035] In a second aspect, the present application provides a GIL equipment fault detection system based on a voiceprint dynamic coupling model, comprising:

[0036] A feature vector extraction module is configured to collect sound signals inside the GIL equipment in real time, extract feature parameters, and obtain a feature vector.

[0037] An abnormality detection model establishment module is configured to establish a Gaussian mixture model using normal working condition data, train the Gaussian mixture model based on the feature vector, and obtain an abnormality detection model.

[0038] A detection parameter calculation module is configured to extract feature parameters from real-time signals to be detected, and calculate the estimated value and residual error of the extracted features in the abnormality detection model.

[0039] A fault detection module is configured to calculate an abnormality score based on the calculated estimated value and residual error, and output corresponding warning information and fault positioning results.

[0040] In a third aspect, the present application provides an electronic device, comprising:

[0041] A memory and a processor.

[0042] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, so as to implement the steps of a GIL equipment fault detection method based on a voiceprint dynamic coupling model.

[0043] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which are executed by a processor to implement a GIL equipment fault detection method based on a voiceprint dynamic coupling model.

[0044] The improved MFCC feature extraction method and Mel filter bank processing provided by the application can accurately capture voiceprint features, time-frequency domain fusion analysis comprehensively analyzes time and frequency information, enhances the detection capability of early weak faults, and significantly improves the fault recognition rate; the integrated monitoring model intelligently learns the device operation mode through machine learning and deep learning algorithms, and combines a dynamic coupling model to effectively distinguish environmental noise and electrical fault voiceprints and improve the abnormal source recognition accuracy; can accurately identify abnormal patterns and fault signs in real time, issue early warnings, and alarm information is classified according to levels and is accurate to components, so that operation and maintenance personnel can quickly locate faults, reduce fault losses, and improve processing efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can be obtained without creative labor under the premise of the drawings.

[0046] Figure 1 is the overall flowchart of the GIL device fault detection method based on the voiceprint dynamic coupling model provided by the application. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned purposes, features and advantages of the application more apparent and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor should be within the protection scope of the application.

[0048] Embodiment 1, refer to Figure 1 The first embodiment of the application provides a GIL device fault detection method based on a voiceprint dynamic coupling model, which comprises:

[0049] S1: Real-time acquisition of sound signals inside the GIL device, feature parameter extraction, and obtaining of a feature vector;

[0050] S2: Establishing a Gaussian mixture model using normal operating condition data, training the Gaussian mixture model based on the feature vector, and obtaining an anomaly detection model;

[0051] S3: Feature parameter extraction of the real-time signal to be detected, calculation of the estimated value and residual of the extracted features on the anomaly detection model;

[0052] S4: Based on the calculated estimated value and residual, calculate the abnormal score and output the corresponding early warning information and fault positioning result.

[0053] It should be noted that through steps S1-S4, the embodiment collects the acoustic signals inside the GIL device through high-precision sensors, and then analyzes the changes in the device operating state. This monitoring method can effectively identify abnormal sounds inside the device, such as partial discharge, mechanical vibration, etc., thereby discovering potential fault hazards in a timely manner. The advantage of the voiceprint monitoring technology lies in its non-invasiveness and sensitivity, which can capture subtle features of device state changes without affecting normal operation of the device.

[0054] Embodiment 2, refer to Figure 1 For an embodiment of the present application, a GIL device fault detection method based on a voiceprint dynamic coupling model is provided based on the previous embodiment, comprising:

[0055] In this embodiment, the sound signals inside the GIL device are collected in real time in step S1, the feature parameters are extracted, and the feature vectors are obtained, including:

[0056] High-precision audio sensors are selected to collect the sound signals inside the GIL device. The audio sensor not only has high precision and high sensitivity, but also can work stably in harsh environments, thereby ensuring the reliability of data collection.

[0057] For the collected sound signals inside the GIL device, wavelet denoising is used for denoising. The signal contains two parts, namely the effective signal and the noise, which is represented as: ;

[0058] Wherein, represents the sound signal, , is the signal length, is the effective signal component to be retained, is the noise component.

[0059] After selecting a suitable wavelet basis, the signal is wavelet decomposed to obtain a series of wavelet coefficients. After threshold processing of the wavelet coefficients and discarding the transform coefficients of the noise, inverse wavelet transform is performed to obtain the signal after removing the noise.

[0060] Further, the wavelet coefficient threshold processing includes various processing methods such as hard threshold and soft threshold. In order to solve the discontinuous jump caused by threshold processing, an improved threshold processing method is adopted, that is, when the absolute value of the wavelet coefficient is greater than or equal to the threshold, a specific function transformation is performed on it; when it is less than the threshold, it is directly set to zero, which is represented as: ;

[0061] Among them, w represents the wavelet coefficient obtained after wavelet decomposition, is a sign function, which is used to determine the positive or negative value of w and is defined as follows: ;

[0062] Threshold The calculation method is as follows: ;

[0063] in, represents the standard deviation of the noise, Indicates the signal length.

[0064] It should be noted that the signal quality can be improved by combining the above algorithm with adaptive filtering technology.

[0065] For the denoised sound signal, pre-emphasis is performed, and the calculation formula is as follows: ;

[0066] in Represents the sample value of the sound signal at the nth sampling moment after pre-emphasis processing, Represents the sample value of the denoised sound signal at the nth sampling moment, represents the sample value of the denoised sound signal at the n-1th sampling moment, is the pre-emphasis coefficient, The value is between 0.9 and 1.

[0067] The pre-emphasized sound signal is divided into frames. The frame length is between 20ms and 30ms, and the overlap time between different frames is 10ms.

[0068] After framing, spectrum leakage is suppressed by adding sound windowing. A Hamming window is added to the framed sound signal, which is expressed as: ; ;

[0069] in, Represents the value of the windowed sound signal at the nth sampling point, Indicates the value of the framed sound signal at the nth sampling point, Represents the value of the window function at the nth sampling point, n is a discrete time index, indicating the position of the current sampling point in the window function sequence, and the value range of n is from 0 to N-1. Represents the number of sampling points in each frame of sound signal, that is, the number of samples contained in one frame of signal.

[0070] After the windowing operation is completed, the sound is converted from the time domain to the frequency domain through fast Fourier transform and the amplitude spectrum is calculated. That is, the amplitude is calculated for each point in the frequency domain, and then the sound spectrum is converted using a triangular bandpass filter bank.

[0071] Specifically, the calculation formula for the triangular bandpass filter is as follows: ;

[0072] in Represents the filter coefficient of the mth triangular bandpass filter at the kth frequency point, is the filter number, ranging from m=1,2,⋯,M, where M is the total number of filters is the weighting coefficient of the amplitude spectrum after filtering, is the center frequency of the mth Mel bandpass filter.

[0073] The conversion relationship between Mel frequency and physical frequency is as follows: ;

[0074] in, Indicates the function value that converts the physical frequency f into the Mel frequency.

[0075] The center frequency calculation formula is as follows: ; ;

[0076] in is the physical frequency, where and are the lower and upper frequency limits of the filter, is the number of sampling points, is the sampling frequency.

[0077] The smoothed sound amplitude spectrum is obtained by multiplying the amplitude spectrum with the triangular filter bank.

[0078] Perform discrete cosine transform, which is defined as follows: ;

[0079] in It is The logarithmic magnitude of the output of the Mel filter bank, is the number of Mel filters, It is the MFCC (Mel Frequency Cepstral Coefficients) feature vector.

[0080] In this embodiment, the normal operating condition data is used to establish a Gaussian mixture model in step S2, and the Gaussian mixture model is trained based on the feature vector to obtain an abnormality detection model including:

[0081] The Gaussian mixture model (GMM) was established using the normal operating data to obtain the characteristic distribution of the conveyor during normal operation.

[0082] The model is defined as follows: ;

[0083] in, represents the probability density function of the Gaussian mixture model, K is the number of Gaussian components in the Gaussian mixture model, is the weight of each Gaussian distribution, and They are The mean vector and covariance matrix of a Gaussian distribution, represents the i-th Gaussian distribution (normal distribution).

[0084] Collect sound data of GIL's normal operation, calculate MFCC features as GMM input, and use the EM algorithm to calculate the parameters of the GMM model.

[0085] In this embodiment, in step S3, feature parameters are extracted from the real-time signal to be detected, and the estimated value and residual of the extracted feature on the anomaly detection model are calculated, including:

[0086] For the sound sample to be tested, first convert the sound into MFCC features, and then calculate the estimated value on the normal GMM model , the specific calculation formula is as follows: ;

[0087] in, The MFCC feature to be tested is The posterior probability on the Gaussian distribution, the feature residual for: ;

[0088] in, Represents the MFCC features obtained by converting the sound sample to be tested.

[0089] In this embodiment, the calculation of the anomaly score based on the calculated estimated value and residual in step S4 and the output of the corresponding warning information and fault location result include:

[0090] Defining anomaly scores As shown below: ;

[0091] wherein D is the dimension of MFCC features, is a variable that measures the degree of abnormality of the sound sample to be tested.

[0092] In another possible implementation, multiple experiments can be performed on normal operating condition data, and a suitable abnormality threshold T can be determined according to the distribution of the calculated abnormality scores. For example, the abnormality scores of normal samples can be counted, and the threshold can be set to a certain quantile (such as the 95th quantile) of the abnormality scores of the normal samples. When the abnormality score exceeds the threshold, it is considered that the sample is abnormal.

[0093] For example, the calculated abnormality score F is compared with the set abnormality threshold T.

[0094] If F > T, it is determined that the GIL device corresponding to the sound sample to be tested is in an abnormal operating state, and corresponding warning information such as "The GIL device may have a fault, please check in time" is output. The warning information can be sent to relevant personnel through a system interface, a short message, an email, or the like.

[0095] If F ≤ T, it is determined that the GIL device is in a normal operating state, and prompt information such as "The GIL device is in a normal operating state" is output.

[0096] The MFCC features of the abnormal sample are analyzed, it is viewed which feature dimensions have larger residuals, and the correlation between the known fault modes and the MFCC features is combined to preliminarily determine the possible fault type. For example, the abnormality of the MFCC features in certain specific frequency ranges can correspond to partial discharge faults, and the abnormality of other features can be related to mechanical vibration faults. According to the analysis result, specific fault positioning information such as "The GIL device [specific position] can have [fault type] fault" is output, thereby providing clear maintenance guidance for device maintenance personnel.

[0097] Embodiment 3, the above is a schematic scheme of the GIL device fault detection method based on the voiceprint dynamic coupling model of the present embodiment. It should be noted that the technical scheme of the GIL device fault detection system based on the voiceprint dynamic coupling model belongs to the same concept as the technical scheme of the GIL device fault detection method based on the voiceprint dynamic coupling model described above. The technical scheme of the GIL device fault detection system based on the voiceprint dynamic coupling model of the present embodiment, which is not described in detail, can be referred to the description of the technical scheme of the GIL device fault detection method based on the voiceprint dynamic coupling model.

[0098] The present embodiment also provides a GIL device fault detection system based on a voiceprint dynamic coupling model, comprising:

[0099] The feature vector extraction module is used to collect the sound signal inside the GIL device in real time, extract the feature parameters, and obtain the feature vector;

[0100] An anomaly detection model building module is used to build a Gaussian mixture model using normal operating condition data, and train the Gaussian mixture model based on the feature vector to obtain an anomaly detection model;

[0101] The detection parameter calculation module is used to extract feature parameters of the real-time signal to be detected and calculate the estimated value and residual of the extracted features on the anomaly detection model;

[0102] The fault detection module is used to calculate the anomaly score based on the calculated estimated value and residual and output the corresponding warning information and fault location results.

[0103] This embodiment further provides an electronic device applicable to the GIL device fault detection method based on the voiceprint dynamic coupling model, including:

[0104] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the GIL equipment fault detection method based on the voiceprint dynamic coupling model proposed in the above embodiment.

[0105] This embodiment further provides a storage medium storing a computer program, which, when executed by a processor, implements the GIL device fault detection method based on the voiceprint dynamic coupling model proposed in the above embodiment.

[0106] The storage medium proposed in this embodiment and the GIL device fault detection method based on the voiceprint dynamic coupling model proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A GIL equipment fault detection method based on a voiceprint dynamic coupling model, characterized in that: include: Collect the sound signals inside the GIL device in real time, extract the characteristic parameters, and obtain the characteristic vector; Use normal operating data to establish a Gaussian mixture model, train the Gaussian mixture model based on the feature vector, and obtain an anomaly detection model; Extract feature parameters of the real-time signal to be detected, and calculate the estimated value and residual of the extracted features on the anomaly detection model; Based on the calculated estimated value and residual, the anomaly score is calculated and the corresponding warning information and fault location results are output.

2. A GIL equipment fault detection method based on a voiceprint dynamic coupling model according to claim 1, characterized in that: The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector include: The collected sound signal is decomposed into effective signal and noise components, and a wavelet basis is selected to perform wavelet decomposition on the sound signal to obtain a series of wavelet coefficients.

3. A GIL equipment fault detection method based on a voiceprint dynamic coupling model as claimed in claim 2, characterized in that: The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes: Different processing is performed based on the relationship between the absolute value of the wavelet coefficient and the preset threshold: when the absolute value of the wavelet coefficient is greater than or equal to the threshold, it is transformed with a specific function; when it is less than the threshold, it is directly set to zero; the preset threshold is calculated based on the standard deviation of the noise and the signal length.

4. A GIL equipment fault detection method based on a voiceprint dynamic coupling model as claimed in claim 3, characterized in that: The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes: The transform coefficients determined to be noise after processing are discarded, and an inverse wavelet transform is performed to obtain the signal after noise removal; The denoised sound signal is pre-emphasized and divided into frames. The frame length is between 20ms and 30ms, and the overlap time between different frames is 10ms.

5. The GIL equipment fault detection method based on the voiceprint dynamic coupling model according to claim 4 is characterized in that: The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes: The sound signal after framing is windowed and each frame signal is weighted by the window function; The windowed sound signal is converted from the time domain to the frequency domain, and the amplitude of each point in the frequency domain is calculated to obtain the amplitude spectrum of the sound signal.

6. A GIL equipment fault detection method based on a voiceprint dynamic coupling model as claimed in claim 5, characterized in that: The real-time acquisition of the sound signal inside the GIL device and the extraction of characteristic parameters to obtain the characteristic vector further includes: The sound amplitude spectrum is transformed using a triangular bandpass filter bank, and the amplitude spectrum is multiplied by the triangular filter bank to obtain a smoothed sound amplitude spectrum; the signal after spectrum smoothing is subjected to discrete cosine transform to extract the Mel-frequency cepstral coefficient eigenvector.

7. A GIL equipment fault detection method based on a voiceprint dynamic coupling model as claimed in claim 6, characterized in that: The Gaussian mixture model is established using normal operating data, and the Gaussian mixture model is trained based on the feature vector to obtain the abnormality detection model, including: The feature vectors extracted from the relevant data under normal equipment operation are used as the input data of the Gaussian mixture model. The expectation maximization algorithm is used to calculate and optimize the parameters of the Gaussian mixture model to complete the model training and obtain the anomaly detection model.

8. A GIL equipment fault detection system based on a voiceprint dynamic coupling model, applying the method according to any one of claims 1 to 7, characterized in that: include: The feature vector extraction module is used to collect the sound signal inside the GIL device in real time, extract the feature parameters, and obtain the feature vector; An anomaly detection model building module is used to build a Gaussian mixture model using normal operating condition data, and train the Gaussian mixture model based on the feature vector to obtain an anomaly detection model; The detection parameter calculation module is used to extract feature parameters of the real-time signal to be detected and calculate the estimated value and residual of the extracted features on the anomaly detection model; The fault detection module is used to calculate the anomaly score based on the calculated estimated value and residual and output the corresponding warning information and fault location results.

9. An electronic device, characterized in that: include: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that It stores computer-executable instructions, which implement the steps of the method according to any one of claims 1 to 7 when executed by a processor.

Images