Cable bridge laying cable temperature prediction method and device, terminal and storage medium

Abstract

The invention provides a cable bridge laying cable temperature prediction method and device, a terminal and a storage medium, and belongs to the technical field of cable detection. The method comprises the following steps: acquiring environment temperature data and load current data of a to-be-predicted cable; inputting the environment temperature data and the load current data of the to-be-predicted cable into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the to-be-predicted cable; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, the data set comprises historical environment temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; the training process of the temperature prediction model comprises the steps that the extreme gradient boosting tree model is optimized according to an NRBO optimization algorithm, the optimized extreme gradient boosting tree model is trained, and the temperature prediction model is obtained. According to the invention, the cable temperature prediction speed and precision can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cable detection, and in particular to a method, device, terminal and storage medium for predicting the temperature of cables laid in a cable bridge. Background Art

[0002] Transmission lines are efficient and fast energy transmission channels and are key to the safe operation of power grids. With the continuous growth of the global economy and population, the surge in electricity demand has undoubtedly brought unprecedented pressure to the existing power grid system. The sharp increase in electricity demand and the large-scale access to renewable energy have put higher requirements on the transportation capacity and operational flexibility of the existing transmission system.

[0003] Increasing the transmission capacity of the power grid by building new transmission lines not only takes a long time and requires large investments, but also brings about environmental pollution problems. Considering the volatility of the load curve and the intermittent nature of renewable energy, the capacity expansion of transmission lines often does not require all-weather operation. The dynamic capacity expansion technology of transmission lines can significantly improve the transmission capacity of transmission lines while ensuring safety, and has good application prospects.

[0004] The key to the dynamic capacity increase of cable bridge cables lies in the evaluation of cable status. In actual situations, the adjustment of ambient temperature and cable load fluctuations will affect the cable temperature. Therefore, the evaluation of cable temperature and current carrying capacity can not only make reasonable design and full use of the cable when transmitting load, realize short-term dynamic capacity increase of DC cable lines, but also effectively reduce investment costs while meeting greater transmission capacity.

[0005] However, for the cable temperature and current-carrying capacity of cable clusters laid in air, the finite element method, one of the commonly used evaluation methods, can simulate the actual working conditions well, but it often takes a long time to calculate in complex situations and lacks flexibility. Therefore, there is an urgent need for a method to quickly predict the temperature of the cable. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, terminal and storage medium for predicting the temperature of cables laid in a cable bridge, so as to solve the problem of slow cable temperature prediction.

[0007] In a first aspect, an embodiment of the present invention provides a method for predicting the temperature of a cable laid in a cable bridge, comprising: Obtaining ambient temperature data and load current data of the cable to be predicted; Input the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, and the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; The training process of the temperature prediction model includes: The extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model. The historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model. The optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model.

[0008] In a possible implementation, the historical cable core temperature data of the cable are obtained according to finite element analysis, including: Obtain the physical properties, boundary conditions and internal physical fields of the cable bridge; the physical properties include the material properties, geometric structure and laying method of the cable, the boundary conditions are the third-class boundary conditions, the internal physical fields of the cable bridge include the coupling of flow field and thermal field and the thermal field, the thermal field includes the heat conduction between the cable body and the bridge body, the convection heat transfer of the air in the closed space of the bridge, and the thermal radiation between the cable surface and the inner wall of the bridge; Construct a finite element model of the cable based on physical properties, boundary conditions and the internal physical fields of the cable bridge; Input the historical ambient temperature data and historical load current data of the set cable into the finite element model to obtain the thermal field distribution inside the cable bridge; The temperature value at the cable core position is extracted from the thermal field as the historical cable core temperature data.

[0009] In a possible implementation, the heat conduction formula between the cable body and the bridge body is:

[0010] In the formula, For point The temperature of the medium, is the volume heat generation rate, is the thermal conductivity of the medium; The convective heat transfer formula of air in the closed space of the bridge is:

[0011]

[0012]

[0013] In the formula, and The fluid velocities of air are Axis and The weight of the axis, is the flow field pressure, is the dynamic viscosity of the fluid, is the fluid reference temperature, is the density of air, g is the acceleration due to gravity, is the volume expansion coefficient, is the specific heat capacity of the fluid; The heat radiation formula between the cable surface and the inner wall of the bridge is:

[0014] In the formula, is the net heat exchange between the first surface and the second surface, is the surface area of ​​the first surface participating in radiation, is the Stefan Pan-Boltzmann constant, and are the surface emissivity of the first surface and the second surface, is the angular coefficient, and is the surface temperature of the first surface and the second surface; The coupling formula of flow field and thermal field is:

[0015] In the formula, is the fluid density, is the fluid pressure, u is the fluid velocity, μ is the dynamic viscosity, is the gradient, is the identity matrix, is the acceleration due to gravity, T It is the real-time temperature.

[0016] In one possible implementation, the boundary condition is formulated as:

[0017] )

[0018]

[0019]

[0020]

[0021] In the formula, is the thermal conductivity, is the boundary temperature, is the fluid temperature, is the boundary heat transfer coefficient, is the Grashof number, is the Prandtl number, is the volume expansion coefficient, is the acceleration due to gravity, is the temperature difference, is the linear dimension, is the dynamic viscosity, is the convective heat transfer coefficient required for boundary conditions, is the Nusselt number, is the specific heat capacity, Set value for experience.

[0022] In a possible implementation, before inputting the ambient temperature data and the load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted, the method further includes: Normalize the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable; A data set is constructed based on the normalized historical ambient temperature data, historical load current data, and historical cable core temperature data of the cable, and an extreme gradient boosting tree model is trained based on the data set.

[0023] In one possible implementation, the extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm, including: Generate an initial random population; Taking the minimum error and model complexity as the optimization goal, the Newton-Raphson search rule is used to control the step size, and the perturbation is added in combination with the trap avoidance operation to optimize the parameters of the extreme gradient boosting tree model; The optimized parameters are applied to the extreme gradient boosting tree model to obtain the optimized extreme gradient boosting tree model.

[0024] In a possible implementation, the method further includes: Use a preset proportion of data in the dataset as the training set and the remaining data as the test set; The optimized extreme gradient boosting tree model is trained according to the training set, and tested according to the test set to obtain a temperature prediction model.

[0025] In a second aspect, an embodiment of the present invention provides a device for predicting the temperature of cables laid in a cable bridge, comprising: A data acquisition module, used to acquire ambient temperature data and load current data of the cable to be predicted; A temperature prediction module is used to input the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, and the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; The training process of the temperature prediction model includes: The extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model. The historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model. The optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model.

[0026] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0027] 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 possible implementation of the first aspect are implemented.

[0028] The embodiment of the present invention provides a method, device, terminal and storage medium for predicting the temperature of cables laid in a cable bridge. The method obtains the ambient temperature data and load current data of the cable to be predicted, inputs the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model, and obtains the predicted value of the cable core temperature of the cable to be predicted. The temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set. The data set includes the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable. The historical cable core temperature data of each cable is obtained according to finite element analysis. The historical cable core temperature data of the cable is determined by high-precision finite element analysis to improve the accuracy of the model training data. The training process of the temperature prediction model includes: optimizing the extreme gradient boosting tree model according to the NRBO optimization algorithm to improve the accuracy of the model. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model, and the historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model. The optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model. Through high-precision finite element analysis to simulate the thermal field distribution inside the cable bridge, the historical cable core temperature data is obtained, and a data set is constructed. The NRBO algorithm is used to optimize the parameters of the extreme gradient boosting tree model to improve the accuracy of the model. The temperature prediction model of the cable is obtained by training the optimized extreme gradient boosting tree model according to the data set. When predicting the cable core temperature of the cable, the newly acquired ambient temperature and load current are input into the temperature prediction model to obtain the predicted value of the cable core temperature, which improves the calculation efficiency of the cable core temperature, can quickly adapt to changes in cable load and ambient temperature, and realize accurate temperature monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] Figure 1 It is a flow chart of the implementation of the temperature prediction method for laying cables in a cable bridge provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a geometric model of a cable bridge provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a cable cross section provided by an embodiment of the present invention; Figure 4 is a schematic diagram of fitting prediction of all samples provided in an embodiment of the present invention; Figure 5is a schematic diagram for comparing prediction results of training sets provided by an embodiment of the present invention; Figure 6 is a schematic diagram for comparing prediction results of a test set provided by an embodiment of the present invention; Figure 7 is a schematic diagram of prediction error of a test set provided by an embodiment of the present invention; Figure 8 It is a schematic diagram of the structure of a device for predicting the temperature of cables laid in a cable bridge provided by an embodiment of the present invention; Fig. 9 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] 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.

[0033] See also Figure 1 , which shows a flow chart of the implementation of the cable bridge cable temperature prediction method provided by an embodiment of the present invention, which is described in detail as follows: Step 101: Acquire ambient temperature data and load current data of the cable to be predicted.

[0034] In this embodiment, the ambient temperature refers to the temperature of the surrounding environment of the cable, reflecting the external thermal conditions of the cable during operation. The ambient temperature has a direct impact on the cable temperature. For example, when the ambient temperature is high, the heat dissipation capacity of the cable will decrease, resulting in an increase in the cable temperature. When the ambient temperature is low, the heat dissipation capacity of the cable is enhanced, and the cable temperature is relatively low. The ambient temperature data comes from meteorological data, sensor measurements, or historical data. In practical applications, the ambient temperature is usually obtained in real time by a temperature sensor installed near the cable. The load current refers to the current flowing through the cable, reflecting the load condition of the cable during operation. The load current is one of the key factors affecting the cable temperature. For example, when the load current increases, the Joule heat (heat caused by the current) inside the cable increases, resulting in an increase in the cable temperature. When the load current decreases, the heat inside the cable decreases and the temperature is relatively low. The load current data is usually measured by a current sensor or obtained from the operation data of the power system. In practical applications, the change in load current can be recorded by a real-time monitoring system.

[0035] Step 102: Input the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, and the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; the training process of the temperature prediction model is specifically processed as follows: optimize the extreme gradient boosting tree model according to the NRBO optimization algorithm, use the historical ambient temperature data and historical load current data of the cable as the input of the optimized extreme gradient boosting tree model, use the historical cable core temperature data as the output of the optimized extreme gradient boosting tree model, train the optimized extreme gradient boosting tree model, and obtain a temperature prediction model.

[0036] In this embodiment, the temperature of the cable is directly affected by the ambient temperature and the load current, so these two parameters are the key input variables for predicting the cable temperature. Finite element analysis is a numerical simulation method used to calculate the cable core temperature of a cable under different ambient temperatures and load current conditions. The cable is a cable with the same structure and the same environment as the cable to be predicted. These simulation results are used as the "real" cable core temperature value in the training data set. The Newton-Raphson-based Optimizer (NRBO) is used to adjust the hyperparameters of the extreme gradient boosting tree model to improve the prediction accuracy and generalization ability of the model. The goal of the optimization is to minimize the prediction error and model complexity. The present invention uses high-quality historical data obtained by finite element analysis to train a machine learning model, thereby achieving rapid and accurate prediction of cable temperature.

[0037] In a possible implementation, the historical cable core temperature data of the cable are obtained according to the finite element analysis, and the specific processing is as follows: the physical properties, boundary conditions and physical fields inside the cable bridge are obtained; wherein the physical properties include the material properties, geometric structure and laying method of the cable, the boundary conditions are the third-type boundary conditions, and the physical fields inside the cable bridge include the coupling of flow field and thermal field and the thermal field, and the thermal field includes the heat conduction between the cable body and the bridge body, the convection heat transfer of the air in the closed space of the bridge, and the thermal radiation between the cable surface and the inner wall of the bridge; according to the physical properties, boundary conditions and the physical field inside the cable bridge, a finite element model of the cable is constructed; the historical ambient temperature data and historical load current data of the set cable are input into the finite element model to obtain the thermal field distribution inside the cable bridge; the temperature value of the cable core position is extracted from the thermal field as the historical cable core temperature data of the cable.

[0038] In this embodiment, material properties such as the conductor material (such as copper or aluminum) and insulating material of the cable determine the thermal conductivity, specific heat capacity and other thermophysical parameters of the cable. Geometric structures such as the size (such as outer diameter, thickness of the insulation layer, etc.) and shape of the cable affect the heat dissipation capacity and temperature distribution of the cable. Laying methods such as the arrangement of cables in the cable bridge (such as single-layer laying, multi-layer laying, etc.) will affect the thermal interaction and heat dissipation conditions between the cables. The physical model of the present invention is surrounded by air, which belongs to the third type of boundary conditions in the thermal field boundary, that is, the known convection heat transfer coefficient and the external fluid temperature. The boundary conditions are set based on the heat exchange method between the cable and the surrounding environment. Finite element analysis software (such as ANSYS, COMSOL, etc.) is used to build a model based on the physical properties and boundary conditions of the cable. The model discretizes the geometric structure of the cable and the cable bridge into multiple small units (grid division), and applies physical equations (such as heat conduction equations, convection equations, etc.) in each unit. In this way, the model can simulate the temperature distribution inside the cable bridge.

[0039] In this embodiment, the finite element model calculates the thermal field distribution inside the cable bridge by solving the heat conduction equation, the convection equation and the radiation equation. The thermal field distribution reflects the temperature conditions at different positions inside the cable bridge, including the temperature of the cable surface and the cable core. In the finite element model, the cable core position corresponds to a specific grid unit or node. By locating these units or nodes, their temperature values ​​are extracted as the cable core temperature, and the extracted temperature values ​​are used as the historical cable core temperature data of the cable.

[0040] In a possible implementation, the heat conduction formula between the cable body and the bridge body is:

[0041] In the formula, For point The temperature of the medium, is the volume heat generation rate, is the thermal conductivity of the medium; In a two-dimensional field, the convection heat transfer of air inside the cable bridge can be described by the law of conservation of mass, the law of conservation of momentum and the law of conservation of energy. The convection heat transfer formula of air in the closed space of the bridge is:

[0042]

[0043]

[0044] In the formula, and The fluid velocities of air are Axis and The weight of the axis, is the flow field pressure, is the dynamic viscosity of the fluid, is the fluid reference temperature, is the density of air, g is the acceleration due to gravity, is the volume expansion coefficient, is the specific heat capacity of the fluid, is the thermal conductivity of the medium; The heat radiation formula between the cable surface and the inner wall of the bridge is:

[0045] In the formula, is the net heat exchange between the first surface and the second surface, is the surface area of ​​the first surface participating in radiation, is the Stefan Pan-Boltzmann constant, and are the surface emissivity of the first surface and the second surface, is the angular coefficient, and is the surface temperature of the first surface and the second surface; The coupling formula of flow field and thermal field is:

[0046] In the formula, is the fluid density, is the fluid pressure, u is the fluid velocity, μ is the dynamic viscosity, is the gradient, is the identity matrix, is the acceleration due to gravity, T It is the real-time temperature.

[0047] In this embodiment, the heat conduction formula between the cable body and the bridge body, the convection heat transfer formula of the air in the closed space of the bridge, the heat radiation formula between the cable surface and the inner wall of the bridge, and the flow field and thermal field coupling formula are the basis for simulating the thermal field distribution inside the cable bridge in finite element analysis. By solving these equations, the temperature distribution at different positions inside the cable bridge can be obtained, thereby providing an accurate physical model for cable temperature prediction.

[0048] In one possible implementation, the boundary condition is formulated as:

[0049] )

[0050]

[0051]

[0052]

[0053] In the formula, is the thermal conductivity, is the boundary temperature, is the fluid temperature, is the boundary heat transfer coefficient, is the Grashof number, is the Prandtl number, is the volume expansion coefficient, is the acceleration due to gravity, is the temperature difference, is the linear dimension, is the dynamic viscosity, is the convective heat transfer coefficient required for boundary conditions, is the Nusselt number, is the specific heat capacity, Set value for experience.

[0054] In this embodiment, the finite element analysis boundary conditions are generally divided into three categories: the first type of boundary conditions: known boundary temperature. The second type of boundary conditions: the normal derivative or heat flux density of the known boundary temperature. The third type of boundary conditions: known convection heat transfer coefficient and fluid temperature. In the simulation of the internal thermal field of the cable bridge of the present invention, the boundary conditions are the third type of boundary conditions. This is because there is convection heat transfer between the air inside the cable bridge and the external environment, and the convection heat transfer coefficient and the external environment temperature are known. The formula of the boundary conditions and the calculation formula of the relevant parameters are the basis for determining the heat exchange relationship between the model and the external environment. By correctly setting the boundary conditions, the accuracy and reliability of the finite element model can be ensured.

[0055] In one possible implementation, before inputting the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain the predicted value of the cable core temperature of the cable to be predicted, the method can also perform the following processing: normalizing the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable; constructing a data set based on the normalized historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and training an extreme gradient boosting tree model based on the data set.

[0056] In this embodiment, the historical ambient temperature, load current and cable core temperature data are normalized to eliminate the dimension and value range differences. The normalized data is used to construct input features and target variables. The extreme gradient boosting tree model is trained based on the normalized data set, so that the model can learn the relationship between the input features and the cable core temperature, improve the training effect and prediction accuracy of the model, and thus more accurately predict the cable core temperature of the cable.

[0057] In one possible implementation, the extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm, and the specific process is as follows: generate an initial random population; take the minimum error and model complexity as the optimization goal, control the step size through the Newton-Raphson search rule, and add disturbances in combination with the trap avoidance operation to optimize the parameters of the extreme gradient boosting tree model; apply the optimized parameters to the extreme gradient boosting tree model to obtain the optimized extreme gradient boosting tree model.

[0058] In this embodiment, NRBO is an algorithm based on Bayesian optimization for optimizing complex nonlinear objective functions. The optimal solution is efficiently searched by constructing a proxy model of the objective function (such as a Gaussian process). NRBO is particularly suitable for optimization problems in high-dimensional parameter space and can effectively balance exploration and utilization. Extreme Gradient Boosting Tree Model (ExtremeGradient Boosting, XGBoost), the algorithm is a type of synthetic algorithm that combines basis functions and weights to form a good data fitting effect. XGBoost is more efficient in processing large-scale data sets and complex models, and also performs well in preventing overfitting and improving generalization ability. By generating an initial random population, a diverse starting point is provided for optimization. By minimizing the error, the prediction accuracy of the model is improved. By minimizing the complexity of the model, overfitting is prevented and the generalization ability of the model is improved. The Newton-Raphson method can quickly converge to the local optimal solution and improve the optimization efficiency. Optimize parameters by trap avoidance operations to avoid the optimization process from falling into the local optimal solution and increase the probability of finding the global optimal solution.

[0059] Specifically, the XGBoost model can be expressed as:

[0060] In the formula, F ={f(x)=wq(x)}(q:Rm→{1,2,...T},w∈RT) is a set of CART decision tree structures, q is the tree structure mapping samples to leaf nodes, T is the number of leaf nodes, and w is the real number score of leaf nodes.

[0061] When setting up the XGBoost model, you need to find the optimal parameters based on the principle of minimizing the objective function to build the optimal model. The objective function of the XGBoost model can be divided into the error function term L and the model complexity function term Ω.

[0062]

[0063]

[0064]

[0065] In the formula, is the true value, is the predicted value, is the L1 regularization term, is the L2 regularization term.

[0066] When using the training data to optimize the model, keep the original model unchanged, add the new function f to get the objective function:

[0067] After the second-order Taylor expansion, the objective function is:

[0068] After removing the constant term, the objective function is expressed as:

[0069] In the formula, is the first-order expansion coefficient, is to define the decision tree function, is the second-order expansion coefficient.

[0070] Substituting the decision tree function into the objective function yields:

[0071] After completing the above parts, the Obj function is optimized through NRBO, the optimal parameters of the model are found through the value of Obj, and the optimal XGBoost model is established.

[0072] The implementation steps of the NRBO optimization algorithm are: Step 1: Generate a random population:

[0073] In the formula, , are the upper and lower bounds for generating random populations.

[0074] Step 2: Find the optimal solution through NRSR (Newton-Raphson search rule):

[0075] In the formula, is the random variation, a , b , , is a random number between (0, 1), is the number of iterations, is the optimal location. It's the worst position. yes and Generate the position of the vector. (With an initial value, find the optimal value from the set random population) Step 3: Achieve better performance and avoid local optimality through trap avoidance operations:

[0076] In the formula, , are consistent random numbers between (-1, 1) and (-0.5, 0.5), , is a random number generated according to the formula, is the best location, is an adaptive function.

[0077] The embodiment of the present invention obtains the ambient temperature data and load current data of the cable to be predicted, inputs the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model, and obtains the predicted value of the cable core temperature of the cable to be predicted, wherein the temperature prediction model is obtained by training the extreme gradient boosting tree model based on a pre-constructed data set, the data set includes the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, the historical cable core temperature data of each cable is obtained according to finite element analysis, and the historical cable core temperature data of the cable is determined by high-precision finite element analysis to improve the accuracy of the model training data. The training process of the temperature prediction model includes: optimizing the extreme gradient boosting tree model according to the NRBO optimization algorithm to improve the accuracy of the model. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model, and the historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model, and the optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model. The thermal field distribution inside the cable bridge is simulated by high-precision finite element analysis to obtain the historical cable core temperature data, and a data set is constructed, and the parameters of the extreme gradient boosting tree model are optimized by the NRBO algorithm to improve the accuracy of the model. The temperature prediction model of the cable is obtained by training the optimized extreme gradient boosting tree model based on the data set. When predicting the cable core temperature, the newly acquired ambient temperature and load current are input into the temperature prediction model to obtain the predicted value of the cable core temperature, thereby improving the calculation efficiency of the cable core temperature, being able to quickly adapt to changes in cable load and ambient temperature, and achieving accurate temperature monitoring and early warning.

[0078] In a possible implementation, the method can also be processed as follows: a preset proportion of data in the data set is used as a training set, and the remaining data is used as a test set; the optimized extreme gradient boosting tree model is trained according to the training set, and the optimized extreme gradient boosting tree model is tested according to the test set to obtain a temperature prediction model.

[0079] In this embodiment, the data set is divided into a training set and a test set, usually in a preset ratio (such as 80% training set, 20% test set). The optimized XGBoost model is trained using the training set so that the model learns the relationship between the input features and the target variable. The trained model is evaluated using the test set to ensure that the model can accurately predict data that has not been seen. If the model performs well on the test set, it can be used as the final temperature prediction model. Through this process, it can be ensured that the model not only performs well on the training data, but also can reliably predict the cable core temperature of the cable in practical applications.

[0080] The present invention simulates the thermal field distribution inside the cable bridge through high-precision finite element analysis, and uses the NRBO algorithm to optimize the parameters of the XGBOOST model, thereby improving the prediction accuracy and calculation efficiency of the cable steady-state temperature, and further improving the calculation accuracy of the cable core temperature. It can quickly adapt to changes in cable load and ambient temperature, and realize accurate temperature monitoring and early warning, thereby reducing maintenance costs, reducing failure risks, extending cable life, and improving the safety and reliability of the power system. In the face of various load modes, this method can better and faster judge the cable condition.

[0081] In other possible ways, one or more stages in the extreme gradient boosting tree model and NRBO can adopt other ways. This application mainly uses the extreme gradient boosting tree model and NRBO processing as examples for explanation.

[0082] In order to better understand the present invention, the above process is described in detail below with reference to a specific example. The numerical values ​​used in this example are only examples, and users can make corresponding changes according to actual needs.

[0083] According to the basic process of this method, the geometric model of the cable bridge is established as follows: Figure 2 As shown. The cable bridge is in the air as a whole. The inside of the cable bridge is air. The air layer is set for convective heat transfer, that is, the uneven thermal field of the fluid itself produces an uneven density field, and the resulting buoyancy becomes the driving force of fluid movement. The geometric structure parameters of the cable bridge are shown in Table 1.

[0084] Table 1

[0085] A cross-sectional view of the cable is shown below: Figure 3 As shown, the structural parameters of each layer of the cable are shown in Table 2.

[0086] Table 2

[0087] In this invention, the physical model is surrounded by air, which belongs to the third type of boundary conditions in the thermal field boundary. The convection heat transfer coefficient and the external environment temperature need to be known. In this paper, the boundary conditions, the upper boundary heat transfer coefficient is set to 4.5W / (K· )The left and right boundaries are set to 4W / (K· )The lower boundary is set to 1.5W / (K· ).

[0088] Through the above parameters, the finite element model of the cable bridge can be established.

[0089] By setting the model temperature, applying the load with an ambient temperature of [0-40]℃ and a load current of [0-1500]A, the steady-state cable core temperature data of the cable bridge is collected.

[0090] After data collection, the data group is divided into a training set and a test set; the training set and the test set are normalized; the normalized training set is used to train the cable core temperature prediction model, and the normalized test set is used to test the performance of the trained cable core temperature prediction model.

[0091] According to the finite element simulation model of the cable bridge, the cable core temperature under different conditions is obtained. The first 80% of the data in the data set is used as the training set of the prediction model; the last 20% of the data is used as the test set of the cable core temperature prediction model. The input and output data of the prediction model take the A phase cable in the three-phase cable as an example. The output of the cable core temperature prediction model is the predicted cable core temperature on the fifth day.

[0092] In view of the error and accuracy of cable core temperature prediction based on finite element NRBO-XGBoost model, the determination coefficient and root mean square error were selected as the evaluation criteria.

[0093] Table 3

[0094] Taking the three-phase A power cable as an example, taking the A-phase cable as an example, the root mean square error (RMSE) and the coefficient of determination (R²) are first used to evaluate the performance of the NRBO-XGBoost model on the A-phase cable temperature test set. From the data in Table 3, it can be seen that the model has a high accuracy in the temperature prediction of the A-phase cable. Specifically, the RMSE value is 0.64774, indicating that the error between the predicted value and the true value is relatively small; at the same time, the R² value is 0.99842, indicating that the model has a very high fit to the temperature change of the A-phase cable, indicating that the model can accurately capture the law of temperature change. As shown in Table 3. Figure 5 As shown in the figure, the predicted value and the true value of the core temperature of phase A cable have a good fit.

[0095] Figure 4 The prediction effect of the model on the entire sample set is shown, comparing the fit between the actual temperature and the predicted temperature; Figure 5 Display the prediction results of the model on the training set, reflecting the model's ability to learn the training data; Figure 6 The model's prediction effect on the test set is shown in the figure above. It can be seen from the figure that the model can learn from the data and adapt to complex nonlinear relationships, and its prediction results can maintain high stability under different conditions. Figure 7 It is a schematic diagram of the prediction error of the test set.

[0096] 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.

[0097] 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.

[0098] Figure 8 The schematic diagram of the structure of the cable temperature prediction device for laying cables on a cable bridge provided by an 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: like Figure 8 As shown, the cable bridge laying cable temperature prediction device 8 includes: A data acquisition module 81 is used to acquire the ambient temperature data and load current data of the cable to be predicted; The temperature prediction module 82 is used to input the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, and the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; The training process of the temperature prediction model includes: The extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model. The historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model. The optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model.

[0099] The embodiment of the present invention obtains the ambient temperature data and load current data of the cable to be predicted, inputs the ambient temperature data and load current data of the cable to be predicted into a pre-trained temperature prediction model, and obtains the predicted value of the cable core temperature of the cable to be predicted, wherein the temperature prediction model is obtained by training the extreme gradient boosting tree model based on a pre-constructed data set, the data set includes the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, the historical cable core temperature data of each cable is obtained according to finite element analysis, and the historical cable core temperature data of the cable is determined by high-precision finite element analysis to improve the accuracy of the model training data. The training process of the temperature prediction model includes: optimizing the extreme gradient boosting tree model according to the NRBO optimization algorithm to improve the accuracy of the model. The historical ambient temperature data and historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model, and the historical cable core temperature data is used as the output of the optimized extreme gradient boosting tree model, and the optimized extreme gradient boosting tree model is trained to obtain the temperature prediction model. The thermal field distribution inside the cable bridge is simulated by high-precision finite element analysis to obtain the historical cable core temperature data, and a data set is constructed, and the parameters of the extreme gradient boosting tree model are optimized by the NRBO algorithm to improve the accuracy of the model. The temperature prediction model of the cable is obtained by training the optimized extreme gradient boosting tree model based on the data set. When predicting the cable core temperature, the newly acquired ambient temperature and load current are input into the temperature prediction model to obtain the predicted value of the cable core temperature, thereby improving the calculation efficiency of the cable core temperature, being able to quickly adapt to changes in cable load and ambient temperature, and achieving accurate temperature monitoring and early warning.

[0100] In a possible implementation, the temperature prediction module 82 is further configured to: Obtain the physical properties, boundary conditions and internal physical fields of the cable bridge; the physical properties include the material properties, geometric structure and laying method of the cable, the boundary conditions are the third-class boundary conditions, the internal physical fields of the cable bridge include the coupling of flow field and thermal field and the thermal field, the thermal field includes the heat conduction between the cable body and the bridge body, the convection heat transfer of the air in the closed space of the bridge, and the thermal radiation between the cable surface and the inner wall of the bridge; Construct a finite element model of the cable based on physical properties, boundary conditions and the internal physical fields of the cable bridge; Input the historical ambient temperature data and historical load current data of the set cable into the finite element model to obtain the thermal field distribution inside the cable bridge; The temperature value at the cable core position is extracted from the thermal field as the historical cable core temperature data.

[0101] In a possible implementation, the temperature prediction module 82 is further configured to: Normalize the historical ambient temperature data, historical load current data and historical cable core temperature data of the cable; A data set is constructed based on the normalized historical ambient temperature data, historical load current data, and historical cable core temperature data of the cable, and an extreme gradient boosting tree model is trained based on the data set.

[0102] In a possible implementation, the temperature prediction module 82 is further configured to: Generate an initial random population; Taking the minimum error and model complexity as the optimization goal, the Newton-Raphson search rule is used to control the step size, and the perturbation is added in combination with the trap avoidance operation to optimize the parameters of the extreme gradient boosting tree model; The optimized parameters are applied to the extreme gradient boosting tree model to obtain the optimized extreme gradient boosting tree model.

[0103] Fig. 9 is a schematic diagram of a terminal provided by an embodiment of the present invention. Fig. 9 As shown, the terminal 9 of this embodiment includes: a processor 90, a memory 91, and a computer program 92 stored in the memory 91 and executable on the processor 90. When the processor 90 executes the computer program 92, the steps in the above-mentioned various cable bridge cable temperature prediction methods are implemented, such as Figure 1 Alternatively, when the processor 90 executes the computer program 92, the functions of the modules in the above-mentioned device embodiments are realized, for example Figure 8 The functions of each module are shown.

[0104] Exemplarily, the computer program 92 may be divided into one or more modules, which are stored in the memory 91 and executed by the processor 90 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 92 in the terminal 9. For example, the computer program 92 may be divided into Figure 8 The modules shown.

[0105] The terminal 9 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 9 may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will appreciate that Fig. 9 It is only an example of terminal 9 and does not constitute a limitation on terminal 9. 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.

[0106] The processor 90 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.

[0107] The memory 91 may be an internal storage unit of the terminal 9, such as a hard disk or memory of the terminal 9. The memory 91 may also be an external storage device of the terminal 9, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 9. Further, the memory 91 may also include both an internal storage unit of the terminal 9 and an external storage device. The memory 91 is used to store the computer program and other programs and data required by the terminal. The memory 91 may also be used to temporarily store data that has been output or is to be output.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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 the modules or units is only a logical function division. 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.

[0112] 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.

[0113] 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.

[0114] If the integrated module 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 cable bridge laying cable temperature prediction method embodiments 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 that can carry the 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. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0115] The embodiments described above 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 all be included in the protection scope of the present invention.

Claims

1. A method for predicting the temperature of cables laid in a cable bridge, characterized in that: include: Obtaining ambient temperature data and load current data of the cable to be predicted; Inputting the ambient temperature data of the cable to be predicted and the load current data into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; The training process of the temperature prediction model includes: The extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm, the historical ambient temperature data and the historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model, the historical cable core temperature data are used as the output of the optimized extreme gradient boosting tree model, the optimized extreme gradient boosting tree model is trained, and the temperature prediction model is obtained.

2. The cable temperature prediction method for laying cables in a cable bridge according to claim 1, characterized in that: The historical cable core temperature data of the cable are obtained based on finite element analysis, including: Obtain the physical properties, boundary conditions and internal physical fields of the cable bridge; wherein the physical properties include the material properties, geometric structure and laying method of the cable, the boundary conditions are third-class boundary conditions, the internal physical fields of the cable bridge include the coupling of flow field and thermal field and the thermal field, and the thermal field includes the heat conduction between the cable body and the bridge body, the convection heat transfer of the air in the closed space of the bridge, and the thermal radiation between the cable surface and the inner wall of the bridge; Constructing a finite element model of the cable according to the physical properties, the boundary conditions and the internal physical field of the cable bridge; Inputting the historical ambient temperature data and the historical load current data of the set cable into the finite element model to obtain the thermal field distribution inside the cable bridge; The temperature value of the cable core position is extracted from the thermal field as the historical cable core temperature data.

3. The cable temperature prediction method for laying cables in a cable bridge according to claim 2, characterized in that: The heat conduction formula between the cable body and the bridge body is: In the formula, For point The temperature of the medium, is the volume heat generation rate, is the thermal conductivity of the medium; The convective heat transfer formula of the air in the closed space of the bridge is: In the formula, and The fluid velocities of air are Axis and The weight of the axis, is the flow field pressure, is the dynamic viscosity of the fluid, is the fluid reference temperature, is the density of air, g is the acceleration due to gravity, is the volume expansion coefficient, is the specific heat capacity of the fluid, is the thermal conductivity of the medium; The heat radiation formula between the cable surface and the inner wall of the bridge is: In the formula, is the net heat exchange between the first surface and the second surface, is the surface area of ​​the first surface participating in radiation, is the Stefan Pan-Boltzmann constant, and are the surface emissivity of the first surface and the second surface, is the angular coefficient, and is the surface temperature of the first surface and the second surface; The coupling formula of flow field and thermal field is: In the formula, is the fluid density, is the fluid pressure, u is the fluid velocity, μ is the dynamic viscosity, is the gradient, is the identity matrix, is the acceleration due to gravity, T It is the real-time temperature.

4. The cable temperature prediction method for laying cables in a cable bridge according to claim 2, characterized in that: The formula for the boundary condition is: ) In the formula, is the thermal conductivity, is the boundary temperature, is the fluid temperature, is the boundary heat transfer coefficient, is the Grashof number, is the Prandtl number, is the volume expansion coefficient, is the acceleration due to gravity, is the temperature difference, is the linear dimension, is the dynamic viscosity, is the convective heat transfer coefficient required for boundary conditions, is the Nusselt number, is the specific heat capacity, Set value for experience.

5. The method for predicting the temperature of cables laid in a cable bridge according to claim 1, characterized in that: Before inputting the ambient temperature data of the cable to be predicted and the load current data into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted, the method further includes: Normalizing the historical ambient temperature data of the cable, the historical load current data, and the historical cable core temperature data; The data set is constructed according to normalized historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and the extreme gradient boosting tree model is trained based on the data set.

6. The cable temperature prediction method for laying cables in a cable bridge according to claim 1, characterized in that: The optimization of the extreme gradient boosting tree model according to the NRBO optimization algorithm includes: Generate an initial random population; Taking the minimum error and model complexity as the optimization goal, the Newton-Raphson search rule is used to control the step size, and the perturbation is added in combination with the trap avoidance operation to optimize the parameters of the extreme gradient boosting tree model; The optimized parameters are applied to the extreme gradient boosting tree model to obtain the optimized extreme gradient boosting tree model.

7. The method for predicting the temperature of cables laid in a cable bridge according to claim 1, characterized in that: The method further comprises: Using a preset proportion of data in the data set as a training set, and using the remaining data as a test set; The optimized extreme gradient boosting tree model is trained according to the training set, and the optimized extreme gradient boosting tree model is tested according to the test set to obtain the temperature prediction model.

8. A device for predicting the temperature of cables installed in a cable bridge, characterized in that: include: A data acquisition module, used to acquire ambient temperature data and load current data of the cable to be predicted; A temperature prediction module, used for inputting the ambient temperature data of the cable to be predicted and the load current data into a pre-trained temperature prediction model to obtain a predicted value of the cable core temperature of the cable to be predicted; wherein the temperature prediction model is obtained by training an extreme gradient boosting tree model based on a pre-constructed data set, the data set includes historical ambient temperature data, historical load current data and historical cable core temperature data of the cable, and each historical cable core temperature data of the cable is obtained according to finite element analysis; The training process of the temperature prediction model includes: The extreme gradient boosting tree model is optimized according to the NRBO optimization algorithm, the historical ambient temperature data and the historical load current data of the cable are used as the input of the optimized extreme gradient boosting tree model, the historical cable core temperature data are used as the output of the optimized extreme gradient boosting tree model, the optimized extreme gradient boosting tree model is trained, and the temperature prediction model is obtained.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. 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 as claimed in any one of claims 1 to 7 are implemented.

Images