Method for Monitoring and Warning Cable Insulation Electric Field Based on Digital Twin

Abstract

The present invention discloses a method for monitoring and warning the insulation electric field of a cable based on digital twin, which relates to the technical field of cable detection. By constructing a digital mirror model of the cable according to the topological structure of the cable section to be monitored, obtaining the historical data of influencing factors at the i-th monitoring node in the topological structure of the cable section to be monitored and the measured historical data of capacitance values measured by FEF sensors, synchronizing the real-time data of influencing factors at the i-th monitoring node into the digital mirror model of the cable according to the obtained data and the correction coefficient for calculating the relative permittivity, calculating the corrected capacitance correction value according to the obtained correction coefficient, and judging the aging condition of the cable insulation layer at the i-th monitoring node in the topological structure of the cable section to be monitored according to the obtained capacitance correction value, the deviation degree between the calculation result of the capacitance value data and the actual situation is reduced, thereby improving the judgment accuracy of the aging condition of the cable insulation layer.

Description

Technical Field

[0001] The present invention relates to the technical field of cable detection, and particularly relates to a method for monitoring and warning the insulation electric field of a cable based on digital twin. Background Technique

[0002] Cross-linked polyethylene (XLPE) insulated power cables have become the preferred products for power cables required in the renovation and construction of urban power grids due to their reasonable process structure, strong corrosion resistance, simple installation and laying, etc. With the increasing application of cross-linked polyethylene power cables in the renovation of urban power grids, the stability during their operation is directly related to the safe operation of the entire power system. Research shows that the generation of water trees in the cable insulation layer is an important factor leading to the shortening of the insulation life of cross-linked polyethylene cables. Therefore, it is of great significance to detect water trees in the insulation layer.

[0003] The edge electric field dielectric method is a widely used non-destructive measurement method and an effective means for detecting water trees in the cable insulation layer. The detection principle is to relate the dielectric characteristics of the material to be measured to the corresponding physical characteristics and study the basic theoretical relationship between the two, with the characteristic of non-destructive measurement. The FEF sensor is a typical application of the edge electric field method, which is connected to an electric field sensor chip. When water trees are generated due to insulation layer aging, since the dielectric constant of water is much larger than that of cross-linked polyethylene, the dielectric constant of the insulation layer material will change greatly, causing a change in the capacitance value between the electrodes of the FEF sensor. After the chip converts the capacitance value into a voltage value and transmits it to the controller, the controller can accurately read the change in the capacitance value, thereby quickly judging the aging condition of the insulation layer.

[0004] When using the edge electric field dielectric method to detect the water tree phenomenon in the cable insulation layer, when calculating the capacitance value data of the FEF sensor, the dielectric constant at the detection point needs to be obtained. However, when the environment around the cable at the detection point, such as temperature and humidity, changes, it will affect the dielectric constant of the air, resulting in a deviation between the calculated capacitance value data and the actual situation, thus leading to an inaccurate judgment of the aging condition of the cable insulation layer. For this reason, we propose a method for monitoring and warning the insulation electric field of a cable based on digital twin. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method for monitoring and warning the insulation electric field of a cable based on digital twin, which can effectively solve the problems in the background technique.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] A method for monitoring and warning the insulation electric field of a cable based on digital twin, comprising:

[0008] Construct a digital model of the cable mirror image according to the topological structure of the cable section to be monitored;

[0009] Obtain the historical data of influencing factors at the i-th monitoring node in the topological structure of the cable segment to be monitored and the measured historical data of capacitance values measured by the FEF sensor wherein represents the k-th measured value of the j-th influencing factor at the i-th monitoring node; represents the k-th measured value of the capacitance value at the i-th monitoring node, wherein the influencing factors include at least one of cable ambient temperature, cable ambient humidity, electric field strength, and cable thickness;

[0010] According to the obtained data and Calculate the correction coefficient k of the dielectric constant ε ;

[0011] Synchronize the real-time data of influencing factors at the i-th monitoring node to the cable mirror digital model, and calculate the corrected capacitance correction value according to the obtained correction coefficient k ε Calculate the corrected capacitance correction value

[0012] According to the obtained capacitance correction value Judge the aging condition of the cable insulation layer at the i-th monitoring node in the topological structure of the cable segment to be monitored

[0013] The real-time value of the corrected capacitance value The calculation formula is:

[0014]

[0015] In the formula, α is the electrode fork index of the FEF sensor; L is the electrode length; a and b are the intervals between the electrodes and the width of a single plate respectively; ε x is the dielectric constant

[0016] The acquisition process of the correction coefficient k ε includes the following steps:

[0017] Taking the K measured values of influencing factors at any monitoring node q as input and the K measured values of the corresponding capacitance values as output, construct a first neural network model. By training the established first neural network model, adjust the number of hidden layers of the model according to the error between the training result and the actual alarm result until the accuracy is not lower than the first expected value, and then output the k-th predicted value of the capacitance value at the q-th monitoring node through the constructed first neural network model where k = 1, 2,..., K; K is the total amount of data sampling at the q-th monitoring node;

[0018] According to the obtained predicted values Calculate the first correction coefficient k ε1 , and the calculation formula is: In the formula, is the measured value of the capacitance corresponding to the k-th measured value of the q-th monitoring node ;

[0019] Using the k-th measured values of the influencing factors at all monitoring nodes as the input, and the k-th measured values of the corresponding capacitance values as the output, construct a second neural network model. By training the established second neural network model, adjust the number of hidden layers of the model according to the error between the training result and the actual alarm result until the accuracy is not lower than the second expected value. Then, output the k-th predicted value of the capacitance at the i-th monitoring node through the constructed second neural network model where i = 1, 2,..., N; N is the total number of monitoring nodes;

[0020] According to the obtained predicted values Calculate the second correction coefficient k ε2 , and the calculation formula is:

[0021]

[0022] Perform weighted average processing on the obtained first correction coefficient k ε1 and the second correction coefficient k ε2 to obtain the correction coefficient k of the dielectric constant ε , and the calculation formula is: where μ, ν ∈ (0, 1), and μ + ν = 1.

[0023] The calculation formulas for the first expected value and the second expected value are

[0024]

[0025] where E(Y) r represents the r-th expected value; N r represents the number of the r-th neural network input samples; f(X mr ) r represents the output function of the r-th neural network; X mr represents the m-th output sample of the r-th neural network, r = 1, 2. Among them, when r = 1, N r = K; when r = 2, N r = N.

[0026] Both the first neural network model and the second neural network model are BP neural network models, and the network model has p rThe input layer of p neurons, q r The input layer of h and s neurons r A three-layer structure of the hidden layer with r neurons, where, Is expressed as rounding up the calculation result of ; h is an integer from 1 to 9.

[0027] The process for judging the aging condition of the cable insulation layer includes the following steps:

[0028] Respectively obtain the capacitance correction values C ib and C ie of the i-th monitoring node in the topological structure of the cable section to be monitored in the initial state and the aging failure state;

[0029] Obtain the capacitance correction value during the use of the cable section to be monitored When , determine that it is in the aging failure state;

[0030] When , calculate the distance between the capacitance correction value and the capacitance correction value C ie in the aging failure state The calculation formula is:

[0031] Use the value of the distance to create a sample set, and obtain the mean and standard deviation in the sample set. Use the mean and standard deviation to standardize the data. The standardization formula is In the formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data;

[0032] Adjust the standard parameter interval to the range of [0,1] using the function , and classify the capacitance correction value using the function value of f(k). The classification mechanism is:

[0033] When , the capacitance correction value is classified as first level;

[0034] When , the capacitance correction value is classified as second level;

[0035] When , the capacitance correction value is classified as third level; where, f(k) min and f(k) max are the minimum and maximum values of the function f(k) respectively;

[0036] Determine the aging degree of the cable insulation layer according to the classification result of the capacitance correction value, where when the capacitance correction value is classified as the first level, the aging degree of the cable insulation layer is slightly aged; when the capacitance correction value is classified as the second level, the aging degree of the cable insulation layer is moderately aged; when the capacitance correction value is classified as the third level, the aging degree of the cable insulation layer is severely aged.

[0037] The method further includes the following steps:

[0038] According to the judgment result of the aging situation of the cable insulation layer, formulate an early warning strategy for the i-th monitoring node in the topological structure of the cable section to be monitored, specifically:

[0039] When the aging degree of the cable insulation layer at the i-th monitoring node is slightly aged, conduct a first-level early warning for the cable insulation;

[0040] When the aging degree of the cable insulation layer at the i-th monitoring node is moderately aged, conduct a second-level early warning for the cable insulation;

[0041] When the aging degree of the cable insulation layer at the i-th monitoring node is severely aged, conduct a third-level early warning for the cable insulation.

[0042] The present invention has the following beneficial effects:

[0043] Compared with the prior art, by constructing a cable mirror digital model according to the topological structure of the cable section to be monitored, obtaining the historical data of influencing factors at the i-th monitoring node in the topological structure of the cable section to be monitored and the measured historical data of the capacitance value measured by the FEF sensor According to the obtained data and calculate the correction coefficient k of the dielectric constant ε , synchronize the real-time data of influencing factors at the i-th monitoring node to the cable mirror digital model, and calculate the corrected capacitance correction value according to the obtained correction coefficient k ε According to the obtained capacitance correction value judge the aging situation of the cable insulation layer at the i-th monitoring node in the topological structure of the cable section to be monitored. By analyzing the dielectric constant, obtain the corrected capacitance value, reduce the deviation degree between the calculation result of the capacitance value data and the actual situation, and thus improve the judgment accuracy of the aging situation of the cable insulation layer. Description of the Drawings

[0044] Figure 1 ​​Flow chart of the cable insulation electric field monitoring and early warning method based on digital twin of the present invention;

[0045] Figure 2 Schematic diagram of the neural network model structure constructed in the solution of the present invention;

[0046] Figure 3 Detection principle diagram of the interdigital FEF sensor in the embodiment of the present invention;

[0047] Figure 4 Schematic diagram of the simplified model of the sensor capacitance in the embodiment of the present invention. Specific implementation mode

[0048] The following further describes the present invention in conjunction with the specific implementation mode. Among them, the drawings are only for illustrative purposes, showing only schematic diagrams, not physical diagrams, and should not be construed as limiting the present invention. In order to better illustrate the specific implementation mode of the present invention, some components in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0049] The specific implementation process of the technical solution of the present invention includes the following steps:

[0050] Step 1: Construct a digital model of the cable mirror according to the topological structure of the cable section to be monitored;

[0051] Step 2: Obtain the historical data of the influencing factors at the i-th monitoring node in the topological structure of the cable section to be monitored and the measured historical data of the capacitance value measured by the FEF sensor In this embodiment, the FEF sensor is an interdigital FEF sensor, and its detection principle of the interdigital FEF sensor is as Figure 3 shown, and the simplified model of the sensor capacitance is as Figure 4 shown, where represents the k-th measured value of the j-th influencing factor at the i-th monitoring node; represents the k-th measured value of the capacitance value at the i-th monitoring node, where the influencing factors include at least one of the cable ambient temperature, cable ambient humidity, electric field strength, and cable thickness. In this embodiment, all the above influencing factors are taken as examples for description;

[0052] Step 3: Construct data sequences A1, A2, B1, and B2 according to the obtained data. The specific expressions of each sequence are as follows:

[0053]

[0054] Step 4: Calculate the correction coefficient k of the dielectric constant according to the obtained data and ε, the acquisition process includes the following steps:

[0055] Step 41: Using the K measured values of the influencing factors at any monitoring node q as the input and the K measured values of the corresponding capacitance values as the output, as shown by the data sequences A1 and B1 in Step 3, respectively using the first column of data in sequence A1 as the input and the first column of data in sequence B1 as the output, construct the first neural network model. By training the established first neural network model and adjusting the number of hidden layers of the model according to the error between the training result and the actual alarm result until the accuracy is not lower than the first expected value, output the k-th predicted value of the capacitance value at the q-th monitoring node through the constructed first neural network model. where k = 1, 2,..., K; K is the total amount of data sampling at the q-th monitoring node;

[0056] Step 42: According to the obtained predicted values calculate the first correction coefficient k ε1 , and the calculation formula is: In the formula, is the k-th measured value of the influencing factor at the q-th monitoring node corresponding to the measured value of the capacitance value;

[0057] Step 43: Using the k-th measured values of the influencing factors at all monitoring nodes as the input and the k-th measured values of the corresponding capacitance values as the output, as shown by the data sequences A2 and B2 in Step 3, respectively using the first column of data in sequence A2 as the input and the first column of data in sequence B2 as the output, construct the second neural network model. By training the established second neural network model and adjusting the number of hidden layers of the model according to the error between the training result and the actual alarm result until the accuracy is not lower than the second expected value, output the k-th predicted value of the capacitance value at the i-th monitoring node through the constructed second neural network model. where i = 1, 2,..., N; N is the total number of monitoring nodes;

[0058] Step 44: According to the obtained predicted values calculate the second correction coefficient k ε2 , and the calculation formula is:

[0059] Step 45: Perform weighted average processing on the obtained first correction coefficient k ε1 and the second correction coefficient k ε2 to obtain the correction coefficient k of the dielectric constant ε , and the calculation formula is: where μ, ν ∈ (0, 1), and μ + ν = 1;

[0060] It should be noted that the calculation formulas for the first expected value and the second expected value are as follows:

[0061]

[0062] where E(Y) r represents the r-th expected value; N r represents the number of the r-th neural network input samples; f(X mr ) r represents the output function of the r-th neural network; X mr represents the m-th output sample of the r-th neural network, r = 1, 2. Among them, when r = 1, N r = K; when r = 2, N r = N;

[0063] Both the first neural network model and the second neural network model are BP neural network models. The network model is a three-layer structure with an input layer having p r neurons, an input layer h having q r neurons, and a hidden layer having s r neurons. Among them, represents rounding up the calculation result of ; h is an integer from 1 to 9. In this embodiment, the number of neurons in the input layer of both the first neural network model and the second neural network model is 4, and the number of neurons in the output layer is 1. When h = 3, the structures of both the first neural network model and the second neural network model are three-layer structures with an input layer having 4 neurons, an input layer h having 1 neuron, and a hidden layer having 6 neurons. The specific structure form is as Figure 2 shown;

[0064] Step 5: Synchronize the real-time data of the influencing factors at the i-th monitoring node to the cable mirror digital model, and calculate the corrected capacitance correction value according to the obtained correction coefficient k ε The calculation formula is: The calculation formula is:

[0065]

[0066] In the formula, α is the electrode fork index of the FEF sensor; L is the electrode length; a and b are the intervals between the electrodes and the width of a single plate respectively; ε x is the dielectric constant;

[0067] Step 6: Judge the aging condition of the cable insulation layer at the i-th monitoring node in the topological structure of the cable segment to be monitored according to the obtained capacitance correction value The judgment process includes the following steps:

[0068] Step 61: Obtain the capacitance correction values C ib and C ie ;

[0069] Step 62: Obtain the capacitance correction value during the use of the cable segment to be monitored When it is determined that it is in the aging failure state;

[0070] Step 63: When calculate the distance between the capacitance correction value and the capacitance correction value C ie in the aging failure state The calculation formula is:

[0071] Step 64: Create a sample set using the value of the distance and obtain the mean and standard deviation in the sample set. Standardize the data using the mean and standard deviation. The standardization formula is In the formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data;

[0072] Step 65: Adjust the standard parameter interval to the range of [0,1] using the function and classify the capacitance correction value using the function value of f(k). The classification mechanism is:

[0073] When the capacitance correction value is classified as level one;

[0074] When the capacitance correction value is classified as level two;

[0075] When the capacitance correction value is classified as level three; where f(k) min and f(k) max are the minimum and maximum values of the function f(k) respectively;

[0076] Step 66: Determine the aging degree of the cable insulation layer according to the classification result of the capacitance correction value Among them, when the capacitance correction value is classified as level one, the aging degree of the cable insulation layer is slight aging; when the capacitance correction value is classified as level two, the aging degree of the cable insulation layer is moderate aging; when the capacitance correction value When classified into three levels, the aging degree of the cable insulation layer is severe aging.

[0077] Step 7: According to the judgment result of the aging condition of the cable insulation layer, formulate an early warning strategy for the i-th monitoring node in the topological structure of the cable section to be monitored, specifically as follows:

[0078] When the aging degree of the cable insulation layer at the i-th monitoring node is slight aging, conduct a first-level early warning for the cable insulation;

[0079] When the aging degree of the cable insulation layer at the i-th monitoring node is moderate aging, conduct a second-level early warning for the cable insulation;

[0080] When the aging degree of the cable insulation layer at the i-th monitoring node is severe aging, conduct a third-level early warning for the cable insulation.

[0081] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A cable insulation electric field monitoring and early warning method based on digital twins, characterized in that: include: According to the topological structure of the cable segment to be monitored, a cable mirror digital model is constructed; Obtain the historical data of the influencing factors at the i-th monitoring node in the topological structure of the cable segment to be monitored And the measured historical data of capacitance value measured by FEF sensor in, It is represented as the kth measured value of the jth influencing factor at the i-th monitoring node; It is represented as the kth measured value of the capacitance at the i-th monitoring node; According to the acquired data and Calculate the correction factor k for the dielectric constant ε ; Synchronize the real-time data of the influencing factors at the i-th monitoring node To the cable mirror digital model, according to the correction factor k ε Calculate the corrected capacitance value According to the obtained capacitance correction value The aging condition of the cable insulation layer at the i-th monitoring node in the topological structure of the monitored cable segment is judged.

2. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 1 is characterized in that: Corrected capacitance real-time value The calculation formula is: Where, α is the electrode fork index of the FEF sensor; L is the electrode length; a and b are the interval between electrodes and the width of a single electrode plate, respectively; ε x is the dielectric constant.

3. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 1 is characterized in that: Correction factor k ε The acquisition process includes the following steps: Taking the K times measured values ​​of the influencing factors at any monitoring node q as input and the K times measured values ​​of the corresponding capacitance value as output, a first neural network model is constructed, and the first neural network model is trained. The number of hidden layers of the model is adjusted according to the error between the training result and the actual alarm result until the accuracy is not less than the first expected value, and the kth predicted value of the capacitance value at the qth monitoring node is output through the constructed first neural network model. Wherein, k = 1, 2, ..., K; K is the total amount of data sampling at the qth monitoring node; Based on the predicted value obtained Calculate the first correction coefficient k ε1 , the calculation formula is: In the formula, is the kth measured value of the qth monitoring node The measured value of the corresponding capacitance; Take the kth measured value of the influencing factors at all monitoring nodes As input, the kth measured value of the corresponding capacitance value For output, a second neural network model is constructed, and the second neural network model is trained. According to the training results and the error of the actual alarm results, the number of hidden layers of the model is adjusted until the accuracy is not lower than the second expected value. The kth predicted value of the capacitance value at the i-th monitoring node is output through the constructed second neural network model. Where, i = 1, 2, ..., N; N is the total number of monitoring nodes; Based on the predicted value obtained Calculate the second correction coefficient k ε2 , the calculation formula is: The first correction coefficient k is obtained ε1 and the second correction factor k ε2 Perform weighted average processing to obtain the correction coefficient k of the dielectric constant ε , the calculation formula is: Among them, μ and ν are both ∈ (0,1), and μ+ν=1.

4. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 3 is characterized in that: The calculation formulas of the first expected value and the second expected value are: Among them, E(Y) r represents the rth expected value; N r represents the number of input samples of the rth neural network; f(X mr ) r represents the output function of the rth neural network; X mr represents the mth output sample of the rth neural network, r = 1, 2, where when r = 1, N r =K; when r = 2, N r =N.

5. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 3 is characterized in that: The first neural network model and the second neural network model are both BP neural network models. r The input layer of neurons, q r The input layer of neurons h and s r The hidden layer has three layers of neurons, among which, Expressed as a pair The calculation result is rounded up; h is an integer from 1 to 9.

6. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 1 is characterized in that: The process of judging the aging of the cable insulation layer includes the following steps: Obtain the capacitance correction value C of the i-th monitoring node in the topological structure of the cable segment to be monitored in the initial state and the aging failure state respectively. ib and C ie ; Obtain the capacitance correction value of the cable segment to be monitored during use when When it is determined to be in an aging failure state; when Calculate the capacitance correction value when The capacitance correction value C under aging failure state ie The distance between The calculation formula is: Use distance The sample set is created by the numerical value of , and the mean and standard deviation in the sample set are obtained. The mean and standard deviation are used to standardize the data. The standardization formula is: Where z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data; Use the function to convert the standard parameter interval into Adjust to the range of [0,1] and use the function value of f(k) to correct the capacitance Classification is performed, and the classification mechanism is: when When the capacitance correction value Classification is level one; when When the capacitance correction value Classification is level 2; when When the capacitance correction value Classification is divided into three levels; among them, f(k) min 、f(k) max are the minimum and maximum values ​​of the function f(k) respectively; Corrected value based on capacitance The classification results determine the degree of cable insulation aging, among which, when the capacitance correction value When classified as level 1, the cable insulation layer is slightly aged; when the capacitance correction value is When classified as Level 2, the cable insulation layer is moderately aged; when the capacitance correction value is When classified as level three, the degree of aging of the cable insulation layer is severe.

7. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 6 is characterized in that: The method further comprises the following steps: According to the judgment result of the aging of the cable insulation layer, the early warning strategy at the i-th monitoring node in the topological structure of the cable segment to be monitored is formulated, specifically: When the aging degree of the cable insulation layer at the i-th monitoring node is slightly aged, a first-level cable insulation warning is issued; When the aging degree of the cable insulation layer at the i-th monitoring node is moderate, a second-level cable insulation warning is issued; When the aging degree of the cable insulation layer at the i-th monitoring node is severe, a third-level cable insulation warning is issued.

8. The cable insulation electric field monitoring and early warning method based on digital twin according to claim 1 is characterized in that: The influencing factors include at least one of cable environment temperature, cable environment humidity, electric field strength, and cable thickness.

Images