New Energy Vehicle High-Voltage Harness Thermal Management Method and System Based on Big Data

Abstract

The present invention relates to the technical field of high-voltage harness thermal management, and discloses a method and system for high-voltage harness thermal management of new energy vehicles based on big data. The method includes: acquiring vehicle operating environment data and harness data, inputting the vehicle operating environment data into a pre-trained temperature change prediction model to output a temperature change trend graph, performing heat generation calculation according to the harness data to obtain the harness heat generation power, performing temperature harness layout optimization according to the harness resistance, the harness heat generation power and the temperature change trend graph to obtain a thermal management harness layout plan, inputting the vehicle operating environment data into a pre-trained load demand model to output a load demand, and performing overall harness layout optimization according to the thermal management harness layout plan and the load demand to obtain an optimal harness layout plan. The method can achieve dynamic high-voltage harness thermal management.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage wire harness thermal management, and particularly to a method and system for thermal management of high-voltage wire harnesses of new energy vehicles based on big data. Background Art

[0002] Currently, due to the increasingly strict requirements for the current-carrying capacity of wire harnesses on the vehicle side, the temperature of the wire harnesses is getting higher, which poses greater challenges to the thermal management of wire harnesses on the vehicle side. On the one hand, a cooling system is used to lower the temperature of the wire harness, but the cost of the cooling system is relatively high and the energy consumption required is large; on the other hand, the shape, material, and current-carrying capacity of the wire harness are adjusted to achieve the purpose of lowering the temperature of the wire harness, but this method places higher requirements on the space of the vehicle and is limited by the vehicle space and the current-carrying capacity of the wire harness.

[0003] In the prior art, the temperature of the wire harness is mainly controlled through static design and passive cooling systems. The methods adopted include optimizing the material selection, cross-section design, and layout of the wire harness to improve the thermal conductivity and current-carrying capacity. In order to reduce the temperature of the wire harness, some solutions also adopt external cooling systems, such as fans or liquid cooling systems, to consume the heat generated inside the wire harness through forced heat transfer. In addition, in some cases, special materials or coatings are used to enhance the temperature resistance of the wire harness to delay the aging of the insulator and prevent overheating.

[0004] The static optimization methods in the prior art have significant deficiencies. The prior art mainly focuses on static design and lacks the ability to adapt to temperature changes in dynamic working conditions in real time, thus unable to achieve thermal management of high-voltage wire harnesses dynamically. Summary of the Invention

[0005] The present invention provides a method and system for thermal management of high-voltage wire harnesses of new energy vehicles based on big data to achieve dynamic thermal management of high-voltage wire harnesses.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a method for thermal management of high-voltage wire harnesses of new energy vehicles based on big data, including:

[0007] Obtain vehicle operating environment data and wire harness data;

[0008] Input the vehicle operating environment data into a pre-trained temperature change prediction model to output a temperature change trend graph;

[0009] Perform heat generation calculation based on the wire harness data to obtain the wire harness heat generation power;

[0010] Perform temperature wire harness layout optimization based on the wire harness resistance, the wire harness heat generation power, and the temperature change trend graph to obtain a thermal management wire harness layout plan;

[0011] Input the vehicle operating environment data into a pre-trained load demand model to output the load demand;

[0012] Optimize the overall harness layout according to the thermal management harness layout plan and the load demand to obtain the optimal harness layout plan.

[0013] Preferably, the vehicle operating environment data includes: driving speed, motor speed, external temperature, humidity, battery power, battery temperature, motor temperature, traffic flow density, and road speed limit;

[0014] The harness data includes: harness bend, harness current, harness cross-sectional area, and harness length.

[0015] Preferably, the step of inputting the vehicle operating environment data into a pre-trained temperature change prediction model to output a temperature change trend graph includes:

[0016] The temperature change prediction model is an LSTM neural network model;

[0017] The training process of the temperature change prediction model is as follows:

[0018] Optimize a pre-prepared training set based on the ATSS algorithm to obtain an optimized training set;

[0019] Input the optimized training set into the temperature change prediction model to perform temporal feature learning to obtain hidden states;

[0020] Plot the hidden states through the output layer of the temperature prediction model to obtain a predicted temperature change trend graph;

[0021] Perform point-by-point calculation on the predicted temperature change trend graph and the true temperature change trend graph to obtain a loss value;

[0022] Based on the loss value, execute the backpropagation algorithm to update the parameters of the temperature change prediction model and optimize the temperature change prediction model;

[0023] Repeat the above process to continuously optimize the temperature change prediction model until the output accuracy of the temperature change prediction model on the training set reaches the preset output accuracy requirement, and then stop training.

[0024] Preferably, the step of calculating the heat generation of the harness based on the harness data to obtain the harness heat generation power includes:

[0025] Calculate the harness resistance through the following formula:

[0026]

[0027] where is the harness resistance, is the resistivity of the wire harness material, is the length of the wire harness, is the cross-sectional area of the wire harness;

[0028] The heat generation power of the wire harness is calculated by the following formula:

[0029]

[0030] where, is the heat generation power of the wire harness, is the current of the wire harness.

[0031] Preferably, based on the heat generation power of the wire harness and the temperature change trend diagram, the wire harness layout is optimized for temperature to obtain a thermal management wire harness layout scheme, including:

[0032] According to the heat generation power of the wire harness and the temperature change trend diagram, temperature evaluation is carried out to obtain the wire harness temperature distribution information;

[0033] The wire harness temperature distribution information is combined and optimized with the thermal management requirements to obtain a thermal management wire harness layout scheme.

[0034] Preferably, the vehicle operating environment data is input into a pre-trained load demand model to output the load demand, including:

[0035] The load demand model is an MLP neural network model;

[0036] The training process of the load demand model is as follows:

[0037] Based on the reinforcement learning algorithm, the pre-prepared training set is optimized to obtain an optimized training set;

[0038] The optimized training set is input into the load demand model, and layer-by-layer calculation is performed to obtain a feature vector;

[0039] Through the output layer of the load demand model, the feature vector is calculated to obtain a predicted load demand;

[0040] According to the predicted load demand and the actual load demand, a difference calculation is performed to obtain an output error value;

[0041] Based on the output error value, the backpropagation algorithm is executed to update the load demand model parameters and optimize the load demand model;

[0042] Repeat the above process to continuously optimize the load demand model until the output accuracy of the load demand on the training set reaches the preset output accuracy requirement, and then stop the training.

[0043] Preferably, according to the thermal management harness layout scheme and the load demand, the overall harness layout is optimized to obtain an optimal harness layout scheme, including:

[0044] Conduct preliminary optimization according to the thermal management harness layout scheme and the load demand to obtain a preliminary harness layout scheme;

[0045] Iteratively optimize the preliminary harness layout scheme based on the genetic algorithm to obtain an optimal harness layout scheme.

[0046] In a second aspect, the present invention provides a high-voltage harness thermal management system for new energy vehicles based on big data, including:

[0047] A data acquisition module for acquiring vehicle operating environment data and harness data;

[0048] A temperature change prediction module for inputting the vehicle operating environment data into a pre-trained temperature change prediction model and outputting a temperature change trend graph;

[0049] A heat generation power module for performing heat generation calculations based on the harness data to obtain the harness heat generation power;

[0050] A thermal management layout module for optimizing the temperature harness layout according to the harness resistance, the harness heat generation power, and the temperature change trend graph to obtain a thermal management harness layout scheme;

[0051] A load demand module for inputting the vehicle operating environment data into a pre-trained load demand model and outputting the load demand;

[0052] An optimal harness layout module for optimizing the overall harness layout according to the thermal management harness layout scheme and the load demand to obtain an optimal harness layout scheme.

[0053] In a third aspect, the present invention further provides an electronic device, including 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 method for high-voltage harness thermal management of new energy vehicles based on big data described in any one of the above.

[0054] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for high-voltage harness thermal management of new energy vehicles based on big data described in any one of the above.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The method obtains vehicle operating environment data and harness data, inputs the vehicle operating environment data into a temperature change prediction model to obtain a temperature change trend graph. Then, heat generation calculation is performed using the harness data to obtain the heat generation power of the harness. Based on these data, combined with the temperature change trend graph, temperature harness layout optimization is carried out, and finally a thermal management harness layout plan is obtained. Next, the vehicle operating environment data is input into a load demand model to obtain the load demand. Subsequently, combined with the thermal management harness layout plan and the load demand, overall harness layout optimization is carried out to obtain an optimal harness layout plan. The method can achieve dynamic high-voltage harness thermal management. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a schematic flow chart of a high-voltage harness thermal management method for new energy vehicles based on big data provided by the first embodiment of the present invention;

[0058] Figure 2 is a schematic diagram of a high-voltage harness thermal management system for new energy vehicles based on big data provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0060] Referring to Figure 1 , the first embodiment of the present invention provides a high-voltage harness thermal management method for new energy vehicles based on big data, including the following steps:

[0061] S11, obtaining vehicle operating environment data and harness data;

[0062] S12, inputting the vehicle operating environment data into a preset temperature change prediction model, and outputting a temperature change trend graph;

[0063] S13, performing heat generation calculation according to the harness data to obtain the harness heat generation power;

[0064] S14, performing temperature harness layout optimization according to the harness resistance, the harness heat generation power and the temperature change trend graph to obtain a thermal management harness layout plan;

[0065] S15, inputting the vehicle operating environment data into a preset load demand model, and outputting a load demand;

[0066] S16. Optimize the overall harness layout according to the thermal management harness layout plan and the load requirements to obtain the optimal harness layout plan.

[0067] In step S11, the vehicle operating environment data includes: driving speed, motor speed, external temperature, humidity, battery power, battery temperature, motor temperature, traffic flow density, and road speed limit.

[0068] The harness data includes: harness bend, harness current, harness cross-sectional area, and harness length.

[0069] It should be noted that in step S11, it is first necessary to obtain the vehicle operating environment data and harness data of the intelligent vehicle. The acquisition method of each parameter is to monitor and record in real time according to vehicle sensors, computing systems, and the external environment.

[0070] For the vehicle operating environment data, first is the driving speed, which is obtained in real time by an on-vehicle speed sensor (such as a GPS or wheel speed sensor). Through the GPS, the system can accurately calculate the vehicle's real-time driving speed, and the data acquisition frequency is completed within one second or even shorter to ensure that it can reflect the vehicle's driving state in real time.

[0071] Next is the motor speed, which is obtained by a speed sensor on the motor. The motor speed is an important indicator to measure the working state of the motor, and it affects the vehicle's acceleration performance and energy efficiency. By collecting the motor speed through the on-vehicle control system, the working condition of the motor can be understood in real time, providing necessary inputs for subsequent temperature prediction and thermal management optimization.

[0072] The external temperature refers to the air temperature of the vehicle's environment, which is measured in real time by a temperature sensor installed outside the vehicle body. The external temperature is crucial for the vehicle's thermal management system. Especially in cold or hot environments, it directly affects the temperature change and heat dissipation requirements of the harness. The external temperature data will be collected in real time and transmitted to the on-vehicle computing system for processing and analysis.

[0073] The humidity is provided by a humidity sensor, which can measure the humidity level of the environment in real time. The change in humidity affects the heat capacity and heat exchange efficiency of the air, thus affecting the vehicle's thermal management system. In an environment with high humidity, the heat exchange efficiency of the air decreases, and the vehicle's thermal management requirements will increase accordingly. Therefore, the acquisition of humidity information is of great significance for accurately predicting the temperature change of the harness.

[0074] The battery power is monitored in real time by the in-vehicle battery management system (BMS). The BMS collects the power, status, and health data of the battery to ensure the effective use of the battery. The battery power directly affects the driving range of the vehicle and the energy management strategy. Therefore, this data is particularly important for subsequent load demand calculation and optimization.

[0075] The battery temperature is collected by temperature sensors installed in the battery pack. The battery temperature is a key factor affecting battery performance and safety. Too high or too low temperature will affect the charge and discharge efficiency and lifespan of the battery. Therefore, accurately monitoring the battery temperature is an important means to achieve battery protection and optimized use.

[0076] The motor temperature is also measured by the motor temperature sensor. The motor generates heat during operation. Too high motor temperature will lead to a decrease in motor efficiency and even cause failures. Therefore, real-time monitoring of the motor temperature can help the in-vehicle system issue warnings and make timely adjustments to prevent motor damage.

[0077] The traffic flow density is obtained through the in-vehicle traffic monitoring system or in-vehicle radar. The traffic flow density reflects the traffic conditions of the vehicle's environment and is of great significance for the assessment of dynamic traffic flow and the adjustment of vehicle driving strategies. On roads with a high traffic flow density, the vehicle's operating speed is slower, and the risk of heat accumulation increases. Therefore, it is necessary to adjust the thermal management strategy to ensure the safe operation of the wiring harness.

[0078] The road speed limit information is provided by the vehicle's navigation system, and the speed limit information of the current driving section of the vehicle is obtained through the GPS positioning system. The road speed limit affects the driving speed of the vehicle, which in turn affects the vehicle's load condition and heat generation. On roads with a low speed limit, the vehicle is in a low-speed driving state for a long time, resulting in heat accumulation. Therefore, the speed limit data plays an important role in dynamically adjusting the vehicle's thermal management system.

[0079] Next, regarding the acquisition of wiring harness data, this data includes multiple parameters such as the bending degree of the wiring harness, the current in the wiring harness, the cross-sectional area of the wiring harness, and the length of the wiring harness. The bending degree of the wiring harness is measured by sensors installed around the cable or wiring harness, and the sensors can detect the bending degree of the wiring harness during use. Excessive bending will lead to an increase in the resistance to current flow, thereby increasing the resistance and generating more heat. Therefore, the bending degree of the wiring harness is a key parameter in thermal management. The current in the wiring harness is obtained in real-time through a current sensor, and the magnitude of the current directly affects the heating degree of the wiring harness. Excessive current will cause an increase in the heating power of the wiring harness, thereby increasing the temperature. The cross-sectional area and length of the wiring harness are directly obtained through measuring tools. The cross-sectional area determines the width of the current flow channel, and the length affects the distance that the current passes through the wiring harness, thereby affecting the resistance of the wiring harness. These parameters are monitored and measured in real-time through sensors and measuring devices installed in the vehicle system to ensure that the system can obtain and accurately record the status of each wiring harness in a timely manner.

[0080] These data are collected in real-time through the vehicle computing system and used as the basic data for subsequent temperature change prediction and thermal management optimization. These input parameters interact with each other and affect the overall thermal management strategy of the vehicle. Accurately and real-time obtaining and processing these data is of crucial significance for optimizing the vehicle's thermal management system, improving system efficiency, and ensuring safe operation.

[0081] In step S12, inputting the vehicle operating environment data into a pre-trained temperature change prediction model to output a temperature change trend graph includes:

[0082] The temperature change prediction model is an LSTM neural network model;

[0083] The training process of the temperature change prediction model is as follows:

[0084] Based on the ATSS algorithm, optimize the pre-prepared training set to obtain an optimized training set;

[0085] Input the optimized training set into the temperature change prediction model for temporal feature learning to obtain hidden states;

[0086] Through the output layer of the temperature prediction model, plot the hidden states to obtain a predicted temperature change trend graph;

[0087] Perform point-by-point calculation on the predicted temperature change trend graph and the real temperature change trend graph to obtain a loss value;

[0088] Based on the loss value, execute the backpropagation algorithm to update the parameters of the temperature change prediction model and optimize the temperature change prediction model;

[0089] Repeat the above process to continuously optimize the temperature change prediction model until the output accuracy of the temperature change prediction model on the training set reaches the preset output accuracy requirement, and then stop the training.

[0090] It should be noted that in step S12, the preparation of the training set is a crucial step. In this technical solution, the training set includes temperature data under different vehicle operating environments, and these data come from measurement data under various working conditions such as vehicle speeds, ambient temperatures, and loads. These data need to ensure sufficient representativeness during collection to cover various operating situations. To further optimize the training set, we use the ATSS algorithm. The core idea of the ATSS algorithm is to select the samples that are most helpful for model training from the original training set, and eliminate unimportant or redundant samples, thereby improving the training effect of the model. By using the ATSS algorithm, the optimized training set can train the model more efficiently, reduce the influence of noise on model training, and improve the prediction accuracy and generalization ability of the model. In the temperature change prediction task, since temperature is a variable with time dependence, the LSTM (Long Short-Term Memory) neural network model is very suitable for processing this type of time series data. The LSTM model is a special type of recurrent neural network (RNN) that can effectively capture long-term dependencies and solve the problem of gradient disappearance that traditional RNNs have when dealing with long time series. For temperature change prediction, the operating state of the vehicle (such as vehicle speed, load, etc.) will interact between different time points, and the LSTM model can combine the temperature change at the current moment with the previous historical data through memory and forgetting mechanisms, so as to make accurate predictions.

[0091] During the process of model training, the training set optimized by ATSS will be input into the input layer of the LSTM model. The input layer of the LSTM will receive this time series data and pass it layer by layer to the hidden layer. In each layer, the LSTM network processes the data through built-in gating mechanisms (including input gate, forget gate, and output gate), retains the historical information that is most useful for temperature change prediction, and discards the unnecessary parts. Through these gating mechanisms, the LSTM can learn the important features in the time series and obtain the final hidden state.

[0092] In the LSTM model, the hidden state refers to the model's understanding of the current moment and historical information. Through time series feature learning, the LSTM model generates a hidden state representing the current moment, which contains information from past time steps and can help predict the future temperature change trend. In the output layer of the LSTM, based on the hidden state and the input data at the current moment, the prediction result of the temperature change is calculated. This prediction result is a continuous value representing the temperature change trend at a future time point.

[0093] Specifically, the output layer of the LSTM model multiplies the hidden state vector by a weight matrix through a fully connected layer, and obtains the final predicted output after passing through an activation function. These outputs form a temperature change trend graph, which reflects the temperature change situation in the future time period.

[0094] After obtaining the predicted temperature change trend graph, the next step is to compare this trend graph with the real temperature change trend graph point by point. This comparison is achieved by calculating the loss function, and the mean squared error (MSE) is used as the loss function. The mean squared error is a commonly used method to calculate the difference between the predicted value and the real value, and its formula is as follows:

[0095]

[0096] where, is the loss value, is the th predicted temperature value, is the th real temperature value, is the total number of samples. By calculating point by point, a loss value can be obtained, and this loss value represents the gap between the prediction result and the actual situation.

[0097] According to the calculated loss value, the parameters of the LSTM model will be updated through the backpropagation algorithm. The backpropagation algorithm is a commonly used optimization algorithm in deep learning. By calculating the gradient of the loss function with respect to the model parameters, it guides the update of the model parameters. Specifically, the backpropagation algorithm will adjust each weight and bias according to the loss function, making the output of the model tend to the real value. During the optimization process, the gradient descent method will be used to continuously update the model parameters to reduce the prediction error and thus improve the accuracy of the model.

[0098] The training process of the LSTM model relies on multiple iterations and the backpropagation algorithm. In each training iteration, the model calculates the loss based on the current training data and updates the weights and biases of the network through backpropagation to gradually optimize the model's parameters. The training process continues until the output accuracy of the model on the training set reaches the preset requirements. In this technical solution, the requirement for output accuracy is measured by the mean squared error (MSE), and MSE is set to be less than 0.01, that is, the error of the temperature change predicted by the model needs to be controlled within 0.01 degrees. This setting of the accuracy requirement is based on several considerations: First, the temperature change of the high-voltage harness of new energy vehicles is crucial for the regulation of the thermal management system and the safety of the harness. An excessive prediction error leads to inaccurate temperature control, affecting the operation safety and efficiency of the system. Therefore, a lower MSE can ensure that the prediction results of the model have high reliability. Second, in actual operation, the temperature change is affected by various factors such as vehicle speed, ambient temperature, battery load, etc., and these factors often carry certain noise. MSE less than 0.01 can effectively balance this noise and ensure the stability and accuracy of the model. In addition, choosing this accuracy standard also helps to optimize the use of computing resources, avoid overfitting, and meet the real-time requirements in engineering applications. During the training process, the model will continuously update its parameters through backpropagation according to the loss value until the set MSE standard is achieved on the training set, marking the completion of training. At this time, the temperature change prediction accuracy of the LSTM model has reached an ideal level and can be applied to the thermal management of the high-voltage harness to ensure real-time optimization of the temperature and current-carrying capacity of the harness and provide an efficient thermal management solution.

[0099] In step S13, according to the harness data, heat generation calculation is performed to obtain the harness heat generation power, including:

[0100] The harness resistance is calculated through the following formula:

[0101]

[0102] Wherein, is the harness resistance, is the resistivity of the harness material, is the harness length, is the cross-sectional area of the harness;

[0103] The harness heat generation power is calculated through the following formula:

[0104]

[0105] Wherein, is the harness heat generation power, is the harness current.

[0106] It should be noted that in step S13, the purpose of calculating heat generation based on the wire harness data is to calculate the heat generated by the flow of current through the wire harness. This process first depends on the resistance calculation of the wire harness, and the calculation of resistance directly depends on multiple factors such as the material, length, and cross-sectional area of the wire harness. Next, we will explain this step in detail, especially the selection of material resistivity, the measurement of wire harness length and cross-sectional area, etc.

[0107] First of all, the resistance calculation is completed according to Ohm's law in physics. The resistance of the wire harness is a key factor in the heat generation when current flows through the wire harness, because when current flows in the resistance, it will encounter resistance and be converted into heat energy. Different materials have different resistivity, which directly affects the resistance size and heat generation characteristics of the wire harness. Therefore, it is crucial to select the appropriate material.

[0108] The resistivity of the wire harness refers to the impedance of the material per unit length and unit cross-sectional area to the current. Common wire materials include copper, aluminum, iron, etc., and their resistivity varies greatly. Copper is a very common electrical conduction material, and its resistivity is about . Due to its very excellent electrical conductivity, copper is used in electrical applications that require high conductivity, such as cables, wires, and motor windings. The low resistivity of copper enables it to reduce heat generation at a relatively small current and improve transmission efficiency. Therefore, it is the preferred material for efficient electrical circuit design.

[0109] Aluminum is another common conductive material, and its resistivity is approximately . Compared with copper, aluminum has a higher resistivity, but its density is lower, which makes aluminum sometimes used as a substitute for copper in circuit design, especially when weight requirements are involved. For example, in the fields of aerospace or electric vehicles, aluminum is often selected as the wire material. Although the conductivity of aluminum is slightly inferior to that of copper, its lighter weight can offset the increase in resistance to a certain extent. Therefore, designers will comprehensively consider various factors such as current requirements, weight, cost, and durability when selecting materials.

[0110] Iron has a relatively high resistivity, approximately , so iron is not a commonly used wire material. The conductivity of iron is not as good as that of copper and aluminum, but in some special applications, such as the coil and iron core parts of the motor, it still has its application value. Iron is used in applications that require magnetism or low cost, rather than for high-performance wires and cables. The relatively high resistivity of iron means that more heat will be generated when it conducts current, so its heat dissipation ability is poor under high load conditions and it is prone to overheating problems.

[0111] Once the materials to be used and their resistivity are determined, the next step is to calculate the resistance of the wire harness. The length L of the wire harness refers to the length of the wiring path between components such as the battery and the motor, and the shortest path of the wiring is determined according to the layout of the vehicle design. The wiring design of the electrical system inside the vehicle needs to minimize the length of the wire harness to reduce the energy loss of the current during transmission.

[0112] The cross-sectional area A of the wire harness determines the area through which the current can flow, and it is selected according to the current load of the wire harness. When the current flows through the conductor, the resistance is inversely proportional to the cross-sectional area. Therefore, in order to ensure that the wire harness can safely transmit a specific current, an appropriate cross-sectional area must be selected. If the cross-sectional area is too small, the current will encounter too much resistance when passing through, resulting in a large amount of heat generation, which may cause a fire or damage electrical components.

[0113] The selection of the cross-sectional area of the wire harness is determined according to the current intensity to be transmitted. The greater the current intensity, the larger the required cross-sectional area. The standard wire size table will provide the cross-sectional area of the wire harness required under different currents to ensure that the wire harness will not be damaged due to overheating when the current flows. For applications with currents such as 15A to 30A, 2.5 mm² cables are used to ensure the safe transmission of the current.

[0114] Next, by calculating the resistance and current, we can obtain the heating power of the wire harness. When the current flows through the resistance, due to the resistance's hindrance to the current, electrical energy is converted into heat energy, resulting in heat generation. Through the formula , we can obtain the heating power P, where P represents power, I represents current, and R represents resistance. The calculation of this heating power can help designers understand how much heat the wire harness will generate during operation and evaluate whether heat dissipation measures need to be taken to avoid overheating. In addition, designers also need to consider the fluctuations of the current because during actual use, the current will be affected by factors such as load changes, acceleration, and braking, resulting in instantaneous fluctuations of the current. These fluctuations will affect the heating situation of the wire harness, so it is necessary to consider the maximum current and minimum current situations during design to ensure the safety of the wire harness under various working conditions.

[0115] In summary, the key to calculating the heat generation of the wire harness lies in accurately measuring the resistivity of the material, the length and cross-sectional area of the wire harness, and then calculating the resistance and heating power. These parameters are essential elements in electrical design, which can help designers predict the working state of the electrical system and ensure the stable and safe operation of the vehicle's electrical system.

[0116] In step S14, according to the heating power of the wire harness and the temperature change trend graph, the wire harness layout is optimized to obtain a thermal management wire harness layout scheme, including:

[0117] Based on the heat generation power of the wire harness and the temperature change trend graph, temperature assessment is carried out to obtain the wire harness temperature distribution information;

[0118] The wire harness temperature distribution information is combined and optimized with the thermal management requirements to obtain a thermal management wire harness layout plan.

[0119] It should be noted that in step S14, the wire harness layout is mainly optimized according to the heat generation power of the wire harness and the temperature change trend graph, so as to obtain a thermal management wire harness layout plan. The key to this step is how to use the temperature change trend graph to guide the optimization of the wire harness layout, so as to make the thermal management of the vehicle electrical system more efficient. Here, first of all, we need to clarify the concept of the temperature change trend graph and how it works in the thermal management system.

[0120] The temperature change trend graph is obtained by analyzing and calculating the vehicle operation environment data and the heat generation power of the wire harness. This graph reflects the temperature change of the wire harness under different working conditions, especially when current flows through the wire harness, over time. The temperature change trend graph is not just a simple temperature record. It is actually a dynamic thermodynamics model that synthesizes the vehicle operation state, environmental factors, and the load condition of the electrical system, and can accurately predict the temperature change trend of the wire harness during actual operation. This temperature change trend graph helps designers understand how temperature changes with various factors such as time, position, and working conditions during the process of the wire harness transmitting current, and then make more accurate wire harness layout optimization decisions.

[0121] In practical applications, the temperature change trend graph is generated by a temperature change prediction model, which relies on deep learning and calculates the prediction results by inputting the real-time operation data of the vehicle. This model first needs to process a large amount of vehicle operation environment data, including external temperature, battery temperature, vehicle speed and other information, and further deduce the temperature of the wire harness at each moment during operation through the temperature change prediction model. Through these calculations, a dynamic temperature change curve is finally formed, which can accurately show the temperature change of the wire harness in the vehicle electrical system under different loads and environmental temperature changes.

[0122] After obtaining the temperature change trend graph, this graph can be used as a basis for optimizing the wire harness layout. According to the temperature change information in the graph, the working state of the wire harness can be evaluated, the overheating areas can be found, and the temperature of these areas can be avoided being too high through optimized layout. Specifically, the wire harness needs to avoid high-load operation for too long in high-temperature areas, while in low-temperature areas, the load and current can be reasonably distributed. In this way, it can effectively prevent the wire harness from being damaged due to too high temperature, and improve the stability and safety of the system.

[0123] In the process of optimizing the wiring harness layout using the temperature change trend chart, it is first necessary to analyze each data point in the chart to confirm the law of temperature change. For example, when the vehicle is driving at different speeds, there will be obvious differences in temperature change. The temperature change trend chart can clearly show the temperature change trend of the wiring harness under various conditions such as vehicle speed, battery power, and load. Based on these data, local optimization can be carried out to adjust the position and path of the wiring harness to ensure that it does not stay in an area with too high temperature. Specifically, designers will choose to place the wiring harness with a large amount of heat generation away from the high-temperature area, or add heat dissipation devices, change the circuit layout, etc. to optimize the heat dissipation effect, so as to ensure that the temperature of the wiring harness is within a safe range.

[0124] In addition, the temperature change trend chart can also be combined with the thermal management requirements for further optimization and adjustment. The thermal management requirements are specific standards for the temperature control and heat dissipation performance of each component (such as wiring harness, battery, motor, etc.) in the system under different working conditions. It includes the upper and lower temperature limits, temperature control range, heat dissipation capacity requirements, etc., aiming to ensure that each component in the system operates within a safe temperature range and avoid damage, reduced efficiency, or performance degradation caused by overheating.

[0125] An example of a specific thermal management requirement can be the temperature control of the battery pack. Suppose a new energy vehicle's battery pack has a temperature control requirement, which clearly states: Upper temperature limit requirement: The temperature of the battery pack cannot exceed 65 degrees Celsius. When the temperature exceeds this value, the chemical reaction rate of the battery is too fast, resulting in battery damage, and even thermal runaway, causing a fire risk. Lower temperature limit requirement: The temperature of the battery pack cannot be lower than -20 degrees Celsius. Low temperature will cause the internal chemical reaction of the battery to slow down, reduce the battery efficiency, and seriously lead to battery capacity loss or inability to charge. Temperature control range: The temperature of the battery should be maintained between 20 degrees Celsius and 45 degrees Celsius. Within this temperature range, the charging and discharging efficiency of the battery is the best, and the service life is the longest. Heat dissipation capacity requirement: Under high load or long-term driving conditions, the battery pack will generate higher heat, so the heat dissipation system needs to ensure that the battery operates within the above temperature range. For example, the heat dissipation system needs to automatically start when the battery temperature reaches 45 degrees Celsius to ensure that the battery temperature does not continue to rise.

[0126] This thermal management requirement ensures that the battery operates within the normal working temperature range and avoids performance loss or safety problems caused by overheating or overcooling. In the battery management system (BMS) of electric vehicles, based on this thermal management requirement, designers will add devices such as temperature sensors, heat exchange systems, and fans to monitor the battery temperature in real time and automatically adjust the working state of the cooling system according to the temperature data. This method effectively avoids the reduction in efficiency or damage of the battery caused by too high or too low temperature during operation, thus ensuring the safety and service life of electric vehicles.

[0127] When using the temperature change trend graph for optimization layout, some dynamic factors also need to be considered, such as load fluctuations during vehicle driving, instantaneous changes in acceleration and braking, etc. These factors cause the temperature of the wire harness to rise instantaneously. Therefore, designers need to adjust the load distribution of the vehicle's electrical system according to the high-temperature areas in the temperature change trend graph to avoid concentrating too much load in these areas. By reasonably distributing current and optimizing the circuit layout, the temperature fluctuation of the wire harness can be minimized without affecting the vehicle's performance, ensuring the safe and stable operation of the entire electrical system.

[0128] In summary, the temperature change trend graph is not only a tool for evaluating the temperature of the wire harness, but also plays a crucial role in the optimization of the thermal management system. Through accurate prediction of temperature change trends, designers can understand the temperature dynamics of the wire harness in the electrical system, and then optimize the circuit layout, load distribution, etc., improving the thermal management efficiency and safety of the vehicle's electrical system. Through this series of operations, not only can overheating problems be effectively prevented, but also the service life of the wire harness and electrical system can be extended, ensuring the reliability and stability of new energy vehicles.

[0129] In step S15, inputting the vehicle operating environment data into a pre-trained load demand model to output a load demand includes:

[0130] The load demand model is an MLP neural network model;

[0131] The training process of the load demand model is as follows:

[0132] Based on the reinforcement learning algorithm, optimize a pre-prepared training set to obtain an optimized training set;

[0133] Input the optimized training set into the load demand model and perform layer-by-layer calculations to obtain feature vectors;

[0134] Through the output layer of the load demand model, calculate the feature vectors to obtain predicted load demands;

[0135] According to the predicted load demand and the actual load demand, perform difference calculations to obtain an output error value;

[0136] Based on the output error value, execute the backpropagation algorithm to update the load demand model parameters and optimize the load demand model;

[0137] Repeat the above process to continuously optimize the load demand model until the output accuracy of the load demand on the training set reaches the preset output accuracy requirement, and then stop training.

[0138] It should be noted that the training set is the basis for the model to learn, and its quality directly affects the training effect of the model. To construct an efficient training set, it is first necessary to collect real load demand data from the vehicle operating environment, which contains vehicle state information under different working conditions. For example, the data sources can include, but are not limited to: vehicle driving speed, battery power, ambient temperature, traffic flow density, road speed limit, etc., as well as the corresponding load demand data. These data can be obtained through sensors and in-vehicle computing systems installed on the vehicle, and the sensors record the operating state and load demand of the vehicle in real time under different working conditions.

[0139] To ensure the diversity and representativeness of the training set, it is necessary to collect data under various driving conditions. This includes different road environments (such as urban roads, highways), different driving modes (such as accelerating, decelerating, driving at a constant speed), different load states (such as high or low battery power, changes in motor power), etc. By integrating data under various driving conditions, the training set can be made more comprehensive, covering all kinds of working conditions, thereby improving the generalization ability of the model.

[0140] After obtaining the original training set, due to the presence of noise or redundant data in the original data, or some data points being of little help to model training, a reinforcement learning algorithm is used to optimize the training set. The goal of this process is to identify which data samples are most important for model training through the exploration and feedback mechanism of reinforcement learning, and to eliminate redundant or irrelevant samples, thereby improving the training efficiency and prediction accuracy of the model. The reinforcement learning algorithm defines a reward mechanism, allowing the algorithm to dynamically adjust the composition of the training set according to the contribution to model training during the training process, so as to obtain an optimized training set and ensure that the final training set can help the model learn the most effective features.

[0141] After data optimization, the optimized training set will be input into the load demand model. This model is a multi-layer perceptron (MLP) neural network, which consists of multiple neurons. Through layer-by-layer calculations, features are gradually extracted from the input data. The input layer of the MLP model receives the training data and performs calculations through the hidden layers, learning the deep features in the data layer by layer.

[0142] Specifically, the input layer passes the received vehicle operating environment data (such as vehicle speed, ambient temperature, etc.) to the next layer. The neurons in each layer perform weighted summation and activation processing, and pass the information to the next layer until a middle representation called a "feature vector" is finally obtained. This feature vector is the feature of the vehicle load demand learned by the model, which contains the key patterns in the input data and provides an important basis for predicting the load demand.

[0143] After layer-by-layer calculation, the feature vector will be passed to the output layer of the MLP model. At the output layer, the model converts the feature vector into the actual load demand prediction value through linear transformation and activation functions (such as ReLU or Sigmoid). This prediction value represents the load demand under the given vehicle operating environment. The model optimizes these parameters through learning to make the output result as close as possible to the real load demand data.

[0144] For example, when the input data is the vehicle speed, temperature, and battery charge at a certain moment, the result calculated by the output layer is the load demand at that moment (for example, a current of 10A). This prediction result will be used for subsequent error calculation and gradually adjust the model parameters through the optimization step.

[0145] After obtaining the prediction result of the load demand, the next step is to calculate the error between the prediction result and the actual real load demand. Error calculation is a crucial step in model training, which determines the update direction of the model parameters. Specifically, the error is obtained by calculating the difference between the predicted load demand and the real load demand.

[0146] The error value is calculated through the following formula:

[0147]

[0148] where is the error value, is the th predicted load demand value, is the th real load demand value, is the total number of samples.

[0149] After calculating the error value, the next step is to optimize the model through the backpropagation algorithm. The backpropagation algorithm is a key algorithm in deep learning. It calculates the gradients of the loss function with respect to the model parameters (including weights and biases) to guide the model to adjust the parameters. In this step, the backpropagation algorithm calculates the gradients of each layer based on the output error value and updates the model parameters using the optimization algorithm.

[0150] The goal of backpropagation is to minimize the loss function, that is, by gradually updating the weights and biases, the prediction error of the model is gradually reduced. The optimization process adjusts the weights of each neuron according to the current error information, so that the model can better predict the load demand in the next iteration.

[0151] The optimization process of the load demand model is an iterative process. After each update of the parameters through backpropagation, the model will recalculate the load demand and calculate the new error value. The training will be repeated until the error value is small enough and the accuracy of the model output reaches the preset requirements.

[0152] In this technical solution, the output accuracy requirement is set such that the mean squared error (MSE) is less than 0.05. The reason for choosing this accuracy requirement is that in practical applications, the prediction results of the load demand need to be highly accurate, as this is related to the safe and efficient operation of the high-voltage wire harness. An MSE less than 0.05 can ensure that the gap between the predicted load demand and the actual load demand is within an acceptable range, avoiding adverse effects on thermal management and current-carrying capacity distribution caused by excessive errors. An MSE less than 0.05 indicates that the prediction results of the model are credible in practical applications and can provide effective data support to ensure the stable operation of the high-voltage wire harness.

[0153] The training will continue until the MSE is less than 0.05. At this point, the training process stops, and the parameters of the load demand model are considered to have been optimized and can provide high-precision load demand predictions for the thermal management of the high-voltage wire harness.

[0154] In step S16, performing the overall wire harness layout optimization based on the thermal management wire harness layout plan and the load demand to obtain the optimal wire harness layout plan includes:

[0155] Performing a preliminary optimization based on the thermal management wire harness layout plan and the load demand to obtain a preliminary wire harness layout plan;

[0156] Performing iterative optimization on the preliminary wire harness layout plan based on the genetic algorithm to obtain the optimal wire harness layout plan.

[0157] It should be noted that in step S16, the overall wire harness layout is optimized based on the thermal management wire harness layout plan and the load demand. The purpose of this process is to combine all the thermal management wire harness plans and load demand plans and obtain the optimal wire harness layout plan through a series of optimization steps to ensure the safety and efficiency of the electrical system. In this optimization process, the genetic algorithm is used to optimize the wire harness layout plan. Especially in the preliminary optimization stage, the genetic algorithm can help us explore the optimal solution through an evolutionary approach to find the most suitable wire harness layout plan.

[0158] First of all, the genetic algorithm is an optimization algorithm that simulates the natural selection and genetic mechanism. Its basic principle draws on the evolutionary process in the biological world, including processes such as selection, crossover, and mutation. Through continuous iteration and optimization, the optimal solution to the problem is finally found. In this step, the genetic algorithm is used to optimize the preliminary wire harness layout plan to ensure that under the given constraints of thermal management and load demand, the most suitable wire harness configuration can be obtained, thereby improving the efficiency of the thermal management system and reducing the losses of electrical equipment.

[0159] In the initial stage of the genetic algorithm, we first encode the solutions to the problem into chromosomes, which represent different wire harness layout schemes. Each chromosome contains information about wire harness layout, load demand allocation, etc., and all layout schemes are expressed through this encoding method. Then, we need to evaluate the quality of each scheme through a fitness function. The design of the fitness function is based on the relationship between the thermal management scheme and the load demand. Specifically, the fitness function comprehensively considers the impact of wire harness layout on current load and the temperature changes of each component, calculates a comprehensive score to evaluate the quality of the layout scheme. The higher the score, the better the scheme is in terms of thermal management and meeting load demands.

[0160] In the crossover operation of the genetic algorithm, a pair of chromosomes are selected as parents, and they will be combined into new chromosomes, namely offspring. The purpose of this step is to "inherit" excellent characteristics from the parents and generate new wire harness layout schemes through the crossover operation. Through crossover, the design of the offspring not only retains some excellent characteristics of the parents but also introduces new permutations and combinations, expanding the optimization space. After the crossover operation, multiple offspring are generated, and each offspring represents a new wire harness layout scheme.

[0161] Meanwhile, the genetic algorithm also introduces a mutation operation. Mutation means that after the crossover operation, small-scale random adjustments are made to the genes in some chromosomes to prevent the algorithm from falling into a local optimal solution. Through the mutation operation, new solutions can explore areas that have not been covered before, enabling the genetic algorithm to optimize in a broader search space. The introduction of the mutation operation enhances the search ability of the genetic algorithm and helps to find more ideal solutions in complex optimization problems.

[0162] After multiple iteration processes, the genetic algorithm continuously optimizes the wire harness layout scheme until an optimal solution is found. In each generation of evolution, the fitness of the chromosomes gradually increases, which means that after multiple iterations, the obtained wire harness layout scheme increasingly meets the requirements of thermal management and load demands. In this way, the genetic algorithm can effectively screen out the optimal solution from a large number of solutions and ensure the optimal performance of the system.

[0163] In this process, the optimal solution generated by the genetic algorithm is the final wire harness layout scheme. This scheme can meet specific thermal management requirements, while optimizing the allocation of load demands to ensure the stability and efficiency of the system in different environments. The optimized wire harness layout scheme will be implemented in practical applications, thereby improving the overall performance of the high-voltage wire harness of new energy vehicles, achieving the goals of reducing losses, increasing efficiency, and ensuring the safety of the electrical system.

[0164] Generally speaking, the application of genetic algorithms in this step can effectively explore the optimal wiring harness layout scheme in a complex search space by simulating the selection, crossover, and mutation mechanisms in nature, providing an efficient and reliable optimization method.

[0165] Referring to Figure 2 , the second embodiment of the present invention provides a new energy vehicle high-voltage wiring harness thermal management system based on big data, including:

[0166] A data acquisition module for acquiring vehicle operating environment data and wiring harness data;

[0167] A temperature change prediction module for inputting the vehicle operating environment data and the wiring harness data into a preset temperature change prediction model and outputting a temperature change trend graph;

[0168] A heating power module for performing heating calculation based on the wiring harness data to obtain the wiring harness heating power;

[0169] A thermal management layout module for optimizing the temperature wiring harness layout according to the wiring harness resistance, the wiring harness heating power, and the temperature change trend graph to obtain a thermal management wiring harness layout scheme;

[0170] A load demand module for inputting the vehicle operating environment data into a preset load demand model and outputting a load demand;

[0171] An optimal wiring harness layout module for optimizing the overall wiring harness layout according to the thermal management wiring harness layout scheme and the load demand to obtain an optimal wiring harness layout scheme.

[0172] It should be noted that a new energy vehicle high-voltage wiring harness thermal management system based on big data provided in the embodiments of the present invention is used to execute all the process steps of a new energy vehicle high-voltage wiring harness thermal management method based on big data in the above embodiments, and the working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0173] The embodiments of the present invention also provide an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a new energy vehicle high-voltage wiring harness thermal management program based on big data. When the processor executes the computer program, it implements the steps in the above-mentioned embodiments of various new energy vehicle high-voltage wiring harness thermal management methods, such as Figure 1 the step S11 shown. Or, when the processor executes the computer program, it implements the functions of each module / unit in the above-mentioned device embodiments, such as the optimal wiring harness layout module.

[0174] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0175] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than those described above, or combine some components, or have different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0176] The so-called processor may be a central processing unit (CPU), or may 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 may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and circuits.

[0177] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and invoking the data stored in the memory, the processor can implement various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, 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 memory device, or other volatile solid-state storage devices.

[0178] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing 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 a processor, it can implement the steps of the above-mentioned 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 disc, 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.

[0179] 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 it without creative efforts.

[0180] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A thermal management method for high-voltage wiring harnesses of new energy vehicles based on big data, characterized in that: Executed by a computer, including: Obtain vehicle operating environment data and wiring harness data; Input the vehicle operating environment data into a pre-trained temperature change prediction model and output a temperature change trend graph; perform heat calculation based on the wiring harness data to obtain the wiring harness heating power; According to the harness resistance, the harness heating power and the temperature change trend diagram, the temperature harness arrangement is optimized to obtain a thermal management harness arrangement scheme; Input the vehicle operating environment data into a pre-trained load demand model, output the load demand, optimize the bus harness arrangement according to the thermal management harness arrangement plan and the load demand, and obtain the optimal harness arrangement plan; The load demand model is an MLP neural network model; the training process of the load demand model is: Based on the reinforcement learning algorithm, the pre-prepared training set is optimized to obtain the optimized training set; Inputting the optimized training set into the load demand model, performing layer-by-layer calculations, and obtaining a feature vector; The characteristic vector is calculated through the output layer of the load demand model to obtain the predicted load demand; The input layer of the MLP model receives training data and performs calculations through the hidden layer to learn the deep features in the data layer by layer. The input layer passes the received vehicle operating environment data to the next layer. The neurons in each layer pass the information to the next layer through weighted summation and activation processing until the intermediate representation of the feature vector is finally obtained. The feature vector is the feature of the vehicle load demand learned by the model. After layer-by-layer calculation, the feature vector will be passed to the output layer of the MLP model. In the output layer, the model converts the feature vector into the actual load demand prediction value through linear transformation and activation function. The load demand prediction value represents the load demand under a given vehicle operating environment.

2. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 1 is characterized in that: The vehicle operating environment data includes: driving speed, motor speed, external temperature, humidity, battery power, battery temperature, motor temperature, traffic density and road speed limit; The harness data includes harness curvature, harness current, harness cross-sectional area and harness length.

3. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 2 is characterized in that: The vehicle operating environment data is input into a pre-trained temperature change prediction model, and a temperature change trend graph is output, including: The temperature change prediction model is an LSTM neural network model; The training process of the temperature change prediction model is as follows: Based on the ATSS algorithm, the pre-prepared training set is optimized to obtain the optimized training set; Inputting the optimized training set into the temperature change prediction model to perform time series feature learning to obtain an implicit state; The implicit state is plotted through the output layer of the temperature prediction model to obtain a predicted temperature change trend graph; The predicted temperature change trend graph and the actual temperature change trend graph are calculated point by point to obtain a loss value; Based on the loss value, executing a back propagation algorithm to update the temperature change prediction model parameters and optimize the temperature change prediction model; Repeat the above process and continuously optimize the temperature change prediction model until the output accuracy of the temperature change prediction model on the training set reaches the preset output accuracy requirement, and then stop training.

4. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 2 is characterized in that: The step of performing heat calculation according to the wiring harness data to obtain the wiring harness heat power includes: The harness resistance is calculated using the following formula: in, is the wiring harness resistance, is the resistivity of the wire harness material, is the harness length, is the cross-sectional area of ​​the harness; The heating power of the wiring harness is calculated by the following formula: in, is the heating power of the wiring harness, is the harness current.

5. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 1 is characterized in that: The step of optimizing the temperature harness arrangement according to the harness heating power and the temperature change trend diagram to obtain a thermal management harness arrangement solution includes: Performing temperature evaluation according to the heating power of the wiring harness and the temperature change trend diagram to obtain wiring harness temperature distribution information; The wiring harness temperature distribution information is combined with the thermal management requirements for optimization to obtain a thermal management wiring harness arrangement solution.

6. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 2 is characterized in that: After calculating the characteristic vector through the output layer of the load demand model to obtain the predicted load demand, the method further includes: Performing a difference calculation based on the predicted load demand and the actual load demand to obtain an output error value; Based on the output error value, executing a back propagation algorithm to update load demand model parameters and optimize the load demand model; Repeat the above process and continuously optimize the load demand model until the output accuracy of the load demand on the training set reaches the preset output accuracy requirement, and then stop training.

7. The method for thermal management of high-voltage wire harnesses for new energy vehicles based on big data according to claim 1 is characterized in that: The step of optimizing the wiring harness arrangement according to the thermal management wiring harness arrangement scheme and the load requirement to obtain the optimal wiring harness arrangement scheme includes: Performing preliminary optimization according to the thermal management harness arrangement scheme and the load requirements to obtain a preliminary harness arrangement scheme; The preliminary wiring harness arrangement scheme is iteratively optimized based on a genetic algorithm to obtain an optimal wiring harness arrangement scheme.

8. A high-voltage wiring harness thermal management system for new energy vehicles based on big data, characterized in that: A method for thermal management of high-voltage wiring harnesses for new energy vehicles based on big data according to any one of claims 1 to 7, comprising: A data acquisition module, used to acquire vehicle operating environment data and wiring harness data; A temperature change prediction module, used to input the vehicle operating environment data into a pre-trained temperature change prediction model and output a temperature change trend graph; A heating power module, used for performing heating calculation according to the wiring harness data to obtain the wiring harness heating power; A thermal management arrangement module, used to optimize the temperature harness arrangement according to the harness resistance, the harness heating power and the temperature change trend diagram, and obtain a thermal management harness arrangement solution; A load demand module, used to input the vehicle operating environment data into a pre-trained load demand model and output the load demand; The optimal wiring harness arrangement module is used to optimize the wiring harness arrangement of the entire bus according to the thermal management wiring harness arrangement scheme and the load demand to obtain the optimal wiring harness arrangement scheme.

9. An electronic device, characterized in that: It 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 thermal management method of high-voltage wire harness for new energy vehicles based on big data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the big data-based thermal management method for high-voltage wire harnesses of new energy vehicles as described in any one of claims 1 to 7.

Images