Direct buried cable core temperature prediction method, device, terminal and storage medium

Abstract

The present invention is applicable to the field of data processing technology, and provides a method, device, terminal and storage medium for predicting the cable core temperature of a direct buried cable. The method includes: establishing a finite element simulation model of a target direct buried cable; applying a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, and obtaining the simulated temperature data of the target direct buried cable under the varying current carrying capacity, which is recorded as the first training set; training the long short-term memory model optimized by the Gray Wolf according to the first training set, and obtaining a cable core temperature prediction model for the target direct buried cable; obtaining a cable core temperature prediction value of the target direct buried cable according to the measured cable core temperature data of the target direct buried cable and the cable core temperature prediction model. The present invention can obtain a more accurate cable core temperature prediction value of the target direct buried cable, and thus reflect the actual cable core temperature of the target direct buried cable in real time.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, terminal and storage medium for predicting the temperature of a direct-buried cable core. Background Art

[0002] With the increasing power load, direct buried cables account for an increasing proportion in distribution network lines. During use, the insulation aging state of direct buried cables is closely related to the cable core temperature. If the cable is operated under high load for a long time, the cable core temperature will remain high, thereby accelerating the aging of the cable insulation; if the cable is operated under low load for a long time, the cable core temperature is not much different from the ambient temperature of the cable, which has little effect on the cable insulation aging and helps to increase the service life of the cable. Therefore, it is very important to accurately obtain the cable core temperature.

[0003] At present, the surface temperature of the cable can usually be monitored by sensors, but it cannot accurately reflect the temperature of the cable core. Even if optical fibers can be added to some cables for temperature measurement, there are still problems such as large errors and high costs. The cable core temperature is obtained by simulating the simulation model. On the one hand, the process of building the simulation model is complicated. On the other hand, since the cable core temperature is time-varying data, the cable core temperature obtained by the simulation model is difficult to reflect the real cable core temperature of the direct buried cable in real time. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, terminal and storage medium for predicting the cable core temperature of a direct buried cable, so as to solve the problem that it is currently difficult to accurately obtain the cable core temperature of the direct buried cable.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting the temperature of a direct buried cable core, comprising:

[0006] Establish a finite element simulation model of the target direct buried cable;

[0007] Applying varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, obtaining simulation temperature data of the target direct buried cable under varying current carrying capacity, which is recorded as a first training set;

[0008] The long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable;

[0009] According to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model, a predicted value of the cable core temperature of the target direct buried cable is obtained.

[0010] In a possible implementation, the method for predicting the temperature of a direct buried cable core further includes:

[0011] According to the finite element simulation model, calculating the stable current carrying capacity of the target direct buried cable under different soil thermal resistance coefficients;

[0012] Applying the stable current carrying capacity to the finite element simulation model to obtain simulation temperature data of the target direct buried cable under the stable current carrying capacity, which is recorded as a second training set;

[0013] The long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable, including:

[0014] Divide each day into a load fluctuation period and a load stable period;

[0015] The long short-term memory model optimized by Gray Wolf is trained in the load fluctuation time period according to the first training set, and the long short-term memory model optimized by Gray Wolf is trained in the load stability time period according to the second training set to obtain the cable core temperature prediction model of the target direct buried cable.

[0016] In a possible implementation, dividing each day into a load fluctuation time period and a load stability time period includes:

[0017] Determine the load fluctuation rate in each time period of each day according to different typical daily loads in the area where the target direct buried cable is located;

[0018] Determine the time period when the load fluctuation rate is less than the set fluctuation threshold as the daily load stable time period;

[0019] The time period in which the load fluctuation rate is greater than or equal to the set fluctuation threshold is determined as the load fluctuation time period of each day.

[0020] In a possible implementation, the method for predicting the temperature of a direct buried cable core further includes:

[0021] Acquire temperature data of different typical days in the area where the target direct buried cable is located, recorded as a third training set;

[0022] The long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable, including:

[0023] The long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain a first cable core temperature prediction model of the target direct buried cable;

[0024] The Gray Wolf optimized long short-term memory model is trained according to the first training set and the third training set to obtain a second cable core temperature prediction model of the target direct buried cable;

[0025] A cable core temperature prediction model of the target direct buried cable is obtained according to the first cable core temperature prediction model and the second cable core temperature prediction model.

[0026] In a possible implementation, obtaining the cable core temperature prediction model of the target direct buried cable according to the first cable core temperature prediction model and the second cable core temperature prediction model includes:

[0027] Obtaining correlation coefficients between the temperature data of different typical days and corresponding loads of different typical days;

[0028] If the correlation coefficient is greater than a set correlation threshold, the second cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day;

[0029] If the correlation coefficient is less than or equal to the set correlation threshold, the first cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day.

[0030] In a possible implementation, obtaining a predicted value of the cable core temperature of the target direct buried cable according to the measured cable core temperature data of the target direct buried cable and the cable core temperature prediction model includes:

[0031] Incrementally training the cable core temperature prediction model according to the measured data of the cable core temperature of the target direct buried cable to obtain a revised cable core temperature prediction model;

[0032] The cable core temperature prediction value of the target direct buried cable is obtained by performing prediction according to the modified cable core temperature prediction model.

[0033] In a possible implementation, the lower boundary of the finite element simulation model is a first-type boundary condition, and the first-type boundary condition is:

[0034] ;

[0035] Among them, Γ represents the object boundary, represents the known wall temperature, represents a known wall temperature function;

[0036] The left and right boundaries of the finite element simulation model are the second type of boundary conditions, and the second type of boundary conditions are:

[0037] ;

[0038] in, represents the known heat flux density, represents the normal direction of the boundary, represents the temperature in the normal direction, represents a known heat flux density function;

[0039] The upper boundary of the soil in the finite element simulation model is the third type of boundary condition, and the third type of boundary condition is:

[0040] ;

[0041] in, represents the heat transfer coefficient of the object surface, Indicates the temperature of the surrounding fluid.

[0042] In a second aspect, an embodiment of the present invention provides a device for predicting the temperature of a direct buried cable core, comprising:

[0043] A modeling module, used to establish a finite element simulation model of the target direct buried cable;

[0044] A simulation module, used for applying a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, and obtaining simulation temperature data of the target direct buried cable under the varying current carrying capacity, which is recorded as a first training set;

[0045] A training module, used for training the long short-term memory model optimized by the gray wolf according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable;

[0046] The prediction module is used to obtain the predicted value of the cable core temperature of the target direct buried cable according to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model.

[0047] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method described in the first aspect or any one of the first aspects.

[0048] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any one of the first aspects are implemented.

[0049] The embodiment of the present invention provides a method, device, terminal and storage medium for predicting the cable core temperature of a direct buried cable. By establishing a finite element simulation model of a target direct buried cable, and applying a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, the simulation temperature data of the target direct buried cable under the varying current carrying capacity is obtained, which is recorded as the first training set. The simulation temperature data of the target direct buried cable under the varying current carrying capacity can be obtained. On this basis, the long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain a cable core temperature prediction model for the target direct buried cable. The accuracy of the prediction of time-varying data by the long short-term memory model optimized by the Gray Wolf can be used to obtain a more accurate cable core temperature prediction model. Therefore, according to the measured cable core temperature data of the target direct buried cable and the cable core temperature prediction model, a more accurate cable core temperature prediction value of the target direct buried cable can be obtained, thereby reflecting the actual cable core temperature of the target direct buried cable in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 It is a flow chart of the implementation of the direct buried cable core temperature prediction method provided by the embodiment of the present invention;

[0052] Figure 2 It is a schematic diagram of a VV22-0.6 / 1kV-3×6mm2 power cable provided in an embodiment of the present invention;

[0053] Figure 3 It is a schematic diagram of the laying model of the VV22-0.6 / 1kV-3×6mm2 power cable provided in an embodiment of the present invention;

[0054] Figure 4 It is a schematic diagram of a calculated value curve and an IEC standard value curve of a simulation model provided by an embodiment of the present invention;

[0055] Figure 5 Schematic diagram of a relative error curve between a calculated value of a simulation model provided by an embodiment of the present invention and an IEC standard value;

[0056] Figure 6 It is a schematic diagram of a typical daily load curve of a certain area provided by an embodiment of the present invention;

[0057] Figure 7is a schematic diagram of simulated temperature data obtained after applying a variable current carrying capacity to a finite element simulation model according to a typical daily load provided by an embodiment of the present invention;

[0058] Figure 8 Schematic diagram of the model structure of the GWO-LSTM model provided in an embodiment of the present invention;

[0059] Fig. 9 is a schematic diagram for comparing prediction results of training sets provided by an embodiment of the present invention;

[0060] Fig.10 is a schematic diagram for comparing prediction results of a test set provided by an embodiment of the present invention;

[0061] Fig.11 is a schematic diagram of prediction error of a test set provided by an embodiment of the present invention;

[0062] Fig.12 is a schematic diagram of simulated temperature data obtained after applying the maximum current carrying capacity to the finite element simulation model provided by an embodiment of the present invention;

[0063] Fig.13 It is a schematic structural diagram of a direct buried cable core temperature prediction device provided by an embodiment of the present invention;

[0064] Fig.14 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0066] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0067] See also Figure 1 , which shows a flow chart of the implementation of the direct buried cable core temperature prediction method provided by an embodiment of the present invention, which is described in detail as follows:

[0068] In step 101, a finite element simulation model of a target direct buried cable is established.

[0069] In this embodiment, considering that the physical field state of the environment in which the direct buried cable is located is relatively complex during actual operation, many environmental parameters are simplified when calculating the current carrying capacity of the direct buried cable by the International Electrotechnical Commission (IEC) standard. In complex environmental conditions, there will be certain errors when calculating the current carrying capacity of the direct buried cable by analytical calculation, which is not conducive to fully utilizing the power transmission capacity of the power cable. Therefore, a finite element simulation model of the direct buried cable is built through finite element calculation software such as COMSOL, and the operating conditions of the direct buried power cable in the actual environment are simulated. Finite element simulation calculations are performed, and on the basis of ensuring the accuracy of the simulation model, the simulation data of the simulation model is used to provide a data basis for subsequent cable core temperature prediction.

[0070] For example, the establishment process of the finite element simulation model is described by taking the establishment of the simulation model of the VV22-0.6 / 1kV-3×6mm2 power cable as an example:

[0071] First, a multiphysics analysis of the direct buried cable is performed:

[0072] The COMSOL finite element analysis software was used to analyze and study the VV22-0.6 / 1kV-3×6mm2 power cable to determine the physical fields with coupling relationships of the direct buried cable:

[0073] (1) Direct buried cables generate losses due to power supply, which increases the temperature of the cable core, thereby increasing the temperature of the soil. The soil is in direct contact with the air and dissipates heat by convection. Therefore, the coupling of the flow field and the temperature field is considered when establishing the finite element simulation model of the direct buried cable.

[0074] (2) The soil and air contain a certain amount of moisture. The soil humidity is affected by the air humidity. When the air humidity is high, the soil evaporation is small and the soil humidity is high. On the contrary, when the air humidity is low, the soil humidity is low. Therefore, the coupling of the flow field and the moisture field is considered when establishing the finite element simulation model of the direct buried cable.

[0075] (3) In the soil covering the direct buried cable, the coupling relationship between the temperature field and the moisture field is relatively close. The change of the temperature field will affect the rate and direction of moisture diffusion. At the same time, the diffusion of moisture will also bring out some heat, causing the temperature field to change. Therefore, the coupling of the temperature field and the moisture field is considered when establishing the finite element simulation model of the direct buried cable.

[0076] (4) When the direct buried cable conductor is powered, it will generate losses and heat up, which will increase the temperature of the entire cable area. The three-phase cable will increase losses due to the proximity effect and skin effect under AC. Temperature changes will also affect the resistivity and other parameters of the conductor. Therefore, the coupling of electromagnetic field and temperature field is considered when establishing the finite element simulation model of the direct buried cable.

[0077] Therefore, when establishing the finite element simulation model of the direct buried cable, the four-field coupling model of flow field and temperature field coupling, flow field and moisture field coupling, temperature field and moisture field coupling, and electromagnetic field and temperature field coupling is considered. The four-field coupling model is close to the actual environment of the direct buried cable laying to a greater extent, and the soil thermal conductivity and ambient temperature data are combined to obtain the precise value of the current carrying capacity of the direct buried cable. The calculation results of the current carrying capacity of the IEC standard are compared and analyzed to verify the accuracy of the multi-physical field coupling model. The finite element simulation model of the direct buried cable is constructed on the basis of ensuring accuracy.

[0078] Secondly, the finite element simulation model of the direct buried cable is constructed:

[0079] This embodiment is to construct a finite element simulation model of a VV22-0.6 / 1kV-3×6mm2 power cable. The structure of each layer of the cable is as follows: Figure 2 As shown, Figure 2 The various layers of the VV22-0.6 / 1kV-3×6mm2 power cable are conductor layer, insulation layer, filling layer, inner sheath, armor layer and outer sheath from inside to outside. The thickness of each layer of the power cable is shown in Table 1:

[0080] Table 1 Structural parameters of VV22-0.6 / 1kV-3×6mm2 power cable

[0081]

[0082] On this basis, the cable laying model can be established as follows: Figure 3 As shown, sand can be laid around the cable and a cement protection plate can be set above the cable. The soil in the environment where the cable is located can be divided into two parts: native soil and backfill soil. The laying conditions comply with GB 50217-2018 standards.

[0083] For example, Figure 3 The air can be 3000mm high and 20000mm wide. The distance from the cable axis to the ground surface can be 800mm. The sand can be 500mm wide and 250mm high. The concrete protection plate can be 100mm high and 150mm wide. The backfill can be 500mm wide and 1000mm deep. The native soil can be 20000mm wide and 10000mm deep.

[0084] Then, set the boundary conditions of the finite element simulation model of the direct buried cable:

[0085] Among them, the physical fields of the environment in which the direct buried cable is located include moisture field, flow field, electromagnetic field and temperature field. In the moisture field calculation, the moisture transfer flux between the outer surface of the cable and the surrounding boundaries of the soil can be defined as zero, and the gas-liquid conversion of moisture can be ignored. In the flow field calculation, the upper boundary and the left and right boundaries of the air domain can be defined as open boundaries, and the lower boundary is in contact with the soil for convective heat transfer. In the electromagnetic field calculation, only the magnetic field changes in the cable can be considered, that is, the magnetic flux on the outer surface of the cable is zero.

[0086] Exemplarily, the lower boundary of the finite element simulation model may be a first-class boundary condition, which specifies the temperature value on the boundary, including a given constant temperature value or a coordinate function. The first-class boundary condition may be as shown in the following formula:

[0087] ;

[0088] Among them, Γ represents the object boundary, represents the known wall temperature, represents a known wall temperature function;

[0089] The left and right boundaries of the finite element simulation model can be second-class boundary conditions, which specify the specific heat flux density value on the boundary or the coordinate function of the given heat flux density. The second-class boundary condition can be shown as follows, defining the heat flux density of the left and right boundaries as zero:

[0090] ;

[0091] in, represents the known heat flux density, represents the normal direction of the boundary, represents the temperature in the normal direction, represents a known heat flux density function;

[0092] The upper boundary of the soil in the finite element simulation model can be a third-type boundary condition, which specifies the surface heat transfer coefficient between the object on the boundary and the surrounding fluid and the temperature of the surrounding fluid. The third-type boundary condition can be shown as follows. In this embodiment, the heat transfer method is defined as natural convection heat transfer.

[0093] ;

[0094] in, represents the heat transfer coefficient of the object surface, Indicates the temperature of the surrounding fluid.

[0095] Then, the established finite element simulation model of the direct buried cable is meshed:

[0096] Exemplarily, in this embodiment, COMSOL is used to mesh the finite element simulation model of the VV22-0.6 / 1kV-3×6mm2 power cable. After the mesh division, the total number of meshes is 29480. The evaluation standard of COMSOL for mesh division is the mesh quality. After the skewness-based mesh quality evaluation of the finite element simulation model of the VV22-0.6 / 1kV-3×6mm2 power cable is performed, the average mesh quality obtained in this embodiment is 0.9, and the mesh division effect is good.

[0097] Finally, the error analysis of the established finite element simulation model is carried out:

[0098] In this embodiment, the established power cable laying model is used to calculate the maximum current-carrying capacity of the cable under different soil thermal resistivity coefficients, wherein the thermal resistivity coefficients of native soil, backfill soil and sandy soil are considered to be consistent, and the influence of moisture field and flow field are ignored. The calculation results are compared with the current-carrying capacity calculation values ​​of the IEC-60287 standard to verify the accuracy of the calculation of the simulation model.

[0099] like Figure 4 and Figure 5 As shown in the figure, when the soil thermal resistivity is 0.0001~1(K·m) / W, the relative error between the calculated value of the simulation model and the IEC standard value is the largest, and then the relative error gradually decreases. Among them, the maximum relative error is about 3.6%, and the average relative error is about 1.52%, indicating that the simulation model is highly accurate, and the simulation data of the simulation model can be used to provide a data basis for subsequent cable core temperature prediction.

[0100] In this embodiment, a COMSOL Multiphysics multi-physics field model of direct buried power cable is built to simulate the operating conditions of the power cable in the actual environment, the temperature state and the current carrying capacity of the direct buried cable are studied, and the calculation results of the simulation model are compared with the IEC standard values. Under the four-field coupling conditions of flow field and temperature field, flow field and moisture field, temperature field and moisture field, and electromagnetic field and temperature field, the average relative error between the calculation results of the simulation model and the IEC standard value is about 1.52%, indicating that the simulation model has high accuracy. In actual engineering applications, the multi-physics field finite element simulation model can be used to conveniently obtain high-precision power cable analysis results under different physical field environments, so as to quickly and accurately obtain the cable temperature state, thereby providing a data basis for subsequent cable core temperature prediction.

[0101] In step 102, varying current carrying capacities are applied to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, and simulation temperature data of the target direct buried cable under varying current carrying capacities is obtained, which is recorded as the first training set.

[0102] In this embodiment, considering that the cable load of the direct buried cable is constantly changing during actual operation, if the temperature distribution data (i.e., simulated temperature data) of the direct buried cable is obtained through the finite element simulation model of the direct buried cable under the condition that the cable load state is stable, the obtained temperature distribution data may be difficult to reflect the actual cable core temperature of the direct buried cable. Therefore, the finite element simulation model is modified, and a changing current-carrying capacity is applied to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, so as to obtain the simulated temperature data of the target direct buried cable under the changing current-carrying capacity.

[0103] For example, taking the case where the target direct buried cable is located in the northern Hebei region, a typical daily load curve in the northern Hebei region is as follows: Figure 6 As shown in the figure, the current carrying capacity fluctuates periodically. Figure 6 The current carrying capacity fluctuates with time, and the parameter settings of the finite element simulation model such as the boundary conditions are consistent with the above, and a total of 4800 sets of temperature data can be calculated. Figure 7 As shown, it can be seen that the cable core temperature of the cable will also change when the current carrying capacity changes. Therefore, by applying a changing current carrying capacity to the finite element simulation model according to the typical daily load of the area where the target direct buried cable is located, the obtained simulation temperature data can be made more accurate.

[0104] It should be noted that Figure 6 This is only an example of a typical daily load curve. In order to make the obtained simulated temperature data closer to the actual value, different typical daily load curves can be obtained according to working days, holidays, etc., so as to apply varying current carrying capacity to the finite element simulation model according to different typical daily load curves.

[0105] Alternatively, a variable current carrying capacity may be applied to the finite element simulation model according to the typical daily load corresponding to each typical daily load curve, thereby obtaining a set of simulation temperature data, and then subsequent cable core temperature prediction is performed based on the simulation temperature data corresponding to each typical daily load curve.

[0106] In step 103, the long short-term memory model optimized by the Grey Wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable.

[0107] In this embodiment, after obtaining the simulated temperature data in combination with step 101 and step 102, the simulated temperature data is used as the first training set, and the long-short term memory model (Long-Short Term Memory, LSTM) of Grey Wolf Optimizer (GWO) is imported to predict the temperature state of the cable core at the future moment. Among them, since the GWO-LSTM model has a better effect on the prediction of time-varying data, the GWO-LSTM model is trained based on the simulated temperature data closer to the real value obtained by the target direct buried cable under the changing current carrying capacity, so that the obtained cable core temperature prediction model has a prediction effect closer to the real value.

[0108] Among them, the GWO-LSTM model combines the GWO algorithm and the LSTM algorithm, optimizes the solution process of the LSTM prediction algorithm through the GWO algorithm, and improves the effect of the prediction model.

[0109] For example, the model structure of the GWO-LSTM model is as follows: Figure 8 As shown, the input data is the time series of the core temperature of the direct buried cable (that is, the simulated temperature data of the first training set), and the output data is the predicted value of the core temperature calculated by the algorithm analysis.

[0110] During training, Figure 8 As shown in the figure, the input simulated temperature data is first preprocessed to clean up the data with large fluctuations and unreasonableness, and then the input data is normalized. On this basis, in order to avoid LSTM from overfitting the training data and thus losing the generalization performance, the input data can be divided into two parts, one for training the prediction algorithm and the other for verifying the accuracy of the prediction algorithm. Among them, LSTM consists of an input layer, an LSTM layer, an activation layer and an output regression layer. The simulated temperature data based on the time series is input. After the data passes through the LSTM layer, it is analyzed and processed by the activation function of the activation layer and finally reaches the output layer. The GWO optimization algorithm is used to optimize the parameters of LSTM. The values ​​of each parameter of LSTM are used as the position of the wolf pack. First, the position of the wolf pack is initialized, and then the fitness of the individuals in the wolf pack is calculated. The gray wolves are assigned levels according to the fitness, and then the individual positions in the wolf pack are updated. The fitness of the individuals is calculated again and the parameters are updated until the maximum number of iterations is reached. The optimized parameters are input into the LSTM layer, and the hyperparameters, number of iterations, number of hidden layer neural units and learning rate in the LSTM model are optimized.

[0111] Among them, the ReLU function is a linear correction unit. When the input is less than 0, the output is 0. When the input is greater than 0, the output is equal to the input. The expression is:

[0112] ;

[0113] Because the ReLU function has a faster convergence speed, simple calculation, stable curve, and can alleviate the problem of gradient disappearance, the ReLU function is selected as the activation function of the activation layer in this embodiment.

[0114] Among them, when optimizing the parameters of LSTM, the value of the learning rate is very important for the model. Whether the learning rate is too large or too small, it will affect the model. When the learning rate is very small, the amount of calculation of the model will increase significantly. When the learning rate is too large, it will cause the function to miss the minimum value. Taking this into account, this embodiment sets the initial learning rate in the model to 0.001.

[0115] After the cable core temperature prediction model is obtained through training, in order to evaluate the trained cable core temperature prediction model, the determination coefficient, root mean square error and relative difference percentage can be selected as evaluation indicators.

[0116] Among them, the coefficient of determination (R 2 ) is used to measure the goodness of fit. The goodness of fit indicates the degree of fit of the regression line to the observed value. The maximum value of the coefficient of determination is 1. The closer the coefficient of determination is to 1, the higher the degree of fit of the regression line to the observed value. Conversely, the lower the degree of fit of the regression line to the observed value. The expression of the coefficient of determination is:

[0117] ;

[0118] The root mean square error (RMSE) is used to measure the deviation between the predicted value and the true value. The smaller the RMSE value, the smaller the deviation between the predicted value and the true value. It is expressed as:

[0119] ;

[0120] The relative percentage difference (RPD) is used to evaluate the consistency between the predicted value and the true value. The larger the RPD value, the higher the consistency between the predicted value and the true value. Conversely, the lower the consistency between the predicted value and the true value. Its expression is:

[0121] ;

[0122] Where S represents the standard deviation of the prediction error.

[0123] The first 70% of the first training set is used as the training set to input into the GWO-LSTM prediction model, and the last 30% is used as the test set. Fig. 9 It can be seen that the training effect of the training set is better when the temperature of the direct buried cable fluctuates, R^2=0.9992, RMSE=0.099, RPD=36. Fig.10It can be seen that when the test set verifies the prediction accuracy, R^2=0.9656, RMSE=0.409, RPD=5, and the prediction effect maintains a certain degree of accuracy. Fig.11 It can be seen that when verifying the accuracy of the test set, the error in the initial stage is large, and then the prediction model is quickly adjusted, and the subsequent error gradually decreases.

[0124] In this embodiment, taking into account that the load will inevitably fluctuate and cause changes in the temperature state during the actual operation of the direct buried cable, the finite element simulation model is subjected to varying current carrying capacities according to different typical daily loads in the area where the target direct buried cable is located, and the simulated temperature data of the target direct buried cable under varying current carrying capacities is obtained, which is recorded as the first training set. The GWO-LSTM prediction model is trained based on the first training set to obtain a cable core temperature prediction model based on GWO-LSTM. The cable core temperature prediction model based on GWO-LSTM is used to assist in analyzing the real-time working status of the direct buried cable, and a more accurate prediction value of the cable core temperature of the direct buried cable is obtained.

[0125] In step 104, a predicted value of the cable core temperature of the target direct buried cable is obtained based on the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model.

[0126] In this embodiment, it is considered that if the state detection equipment is not installed in advance when the direct buried cable is actually working, it is difficult to perform real-time analysis on the working state of the cable, and it is not convenient to re-construct the direct buried cable that has been laid in the soil to assemble the detection equipment. Therefore, in order to analyze the real-time working state of the direct buried cable, the finite element simulation model of the direct buried cable is used to simulate the transient temperature distribution data of the direct buried cable under the current carrying capacity fluctuation state, and the transient temperature distribution data is used to train the GWO-LSTM prediction model to obtain the cable core temperature prediction model based on GWO-LSTM. The cable core temperature prediction model based on GWO-LSTM is used to predict and analyze the temperature state of the direct buried cable. The prediction result has certain fluctuations in the initial stage, and then the accuracy is rapidly improved. When analyzing the working state of the cable, the cable core temperature prediction model based on GWO-LSTM can provide a high-precision prediction result, assist in analyzing the real-time working state of the direct buried cable, and provide a reference for analyzing the real-time working state of the direct buried cable.

[0127] The embodiment of the present invention establishes a finite element simulation model of the target direct buried cable, and applies a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, thereby obtaining the simulated temperature data of the target direct buried cable under the varying current carrying capacity, which is recorded as the first training set, and the simulated temperature data of the target direct buried cable under the varying current carrying capacity that is closer to the true value can be obtained. On this basis, the long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain the cable core temperature prediction model of the target direct buried cable. The accuracy of the prediction of time-varying data by the long short-term memory model optimized by the Gray Wolf can be used to obtain a more accurate cable core temperature prediction model, so that according to the measured cable core temperature data of the target direct buried cable and the cable core temperature prediction model, a more accurate cable core temperature prediction value of the target direct buried cable can be obtained, thereby reflecting the real cable core temperature of the target direct buried cable in real time.

[0128] In another embodiment of the direct buried cable core temperature prediction method, the method may further include:

[0129] According to the finite element simulation model, the stable current-carrying capacity of the target direct-buried cable under different soil thermal resistance coefficients is calculated; the stable current-carrying capacity is applied to the finite element simulation model to obtain the simulated temperature data of the target direct-buried cable under the stable current-carrying capacity, which is recorded as the second training set.

[0130] Accordingly, the long short-term memory model optimized by the gray wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable, which may include:

[0131] Each day is divided into a load fluctuation period and a load stable period.

[0132] According to the first training set, the long short-term memory model optimized by Gray Wolf is trained in the load fluctuation period, and according to the second training set, the long short-term memory model optimized by Gray Wolf is trained in the load stable period to obtain the cable core temperature prediction model of the target direct buried cable.

[0133] In this embodiment, in order to further improve the prediction accuracy of the cable core temperature prediction model, the current carrying capacity of the cable is divided into fluctuating current carrying capacity and stable current carrying capacity in combination with the different typical daily loads in the area where the target direct buried cable is located. Correspondingly, each day is divided into a load fluctuation time period and a load stability time period. In the load fluctuation time period, the GWO-LSTM model is trained according to the simulated temperature data obtained according to the changing current carrying capacity, and in the load stability time period, the GWO-LSTM model is trained according to the simulated temperature data obtained according to the stable current carrying capacity, thereby obtaining the cable core temperature prediction model of the target direct buried cable.

[0134] For example, in combination with different typical daily loads, multiple stable current carrying capacities can be obtained, such as the maximum stable current carrying capacity, the second largest stable current carrying capacity, the minimum stable current carrying capacity, etc. In the finite element simulation model of the direct buried cable, the influence of different thermal resistance coefficients of different soils such as native soil, backfill soil and sandy soil can be considered to determine the stable current carrying capacity. The thermal resistance coefficients of different soils are shown in Table 2.

[0135] Table 2 Thermal resistance coefficients of different soils

[0136]

[0137] For example, in a steady state, the maximum current carrying capacity under different soil thermal resistance coefficients can be calculated to be 47.69A, and then the current carrying capacity is used as the maximum stable current carrying capacity, and the current carrying capacity is used as the cable current carrying capacity when calculating the transient model, and then the simulation temperature data of the direct buried cable in the transient state is analyzed and obtained as the second training set. The GWO-LSTM model is trained based on the first training set in the load fluctuation time period, and the GWO-LSTM model is trained based on the second training set in the load stable time period to obtain the cable core temperature prediction model of the target direct buried cable.

[0138] For example, when the current carrying capacity is 47.69A as the current carrying capacity of the cable during transient model calculation, the simulated temperature data obtained is as follows: Fig.12 As shown in the figure, when training the model, the first 70% can be used as the training set and the last 30% as the test set.

[0139] Exemplarily, the process of dividing each day into a load fluctuation time period and a load stability time period may include: determining the load fluctuation rate of each time period of each day according to different typical daily loads in the area where the target direct buried cable is located. Determining a time period in which the load fluctuation rate is less than a set fluctuation threshold as a load stability time period of each day. Determining a time period in which the load fluctuation rate is greater than or equal to a set fluctuation threshold as a load fluctuation time period of each day.

[0140] Combination Figure 6 As shown, in this embodiment, the load fluctuation rate of each time period of each day in different typical daily loads can be measured, so that each day can be divided into a load fluctuation time period and a load stable time period according to the load fluctuation rate of each time period and the set fluctuation threshold, so that the GWO-LSTM model is trained based on the first training set in the load fluctuation time period, and the GWO-LSTM model is trained based on the second training set in the load stable time period.

[0141] In another embodiment of the direct buried cable core temperature prediction method, the method may further include:

[0142] The temperature data of different typical days in the area where the target direct buried cable is located are obtained and recorded as the third training set.

[0143] Accordingly, the long short-term memory model optimized by the gray wolf is trained according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable, which may include:

[0144] The Gray Wolf optimized long short-term memory model is trained according to the first training set to obtain the first cable core temperature prediction model of the target direct buried cable.

[0145] The Gray Wolf optimized long short-term memory model is trained according to the first training set and the third training set to obtain the second cable core temperature prediction model of the target direct buried cable.

[0146] A cable core temperature prediction model of the target direct buried cable is obtained according to the first cable core temperature prediction model and the second cable core temperature prediction model.

[0147] In this embodiment, in order to improve the prediction accuracy of the cable core stability prediction model, in addition to considering load fluctuations, other data that affect the cable core temperature, such as temperature data, are also considered when training the GWO-LSTM model. For example, since load fluctuations are considered according to different typical days, when considering temperature data, temperature data of different typical days can also be considered.

[0148] On this basis, when the temperature data is not considered, a first cable core temperature prediction model is obtained by training with the first training set, or a first cable core temperature prediction model is obtained by training with the first training set and the second training set. When the temperature data is considered, a second cable core temperature prediction model is obtained by training with the first training set and the third training set (i.e., the training set of the temperature data), or a second cable core temperature prediction model is obtained by training with the first training set, the second training set, and the third training set. Then, based on the first cable core temperature prediction model and the second cable core temperature prediction model, the cable core temperature prediction model of the target direct buried cable is obtained, so that the prediction result of the cable core temperature prediction model is closer to the true value.

[0149] Optionally, obtaining a cable core temperature prediction model of a target direct buried cable according to the first cable core temperature prediction model and the second cable core temperature prediction model may include:

[0150] Obtain the correlation coefficient between the temperature data of different typical days and the corresponding loads of different typical days.

[0151] If the correlation coefficient is greater than the set correlation threshold, the second cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day.

[0152] If the correlation coefficient is less than or equal to the set correlation threshold, the first cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day.

[0153] In this embodiment, it is considered that in some cases, the temperature data has a small effect on the cable core temperature, such as in spring and autumn, while in some cases, the temperature data has a large effect on the cable core temperature, such as in summer and winter. Therefore, the correlation coefficient between the temperature data of different typical days and the corresponding different typical daily loads is obtained, and according to the correlation coefficient, it is determined whether to use the second cable core temperature prediction model as the cable core temperature prediction model or the first cable core temperature prediction model as the cable core temperature prediction model. In this embodiment, the influence of the temperature data on the cable core temperature is measured by the correlation coefficient between the temperature data of different typical days and the corresponding different typical daily loads, so as to determine different cable core temperature prediction models in different time periods, so that the cable core temperature value predicted by the cable core temperature prediction model can better reflect the real-time working status of the cable.

[0154] In one embodiment, obtaining a predicted value of the cable core temperature of the target direct buried cable according to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model may include:

[0155] The cable core temperature prediction model is incrementally trained according to the measured data of the cable core temperature of the target direct buried cable to obtain a revised cable core temperature prediction model.

[0156] The cable core temperature prediction value of the target direct buried cable is obtained by performing prediction based on the modified cable core temperature prediction model.

[0157] In this embodiment, in order to further improve the accuracy of the cable core temperature prediction value, before obtaining the cable core temperature prediction value of the target direct buried cable, the cable core temperature prediction model is incrementally trained based on the measured cable core temperature data of the target direct buried cable to obtain a revised cable core temperature prediction model, and prediction is performed according to the revised cable core temperature prediction model to obtain the cable core temperature prediction value of the target direct buried cable.

[0158] This embodiment establishes a finite element simulation model of a direct buried cable based on multi-physical field coupling. The average relative error between the calculated value of the simulation model and the IEC standard value is about 1.52%, indicating that the simulation model has a high accuracy. On this basis, by using finite element analysis software, the temperature state of the cable core of the direct buried cable is solved under the condition of changing current carrying capacity, and a calculation result close to the theoretical value can be obtained. In practical engineering applications, the cable temperature state can be obtained quickly and accurately. Then, based on the temperature state of the cable core of the direct buried cable obtained by simulation, the GWO-LSTM model is trained, and the advantages of strong convergence, few parameters and easy implementation of the gray wolf optimization algorithm are used to combine the gray wolf optimization algorithm with the long short-term memory algorithm. The solution process of the long short-term memory prediction algorithm is optimized by the gray wolf algorithm, and the effect of the prediction model is improved to obtain a cable core temperature prediction model. Then, the cable core temperature prediction model is used to predict and analyze the transient cable core temperature state of the direct buried cable. The prediction result has certain fluctuations in the initial stage, and then the accuracy is rapidly improved. When analyzing the working state of the cable, the prediction algorithm can provide a high-precision prediction result to assist in analyzing the real-time working state of the cable.

[0159] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0160] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0161] Fig.13 The schematic diagram of the structure of the direct buried cable core temperature prediction device provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0162] like Fig.13 As shown, the direct buried cable core temperature prediction device includes: a modeling module 131, a simulation module 132, a training module 133 and a prediction module 134.

[0163] The modeling module 131 is used to establish a finite element simulation model of the target direct buried cable.

[0164] The simulation module 132 is used to apply varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, and obtain simulated temperature data of the target direct buried cable under varying current carrying capacity, which is recorded as the first training set.

[0165] The training module 133 is used to train the long short-term memory model optimized by the Gray Wolf according to the first training set to obtain a cable core temperature prediction model of the target direct buried cable.

[0166] The prediction module 134 is used to obtain a predicted value of the cable core temperature of the target direct buried cable according to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model.

[0167] The embodiment of the present invention establishes a finite element simulation model of the target direct buried cable, and applies a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, thereby obtaining the simulated temperature data of the target direct buried cable under the varying current carrying capacity, which is recorded as the first training set, and the simulated temperature data of the target direct buried cable under the varying current carrying capacity that is closer to the true value can be obtained. On this basis, the long short-term memory model optimized by the Gray Wolf is trained according to the first training set to obtain the cable core temperature prediction model of the target direct buried cable. The accuracy of the prediction of time-varying data by the long short-term memory model optimized by the Gray Wolf can be used to obtain a more accurate cable core temperature prediction model, so that according to the measured cable core temperature data of the target direct buried cable and the cable core temperature prediction model, a more accurate cable core temperature prediction value of the target direct buried cable can be obtained, thereby reflecting the real cable core temperature of the target direct buried cable in real time.

[0168] In one possible implementation, the simulation module 132 can also be used to calculate the stable current-carrying capacity of the target direct-buried cable under different soil thermal resistance coefficients based on the finite element simulation model; apply the stable current-carrying capacity to the finite element simulation model to obtain the simulated temperature data of the target direct-buried cable under the stable current-carrying capacity, which is recorded as the second training set; the training module 133 can be used to divide each day into a load fluctuation time period and a load stability time period; train the Gray Wolf optimized long short-term memory model in the load fluctuation time period according to the first training set, and train the Gray Wolf optimized long short-term memory model in the load stability time period according to the second training set to obtain a cable core temperature prediction model for the target direct-buried cable.

[0169] In one possible implementation, the training module 133 can be used to determine the load fluctuation rate in each time period of the day based on different typical daily loads in the area where the target direct buried cable is located; determine the time period when the load fluctuation rate is less than the set fluctuation threshold as the daily load stable time period; and determine the time period when the load fluctuation rate is greater than or equal to the set fluctuation threshold as the daily load fluctuation time period.

[0170] In one possible implementation, the simulation module 132 can also be used to obtain temperature data of different typical days in the area where the target direct buried cable is located, which is recorded as the third training set; the training module 133 can be used to train the long short-term memory model optimized by the Gray Wolf according to the first training set to obtain a first cable core temperature prediction model of the target direct buried cable; the long short-term memory model optimized by the Gray Wolf is trained according to the first training set and the third training set to obtain a second cable core temperature prediction model of the target direct buried cable; the cable core temperature prediction model of the target direct buried cable is obtained according to the first cable core temperature prediction model and the second cable core temperature prediction model.

[0171] In one possible implementation, the training module 133 can be used to obtain the correlation coefficient between the temperature data of different typical days and the corresponding loads of different typical days; if the correlation coefficient is greater than the set correlation threshold, the second cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day; if the correlation coefficient is less than or equal to the set correlation threshold, the first cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day.

[0172] In one possible implementation, the prediction module 134 can be used to perform incremental training on the cable core temperature prediction model based on the measured cable core temperature data of the target direct buried cable to obtain a revised cable core temperature prediction model; and perform prediction based on the revised cable core temperature prediction model to obtain a predicted value of the cable core temperature of the target direct buried cable.

[0173] In a possible implementation, the lower boundary of the finite element simulation model is a first-class boundary condition, and the first-class boundary condition is:

[0174] ;

[0175] Among them, Γ represents the object boundary, represents the known wall temperature, represents a known wall temperature function.

[0176] The left and right boundaries of the finite element simulation model are the second-type boundary conditions, which are:

[0177] ;

[0178] in, represents the known heat flux density, represents the normal direction of the boundary, represents the temperature in the normal direction, represents a known heat flux function.

[0179] The upper boundary of the soil in the finite element simulation model is the third type of boundary condition, and the third type of boundary condition is:

[0180] ;

[0181] in, represents the heat transfer coefficient of the object surface, Indicates the temperature of the surrounding fluid.

[0182] Fig.14 is a schematic diagram of a terminal provided by an embodiment of the present invention. Fig.14 As shown, the terminal 14 of this embodiment includes: a processor 140, a memory 141, and a computer program 142 stored in the memory 141 and executable on the processor 140. When the processor 140 executes the computer program 142, the steps in the above-mentioned direct buried cable core temperature prediction method embodiments are implemented, for example Figure 1 Alternatively, when the processor 140 executes the computer program 142, the functions of each module in the above-mentioned device embodiments are implemented, for example Fig.13 The functions of each module are shown.

[0183] Exemplarily, the computer program 142 may be divided into one or more modules / units, one or more modules / units are stored in the memory 141 and executed by the processor 140 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 142 in the terminal 14. For example, the computer program 142 may be divided into Fig.13 The modules shown.

[0184] The terminal 14 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 14 may include, but is not limited to, a processor 140 and a memory 141. Those skilled in the art will appreciate that Fig.14 It is only an example of terminal 14 and does not constitute a limitation on terminal 14. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0185] The processor 140 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0186] The memory 141 may be an internal storage unit of the terminal 14, such as a hard disk or memory of the terminal 14. The memory 141 may also be an external storage device of the terminal 14, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal 14. Further, the memory 141 may also include both an internal storage unit of the terminal 14 and an external storage device. The memory 141 is used to store computer programs and other programs and data required by the terminal. The memory 141 may also be used to temporarily store data that has been output or is to be output.

[0187] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0188] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0189] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0190] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0191] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0193] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned embodiments of the direct buried cable core temperature prediction method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0194] 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 aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned 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 predicting the core temperature of a direct buried cable, characterized in that: include: Establish a finite element simulation model of the target direct buried cable; Applying varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, obtaining simulation temperature data of the target direct buried cable under varying current carrying capacity, which is recorded as a first training set; According to the finite element simulation model, calculating the stable current carrying capacity of the target direct buried cable under different soil thermal resistance coefficients; Applying the stable current carrying capacity to the finite element simulation model to obtain simulation temperature data of the target direct buried cable under the stable current carrying capacity, which is recorded as a second training set; Determine the load fluctuation rate in each time period of each day according to different typical daily loads in the area where the target direct buried cable is located; Determine the time period when the load fluctuation rate is less than the set fluctuation threshold as the daily load stable time period; Determine a time period during which the load fluctuation rate is greater than or equal to the set fluctuation threshold as a daily load fluctuation time period; The long short-term memory model optimized by the Gray Wolf is trained according to the first training set during the load fluctuation period, and the long short-term memory model optimized by the Gray Wolf is trained according to the second training set during the load stability period to obtain a cable core temperature prediction model of the target direct buried cable; According to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model, a predicted value of the cable core temperature of the target direct buried cable is obtained.

2. The method for predicting the temperature of a direct buried cable core according to claim 1, characterized in that: Also includes: Acquire temperature data of different typical days in the area where the target direct buried cable is located, recorded as a third training set; The long short-term memory model optimized by the Gray Wolf is trained according to the first training set and the second training set to obtain a first cable core temperature prediction model of the target direct buried cable; The Gray Wolf optimized long short-term memory model is trained according to the first training set, the second training set and the third training set to obtain a second cable core temperature prediction model of the target direct buried cable; A cable core temperature prediction model of the target direct buried cable is obtained according to the first cable core temperature prediction model and the second cable core temperature prediction model.

3. The method for predicting the temperature of a direct buried cable core according to claim 2, characterized in that: According to the first cable core temperature prediction model and the second cable core temperature prediction model, a cable core temperature prediction model of the target direct buried cable is obtained, including: Obtaining correlation coefficients between the temperature data of different typical days and corresponding loads of different typical days; If the correlation coefficient is greater than a set correlation threshold, the second cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day; If the correlation coefficient is less than or equal to the set correlation threshold, the first cable core temperature prediction model is used as the cable core temperature prediction model for the time period corresponding to the typical day.

4. The method for predicting the temperature of a direct buried cable core according to claim 1, characterized in that: According to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model, a predicted value of the cable core temperature of the target direct buried cable is obtained, including: Incrementally training the cable core temperature prediction model according to the measured data of the cable core temperature of the target direct buried cable to obtain a revised cable core temperature prediction model; The cable core temperature prediction value of the target direct buried cable is obtained by performing prediction according to the modified cable core temperature prediction model.

5. The method for predicting the temperature of a direct buried cable core according to claim 1, characterized in that: The lower boundary of the finite element simulation model is a first-class boundary condition, and the first-class boundary condition is: ； Among them, Γ represents the object boundary, represents the known wall temperature, represents a known wall temperature function; The left and right boundaries of the finite element simulation model are the second type of boundary conditions, and the second type of boundary conditions are: ； in, represents the known heat flux density, represents the normal direction of the boundary, represents the temperature in the normal direction, represents a known heat flux density function; The upper boundary of the soil in the finite element simulation model is the third type of boundary condition, and the third type of boundary condition is: ； in, represents the heat transfer coefficient of the object surface, Indicates the temperature of the surrounding fluid.

6. A direct buried cable core temperature prediction device, characterized in that: include: A modeling module, used to establish a finite element simulation model of the target direct buried cable; A simulation module, used for applying a varying current carrying capacity to the finite element simulation model according to different typical daily loads in the area where the target direct buried cable is located, and obtaining simulation temperature data of the target direct buried cable under the varying current carrying capacity, which is recorded as a first training set; According to the finite element simulation model, calculating the stable current carrying capacity of the target direct buried cable under different soil thermal resistance coefficients; Applying the stable current carrying capacity to the finite element simulation model to obtain simulation temperature data of the target direct buried cable under the stable current carrying capacity, which is recorded as a second training set; A training module, used to determine the load fluctuation rate in each time period of each day according to different typical daily loads in the area where the target direct buried cable is located; Determine the time period when the load fluctuation rate is less than the set fluctuation threshold as the daily load stable time period; determine the time period when the load fluctuation rate is greater than or equal to the set fluctuation threshold as the daily load fluctuation time period; train the long short-term memory model optimized by the Gray Wolf according to the first training set in the load fluctuation time period, and train the long short-term memory model optimized by the Gray Wolf according to the second training set in the load stable time period to obtain the cable core temperature prediction model of the target direct buried cable; The prediction module is used to obtain the predicted value of the cable core temperature of the target direct buried cable according to the measured data of the cable core temperature of the target direct buried cable and the cable core temperature prediction model.

7. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images