Heat absorption and heat dissipation coefficient calculation method and device, terminal equipment and storage medium

Abstract

The invention discloses a heat absorption and heat dissipation coefficient calculation method and device, terminal equipment and a storage medium, and the method comprises the steps: obtaining the wire allowable temperature, environment temperature, sunlight intensity, wind speed and wire current of a to-be-detected wire, inputting the obtained temperature, environment temperature, sunlight intensity, wind speed and wire current into a trained heat absorption and heat dissipation coefficient prediction model, the heat absorption and heat dissipation coefficient prediction model outputs a heat absorption coefficient prediction value and a heat dissipation coefficient prediction value; wherein the training process of the heat absorption and heat dissipation coefficient prediction model comprises the following steps: taking historical lead allowable temperature, historical environment temperature, historical sunlight intensity, historical wind speed and historical lead current of historical data as sample data, and taking historical lead heat absorption data and historical lead heat dissipation data corresponding to the historical data as labels of the sample data; and training the constructed heat absorption and heat dissipation coefficient prediction model according to each piece of sample data and the corresponding label. The technical problem that the accurate and specific heat absorption coefficient and heat dissipation coefficient of the wire cannot be obtained in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of transmission line detection, and particularly to a method, device, terminal device and storage medium for calculating the heat absorption and dissipation coefficients. Background Art

[0002] In recent years, in order to get rid of the dependence on fossil energy, the power generation of new energy has been continuously increased. However, the corresponding new energy consumption system is not perfect, resulting in large-scale electric energy loss and resource waste. Among them, the amount of abandoned electricity caused by the limitation of line current-carrying capacity accounts for about half of the new energy abandoned electricity, and the current-carrying capacity of transmission lines faces severe challenges. As an important data for line design and operation, the current-carrying capacity has attracted wide attention. Among the factors affecting the current-carrying capacity, environmental temperature, wind speed, sunshine intensity, etc. can be measured accurately by instruments, while the heat absorption and dissipation coefficients of the wire are not given clear values in relevant standards. Therefore, accurately calculating the heat absorption and dissipation coefficients of the wire is crucial for the wire temperature rise, heat balance and current-carrying capacity. However, the existing heat absorption and dissipation coefficients of the wire only have a range for reference in relevant standards, and accurate and specific values cannot be obtained. Summary of the Invention

[0003] The present invention provides a method, device, terminal device and storage medium for calculating the heat absorption and dissipation coefficients to solve the technical problem that the existing technology cannot obtain accurate and specific heat absorption and dissipation coefficients of the wire.

[0004] To solve the above technical problem, an embodiment of the present invention provides a method for calculating the heat absorption and dissipation coefficients, including:

[0005] Obtaining the allowable temperature of the wire to be measured, environmental temperature, sunshine intensity, wind speed and wire current;

[0006] Inputting the allowable temperature of the wire, environmental temperature, sunshine intensity, wind speed and wire current into the trained heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model predicts the heat absorption coefficient and heat dissipation coefficient of the wire to be measured according to the allowable temperature of the wire, environmental temperature, sunshine intensity, wind speed and wire current, and outputs the predicted heat absorption coefficient value and the predicted heat dissipation coefficient value;

[0007] Wherein, the training process of the heat absorption and dissipation coefficient prediction model includes:

[0008] Obtaining a number of historical data; wherein each historical data includes the historical allowable temperature of the wire, historical environmental temperature, historical sunshine intensity, historical wind speed, historical wire current, historical wire heat absorption data and historical wire heat dissipation data at the same moment;

[0009] Taking the historical allowable temperature of the conductor, historical ambient temperature, historical sunshine intensity, historical wind speed, and historical conductor current of each historical data as sample data, and taking the historical heat absorption data and historical heat dissipation data corresponding to the historical data as labels of the sample data;

[0010] According to each sample data and the corresponding label, train the constructed heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model makes a prediction based on the sample data and outputs a sample heat absorption coefficient prediction value and a sample heat dissipation prediction value;

[0011] Calculate the training error according to the sample heat absorption coefficient prediction value, sample heat dissipation coefficient prediction value, and the corresponding label;

[0012] Adjust the weights and thresholds of the heat absorption and dissipation coefficient prediction model according to the training error to obtain a trained heat absorption and dissipation coefficient prediction model.

[0013] As a preferred solution, the construction process of the heat absorption and dissipation coefficient prediction model includes:

[0014] Construct an initial BP neural network according to the preset number of input layer nodes and output layer nodes;

[0015] Determine the number of hidden layer nodes of the BP neural network by trial and error according to the number of input layer nodes and output layer nodes;

[0016] Determine the initial weights and initial thresholds of the BP neural network according to the number of input layer nodes and output layer nodes;

[0017] Take the BP neural network as the heat absorption and dissipation coefficient prediction model.

[0018] As a preferred solution, the adjustment of the weights and thresholds of the heat absorption and dissipation coefficient prediction model according to the training error includes:

[0019] Take the weights and thresholds of the heat absorption and dissipation coefficient prediction model as optimization variables, take the training error as the fitness function, and optimize and adjust the weights and thresholds through the whale optimization algorithm with the goal of minimizing the fitness function.

[0020] As a preferred solution, the optimization and adjustment of the weights and thresholds through the whale optimization algorithm includes:

[0021] Take the weights and thresholds of the heat absorption and dissipation coefficient prediction model as the whale position;

[0022] Repeat the whale position iteration operation for a preset number of times;

[0023] Among them, the whale position iteration operation includes:

[0024] Randomly obtain a first random number within the interval [0, 1];

[0025] When the first random number is greater than or equal to a preset first random number threshold, select the spiral mechanism as the whale position update mechanism;

[0026] When the first random number is less than the first random number threshold, obtain the iteration parameter of the current iteration and randomly obtain a second random number within the interval [0, 1]; wherein, the iteration parameter is a parameter that linearly decreases with the number of iterations;

[0027] Calculate a first coefficient according to the iteration parameter and the second random number;

[0028] When the absolute value of the first coefficient is less than a preset first coefficient threshold, select the encircling mechanism as the whale position update mechanism;

[0029] When the absolute value of the first coefficient is greater than or equal to the first coefficient threshold, select the search mechanism as the whale position update mechanism;

[0030] Update the whale position according to the selected whale position update mechanism to realize the optimization and adjustment of the weights and thresholds.

[0031] As a preferred solution, the whale position update formula of the spiral mechanism is:

[0032] X(t + 1) = X * (t) + D 1 ·e bl ·cos(2πl);

[0033] D 1 = |X * (t) - X(t)|;

[0034] In the formula, X(t + 1) represents the updated whale position; X(t) represents the whale position before update; X * (t) represents the optimal whale position of the current iteration; b is a constant used to define the shape of the spiral; l represents a random number in the interval [-1, 1]; D 1 represents the length of the spiral path; t represents the current iteration number;

[0035] The whale position update formula of the encircling mechanism is:

[0036] X(t + 1) = X * (t) - A·D 2 ;

[0037] D 2 = |C·X* |(t) - X(t)|;

[0038] A = 2ar - a;

[0039] C = 2r;

[0040] In the formula, D 2 represents the enclosed path length; A represents the first coefficient; C represents the second coefficient; a represents the iteration parameter; r represents the second random number;

[0041] The formula for updating the whale position of the search mechanism is:

[0042] X(t + 1) = X rand (t) - A·D 3 ;

[0043] D 3 = |C·X rand (t) - X(t)|;

[0044] In the formula, D 3 represents the search path length; X rand (t) represents the random whale position.

[0045] As a preferred solution, the activation function of the output layer of the BP neural network is the pure lin activation function; the activation function of the hidden layer of the BP neural network is the tansig activation function.

[0046] As a preferred solution, the initial population number of the whale optimization algorithm is 30, and the preset number of iterations is 80.

[0047] On the basis of the above embodiments, another embodiment of the present invention provides a device for calculating the endothermic and heat dissipation coefficients, including: a data acquisition module and an endothermic and heat dissipation coefficient prediction module;

[0048] The data acquisition module is used to acquire the allowable temperature of the wire to be measured, the ambient temperature, the sunlight intensity, the wind speed, and the wire current;

[0049] The endothermic and heat dissipation coefficient prediction module is used to input the allowable temperature of the wire, the ambient temperature, the sunlight intensity, the wind speed, and the wire current into the trained endothermic and heat dissipation coefficient prediction model, so that the endothermic and heat dissipation coefficient prediction model predicts the endothermic coefficient and the heat dissipation coefficient of the wire to be measured according to the allowable temperature of the wire, the ambient temperature, the sunlight intensity, the wind speed, and the wire current, and outputs the predicted endothermic coefficient value and the predicted heat dissipation coefficient value;

[0050] Among them, the training process of the endothermic and heat dissipation coefficient prediction model includes:

[0051] Obtain a number of historical data; wherein, each historical data includes the historical allowable temperature of the wire, historical ambient temperature, historical sunshine intensity, historical wind speed, historical wire current, historical wire heat absorption data, and historical wire heat dissipation data at the same moment;

[0052] Take the historical allowable temperature of the wire, historical ambient temperature, historical sunshine intensity, historical wind speed, and historical wire current of each historical data as sample data, and take the historical wire heat absorption data and historical wire heat dissipation data corresponding to the historical data as labels of the sample data;

[0053] According to each sample data and its corresponding label, train the constructed heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model makes a prediction based on the sample data and outputs a sample heat absorption coefficient prediction value and a sample heat dissipation prediction value;

[0054] Calculate the training error according to the sample heat absorption coefficient prediction value, sample heat dissipation coefficient prediction value, and their corresponding labels;

[0055] Adjust the weights and thresholds of the heat absorption and dissipation coefficient prediction model according to the training error to obtain a trained heat absorption and dissipation coefficient prediction model.

[0056] Based on the above embodiments, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the heat absorption and dissipation coefficient calculation method described in the above embodiments of the present invention.

[0057] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute the heat absorption and dissipation coefficient calculation method described in the above embodiments of the present invention.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] The present invention obtains the allowable temperature of the wire to be measured, the ambient temperature, the sunshine intensity, the wind speed, and the wire current of the wire to be measured, and inputs the obtained values into a trained heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model outputs a heat absorption coefficient prediction value and a heat dissipation coefficient prediction value. The training process of the heat absorption and dissipation coefficient prediction model includes: obtaining a number of historical data; each historical data includes the historical allowable temperature of the wire, the historical ambient temperature, the historical sunshine intensity, the historical wind speed, the historical wire current, the historical wire heat absorption data, and the historical wire heat dissipation data at the same moment; using the historical allowable temperature of the wire, the historical ambient temperature, the historical sunshine intensity, the historical wind speed, and the historical wire current of each historical data as sample data, and using the historical wire heat absorption data and the historical wire heat dissipation data corresponding to the historical data as the labels of the sample data; training the constructed heat absorption and dissipation coefficient prediction model according to each sample data and the corresponding label, so that the heat absorption and dissipation coefficient prediction model makes a prediction based on the sample data and outputs a sample heat absorption coefficient prediction value and a sample heat dissipation prediction value; calculating a training error according to the sample heat absorption coefficient prediction value, the sample heat dissipation coefficient prediction value, and the corresponding label; adjusting the weights and thresholds of the heat absorption and dissipation coefficient prediction model according to the training error to obtain a trained heat absorption and dissipation coefficient prediction model. The present invention can obtain the allowable temperature of the wire to be measured, the ambient temperature, the sunshine intensity, the wind speed, and the wire current of the wire to be measured according to the actual operating conditions of the wire, and calculate the heat absorption and dissipation coefficients based on the obtained data, solving the technical problem that the prior art cannot obtain accurate and specific wire heat absorption and dissipation coefficients. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a schematic flowchart of a method for calculating a heat absorption and dissipation coefficient provided by an embodiment of the present invention;

[0061] Figure 2 is a schematic structural diagram of a device for calculating a heat absorption and dissipation coefficient provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present application fall within the scope of protection of the present application.

[0063] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "plural" is more than two, unless otherwise specifically defined.

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] Embodiment 1

[0066] Please refer to Figure 1 , which is a schematic structural diagram of a method for calculating the heat absorption and dissipation coefficient provided by an embodiment of the present invention, including:

[0067] S1. Obtain the allowable temperature of the wire to be measured, the ambient temperature, the sunlight intensity, the wind speed and the wire current.

[0068] It should be noted that after obtaining the allowable temperature of the wire to be measured, the ambient temperature, the sunlight intensity, the wind speed and the wire current, the data can also be processed as follows:

[0069] (1) Eliminate abnormal data: The judgment of abnormal data uses the Grubbs two-sided test method

[0070]

[0071] In the formula, represents the sample mean; S represents the sample standard deviation; x n represents the nth data after sorting from small to large; G n represents the upper statistic; G n ′ represents the lower statistic;

[0072] Determine the detection level α, and determine the critical value G 1-α / 2 (n) by referring to the Grubbs table. When G n >G n ′ and G n >G 1-α / 2 (n), it is determined that x n is an outlier. When G n ′>G n and G n ′>

[0073] G 1-α / 2 (n), it is determined that x1 is an outlier, otherwise it is determined that no outlier is found.

[0074] (2) Preprocess the data using the Z - normalization method:

[0075]

[0076] In the formula, i represents the i - th type of parameter; j represents the j - th sample point; x ij is the original data collected; μ i represents the calculation method of the average value of the i - th type of parameter; σ i represents the calculation method of the standard deviation of the i - th type of parameter; n i represents the number of sample points of the i - th type of parameter.

[0077] S2. Input the allowable wire temperature, ambient temperature, sunshine intensity, wind speed, and wire current into the trained heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model predicts the heat absorption coefficient and heat dissipation coefficient of the wire to be measured according to the wire allowable temperature, ambient temperature, sunshine intensity, wind speed, and wire current, and outputs the predicted heat absorption coefficient value and the predicted heat dissipation coefficient value.

[0078] Among them, the training process of the heat absorption and dissipation coefficient prediction model includes:

[0079] Obtain a number of historical data; among them, each historical data includes the historical wire allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed, historical wire current, historical wire heat absorption data, and historical wire heat dissipation data at the same moment;

[0080] Take the historical wire allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed, and historical wire current of each historical data as sample data, and take the historical wire heat absorption data and historical wire heat dissipation data corresponding to the historical data as the labels of the sample data;

[0081] According to each sample data and the corresponding label, train the constructed heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model predicts according to the sample data and outputs the predicted sample heat absorption coefficient value and the predicted sample heat dissipation value;

[0082] Calculate the training error according to the predicted sample heat absorption coefficient value, the predicted sample heat dissipation coefficient value, and the corresponding label;

[0083] According to the training error, adjust the weights and thresholds of the heat absorption and dissipation coefficient prediction model to obtain the trained heat absorption and dissipation coefficient prediction model.

[0084] It should be noted that during the model training process, the number of training times is set to 1000, and the learning rate is set to 0.01.

[0085] In a preferred embodiment, the process of constructing the endothermic and exothermic coefficient prediction model includes:

[0086] Construct an initial BP neural network according to the preset number of input layer nodes and the number of output layer nodes;

[0087] According to the number of input layer nodes and the number of output layer nodes, determine the number of hidden layer nodes of the BP neural network by the trial and error method;

[0088] According to the number of input layer nodes and the number of output layer nodes, determine the initial weights and initial thresholds of the BP neural network;

[0089] Take the BP neural network as the endothermic and exothermic coefficient prediction model.

[0090] In this embodiment, when determining the number of hidden layer nodes, too few hidden layer nodes may not be able to capture the complex relationships in the input data, resulting in underfitting of the model and insufficient prediction ability; too many hidden layer nodes may cause overfitting, making the model too complex to generalize to new data. In the present invention, the number of hidden layers of the neural network is determined by using an empirical formula. The empirical formula is:

[0091]

[0092] In the formula, num is the number of hidden layers, m is the number of input layer nodes, n is the number of output layer nodes, and a is a constant between 1 and 10. Therefore, there are ten choices for the number of hidden nodes. The trial and error method can be used to determine the number of hidden nodes. Before constructing the BP neural network model, use ten different numbers of hidden layer nodes to establish models respectively, substitute the training input data into the models, calculate the outputs of the models, compare the errors between the calculated outputs and the true outputs of the training samples, and select the model with the smallest error as the final number of hidden layer nodes of the model.

[0093] In a preferred embodiment, the adjustment of the weights and thresholds of the endothermic and exothermic coefficient prediction model according to the training error includes:

[0094] Take the weights and thresholds of the endothermic and exothermic coefficient prediction model as optimization variables, take the training error as the fitness function, and optimize and adjust the weights and thresholds through the whale optimization algorithm with the goal of minimizing the fitness function.

[0095] In this embodiment, the whale optimization algorithm is used to find the optimal initial weights and thresholds of the BP neural network. That is, the weights and thresholds of the BP neural network are used as the optimization variables of the whale algorithm, and the mean square error of the training and test samples is used as the fitness function. The smaller the obtained fitness function value, the more accurate the training, and the higher the prediction accuracy of the model. The optimized BP neural network can calculate the heat absorption and heat dissipation coefficients of the wire more accurately.

[0096] The fitness function is the training error of the BP neural network. With the goal of minimizing the fitness function, the initial weights and thresholds when the error is minimized are saved. The specific fitness function is as follows:

[0097]

[0098] In the formula, n is the number of samples; T i is the label value; is the predicted value.

[0099] It should be noted that the position of each whale corresponds to a specific configuration of the BP neural network, that is, a specific set of weights and thresholds. These positions (i.e., the parameters of the BP network) are updated through the search and optimization process of the whale algorithm to minimize the error between the network prediction value and the actual value. Specifically, the whale algorithm updates the position of the whale by simulating the hunting behavior of the humpback whale, such as surrounding the prey, spiral movement, and shrinking the surrounding mechanism, so as to adjust the weights and thresholds of the BP network to achieve the purpose of optimizing the network performance.

[0100] In a preferred embodiment, the optimization and adjustment of the weights and thresholds by the whale optimization algorithm include:

[0101] Taking the weights and thresholds of the heat absorption and heat dissipation coefficient prediction model as the whale position;

[0102] Repeatedly performing the whale position iteration operation for a preset number of times;

[0103] Among them, the whale position iteration operation includes:

[0104] Randomly obtaining a first random number within the range of [0, 1];

[0105] When the first random number is greater than or equal to the preset first random number threshold, select the spiral mechanism as the whale position update mechanism;

[0106] When the first random number is less than the first random number threshold, obtain the iteration parameter of the current iteration and randomly obtain a second random number within the range of [0, 1]; among them, the iteration parameter is a parameter that linearly decreases with the number of iterations;

[0107] Calculate the first coefficient according to the iteration parameter and the second random number;

[0108] When the absolute value of the first coefficient is less than a preset first coefficient threshold, select the encircling mechanism as the whale position update mechanism;

[0109] When the absolute value of the first coefficient is greater than or equal to the first coefficient threshold, select the search mechanism as the whale position update mechanism;

[0110] Update the whale position according to the selected whale position update mechanism to realize the optimization adjustment of the weights and thresholds.

[0111] It should be noted that the threshold of the first random number is generally set to 0.5, and the first coefficient threshold is generally set to 1. When the first random number is greater than or equal to 0.5, select the spiral update mechanism for position update; when the first random number is less than 0.5 and the absolute value of the first coefficient is less than 1, select the encircling prey mechanism for position update; when the first random number is less and the absolute value of the first coefficient is greater than or equal to, select the searching prey mechanism for position update. After each position update, calculate the current fitness value and update the best position until the preset number of whale position iteration operations is completed. Finally, assign the best initial weight threshold to the BP neural network and perform model training.

[0112] In a preferred embodiment, the whale position update formula of the spiral mechanism is:

[0113] X(t + 1) = X * (t) + D 1 ·e bl ·cos(2πl);

[0114] D 1 = |X * (t) - X(t)|;

[0115] In the formula, X(t + 1) represents the updated whale position; X(t) represents the whale position before update; X * (t) represents the optimal whale position of the current iteration; b is a constant used to define the shape of the spiral; l represents a random number in the interval [-1, 1]; D 1 represents the length of the spiral path; t represents the current iteration number;

[0116] The whale position update formula of the encircling mechanism is:

[0117] X(t + 1) = X * (t) - A·D 2 ;

[0118] D 2 = |C·X *(t) - X(t)|;

[0119] A = 2ar - a;

[0120] C = 2r;

[0121] In the formula, D 2 represents the enclosed path length; A represents the first coefficient; C represents the second coefficient; a represents the iteration parameter; r represents the second random number;

[0122] The formula for updating the whale position of the search mechanism is:

[0123] X(t + 1) = X rand (t) - A·D 3 ;

[0124] D 3 = |C·X rand (t) - X(t)|;

[0125] In the formula, D 3 represents the search path length; X rand (t) represents the random whale position.

[0126] In a preferred embodiment, the initial population number of the whale optimization algorithm is 30, and the preset number of iterations is 80.

[0127] It should be noted that the present invention proposes a precise calculation method for the heat absorption and dissipation coefficients of a wire, which can obtain the allowable temperature of the wire to be measured, the ambient temperature, the solar radiation intensity, the wind speed, and the wire current according to the actual operating conditions of the wire, and calculate the heat absorption and dissipation coefficients based on the obtained data.

[0128] Embodiment 2

[0129] Please refer to Figure 2 , which is a schematic flowchart of a heat absorption and dissipation coefficient calculation device provided by an embodiment of the present invention, including: a data acquisition module and a heat absorption and dissipation coefficient prediction module;

[0130] The data acquisition module is used to acquire the allowable temperature of the wire to be measured, the ambient temperature, the solar radiation intensity, the wind speed, and the wire current;

[0131] The heat absorption and dissipation coefficient prediction module is used to input the allowable temperature of the wire, the ambient temperature, the solar radiation intensity, the wind speed, and the wire current into the trained heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model predicts the heat absorption coefficient and the heat dissipation coefficient of the wire to be measured according to the allowable temperature of the wire, the ambient temperature, the solar radiation intensity, the wind speed, and the wire current, and outputs the predicted value of the heat absorption coefficient and the predicted value of the heat dissipation coefficient;

[0132] Among them, the training process of the heat absorption and dissipation coefficient prediction model includes:

[0133] Obtain a number of historical data; among them, each historical data includes the historical allowable temperature of the conductor, historical ambient temperature, historical sunshine intensity, historical wind speed, historical conductor current, historical conductor heat absorption data, and historical conductor heat dissipation data at the same moment;

[0134] Take the historical allowable temperature of the conductor, historical ambient temperature, historical sunshine intensity, historical wind speed, and historical conductor current of each historical data as sample data, and take the historical conductor heat absorption data and historical conductor heat dissipation data corresponding to the historical data as the labels of the sample data;

[0135] According to each sample data and the corresponding label, train the constructed heat absorption and dissipation coefficient prediction model, so that the heat absorption and dissipation coefficient prediction model makes predictions based on the sample data and outputs the sample heat absorption coefficient prediction value and the sample heat dissipation prediction value;

[0136] Calculate the training error according to the sample heat absorption coefficient prediction value, sample heat dissipation coefficient prediction value, and the corresponding label;

[0137] Adjust the weights and thresholds of the heat absorption and dissipation coefficient prediction model according to the training error to obtain the trained heat absorption and dissipation coefficient prediction model.

[0138] Embodiment III

[0139] Correspondingly, an embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the heat absorption and dissipation coefficient calculation method described in the above-mentioned embodiment of the invention.

[0140] Embodiment IV

[0141] Correspondingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute the heat absorption and dissipation coefficient calculation method described in the above-mentioned embodiment of the invention.

[0142] It should be noted that the device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0143] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0144] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0145] The processor can be a Central Processing Unit (CPU), or can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the device, connecting various parts of the entire device through various interfaces and lines.

[0146] The memory can be used to store the computer program. By running or executing the computer program stored in the memory and invoking the data stored in the memory, the processor realizes various functions of the device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0147] The storage medium is a storage medium, and the computer program is stored in the storage medium. When the computer program is executed by the processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0148] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for calculating heat absorption and heat dissipation coefficient, characterized in that: include: Obtain the conductor allowable temperature, ambient temperature, sunshine intensity, wind speed and conductor current of the conductor to be tested; Input the conductor allowable temperature, ambient temperature, sunshine intensity, wind speed and conductor current into a trained heat absorption and heat dissipation coefficient prediction model, so that the heat absorption and heat dissipation coefficient prediction model predicts the heat absorption coefficient and heat dissipation coefficient of the conductor to be tested according to the conductor allowable temperature, ambient temperature, sunshine intensity, wind speed and conductor current, and outputs a predicted value of the heat absorption coefficient and a predicted value of the heat dissipation coefficient; The training process of the heat absorption and heat dissipation coefficient prediction model includes: Acquire a number of historical data; wherein each historical data includes the historical conductor allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed, historical conductor current, historical conductor heat absorption data and historical conductor heat dissipation data at the same time; The historical conductor allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed and historical conductor current of each historical data are used as sample data, and the historical conductor heat absorption data and historical conductor heat dissipation data corresponding to the historical data are used as labels of the sample data; According to each sample data and the corresponding label, the constructed heat absorption and heat dissipation coefficient prediction model is trained so that the heat absorption and heat dissipation coefficient prediction model makes predictions according to the sample data and outputs the sample heat absorption coefficient prediction value and the sample heat dissipation prediction value; Calculating a training error based on the sample heat absorption coefficient prediction value, the sample heat dissipation coefficient prediction value and the corresponding label; According to the training error, the weight and threshold of the heat absorption and heat dissipation coefficient prediction model are adjusted to obtain a trained heat absorption and heat dissipation coefficient prediction model.

2. The method for calculating the heat absorption and heat dissipation coefficient according to claim 1, characterized in that: The process of constructing the heat absorption and heat dissipation coefficient prediction model includes: Construct an initial BP neural network according to the preset number of input layer nodes and output layer nodes; According to the number of nodes in the input layer and the number of nodes in the output layer, the number of hidden layer nodes of the BP neural network is determined by trial and error; Determine the initial weight and initial threshold of the BP neural network according to the number of nodes in the input layer and the number of nodes in the output layer; The BP neural network is used as the heat absorption and heat dissipation coefficient prediction model.

3. The method for calculating the heat absorption and heat dissipation coefficient according to claim 2, characterized in that: The step of adjusting the weight and threshold of the heat absorption and heat dissipation coefficient prediction model according to the training error includes: The weights and thresholds of the heat absorption and heat dissipation coefficient prediction model are used as optimization variables, the training error is used as the fitness function, and the minimum fitness function is taken as the goal. The weights and thresholds are optimized and adjusted through the whale optimization algorithm.

4. The method for calculating the heat absorption and heat dissipation coefficient according to claim 3, characterized in that: The weights and thresholds are optimized and adjusted by the whale optimization algorithm, including: The weight and threshold of the heat absorption and heat dissipation coefficient prediction model are used as the whale position; Repeat the whale position iteration operation for a preset number of times; The whale position iteration operation includes: Randomly obtain the first random number in the interval [0,1]; When the first random number is greater than or equal to a preset first random number threshold, selecting the spiral mechanism as the whale position update mechanism; When the first random number is less than the first random number threshold, obtaining an iteration parameter of the current iteration and randomly obtaining a second random number in the interval [0,1]; wherein the iteration parameter is a parameter that decreases linearly with the number of iterations; Calculate a first coefficient according to the iteration parameter and the second random number; When the absolute value of the first coefficient is less than a preset first coefficient threshold, selecting the encirclement mechanism as the whale position update mechanism; When the absolute value of the first coefficient is greater than or equal to the first coefficient threshold, selecting a search mechanism as a whale position update mechanism; According to the selected whale position update mechanism, the whale position is updated to achieve optimal adjustment of weights and thresholds.

5. The method for calculating the heat absorption and heat dissipation coefficient according to claim 4, characterized in that: The whale position update formula of the spiral mechanism is: X(t+1)=X * (t)+D1·e bl ·cos(2πl); D1=|X * (t)-X(t)|; Where X(t+1) represents the updated whale position; X(t) represents the whale position before the update; X * (t) represents the optimal whale position of the current iteration; b is a constant used to define the shape of the spiral; l represents a random number in the interval [-1,1]; D1 represents the length of the spiral path; t represents the current iteration number; The whale position update formula of the encirclement mechanism is: X(t+1)=X * (t)-A·D2; D2=|C·X * (t)-X(t)|; A = 2ar-a; C＝2r； Wherein, D2 represents the enclosing path length; A represents the first coefficient; C represents the second coefficient; a represents the iteration parameter; r represents the second random number; The whale position update formula of the search mechanism is: X(t+1)=X rand (t)-A·D3; D3=|C·X rand (t)-X(t)|; Where D3 represents the search path length; X rand (t) represents the random whale position.

6. The method for calculating the heat absorption and heat dissipation coefficient according to claim 2, characterized in that: The activation function of the output layer of the BP neural network is the purelin activation function; the activation function of the hidden layer of the BP neural network is the tansig activation function.

7. The method for calculating heat absorption and heat dissipation coefficient according to claim 1, characterized in that: The initial population size of the whale optimization algorithm is 30, and the preset number of iterations is 80.

8. A device for calculating heat absorption and heat dissipation coefficient, characterized in that: include: Data acquisition module and heat absorption and heat dissipation coefficient prediction module; The data acquisition module is used to obtain the allowable wire temperature, ambient temperature, sunshine intensity, wind speed and wire current of the wire to be tested; The heat absorption and heat dissipation coefficient prediction module is used to input the conductor allowable temperature, ambient temperature, sunshine intensity, wind speed and conductor current into the trained heat absorption and heat dissipation coefficient prediction model, so that the heat absorption and heat dissipation coefficient prediction model predicts the heat absorption coefficient and heat dissipation coefficient of the conductor to be tested according to the line allowable temperature, ambient temperature, sunshine intensity, wind speed and conductor current, and outputs the heat absorption coefficient prediction value and the heat dissipation coefficient prediction value; The training process of the heat absorption and heat dissipation coefficient prediction model includes: Acquire a number of historical data; wherein each historical data includes the historical conductor allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed, historical conductor current, historical conductor heat absorption data and historical conductor heat dissipation data at the same time; The historical conductor allowable temperature, historical ambient temperature, historical sunshine intensity, historical wind speed and historical conductor current of each historical data are used as sample data, and the historical conductor heat absorption data and historical conductor heat dissipation data corresponding to the historical data are used as labels of the sample data; According to each sample data and the corresponding label, the constructed heat absorption and heat dissipation coefficient prediction model is trained so that the heat absorption and heat dissipation coefficient prediction model makes predictions according to the sample data and outputs the sample heat absorption coefficient prediction value and the sample heat dissipation prediction value; Calculating a training error based on the sample heat absorption coefficient prediction value, the sample heat dissipation coefficient prediction value and the corresponding label; According to the training error, the weight and threshold of the heat absorption and heat dissipation coefficient prediction model are adjusted to obtain a trained heat absorption and heat dissipation coefficient prediction model.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for calculating the heat absorption and heat dissipation coefficient according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the method for calculating the heat absorption and heat dissipation coefficient according to any one of claims 1 to 7.

Images