Power cable insulation performance evaluation method

Abstract

The invention relates to the technical field of insulation performance evaluation, in particular to a power cable insulation performance evaluation method. Comprising the following steps: acquiring electrical parameters of a power cable in real time by adopting a measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering; preprocessing the electrical parameters of the power cable to obtain preprocessed electrical parameters; carrying out fusion processing on the preprocessed electrical parameters to obtain fused electrical parameters; and performing performance evaluation on the fused electrical parameters by using an evaluation algorithm based on a hybrid neural network and fuzzy logic to obtain a comprehensive health evaluation value of the power cable. The technical problem that the electrical parameters of the power cable are not accurately collected and processed is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of insulation performance evaluation, and in particular to a method for evaluating the insulation performance of a power cable. Background Art

[0002] At present, with the continuous development of the power system and the expansion of the scale of the power grid, higher requirements are placed on the operation monitoring and maintenance management of power cables. Power cables play a vital role in modern power systems and are widely used in power transmission, distribution, equipment connection and other links. However, since power cables are often buried underground or hidden in buildings and exposed to different environmental factors, cable faults are difficult to be discovered in time. Cable failures not only affect the stability and safety of the power system, but may also cause equipment damage and economic losses. Therefore, how to monitor the electrical status of power cables in real time and identify potential faults early has become an important issue that needs to be solved in the power industry.

[0003] Traditional power cable detection methods mainly rely on regular manual inspections and traditional electrical testing equipment, which often fail to meet the requirements of real-time, comprehensiveness, and high precision. With the continuous development of intelligent sensing technology, wireless communication technology, and data processing technology, power cable monitoring systems based on sensor networks have gradually become an effective solution. This type of system can realize real-time data collection and fault diagnosis of power cables, especially in the monitoring of high-voltage power cables, and has broad application prospects.

[0004] However, the existing power cable insulation performance evaluation method has the following technical problems: the collection and processing of the electrical parameters of the power cable are not accurate enough. Summary of the invention

[0005] The invention provides a method for evaluating the insulation performance of a power cable, so as to solve the technical problem that the collection and processing of the electrical parameters of the power cable are not accurate enough.

[0006] A method for evaluating the insulation performance of a power cable of the present invention specifically includes the following technical solutions: A method for evaluating the insulation performance of a power cable comprises the following steps: S1. Using a measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, real-time acquisition of electrical parameters of the power cable is performed; preprocessing of the electrical parameters of the power cable is performed to obtain preprocessed electrical parameters; and fusion processing of the preprocessed electrical parameters is performed to obtain fused electrical parameters; S2. The fused electrical parameters are evaluated using an evaluation algorithm based on a hybrid neural network and fuzzy logic to obtain a comprehensive health assessment value of the power cable.

[0007] Preferably, the S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, sensors are deployed to collect signals in real time, and the time-frequency coupling analysis method is used to perform time-frequency coupling conversion on the collected signals to obtain the converted signals.

[0008] Preferably, the S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, a nonlinear adaptive filtering algorithm is introduced to filter the converted signal. The nonlinear adaptive filtering algorithm dynamically adjusts the filtering parameters according to the changes of the converted signal, removes the noise of the converted signal, and obtains the filtered signal.

[0009] Preferably, the S1 specifically includes: The specific calculation formula of the filtered signal is: , in, is the filtered signal; is the window size of the adaptive filter; is the adaptive filter at time and frequency The weighting coefficient on ; It is at the moment and frequency The input signal at time and frequency The up-converted signal; is the nonlinear enhancement coefficient; is the number of history time steps used in nonlinear enhancement; It is at the moment and frequency Up-converted signal.

[0010] Preferably, the S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, after the converted signal is filtered, the filtered signal is enhanced to obtain an enhanced signal.

[0011] Preferably, the S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, a time-frequency domain joint modeling method is introduced based on the enhanced signal. The time-frequency domain joint modeling method combines the time domain and frequency domain information, and extracts the electrical parameters of the power cable by integrating the enhanced signal.

[0012] Preferably, the S1 specifically includes: The implementation formula of the time-frequency domain joint modeling method is: , in, It is the electrical parameter of the power cable; is the enhanced signal; is the time domain weighting coefficient; is the frequency domain weighting coefficient; is the upper limit of the frequency part integration; It is the upper limit of the time part integral.

[0013] Preferably, the S2 specifically includes: In the process of implementing the evaluation algorithm based on hybrid neural network and fuzzy logic, a neural network model is designed and trained, and the neural network model consists of an input layer, a hidden layer and an output layer; the input layer receives the fused electrical parameters; the hidden layer learns the relationship between different fused electrical parameters through multi-layer nonlinear transformation; and the output layer generates a preliminary health assessment value.

[0014] Preferably, the S2 specifically includes: In the implementation process of the evaluation algorithm based on hybrid neural network and fuzzy logic, the health status of the power cable is inferred by introducing fuzzy rules and fuzzy membership functions, and the fuzzy value is output. The fuzzy value is defuzzified to obtain the health assessment value; the comprehensive health assessment value of the power cable is obtained by weighted fusion of the preliminary health assessment value and the health assessment value in the output layer of the neural network model.

[0015] The beneficial effects of the technical solution of the present invention are: 1. Under the multi-channel sensor network, the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering is used to collect the electrical parameters of the power cable in real time, better reveal the frequency domain characteristics of the signal, and effectively solve the problem that the traditional time domain analysis method cannot capture high-frequency signals. At the same time, through the adjustment of the nonlinear enhancement coefficient and the adaptive filter, it is possible to adaptively denoise and enhance the electrical characteristics in the dynamically changing signal, effectively eliminate the noise from environmental interference, and enhance the useful information in the signal. Finally, the composite signal enhancement processing is introduced to perform multiple enhancements and suppressions on the converted signal, which improves the quality of the converted signal and the extraction accuracy of the electrical parameters.

[0016] 2. An evaluation algorithm based on hybrid neural network and fuzzy logic is introduced. By combining the deep learning ability of neural network and the nonlinear reasoning advantage of fuzzy logic system, the health status assessment of power cables is more robust. The training of neural network model can learn the complex nonlinear relationship between electrical parameters, while fuzzy logic reasoning can effectively handle the uncertainty of data and provide more accurate results for health assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a method for evaluating insulation performance of a power cable according to the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all 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] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The following is a detailed description of a method for evaluating the insulation performance of a power cable provided by the present invention in conjunction with the accompanying drawings. Figure 1 , which shows a flow chart of a method for evaluating the insulation performance of a power cable provided by an embodiment of the present invention, the method comprising the following steps: S1. Using a measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, real-time acquisition of electrical parameters of the power cable is performed; preprocessing of the electrical parameters of the power cable is performed to obtain preprocessed electrical parameters; and fusion processing of the preprocessed electrical parameters is performed to obtain fused electrical parameters; In order to realize real-time monitoring of power cables, a multi-channel sensor network is designed. The multi-channel sensor network collects the electrical parameters of power cables in real time through multi-channel configuration. The specific design includes arranging sensors at key positions of power cables (such as joints, cable middles, access ends, corners, and parts that bear heavy loads) according to the layout of power cables, including current sensors, voltage sensors, temperature and humidity sensors, dielectric loss sensors, etc. The key positions of electrical cables are determined based on expert experience. In the deployed multi-channel sensor network, the electrical parameters of power cables, including resistance, leakage current, dielectric loss, voltage, temperature, humidity, etc., are collected in real time using a measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering. The measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering converts the signal through a time-frequency coupling analysis method, and introduces multiple enhancement processing to further extract the electrical parameters of the power cable. The specific implementation process is as follows: First, start with signal acquisition to measure the electrical parameters of the power cable. By deploying sensors such as dielectric loss sensors, current sensors, voltage sensors, temperature sensors, and humidity sensors, real-time signal acquisition is performed at key locations of the electrical cable. ; Indicates at time No. The signals collected by the sensors are is a time variable.

[0021] In order to better capture the collected signal The frequency domain characteristics in the image are analyzed by using time-frequency coupling analysis methods such as wavelet transform and short-time Fourier transform to perform time-frequency coupling conversion on the collected signal to obtain the converted signal. ; Convert the signal from the time domain to the time-frequency domain, thereby retaining the time information and frequency information of the signal at the same time, providing rich time-frequency information for subsequent signal enhancement and electrical parameter extraction. The representation in the time-frequency domain is ,in is a frequency variable.

[0022] After the time-frequency coupling conversion, since the measurement of the power cable is often interfered by environmental noise, a nonlinear adaptive filtering algorithm is introduced to filter the converted signal to remove the noise in the converted signal and improve the quality of the converted signal. The nonlinear adaptive filtering algorithm can dynamically adjust the filtering parameters according to the changes of the converted signal, effectively remove the noise of the converted signal, and enhance the electrical characteristics of the converted signal. The specific formula is as follows: , , , in, is the filtered signal; is the window size of the adaptive filter, which is determined according to the specific scenario; is the adaptive filter at time and frequency The weighting coefficient on represents the input signal The filtered signal the extent of contribution; It is at the moment and frequency The input signal at time and frequency The up-converted signal; It is the nonlinear enhancement coefficient, which indicates the degree of nonlinear enhancement of the converted signal. It is a dynamic adjustment factor that adjusts the intensity of nonlinear enhancement according to the signal characteristics. It is the number of historical time steps used in nonlinear enhancement, which controls the historical range of nonlinear enhancement and is determined according to the specific scenario; It is at the moment and frequency The up-converted signal; is the adaptive filter at the last moment and frequency The weighting coefficient on ; It is the adaptive step size parameter, which is used to control the rate of weight update and determine the sensitivity of the adaptive filter to adjust the weight. It is determined according to the expert experience method; is the expected output signal, which is the target output of the adaptive filter and is compared with the actual filtered signal and is calculated using the existing theoretical model; It is the adjustment factor, which determines the signal energy of the converted signal to the nonlinear enhancement coefficient The influence degree of the signal energy fluctuation of the converted signal is used to control the contribution of the nonlinear enhancement, which is determined according to the expert experience method; It is an adjustment parameter used to control the signal energy of the converted signal to the nonlinear enhancement coefficient The response speed is determined by experimental method; is the signal energy of the converted signal; is the length of the time window, which represents the time period used to calculate the signal energy of the converted signal and is determined based on expert experience.

[0023] After the converted signal is filtered, the filtered signal is further enhanced by the composite signal enhancement algorithm; the specific composite signal enhancement formula is as follows: , in, is the enhanced signal; is the exponential enhancement coefficient, which is used to control the intensity of signal enhancement after filtering and is obtained by experimental method; It is the power coefficient of the exponential, which is used to control the relationship between the enhancement amplitude and the size of the filtered signal, and is determined by experimental method; is the suppression coefficient, which determines the suppression effect when the signal is too strong after filtering and is determined according to the expert experience method; is the exponential coefficient in the inhibition term, which determines the sensitivity of inhibition and is determined by experimental method; is the power exponent of the suppression term, which is used to control the nonlinear effect of the suppression strength of the filtered signal and is determined by experimental methods; is the logarithmic enhancement coefficient, which is used to control the enhancement amplitude of the signal after low-intensity filtering and is determined according to the expert experience method; After composite signal enhancement processing, the enhanced signal , which contains the multi-dimensional electrical characteristics of the power cable. In order to extract the electrical parameters of the power cable from the enhanced signal, a time-frequency domain joint modeling method is introduced. The time-frequency domain joint modeling method combines the time domain and frequency domain information by Perform integral calculations to extract the electrical parameters of the power cable, such as resistance, dielectric loss, load current, etc. The implementation formula of the time-frequency domain joint modeling method is: , in, It is the electrical parameter of the power cable; It is the time domain weighting coefficient, which reflects the influence of the power of the frequency component on the electrical parameters of the power cable and is determined by experimental method; is the frequency domain weighting coefficient, which is used to control the influence of the cumulative effect of the enhanced signal in a specific frequency band on the electrical parameters of the power cable and is obtained by experimental method; is the upper limit of the integral of the frequency part, which is determined according to the expert experience method; It is the upper limit of the integral of the time part, which is determined according to the expert experience method.

[0024] Furthermore, the electrical parameters of the power cable are preprocessed such as smoothing, correction, and normalization to obtain preprocessed electrical parameters. The preprocessing process adopts existing technologies well known to those skilled in the art and will not be described in detail here.

[0025] Finally, the pre-processed electrical parameters are fused using existing data fusion algorithms (such as weighted average method, multi-sensor data fusion algorithm, Kalman filter, etc.) to obtain the fused electrical parameters. .

[0026] S2. The fused electrical parameters are evaluated using an evaluation algorithm based on a hybrid neural network and fuzzy logic to obtain a comprehensive health assessment value of the power cable.

[0027] The evaluation algorithm based on hybrid neural network and fuzzy logic combines the deep learning ability of neural network and the nonlinear reasoning advantage of fuzzy logic system, which can handle the complex relationship between various electrical parameters involved in the power cable monitoring process and effectively deal with the uncertainty and ambiguity of data. The specific implementation process is as follows: First, a neural network model is designed. The neural network model, such as a feedforward neural network, is composed of an input layer, a hidden layer, and an output layer. The input layer receives the fused electrical parameters , each element of which corresponds to a fused electrical parameter, such as resistance, dielectric loss, etc.; the hidden layer learns the potential relationship of the fused electrical parameters through multiple layers of nonlinear transformation; the output layer generates a preliminary health assessment value The preliminary health assessment value is a quantitative indicator of the health status of the power cable. The specific number of transformation layers of the multi-layer nonlinear transformation in the hidden layer is determined according to the specific scenario, and the multi-layer nonlinear transformation is implemented by selecting an existing activation function according to the expert experience method.

[0028] The existing back propagation algorithm is further used to adjust the weights and biases of the neural network model to implement model training, thereby obtaining a model that can accurately reflect the health status of power cable insulation.

[0029] Furthermore, the existing fuzzy logic reasoning technology is introduced, which infers the health status of the power cable by introducing fuzzy rules and fuzzy membership functions to process the fuzzy relationship between the fused electrical parameters. The input of the fuzzy logic reasoning process includes the preliminary health assessment value generated in the output layer of the neural network model The fused electrical parameters are then converted into fuzzy values ​​by defining appropriate fuzzy membership functions based on specific scenarios. The fuzzy logic reasoning process combines fuzzy rules for decision making and outputs fuzzy values.

[0030] The fuzzy membership function is as follows: , , in, is the combined electrical parameter of any power cable. and Indicates the minimum and maximum values ​​of the fused electrical parameters; and are the membership degrees for low and high values ​​respectively.

[0031] According to the membership calculated by the fuzzy membership function, fuzzy rules are defined, for example: if the resistance is low and the current is low, the power cable is healthy; if the resistance is high and the current is high, the power cable is aged.

[0032] After the above existing fuzzy logic reasoning technology, a fuzzy value is output, and the output fuzzy value is defuzzified by an existing defuzzification method such as weighted average method to obtain a health assessment value. .

[0033] Finally, the preliminary health assessment value in the output layer of the neural network model is and fuzzy logic reasoning health assessment value The weighted fusion is performed to obtain the comprehensive health assessment value of the power cable. The goal of this weighted fusion process is to combine the advantages of the two methods to obtain a more accurate cable health assessment value.

[0034] In summary, a method for evaluating the insulation performance of power cables is completed.

[0035] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0036] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0037] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the insulation performance of a power cable, characterized in that: The following steps are involved: S1. Using a measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, the electrical parameters of the power cable are collected in real time; the electrical parameters of the power cable are preprocessed to obtain the preprocessed electrical parameters; and performing fusion processing on the preprocessed electrical parameters to obtain fused electrical parameters; S2. The fused electrical parameters are evaluated using an evaluation algorithm based on a hybrid neural network and fuzzy logic to obtain a comprehensive health assessment value of the power cable.

2. A method for evaluating the insulation performance of a power cable according to claim 1, characterized in that: The S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, sensors are deployed to collect signals in real time, and the time-frequency coupling analysis method is used to perform time-frequency coupling conversion on the collected signals to obtain the converted signals.

3. A method for evaluating the insulation performance of a power cable according to claim 2, characterized in that: The S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, a nonlinear adaptive filtering algorithm is introduced to filter the converted signal. The nonlinear adaptive filtering algorithm dynamically adjusts the filtering parameters according to the changes of the converted signal, removes the noise of the converted signal, and obtains the filtered signal.

4. A method for evaluating the insulation performance of a power cable according to claim 3, characterized in that: The S1 specifically includes: The specific calculation formula of the filtered signal is: ， in, is the filtered signal; is the window size of the adaptive filter; is the adaptive filter at time and frequency The weighting coefficient on ; It is at the moment and frequency The input signal at time and frequency The up-converted signal; is the nonlinear enhancement coefficient; is the number of history time steps used in nonlinear enhancement; It is at the moment and frequency Up-converted signal.

5. A method for evaluating the insulation performance of a power cable according to claim 4, characterized in that: The S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, after the converted signal is filtered, the filtered signal is enhanced to obtain an enhanced signal.

6. A method for evaluating the insulation performance of a power cable according to claim 5, characterized in that: The S1 specifically includes: In the measurement method based on time-frequency coupling enhancement and nonlinear adaptive filtering, a time-frequency domain joint modeling method is introduced based on the enhanced signal. The time-frequency domain joint modeling method combines the time domain and frequency domain information, and extracts the electrical parameters of the power cable by integrating the enhanced signal.

7. A method for evaluating the insulation performance of a power cable according to claim 6, characterized in that: The S1 specifically includes: The implementation formula of the time-frequency domain joint modeling method is: ， in, It is the electrical parameter of the power cable; is the enhanced signal; is the time domain weighting coefficient; is the frequency domain weighting coefficient; is the upper limit of the frequency part integration; It is the upper limit of the time part integral.

8. A method for evaluating the insulation performance of a power cable according to claim 1, characterized in that: The S2 specifically includes: In the process of implementing the evaluation algorithm based on hybrid neural network and fuzzy logic, a neural network model is designed and trained, and the neural network model consists of an input layer, a hidden layer and an output layer; the input layer receives the fused electrical parameters; the hidden layer learns the relationship between different fused electrical parameters through multi-layer nonlinear transformation; and the output layer generates a preliminary health assessment value.

9. A method for evaluating the insulation performance of a power cable according to claim 8, characterized in that: The S2 specifically includes: In the implementation process of the evaluation algorithm based on hybrid neural network and fuzzy logic, the health status of the power cable is inferred by introducing fuzzy rules and fuzzy membership functions, and the fuzzy value is output. The fuzzy value is defuzzified to obtain the health assessment value; the comprehensive health assessment value of the power cable is obtained by weighted fusion of the preliminary health assessment value and the health assessment value in the output layer of the neural network model.

Images