Intelligent monitoring control method and system for state of high-voltage power distribution cabinet

Abstract

The invention discloses an intelligent monitoring control method and system for the state of a high-voltage power distribution cabinet, and relates to the technical field of power equipment control. The method comprises the following steps: acquiring a partial discharge signal of target equipment in real time, and denoising the partial discharge signal to obtain a corrected signal; the partial discharge signal comprises a transient ground voltage signal and an ultrasonic signal; taking the correction signal as the input of a pre-trained state evaluation model to obtain a state type; and making a control decision according to the state type. By eliminating the interference of the noise on the partial discharge signal, the potential fault information of the electrical equipment can be more accurately captured and identified, so that an accurate control decision is made, the fault expansion is avoided, and the safe operation of a power system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment control, and in particular to a method and system for intelligently monitoring and controlling the state of a high-voltage power distribution cabinet. Background Art

[0002] In the high-voltage power distribution system, the distribution cabinet, as a key power equipment, undertakes the important task of power transmission and distribution. Its stable operation is directly related to the safety and reliability of the power system. Insulation is an indispensable part of high-voltage electrical equipment, and its slight damage will lead to the formation of potential defects. As the insulation gradually deteriorates, the defects will continue to expand until the equipment fails, seriously affecting the normal operation of the power system.

[0003] Partial discharge (PD) is considered to be the root cause of insulation breakdown. Since the PD signals from different types of insulation defects are different, the cause of PD can be inferred from the PD signal, that is, the type of defect in the electrical equipment can be detected. With the development of intelligent technology, PD signals have received more and more attention as an important precursor to faults. The monitoring of partial discharge signals can timely capture potential electrical fault information in the distribution cabinet, providing an important basis for fault warning. However, the PD signals collected on site are always coupled with noise or interference, such as periodic narrowband interference and white noise. Severe noise can drown out the PD signal, weaken its expression ability, and lead to inaccurate state recognition, which can cause the protection device to malfunction or refuse to operate. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of misoperation or refusal to operate of the protection device mentioned in the above background technology, and to propose a method and system for intelligent monitoring and control of the status of a high-voltage distribution cabinet.

[0005] A first aspect of the present invention provides a method for intelligent monitoring and control of a high-voltage power distribution cabinet state, the method comprising: Collecting partial discharge signals of target equipment in real time; the partial discharge signals include transient voltage signals and ultrasonic signals; Performing denoising processing on the partial discharge signal to obtain a corrected signal; Using the correction signal as an input of a pre-trained state evaluation model to obtain a state type; A control decision is made according to the state type; the control decision includes load adjustment, operation mode adjustment and fault isolation.

[0006] Optionally, the denoising the partial discharge signal to obtain a corrected signal includes: Performing variational modal decomposition on a first target signal to obtain a plurality of modal components; the first target signal is any one of a transient voltage signal and an ultrasonic signal; Calculate the kurtosis of each modal component, include the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and include the modal components with kurtosis values ​​less than the preset threshold into the second component set; The first component set is filtered by using a wavelet threshold denoising method, and the second component set is inversely suppressed by using a triple standard deviation criterion to obtain a denoised modal component set; Signal reconstruction is performed according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

[0007] Optionally, performing variational modal decomposition on the first target signal to obtain multiple modal components includes: Performing empirical mode decomposition on the first target signal to determine the number of decomposition layers K as the number of layers of variational mode decomposition; The weighted fusion of envelope entropy and reconstruction error is used as the objective function, and the penalty factor α of the variational mode decomposition algorithm is optimized with the goal of minimizing the objective function to obtain the penalty factor α; According to the decomposition layer number K and the penalty factor α, variational modal decomposition is performed on the first target signal to obtain multiple modal components.

[0008] Optionally, filtering the first component set by using a wavelet threshold denoising method includes: Performing wavelet transformation on the target modal component to obtain wavelet coefficients; the wavelet coefficients include approximate coefficients and detail coefficients; the target modal component is any modal component in the first component set; The improved threshold function is used to perform threshold processing on the detail coefficients; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level scale; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant; The approximate coefficients and the detail coefficients after threshold processing are subjected to inverse wavelet transform to obtain denoised modal components.

[0009] Optionally, the state evaluation model consists of a first feature extraction branch, a second feature extraction branch, an attention module and a classifier; wherein: The first feature extraction branch is used to extract features of the correction signal of the transient ground voltage signal using a gated cycle unit to obtain a first feature; The second feature extraction branch is used to extract features of the corrected signal of the ultrasonic signal using a gated cycle unit to obtain a second feature; The attention module is used to fuse and enhance the joint features of the first feature and the second feature by using a multi-head self-attention mechanism to obtain a third feature; The classifier is used to process the third feature using a fully connected network and output a state type.

[0010] A second aspect of the present invention provides a high-voltage distribution cabinet state intelligent monitoring and control system, the system comprising: A sensor monitoring module, used for collecting partial discharge signals of target equipment in real time; the partial discharge signals include transient ground voltage signals and ultrasonic signals; A signal denoising module, used for denoising the partial discharge signal to obtain a corrected signal; An abnormality identification module, used for taking the correction signal as an input of a pre-trained state evaluation model to obtain a state type; The action generation module is used to make control decisions according to the state type; the control decisions include load adjustment, operation mode adjustment and fault isolation.

[0011] Optionally, the signal denoising module includes: A signal decomposition module, used for performing variational modal decomposition on a first target signal to obtain a plurality of modal components; the first target signal is any one of a transient voltage signal and an ultrasonic signal; A dominant classification module, used for calculating the kurtosis of each modal component, including the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and including the modal components with kurtosis values ​​less than the preset threshold into the second component set; An item-by-item denoising module, configured to filter the first component set by using a wavelet threshold denoising method, and reversely suppress the second component set by using a triple standard deviation criterion, so as to obtain a denoised modal component set; The signal reconstruction module is used to reconstruct the signal according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

[0012] Optionally, the signal decomposition module includes: A layer number determination module, used for performing empirical mode decomposition on the first target signal to determine the decomposition layer number K as the layer number of variational mode decomposition; A penalty factor determination module is used to optimize the penalty factor α of the variational mode decomposition algorithm by adopting a weighted fusion of envelope entropy and reconstruction error as an objective function and minimizing the objective function to obtain the penalty factor α; The decomposition execution module is used to perform variational modal decomposition on the first target signal according to the decomposition layer number K and the penalty factor α to obtain multiple modal components.

[0013] Optionally, the item-by-item denoising module includes: A wavelet transform module is used to perform wavelet transform on the target modal component to obtain wavelet coefficients; the wavelet coefficients include approximate coefficients and detail coefficients; the target modal component is any modal component in the first component set; The threshold processing module is used to perform threshold processing on the detail coefficients by using an improved threshold function; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant; The inverse wavelet transform module is used to perform inverse wavelet transform on the approximate coefficients and detail coefficients after threshold processing to obtain denoised modal components.

[0014] Optionally, the state evaluation model consists of a first feature extraction branch, a second feature extraction branch, an attention module and a classifier; wherein: The first feature extraction branch is used to extract features of the correction signal of the transient ground voltage signal using a gated cycle unit to obtain a first feature; The second feature extraction branch is used to extract features of the corrected signal of the ultrasonic signal using a gated cycle unit to obtain a second feature; The attention module is used to fuse and enhance the joint features of the first feature and the second feature by using a multi-head self-attention mechanism to obtain a third feature; The classifier is used to process the third feature using a fully connected network and output a state type.

[0015] Beneficial effects of the present invention: The present invention proposes a method for intelligent monitoring and control of the state of a high-voltage power distribution cabinet, the method comprising: real-time acquisition of partial discharge signals of target equipment; the partial discharge signals include transient ground voltage signals and ultrasonic signals; De-noising the partial discharge signal to obtain a corrected signal; The correction signal is used as the input of the pre-trained state evaluation model to obtain the state type; Based on the state type, control decisions are made; control decisions include load adjustment, operation mode adjustment, and fault isolation.

[0016] By collecting partial discharge signals in real time and performing denoising processing to eliminate the interference of noise on partial discharge signals, the potential fault information of electrical equipment can be captured and identified more accurately, thereby making accurate control decisions, avoiding the expansion of faults, and ensuring the safe operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a method for intelligent monitoring and control of the state of a high-voltage power distribution cabinet is provided for an embodiment of the present invention; Figure 2 A structural schematic diagram of a state evaluation model is provided for an embodiment of the present invention; Figure 3 An architecture diagram of an intelligent monitoring and control system for the status of a high-voltage power distribution cabinet is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The embodiment of the present invention provides a method for intelligent monitoring and control of the state of a high-voltage power distribution cabinet. Figure 1 , Figure 1 A flowchart of a method for intelligent monitoring and control of the state of a high-voltage power distribution cabinet provided by an embodiment of the present invention. The method comprises the following steps: S101, collecting partial discharge signals of target devices in real time.

[0020] S102, performing denoising processing on the partial discharge signal to obtain a corrected signal.

[0021] S103, using the correction signal as the input of the pre-trained state evaluation model to obtain the state type.

[0022] S104, making a control decision according to the state type.

[0023] The partial discharge signal includes a transient earth voltage signal TEV and an ultrasonic signal US; and the control decision includes load adjustment, operation mode adjustment and fault isolation.

[0024] An intelligent monitoring and control method for the status of a high-voltage distribution cabinet provided in an embodiment of the present invention can more accurately capture and identify potential fault information of electrical equipment by collecting partial discharge signals in real time and performing denoising processing to eliminate the interference of noise on the partial discharge signals, thereby making accurate control decisions, avoiding the expansion of faults, and ensuring the safe operation of the power system.

[0025] In one embodiment, step S102 includes: Step 1: Perform variational modal decomposition on the first target signal to obtain multiple modal components.

[0026] Step 2: Calculate the kurtosis of each modal component, include the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and include the modal components with kurtosis values ​​not greater than the preset threshold into the second component set.

[0027] Step three, use the wavelet threshold denoising method to filter the first component set, use the triple standard deviation criterion to reversely suppress the second component set, and obtain the denoised modal component set.

[0028] Step 4: Reconstruct the signal according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

[0029] The first target signal is any one of a transient voltage signal and an ultrasonic signal.

[0030] In one embodiment, variational modal decomposition is performed on the first target signal to obtain multiple modal components including: Through the particle swarm optimization algorithm or the sparrow search algorithm, the decomposition layer number K and the penalty factor α are jointly optimized to obtain the best combination, and the first target signal is subjected to variational mode decomposition according to the best combination. Specifically, in various optimization algorithms, the fitness function can adopt the weighted fusion of envelope entropy and reconstruction error: .in, is the fitness function; H is the normalized envelope entropy; E is the normalized reconstruction error; and is the weight coefficient, .

[0031] In one implementation, considering the computational efficiency of real-time monitoring, the first target signal can be first subjected to empirical mode decomposition to determine the number of decomposition layers K as the number of layers of variational mode decomposition. After the number of layers is determined, the penalty factor α of the variational mode decomposition algorithm is optimized with the goal of minimizing the above-mentioned fitness function to obtain the penalty factor α. Finally, according to the number of decomposition layers K and the penalty factor α, the first target signal is subjected to variational mode decomposition to obtain multiple modal components. Empirical mode decomposition (EMD) is an adaptive signal processing method that can automatically select the number of decomposition layers according to the characteristics of the signal without presetting. Determining the number of decomposition layers by EMD can effectively avoid the problem of over-decomposition caused by too many layers or under-decomposition caused by too few layers, so that the subsequent variational mode decomposition (VMD) algorithm can better capture the key features of the signal.

[0032] In one embodiment, the preset threshold can be set to 3. The kurtosis of the normal distribution is about 3. The PD signal interval deviates significantly from the normal distribution, and its kurtosis value is much greater than 3. The white noise and narrowband interference signal intervals obey the normal distribution, and their kurtosis values ​​are less than or equal to 3, so 3 is used as the dividing line, and the components with kurtosis values ​​greater than 3 are regarded as modal components dominated by partial discharge signals, and the components not greater than 3 are regarded as modal components dominated by noise. The two modal components are included in different sets and filtered using different denoising methods. Specifically, for the first component set, that is, the modal components dominated by partial discharge signals, the wavelet threshold denoising method is used for processing, which can effectively extract the partial discharge characteristic signals in the components. For the second component set, that is, the modal components dominated by noise signals, the three times standard deviation criterion is used for reverse suppression, which can effectively remove the noise characteristic signals in the components. This classification processing method can retain the partial discharge characteristics while effectively removing noise, thereby improving the purity and feature fidelity of the signal.

[0033] In one embodiment, filtering the first component set using a wavelet threshold denoising method includes: Step 1: Perform wavelet transform on the target modal component to obtain wavelet coefficients; the wavelet coefficients include approximate coefficients and detail coefficients.

[0034] Step 2: Use the improved threshold function to perform threshold processing on the detail coefficients; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level scale; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant.

[0035] Step 3: Perform inverse wavelet transform on the detail coefficients after approximate coefficient and threshold processing to obtain the denoised modal components.

[0036] Among them, the target modal component is any one of the modal components in the first component set.

[0037] In one implementation, conventional threshold functions include soft threshold functions and hard threshold functions. The threshold operation of the hard threshold is discontinuous, which may cause mutations or unevenness in the denoised signal. Especially at the transient change points of the signal, it may cause large fluctuations and affect the smoothness of the signal. The soft threshold function can achieve smooth noise reduction, but it may introduce amplitude scaling, resulting in distortion of the original signal. In this embodiment, the parameter n is set to 2, which can maintain continuity and smoothness at the threshold point while minimizing the amplitude distortion introduced by the soft threshold function.

[0038] In one embodiment, the reverse suppression of the second component set using the three - standard - deviation criterion is specifically as follows: Calculate the mean and standard deviation of the second target modal component, subtract the mean from the second modal component, take the absolute value, zero out the points not greater than three standard deviations, and retain the remaining points. Thus, the partial discharge characteristic signal is extracted from the modal components dominated by the noise signal.

[0039] In one embodiment, the state evaluation model can be a machine - learning model, such as a support vector machine.

[0040] In one embodiment, the state evaluation model can be a neural network model. Specifically, refer to Figure 2 , Figure 2 which is a schematic structural diagram of a state evaluation model provided by an embodiment of the present invention. The state evaluation model consists of a first feature extraction branch FFE, a second feature extraction branch SFE, an attention module AM, and a classifier Cls; where: The first feature extraction branch is used to extract features from the corrected signal of the transient ground voltage signal using a gated recurrent unit GRU to obtain the first feature.

[0041] The second feature extraction branch is used to extract features from the corrected signal of the ultrasonic signal using a gated recurrent unit GRU to obtain the second feature. Specifically, the second feature and the first feature have the same dimension.

[0042] The attention module is used to fuse and enhance the joint features of the first feature and the second feature using a multi - head self - attention mechanism to obtain the third feature. Specifically, the first feature and the second feature are concatenated to obtain a joint feature matrix, and a multi - head attention module MHA calculates the attention weights according to the joint feature matrix and outputs the weighted result. The output matrix is sent to the subsequent feed - forward network FFN for further processing to obtain the third feature.

[0043] The classifier is used to process the third feature using a fully connected network and output a state type.

[0044] By combining multimodal signals, the model can adapt to more complex equipment monitoring environments and provide more accurate diagnostic support.

[0045] In one embodiment, the status types can be divided into normal, slight abnormality, moderate abnormality and severe abnormality. For normal status, no adjustment is required. For any abnormality, the abnormal information is uploaded for early warning. Specifically, for slight abnormality, the load can be adjusted to reduce the frequency of partial discharge. For moderate abnormality, the device can be switched to low power or standby mode to avoid further development of partial discharge. For severe abnormality, system fault isolation can be performed to transfer the load to the standby system.

[0046] The embodiment of the present invention provides a high-voltage power distribution cabinet state intelligent monitoring and control system. Figure 3 , Figure 3 The present invention provides an architecture diagram of a high-voltage distribution cabinet state intelligent monitoring and control system. The system includes: The sensor monitoring module is used to collect the partial discharge signal of the target device in real time.

[0047] The signal denoising module is used to denoise the partial discharge signal to obtain a corrected signal.

[0048] The anomaly recognition module is used to use the correction signal as the input of the pre-trained state evaluation model to obtain the state type.

[0049] The action generation module is used to make control decisions based on the state type.

[0050] Among them, the partial discharge signal includes transient ground voltage signal and ultrasonic signal; the control decision includes load adjustment, operation mode adjustment and fault isolation.

[0051] An intelligent monitoring and control method for the status of a high-voltage distribution cabinet provided in an embodiment of the present invention can more accurately capture and identify potential fault information of electrical equipment by collecting partial discharge signals in real time and performing denoising processing to eliminate the interference of noise on the partial discharge signals, thereby making accurate control decisions, avoiding the expansion of faults, and ensuring the safe operation of the power system.

[0052] In one embodiment, the signal denoising module includes: The signal decomposition module is used to perform variational modal decomposition on the first target signal to obtain multiple modal components. The first target signal is any one of a transient voltage signal and an ultrasonic signal.

[0053] The dominant classification module is used to calculate the kurtosis of each modal component, incorporate the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and incorporate the modal components with kurtosis values ​​not greater than the preset threshold into the second component set.

[0054] The item-by-item denoising module is used to filter the first component set by using a wavelet threshold denoising method, and to reversely suppress the second component set by using a triple standard deviation criterion to obtain a denoised modal component set.

[0055] The signal reconstruction module is used to reconstruct the signal according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

[0056] In one embodiment, the signal decomposition module includes: The layer number determination module is used to perform empirical mode decomposition on the first target signal and determine the decomposition layer number K as the layer number of variational mode decomposition.

[0057] The penalty factor determination module is used to adopt the weighted fusion of envelope entropy and reconstruction error as the objective function, minimize the objective function as the goal, optimize the penalty factor α of the variational mode decomposition algorithm, and obtain the penalty factor α.

[0058] The decomposition execution module is used to perform variational modal decomposition on the first target signal according to the decomposition layer number K and the penalty factor α to obtain multiple modal components.

[0059] In one embodiment, the item-by-item denoising module includes: The wavelet transform module is used to perform wavelet transform on the target modal component to obtain wavelet coefficients. The wavelet coefficients include approximate coefficients and detail coefficients. The target modal component is any modal component in the first component set.

[0060] The threshold processing module is used to perform threshold processing on detail coefficients using an improved soft threshold function; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level scale; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant.

[0061] The inverse wavelet transform module is used to perform inverse wavelet transform on the approximate coefficients and the detail coefficients after threshold processing to obtain the denoised modal components.

[0062] It should be noted that, in this article, terms such as "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus.

[0063] The embodiments of the present invention are described in detail above, but the contents are only preferred embodiments of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of application of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for intelligent monitoring and control of high-voltage distribution cabinet status, characterized in that: The method comprises: Collecting partial discharge signals of target equipment in real time; the partial discharge signals include transient voltage signals and ultrasonic signals; Performing denoising processing on the partial discharge signal to obtain a corrected signal; Using the correction signal as an input of a pre-trained state evaluation model to obtain a state type; A control decision is made according to the state type; the control decision includes load adjustment, operation mode adjustment and fault isolation.

2. A method for intelligent monitoring and control of high-voltage distribution cabinet status according to claim 1, characterized in that: The denoising process of the partial discharge signal to obtain a corrected signal comprises: Performing variational modal decomposition on a first target signal to obtain a plurality of modal components; the first target signal is any one of a transient voltage signal and an ultrasonic signal; Calculate the kurtosis of each modal component, include the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and include the modal components with kurtosis values ​​less than the preset threshold into the second component set; The first component set is filtered by using a wavelet threshold denoising method, and the second component set is inversely suppressed by using a triple standard deviation criterion to obtain a denoised modal component set; Signal reconstruction is performed according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

3. A method for intelligent monitoring and control of high-voltage distribution cabinet status according to claim 2, characterized in that: The performing variational modal decomposition on the first target signal to obtain multiple modal components includes: Performing empirical mode decomposition on the first target signal to determine the number of decomposition layers K as the number of layers of variational mode decomposition; The weighted fusion of envelope entropy and reconstruction error is used as the objective function, and the penalty factor α of the variational mode decomposition algorithm is optimized with the goal of minimizing the objective function to obtain the penalty factor α; According to the decomposition layer number K and the penalty factor α, variational modal decomposition is performed on the first target signal to obtain multiple modal components.

4. A method for intelligent monitoring and control of high-voltage distribution cabinet status according to claim 2, characterized in that: The filtering of the first component set by using the wavelet threshold denoising method comprises: Performing wavelet transformation on the target modal component to obtain wavelet coefficients; the wavelet coefficients include approximate coefficients and detail coefficients; the target modal component is any modal component in the first component set; The improved threshold function is used to perform threshold processing on the detail coefficients; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level scale; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant; The approximate coefficients and the detail coefficients after threshold processing are subjected to inverse wavelet transform to obtain denoised modal components.

5. The method for intelligent monitoring and control of high-voltage distribution cabinet status according to claim 1 is characterized in that: The state evaluation model consists of a first feature extraction branch, a second feature extraction branch, an attention module and a classifier; wherein: The first feature extraction branch is used to extract features of the correction signal of the transient ground voltage signal using a gated cycle unit to obtain a first feature; The second feature extraction branch is used to extract features of the corrected signal of the ultrasonic signal using a gated cycle unit to obtain a second feature; The attention module is used to fuse and enhance the joint features of the first feature and the second feature by using a multi-head self-attention mechanism to obtain a third feature; The classifier is used to process the third feature using a fully connected network and output a state type.

6. A high-voltage distribution cabinet state intelligent monitoring and control system, characterized in that: The system comprises: A sensor monitoring module, used for collecting partial discharge signals of target equipment in real time; the partial discharge signals include transient ground voltage signals and ultrasonic signals; A signal denoising module, used for denoising the partial discharge signal to obtain a corrected signal; An abnormality identification module, used for taking the correction signal as an input of a pre-trained state evaluation model to obtain a state type; The action generation module is used to make control decisions according to the state type; the control decisions include load adjustment, operation mode adjustment and fault isolation.

7. The intelligent monitoring and control system for high-voltage power distribution cabinet status according to claim 6 is characterized in that: The signal denoising module comprises: A signal decomposition module, used for performing variational modal decomposition on a first target signal to obtain a plurality of modal components; the first target signal is any one of a transient voltage signal and an ultrasonic signal; A dominant classification module, used for calculating the kurtosis of each modal component, including the modal components with kurtosis values ​​greater than a preset threshold into the first component set, and including the modal components with kurtosis values ​​less than the preset threshold into the second component set; An item-by-item denoising module, configured to filter the first component set by using a wavelet threshold denoising method, and reversely suppress the second component set by using a triple standard deviation criterion, so as to obtain a denoised modal component set; The signal reconstruction module is used to reconstruct the signal according to the filtered modal component set to obtain a second target signal as a correction signal of the first target signal.

8. The intelligent monitoring and control system for high-voltage power distribution cabinet status according to claim 7 is characterized in that: The signal decomposition module comprises: A layer number determination module, used for performing empirical mode decomposition on the first target signal to determine the decomposition layer number K as the layer number of variational mode decomposition; A penalty factor determination module is used to optimize the penalty factor α of the variational mode decomposition algorithm by adopting a weighted fusion of envelope entropy and reconstruction error as an objective function and minimizing the objective function to obtain the penalty factor α; The decomposition execution module is used to perform variational modal decomposition on the first target signal according to the decomposition layer number K and the penalty factor α to obtain multiple modal components.

9. The intelligent monitoring and control system for high-voltage power distribution cabinet status according to claim 7 is characterized in that: The item-by-item denoising module comprises: A wavelet transform module is used to perform wavelet transform on the target modal component to obtain wavelet coefficients; the wavelet coefficients include approximate coefficients and detail coefficients; the target modal component is any modal component in the first component set; The threshold processing module is used to perform threshold processing on the detail coefficients by using an improved threshold function; specifically: in, is the wavelet threshold; median() means taking the median; is the detail coefficient of the j-th level scale; is the length of the detail coefficient at the j-th level scale; is the detail coefficient after threshold processing; sgn() is the sign function; n is a constant; The inverse wavelet transform module is used to perform inverse wavelet transform on the approximate coefficients and detail coefficients after threshold processing to obtain denoised modal components.

10. The intelligent monitoring and control system for high-voltage power distribution cabinet status according to claim 6, characterized in that: The state evaluation model consists of a first feature extraction branch, a second feature extraction branch, an attention module and a classifier; wherein: The first feature extraction branch is used to extract features of the correction signal of the transient ground voltage signal using a gated cycle unit to obtain a first feature; The second feature extraction branch is used to extract features of the corrected signal of the ultrasonic signal using a gated cycle unit to obtain a second feature; The attention module is used to fuse and enhance the joint features of the first feature and the second feature by using a multi-head self-attention mechanism to obtain a third feature; The classifier is used to process the third feature using a fully connected network and output a state type.

Images