A multi-loop cable group electromagnetic loss intelligent calculation method and device

Abstract

The present application relates to a kind of multi-loop cable group electromagnetic loss intelligent calculation method and device, belong to power cable operation technical field, method includes: with finite element method to establish the cable group electromagnetic field model including multi-loop, current sample is randomly generated and corresponding cable core and metal sleeve loss are calculated, form current-loss sample set;GWO-RBF-Adaboost Intelligent Prediction Model is constructed, the center point of radial basis function neural network RBF, width and output weight are globally optimized by grey wolf optimization algorithm GWO, and the RBF neural network is used as the base learner of Adaboost, and current-loss sample set is used to train to obtain current-loss mapping relationship model;The current data of multi-loop cable group to be evaluated is input into the GWO-RBF-Adaboost model trained, and the cable core loss and metal sleeve loss of each loop are predicted.The present application realizes the convenient calculation of multi-loop cable group electromagnetic loss by current, and significantly improves the calculation precision of electromagnetic loss.

Description

Technical Field

[0001] This invention relates to the field of power cable operation technology, and in particular to a method and device for intelligent calculation of electromagnetic loss of multi-circuit cable groups. Background Technology

[0002] Accurate assessment of the core temperature and dynamic current-carrying capacity of power cable groups is a crucial supporting technology for emergency loads, transferred loads, and new energy access in modern power systems. Researchers have proposed various thermal circuit models to support convenient and rapid assessment of the dynamic current-carrying capacity of power cable groups. The heat sources in existing thermal circuit models include the electromagnetic losses of the power cable core and metal sheath, as well as the insulation layer losses.

[0003] Insulation layer loss is related to cable voltage and is not affected by adjacent cables; relevant calculation formulas already exist. However, the electromagnetic loss of the cable core and sheath in power cable groups is significantly affected by adjacent cables. Existing methods for calculating the loss of the cable core and sheath in power cable groups include IEC 60287 and numerical calculation methods.

[0004] IEC 60287 only provides loss calculation formulas for simple single-circuit and double-circuit power cables. For tunnels and cable bridges containing more cable groups, the loss calculation formulas for the cable core and metal sheath given in IEC 60287 can only be used to calculate the loss of adjacent circuits, while ignoring the influence of cable circuits that are farther away. Obviously, the calculation results are biased.

[0005] Numerical calculation methods can calculate power cable groups with arbitrary layout and number of loops with high accuracy. However, considering thermoelectric coupling and the fact that existing calculations rely on software tools such as ANSYS / COMSOL / MAGNET / OPERA, they cannot be directly combined with thermal circuit models to calculate the core temperature and dynamic current carrying capacity of power cables in engineering.

[0006] Therefore, it is necessary to explore a convenient and rapid calculation method for electromagnetic loss of multi-circuit cable groups based on current, so as to couple it with the thermal circuit model to directly calculate the core temperature of the power cable, and then use an iterative method to calculate the dynamic current carrying capacity. Summary of the Invention

[0007] Based on the above analysis, the present invention aims to disclose an intelligent calculation method and device for electromagnetic loss of multi-circuit cable groups, thereby solving the problem of electromagnetic loss calculation for multi-circuit cable groups.

[0008] This invention discloses an intelligent calculation method for electromagnetic losses in multi-loop cable groups, comprising:

[0009] Step S1: Establish an electromagnetic field model of a cable group containing multiple loops using the finite element method, randomly generate current samples and calculate the corresponding cable core and metal sheath losses to form a current-loss sample set.

[0010] Step S2: Construct the GWO-RBF-Adaboost intelligent prediction model. Use the Grey Wolf Optimization Algorithm (GWO) to globally optimize the center point, width, and output weights of the Radial Basis Network (RBF). Use the RBF neural network as the base learner of Adaboost and train the current-loss mapping relationship model using the current-loss sample set.

[0011] Step S3: Input the current data of the multi-circuit cable group to be evaluated into the trained GWO-RBF-Adaboost model to predict the core loss and sheath loss of each circuit.

[0012] Furthermore, in step S1, in the established electromagnetic field model of the cable group containing ≥3 loops, the Poisson equation is used for the conductive region and the Laplace equation is used for the non-conductive region, and the boundary condition at infinity is applied. Through multiple randomly generated current input samples, the eddy current loss of the corresponding cable core and metal sheath is calculated to form a current-loss sample set.

[0013] Further, step S1 includes:

[0014] Step S101: Establish vector magnetic potential equations for each region of the cable field, with vector magnetic potential as the independent variable, including the Poisson equation for the conductive region, the Laplace equation for the non-conductive region, and the boundary condition at infinity.

[0015] Step S102: Introduce the Coulomb specification to obtain the finite element matrix equation, calculate the vector magnetic potential of each node, and derive the eddy current density of the cable core region composed of the conductor, insulation layer and metal shielding layer.

[0016] Step S103: Calculate the unit electromagnetic loss; the unit electromagnetic loss includes the loss of the cable core region calculated based on the eddy current density and the source current density, and the loss of the metal sheath region calculated based on the eddy current density.

[0017] Step S104: Randomly generate multiple sets of loop current values, repeat step S103 to calculate the cable core loss and metal sheath loss corresponding to each set of current values ​​as current-loss samples, and form a current-loss sample set.

[0018] Furthermore, the GWO-RBF-Adaboost training process includes:

[0019] Step S201: Read in the current-loss training set;

[0020] Step S202: Initialize the gray wolf population; each wolf corresponds to a set of RBF center, width, and output weights;

[0021] Step S203: Perform iterative optimization;

[0022] In each iteration, an RBF weak learner is generated using the current wolf parameters and the Adaboost prediction error is calculated. The wolf pack position is updated by α, β, and δ wolves with the reciprocal of the error as the fitness. At the same time, Adaboost adjusts the weights of the samples and the weak learner until the iteration or error termination condition is met.

[0023] Step S204: Output the GWO-RBF-Adaboost model corresponding to the optimal wolf parameters.

[0024] Furthermore, the iterative optimization process includes:

[0025] Step S2031: Calculate model error; Use the RBF network parameters corresponding to the current gray wolf position to train the Adaboost ensemble model, and calculate the prediction error on the training set;

[0026] Step S2032: Calculate fitness; Calculate the fitness value of each individual gray wolf based on the model error. The smaller the error, the higher the fitness.

[0027] Step S2033: Determine whether the convergence condition is met. If not, proceed to step S2034; if yes, proceed to step S2035.

[0028] Step S2034: Update the gray wolf's position and return to step S2031 to continue model training;

[0029] Based on the hierarchical hunting mechanism of the gray wolf optimization algorithm, the positions of ω wolf are updated by α, β, and δ wolves, and the RBF network parameters are adjusted accordingly.

[0030] Step S2035: Evaluate the model performance at the current location of the gray wolf, and record the individual errors and the overall prediction error after integration;

[0031] Step S2036 determines whether the number of iterations or the convergence condition has met the requirements; if yes, output the GWO-RBF-Adaboost model corresponding to the optimal wolf parameters; otherwise, proceed to step S2037.

[0032] Step S2037: Adjust sample weights according to the error; The Adaboost mechanism adjusts the sample weights according to the prediction error, so that the subsequent weak learner pays more attention to the samples that are difficult to fit, and then returns to step S2031.

[0033] Furthermore, the update formula for updating the position of wolf ω, guided by α, β, and δ wolves, is as follows:

[0034] ;

[0035] in,

[0036] ;

[0037] ;

[0038] ;

[0039] This is the current position of Gray Wolf ω. This is the update location for Grey Wolf ω; , , Let α, β, and δ represent the current positions of the wolves. , , , , , Let be the synergy coefficient; where,

[0040] ; ; ;

[0041] ; ; ;

[0042] It is a random vector; It decreases linearly from 2 to 0.

[0043] Furthermore, the Adaboost mechanism adjusts sample weights based on prediction error, the process of which includes:

[0044] 1) Calculate the normalized weighted error of the current weak learner;

[0045] ;

[0046] in For the first The weights of each sample;

[0047] ;

[0048] 2) Calculate the ensemble weights of the weak learner;

[0049] Weak learner weights , The learning rate;

[0050] 3) Update sample weights;

[0051] ;

[0052] And for all Renormalization, This allows for greater focus on samples that are difficult to fit in the next iteration.

[0053] Furthermore, when constructing the electromagnetic field model of the cable group, the cable core and metal sleeve are set as single coils, and each loop cable core is input with three-phase AC currents that are 120 degrees out of phase. According to the cable grounding method, when the grounding is single-end, the current of the metal sleeve is set to 0, and when the grounding is double-end, the metal sleeve is not set separately.

[0054] Furthermore, the predicted core loss and sheath loss of each circuit in step S3 are used as the heat source for the thermal circuit model to calculate the cable core temperature, and further to evaluate the dynamic current carrying capacity and provide early warning of the operating status.

[0055] This invention also discloses an intelligent calculation device for electromagnetic losses in multi-circuit cable groups, used to implement the intelligent calculation method for electromagnetic losses in multi-circuit cable groups as described above, comprising:

[0056] The sample set construction module is used to establish an electromagnetic field model of a cable group containing multiple loops using the finite element method, randomly generate current samples and calculate the corresponding cable core and metal sheath losses to form a current-loss sample set.

[0057] The model training module is used to construct the GWO-RBF-Adaboost intelligent prediction model. The center point, width and output weight of the radial basis function neural network RBF are globally optimized using the Grey Wolf Optimization Algorithm (GWO). The RBF neural network is used as the base learner of Adaboost, and the current-loss mapping relationship model is obtained by training with the current-loss sample set.

[0058] The loss calculation module is used to input the current data of the multi-circuit cable group to be evaluated into the trained GWO-RBF-Adaboost model to predict the core loss and sheath loss of each circuit.

[0059] This invention can achieve one of the following beneficial effects:

[0060] This invention discloses an intelligent calculation method and device for electromagnetic losses in multi-circuit cable groups, enabling convenient and rapid calculation of electromagnetic losses in multi-circuit cable groups. The established GWO-RBF-Adaboost model, through the synergistic effect of GWO, RBF, and Adaboost, significantly improves the model's prediction accuracy, generalization ability, and robustness. The solution greatly improves the automation and intelligence level of cable loss calculation, reduces interference from human factors, and improves calculation accuracy. It can be directly combined with thermal circuit models in engineering to evaluate cable core temperature in real time and dynamically determine current-carrying capacity. Attached Figure Description

[0061] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0062] Figure 1 This is a flowchart of the intelligent calculation method for electromagnetic loss of multi-loop cable groups in an embodiment of the present invention;

[0063] Figure 2 This is a flowchart illustrating the model training and testing process in an embodiment of the present invention.

[0064] Figure 3 This is a schematic diagram showing the connection of the intelligent computing device for electromagnetic loss of multi-loop cable groups in an embodiment of the present invention.

[0065] Figure 4 This is a schematic diagram of the circuit laying of 8 single-circuit single-core cables (circuit 1 to circuit 8) in an embodiment of the present invention;

[0066] Figures 5a-5h The figures show the electromagnetic loss prediction error results for the eight single-loop single-core cables (loop 1 to loop 8) in the embodiments of the present invention. Detailed Implementation

[0067] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and, together with the embodiments of the present invention, serve to illustrate the principles of the present invention.

[0068] Example 1

[0069] One embodiment of the present invention discloses an intelligent calculation method for electromagnetic losses in multi-loop cable groups, such as... Figure 1 As shown, it includes:

[0070] Step S1: Establish an electromagnetic field model of a cable group containing multiple loops using the finite element method, randomly generate current samples and calculate the corresponding cable core and metal sheath losses to form a current-loss sample set.

[0071] Step S2: Construct the GWO-RBF-Adaboost intelligent prediction model. Use the Grey Wolf Optimization Algorithm (GWO) to globally optimize the center point, width, and output weights of the Radial Basis Network (RBF). Use the RBF neural network as the base learner of Adaboost and train the current-loss mapping relationship model using the current-loss sample set.

[0072] Step S3: Input the current data of the multi-circuit cable group to be evaluated into the trained GWO-RBF-Adaboost model to predict the core loss and sheath loss of each circuit.

[0073] Specifically, in step S1, the electromagnetic field model of the cable group containing ≥3 loops is established. The Poisson equation is used for the conductive region and the Laplace equation is used for the non-conductive region. The boundary condition at infinity is applied. The eddy current loss of the corresponding cable core and metal sheath is calculated by randomly generating multiple sets of current input samples, forming a current-loss sample set.

[0074] Preferably, when building the electromagnetic field model of the cable group, the cable core and the metal sleeve are set as single coils, and each loop cable core is input with three-phase AC current with a phase difference of 120 degrees. According to the cable grounding method, when single-end grounding, the current of the metal sleeve is set to 0, and when double-end grounding, the metal sleeve is not set separately.

[0075] More specifically, step S1 includes:

[0076] Step S101: Establish vector magnetic potential equations for each region of the cable field, with vector magnetic potential as the independent variable, including the Poisson equation for the conductive region, the Laplace equation for the non-conductive region, and the boundary condition at infinity.

[0077] Specifically, the vector magnetic potential equations for each region of the cable field are as follows:

[0078] ;

[0079] In the formula, is the Laplace operator, representing the second derivative in space; The imaginary unit; Angular frequency; Electrical conductivity; is the magnetic permeability.

[0080] Step S102: Introduce the Coulomb specification to obtain the finite element matrix equation, calculate the vector magnetic potential of each node, and derive the eddy current density of the cable core region composed of the conductor, insulation layer and metal shielding layer.

[0081] The formula for calculating the eddy current density in the cable core region is as follows:

[0082] ;

[0083] In the formula, In three-phase alternating current, the first The vector magnetic potential of the phase.

[0084] Step S103: Calculate the unit electromagnetic loss; the unit electromagnetic loss includes the loss of the cable core region calculated based on the eddy current density and the source current density, and the loss of the metal sheath region calculated based on the eddy current density.

[0085] The losses in the cable core region are calculated from the eddy current density and the source current density:

[0086] ;

[0087] In the formula, , These are the source current density and eddy current density, respectively. The area of ​​the cable core region;

[0088] Losses in the metal sleeve region calculated based on eddy current density:

[0089] ;

[0090] In the formula, This represents the area of ​​the metal casing region.

[0091] Step S104: Randomly generate multiple sets of loop current values, repeat step S103 to calculate the cable core loss and metal sheath loss corresponding to each set of current values ​​as current-loss samples, and form a current-loss sample set.

[0092] Specifically, the GWO-RBF-Adaboost training process in step S2 includes:

[0093] Step S201: Read in the current-loss training set;

[0094] Step S202: Initialize the gray wolf population; each wolf corresponds to a set of RBF center, width, and output weights;

[0095] Step S203: Perform iterative optimization;

[0096] In each iteration, an RBF weak learner is generated using the current wolf parameters and the Adaboost prediction error is calculated. The wolf pack position is updated by α, β, and δ wolves with the reciprocal of the error as the fitness. At the same time, Adaboost adjusts the weights of the samples and the weak learner until the iteration or error termination condition is met.

[0097] Step S204: Output the GWO-RBF-Adaboost model corresponding to the optimal wolf parameters.

[0098] Specifically, the iterative optimization process in step S203 includes:

[0099] Step S2031: Calculate model error; Use the RBF network parameters corresponding to the current gray wolf position to train the Adaboost ensemble model, and calculate the prediction error on the training set;

[0100] Step S2032: Calculate fitness; Calculate the fitness value of each gray wolf individual based on the model error. Generally, the smaller the prediction error, the higher the fitness.

[0101] Step S2033: Determine whether the convergence condition is met. If not, proceed to step S2034; if yes, proceed to step S2035.

[0102] Step S2034: Update the gray wolf's position and return to step S2031 to continue model training;

[0103] Based on the hierarchical hunting mechanism of the gray wolf optimization algorithm, the positions of ω wolf are updated by α, β, and δ wolves, and the RBF network parameters are adjusted accordingly.

[0104] Step S2035: Evaluate the model performance at the current location of the gray wolf, and record the individual errors and the overall prediction error after integration;

[0105] Step S2036 determines whether the number of iterations or the convergence condition has met the requirements; if yes, output the GWO-RBF-Adaboost model corresponding to the optimal wolf parameters; otherwise, proceed to step S2037.

[0106] Step S2037: Adjust sample weights according to the error; The Adaboost mechanism adjusts the sample weights according to the prediction error, so that the subsequent weak learner pays more attention to the samples that are difficult to fit, and then returns to step S2031.

[0107] More specifically, the update formula for updating the position of wolf ω, guided by α, β, and δ wolves, is as follows:

[0108] ;

[0109] in,

[0110] ;

[0111] ;

[0112] ;

[0113] This is the current position of Gray Wolf ω. This is the update location for Grey Wolf ω; , , Let α, β, and δ represent the current positions of the wolves. , , , , , Let be the synergy coefficient; where,

[0114] ; ; ;

[0115] ; ; ;

[0116] It is a random vector; It decreases linearly from 2 to 0.

[0117] The Grey Wolf Optimization Algorithm is used to determine the center point, the width of the radial basis function, and the output weight matrix of the RBF neural network, and to find the optimal solution.

[0118] RBF neural networks have the characteristic that only a few connection weights in a local domain of the input space affect the output, thus they have the advantages of fast learning speed, good convergence, simple structure, and no tendency to get stuck in local extrema.

[0119] Furthermore, the RBF network parameters include: hidden layer center vector, the dimension of which is equal to the number of input current loops; expansion constant, which can be a single scalar or an independent scalar for each center; output weight matrix, the dimension of which is the number of centers × the number of output loss categories; and cable core loss and metal sheath loss are output separately.

[0120] AdaBoost is a classic ensemble learning algorithm. Its core lies in dynamically adjusting sample weights to optimize sample distribution. This means increasing the weight of samples that were misclassified in previous learners, combining multiple weak learners into a strong learner, and through iterative training, making subsequent weak learners pay more attention to previously misclassified samples, thereby improving overall performance.

[0121] Furthermore, the Adaboost mechanism adjusts sample weights based on prediction error, the process of which includes:

[0122] 1) Calculate the normalized weighted error of the current weak learner. ;

[0123] ;

[0124] in For the first The weights of each sample;

[0125] ;

[0126] 2) Calculate the ensemble weights of the weak learner. ;

[0127] ;

[0128] in, The learning rate;

[0129] 3) Update sample weights ;

[0130] ;

[0131] And for all Renormalization, This allows for greater focus on samples that are difficult to fit in the next iteration.

[0132] The specific model training and testing process flow in this embodiment is as follows: Figure 2 As shown.

[0133] In step S3, the current data of the multi-circuit cable group to be evaluated is input into the trained GWO-RBF-Adaboost model to predict the core loss and sheath loss of each circuit.

[0134] Furthermore, the predicted core loss and sheath loss of each circuit are used as heat sources for the thermal circuit model to calculate the cable core temperature, and to further evaluate the dynamic current carrying capacity and provide early warning of operating status.

[0135] In summary, the intelligent calculation method and device for electromagnetic losses of multi-circuit cable groups in this embodiment realizes convenient and rapid calculation of electromagnetic losses of multi-circuit cable groups. The established GWO-RBF-Adaboost model, through the synergistic effect of GWO, RBF and Adaboost, significantly improves the prediction accuracy, generalization ability and robustness of the model. The solution greatly improves the automation and intelligence level of cable loss calculation and reduces the interference of human factors. It can be directly combined with the thermal circuit model in engineering to evaluate the cable core temperature in real time and dynamically determine the current carrying capacity.

[0136] Example 2

[0137] This embodiment discloses an intelligent calculation device for electromagnetic losses in multi-circuit cable groups, used to implement the intelligent calculation method for electromagnetic losses in multi-circuit cable groups as described in Embodiment 1. Figure 3 As shown, it includes:

[0138] The sample set construction module is used to establish an electromagnetic field model of a cable group containing multiple loops using the finite element method, randomly generate current samples and calculate the corresponding cable core and metal sheath losses to form a current-loss sample set.

[0139] The model training module is used to construct the GWO-RBF-Adaboost intelligent prediction model. The center point, width and output weight of the radial basis function neural network RBF are globally optimized using the Grey Wolf Optimization Algorithm (GWO). The RBF neural network is used as the base learner of Adaboost, and the current-loss mapping relationship model is obtained by training with the current-loss sample set.

[0140] The loss calculation module is used to input the current data of the multi-circuit cable group to be evaluated into the trained GWO-RBF-Adaboost model to predict the core loss and sheath loss of each circuit.

[0141] The more specific technical details and beneficial effects in this embodiment are the same as those disclosed in Embodiment 1. Please refer to them for details, and they will not be repeated here.

[0142] Example 3

[0143] This embodiment provides a specific example of an intelligent calculation method for electromagnetic losses in multi-loop cable groups to verify the effectiveness of the method.

[0144] In this embodiment, the implementation process of the method includes:

[0145] A finite element electromagnetic field model of the cable group was constructed, with the cable core and metal sheath set as single coils. Each loop cable core was input with three-phase AC currents that were 120 degrees out of phase. According to the cable grounding method, when the grounding was single-end, the current of the metal sheath was set to 0, and when the grounding was double-end, the metal sheath was not set separately.

[0146] 149 sets of input currents were randomly generated, and 149 sets of cable core loss and metal sheath loss sample data were calculated to form a current-loss sample set.

[0147] Eighty current-loss samples were selected to form a training set, and the GWO-RBF-Adaboost model was trained to form a defined loss calculation model based on current.

[0148] A test set of 69 current-loss samples was selected to verify the effectiveness and correctness of the GWO-RBF-Adaboost model.

[0149] Repeatedly train and test the model to obtain the final model that calculates the loss based on the current.

[0150] Based on the obtained model, the loss calculation of multi-circuit cable groups in cable operation and maintenance is applied.

[0151] In a specific example model, a cable bridge contains 8 single-core cables, and there is a strong mutual influence between the cables. The schematic diagram of the 8-circuit single-core cable laying is shown below. Figure 4 As shown, the electromagnetic loss of an 8-circuit single-core cable is intelligently calculated here.

[0152] 149 sets of input currents were randomly generated, as shown in Table 1. The corresponding electromagnetic losses were calculated using the finite element method, as shown in Tables 2-7. It should be noted that the first 10 data points are given in each table for illustrative purposes.

[0153] Table 1 Input Current Samples (A)

[0154]

[0155] Table 2. Sample 1 of cable core loss results (W / m)

[0156]

[0157] Table 3. Sample 2 of cable core loss results (W / m)

[0158]

[0159] Table 4. Sample results of cable core loss - 3 (W / m)

[0160]

[0161] Table 5 Results of metal sheath samples - 1 (W / m)

[0162]

[0163] Table 6. Sample 2 of metal sheath loss results (W / m)

[0164]

[0165] Table 7 Sample 3 of metal sheath loss results (W / m)

[0166]

[0167] Eighty sets of current and loss data were selected as training samples to obtain a current-loss calculation model, and the remaining 69 sets of current-loss data were used as test samples. The error of the electromagnetic loss result of the 8-loop single-core cable calculated from the 69 sets of test samples is as follows: Figures 5a-5h As shown, Figures 5a-5h Corresponding to loops 1 to 8 respectively, the maximum error in each diagram does not exceed 0.25W / m.

[0168] Through testing and verification, the established GWO-RBF-Adaboost model significantly improves the model's prediction accuracy, generalization ability, and robustness through the synergistic effect of GWO, RBF, and Adaboost.

[0169] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-loop cable group electromagnetic loss intelligent calculation method, characterized in that, Comprise: Step S1, the finite element method is established including the cable group electromagnetic field model of multi-loop, random current sample is generated and the corresponding cable core and metal sleeve loss is calculated, and the current-loss sample set is formed; The unit electromagnetic loss includes the loss of the cable core area solved according to the eddy current density and source current density and the loss of the metal sleeve area solved according to the eddy current density; Step S2, the GWO-RBF-Adaboost intelligent prediction model is constructed, the center point, width and output weight of the radial basis function neural network RBF are globally optimized by the grey wolf optimization algorithm GWO, and the RBF neural network is used as the base learner of Adaboost, and the current-loss mapping relationship model is obtained by training the current-loss sample set; Step S3, the multi-loop cable group current data to be evaluated is input into the GWO-RBF-Adaboost model trained, and the core loss and metal sleeve loss of each loop are predicted.

2. The multi-loop cable group electromagnetic loss intelligent calculation method according to claim 1, wherein in step S1, in the cable group electromagnetic field model including ≥3 loops, Poisson equation is used for the conductive area, Laplace equation is used for the non-conductive area, and infinite boundary conditions are applied, and the current-loss sample set is formed by calculating the corresponding eddy current loss of the cable core and the metal sleeve through a plurality of groups of randomly generated current input samples.

3. The multi-loop cable group electromagnetic loss intelligent calculation method according to claim 2, wherein step S1 comprises: Step S101, the vector magnetic potential equation of each region of the cable field is established, taking the vector magnetic potential as the independent variable, including the Poisson equation of the conductive area, the Laplace equation of the non-conductive area and the infinite boundary condition; Step S102, the Coulomb norm is introduced to obtain the finite element matrix equation, the vector magnetic potential of each node is solved, and the eddy current density of the cable core area composed of the core conductor, the insulating layer and the metal shielding layer is derived; Step S103, the unit electromagnetic loss is calculated; the unit electromagnetic loss includes the loss of the cable core area solved according to the eddy current density and source current density and the loss of the metal sleeve area solved according to the eddy current density; Step S104, a plurality of groups of loop current values are randomly generated, and the cable core loss and metal sleeve loss corresponding to each group of current values are calculated as current-loss samples by repeating step S103, to form a current-loss sample set.

4. The multi-loop cable group electromagnetic loss intelligent calculation method according to claim 1, wherein the GWO-RBF-Adaboost training process comprises: Step S201, read the current-loss training set; Step S202, initialize the grey wolf population; each wolf corresponds to a set of RBF center points, widths and output weights; Step S203, iterative optimization is performed; In each iteration, the RBF weak learner is generated by the current wolf parameters and the Adaboost prediction error is calculated, the wolf population position is updated by the error reciprocal as fitness, and the Adaboost adjusts the sample and weak learner weight, until the iteration or error termination condition is reached. ​ ​ ​ Step S204, output the GWO-RBF-Adaboost model corresponding to the optimal wolf parameter.

5. The multi-circuit cable group electromagnetic loss intelligent calculation method according to claim 4, wherein, The iterative optimization process comprises: Step S2031, calculating the model error; using the RBF network parameters corresponding to the current gray wolf position, training the Adaboost integrated model, and calculating the prediction error on the training set; Step S2032, calculating the fitness; calculating the fitness value of each gray wolf individual according to the model error, and the smaller the error, the higher the fitness; Step S2033, judging whether the convergence condition is met; no, then entering step S2034; yes, then performing step S2035; Step S2034, updating the gray wolf position and returning to step S2031 to continue model training; According to the hierarchical hunting mechanism of the gray wolf optimization algorithm, the positions of the omega wolves are updated by the alpha, beta and delta wolves to adjust the RBF network parameters; Step S2035, evaluating the model performance under the current gray wolf position and recording the individual error and the overall prediction error after integration; Step S2036, judging whether the iteration number or the convergence condition meets the requirements; yes, outputting the GWO-RBF-Adaboost model corresponding to the optimal wolf parameter; otherwise, entering step S2037; Step S2037, adjusting the sample weight according to the error; the Adaboost mechanism adjusts the sample weight according to the prediction error, so that the subsequent weak learners pay more attention to the samples that are difficult to fit, and then returns to step S2031.

6. The multi-circuit cable group electromagnetic loss intelligent calculation method according to claim 5, wherein, The updating formula for updating the positions of the omega wolves guided by the alpha, beta and delta wolves is: ； wherein, ； ； ； is the current position of the gray wolf ω, is the updated position of the gray wolf ω; , , is the current position of the alpha, beta, and delta wolves; , , , , , is the coefficient of coordination; wherein, ； ； ； ； ； ； is a random vector; decreases linearly from 2 to 0.

7. The multi-circuit cable group electromagnetic loss intelligent calculation method according to claim 6, wherein, The Adaboost mechanism adjusts the sample weight according to the prediction error, and the process comprises: 1) calculating the normalized weighted error of the current weak learner; ； wherein is the weight of the th sample; ； 2) calculating the integrated weight of the weak learner; weak learner weights , is the learning rate; 3) updating the sample weight; ； and all re-normalize, so that to focus more on samples that are difficult to fit in the next iteration.

8. The multi-circuit cable group electromagnetic loss intelligent calculation method according to any one of claims 1-7, wherein, When building the electromagnetic field model of the cable group, the cable core and the metal sleeve are set as single coils, and each circuit cable core is input with three-phase alternating current with a phase difference of 120 degrees; according to the cable grounding mode, when single-ended grounding, the metal sleeve is set as a current of 0, and when double-ended grounding, the metal sleeve is not set separately.

9. The multi-circuit cable group electromagnetic loss intelligent calculation method according to claim 8, wherein, The predicted core loss and metal sleeve loss of each circuit in step S3 are used as heat sources of the thermal model to calculate the cable core temperature and further evaluate the dynamic ampacity and perform operation state warning.

10. A multi-circuit cable bundle electromagnetic loss intelligent computing device for implementing the multi-circuit cable bundle electromagnetic loss intelligent computing method according to any one of claims 1-9, characterized in that, Comprise: The sample set construction module is used to establish an electromagnetic field model of a cable group comprising multiple circuits by finite element method, randomly generate current samples and calculate the corresponding core and metal sleeve losses to form a current-loss sample set; The model training module is configured to construct a GWO-RBF-Adaboost intelligent prediction model, to globally optimize the center point, width and output weight of a radial basis function neural network (RBF) by using a grey wolf optimization algorithm (GWO), and to use the RBF neural network as a base learner of Adaboost, so as to train a current-loss mapping relationship model by using a current-loss sample set. The loss calculation module is configured to input the current data of the to-be-evaluated multi-loop cable group into the trained GWO-RBF-Adaboost model, and to predict the loss of each loop cable core and the loss of the metal sleeve.

Images