Electric vehicle battery temperature global trajectory optimization method, system, device and medium

Abstract

The invention discloses an electric vehicle battery temperature global trajectory optimization method, system and device, and a medium, and the method comprises the steps: collecting historical working condition data and a temperature trajectory, constructing an initial working condition prediction model through an RBF and LSTM network, and carrying out the training optimization through Bayesian optimization, and obtaining a trained model; then, carrying out real-time iterative prediction and optimization by using transfer learning to obtain an optimized working condition prediction model, and executing real-time working condition prediction based on the model to obtain prediction data; the method comprises the following steps of: establishing an NARX energy consumption prediction model, training by using prediction data and a temperature control target to realize real-time energy consumption prediction, and finally, establishing a fitness function by taking weighted value minimization of energy consumption and temperature deviation as a target, and optimizing in a population through a genetic algorithm to obtain an optimal global temperature trajectory. According to the technical scheme, the global working condition can be predicted in real time and the global thermal management temperature track can be optimized by combining the short-distance driving data with the historical working condition data.

Description

Technical Field

[0001] The present invention belongs to the technical field of thermal management of electric vehicles, and in particular relates to a method, system, device and medium for optimizing the global trajectory of battery temperature of an electric vehicle. Background Art

[0002] Temperature optimization of electric vehicle batteries is the key to improving battery performance and extending battery life. Batteries generate heat during the charging and discharging process, which results in energy loss of the battery and affects the performance of the battery. Therefore, it is crucial to study the mechanism and characteristics of the battery, explore the relationship between the remaining battery power, temperature factors and energy consumption, and establish a driving energy consumption model for optimizing the battery temperature of electric vehicles. However, the current global optimization method has two main drawbacks. One is that it can only be used for global optimization offline and when the global working conditions are known, and it cannot be applied online in real time. The other is that the commonly used dynamic programming algorithm (DP) has been found in actual applications that it cannot constrain and optimize the global quantity because it solves all possible decision quantities at each moment, which will cause the optimization results to partially deviate from the actual value and has certain limitations. Summary of the invention

[0003] The purpose of the present invention is to provide a method, system, device and medium for optimizing the global trajectory of battery temperature of an electric vehicle to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above object, the present invention provides a method for optimizing the global trajectory of battery temperature in an electric vehicle, comprising:

[0005] Obtain historical operating data and global temperature trajectory of electric vehicles;

[0006] An initial operating condition prediction model is constructed by combining a radial basis function neural network and a long short-term memory network, and the initial operating condition prediction model is trained and optimized based on the historical operating condition data combined with a Bayesian optimization algorithm to obtain a trained operating condition prediction model; the trained operating condition prediction model is iteratively predicted and optimized in real time based on a transfer learning algorithm to obtain an optimized operating condition prediction model;

[0007] Execute real-time working condition prediction based on the optimized working condition prediction model to obtain working condition prediction data;

[0008] Construct an initial thermal management system energy consumption prediction model based on nonlinear autoregressive neural network;

[0009] The initial thermal management system energy consumption prediction model is trained based on the operating condition prediction data and the preset temperature control target, and the real-time energy consumption prediction of the thermal management system is performed based on the trained thermal management system energy consumption prediction model to obtain the thermal management system energy consumption prediction data;

[0010] A fitness function is constructed with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the mean temperature offset value; a population is constructed with the global temperature trajectory as an individual, and an iterative search is performed within the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm. After the iteration is completed, the optimal global temperature trajectory is output.

[0011] Optionally, before combining the radial basis function neural network and the long short-term memory network to build the initial operating condition prediction model, the following is further included:

[0012] Performing cluster analysis on the historical operating condition data, and using the cluster analysis results as model structure parameters;

[0013] Based on the model structure parameters, a radial basis function neural network and a long short-term memory network are combined to construct an initial operating condition prediction model.

[0014] Optionally, the training and optimizing the initial operating condition prediction model based on the historical operating condition data in combination with a Bayesian optimization algorithm specifically includes:

[0015] The objective function is to minimize the verification loss of the initial working condition prediction model under hyperparameters;

[0016] Based on the Bayesian optimization algorithm and the objective function, the initial operating condition prediction model is optimized for hyperparameters to obtain the optimal hyperparameters, and the operating condition prediction model corresponding to the optimal hyperparameters is trained based on the historical operating condition data to obtain the trained operating condition prediction model.

[0017] Optionally, the real-time iterative prediction and optimization of the trained operating condition prediction model based on the transfer learning algorithm specifically includes:

[0018] The trained working condition prediction model is frozen based on the preset number of freezing layers, and a new output layer is added to the working condition prediction model after the model freezing is completed. The working condition prediction model with the new output layer added is trained and iterated based on real-time working condition data, and an optimized working condition prediction model is obtained after the iteration is completed.

[0019] Optionally, the iterative optimization within the population based on the fitness value corresponding to each of the individuals in combination with a genetic optimization algorithm specifically includes:

[0020] Based on the genetic optimization algorithm, each individual is iteratively updated. In each iterative update process, the fitness value corresponding to each individual is calculated, and the population is iteratively updated based on the fitness value corresponding to each individual until the number of iterations reaches a preset value, and the optimal individual is output to obtain the optimal global temperature trajectory.

[0021] A global trajectory optimization system for battery temperature of an electric vehicle, comprising:

[0022] Data acquisition module, used to obtain historical operating data and global temperature trajectory of electric vehicles;

[0023] The working condition prediction module is used to construct an initial working condition prediction model by combining a radial basis function neural network and a long short-term memory network, train and optimize the initial working condition prediction model based on the historical working condition data in combination with a Bayesian optimization algorithm to obtain a trained working condition prediction model; perform real-time iterative prediction and optimization on the trained working condition prediction model based on a transfer learning algorithm to obtain an optimized working condition prediction model; perform real-time working condition prediction based on the optimized working condition prediction model to obtain working condition prediction data;

[0024] The thermal management system energy consumption prediction module is used to construct an initial thermal management system energy consumption prediction model based on a nonlinear autoregressive neural network; the initial thermal management system energy consumption prediction model is trained based on the operating condition prediction data and the preset temperature control target, and the real-time energy consumption prediction of the thermal management system is performed based on the trained thermal management system energy consumption prediction model to obtain the thermal management system energy consumption prediction data;

[0025] The global optimization module is used to construct a fitness function with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the mean temperature offset value; construct a population with the global temperature trajectory as an individual, and perform iterative optimization within the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm. After the iteration is completed, the optimal global temperature trajectory is output.

[0026] An electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute a method for optimizing the global trajectory of the battery temperature of an electric vehicle.

[0027] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for optimizing the global trajectory of the battery temperature of an electric vehicle is implemented.

[0028] The technical effects of the present invention are:

[0029] The present invention provides an effective method for global operating condition prediction and global optimization of battery temperature trajectory. By combining cluster analysis, RBF and LSTM neural networks, and transfer learning technology, high-precision, high-real-time and highly adaptable operating condition prediction is achieved. The energy consumption model of the thermal management system is established through the NARX neural network, and the global optimization of the predicted global operating condition is achieved using a genetic algorithm. The present invention can use short-distance driving data combined with historical operating condition data to predict global operating conditions and optimize global thermal management temperature trajectories. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0032] Figure 1 It is an implementation flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0033] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as limiting the present invention, but should be understood as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0034] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0035] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present invention description without departing from the scope or spirit of the present invention. Other embodiments derived from the present invention description will be apparent to those skilled in the art. The present application description and examples are exemplary only.

[0036] The words “include,” “including,” “have,” “contain,” etc. used in this article are open-ended terms, meaning including but not limited to.

[0037] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] Embodiment 1

[0039] like Figure 1As shown, in this embodiment, a method for optimizing the global trajectory of battery temperature of an electric vehicle is provided, including: obtaining historical operating condition data and global temperature trajectory of the electric vehicle; constructing an initial operating condition prediction model by combining a radial basis function neural network and a long short-term memory network, training and optimizing the initial operating condition prediction model based on the historical operating condition data in combination with a Bayesian optimization algorithm to obtain a trained operating condition prediction model; performing real-time iterative prediction and optimization on the trained operating condition prediction model based on a transfer learning algorithm to obtain an optimized operating condition prediction model; performing real-time operating condition prediction based on the optimized operating condition prediction model to obtain operating condition prediction data; constructing an initial thermal management system energy consumption prediction model based on a nonlinear autoregressive neural network; training the initial thermal management system energy consumption prediction model based on the operating condition prediction data and a preset temperature control target, performing real-time energy consumption prediction of the thermal management system based on the trained thermal management system energy consumption prediction model to obtain thermal management system energy consumption prediction data; constructing a fitness function with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the average temperature offset value; constructing a population with the global temperature trajectory as an individual, iterating and optimizing within the population based on the fitness value corresponding to each of the individuals in combination with a genetic optimization algorithm, and outputting the optimal global temperature trajectory after the iteration.

[0040] 1. Cluster analysis of big data working condition eigenvalues: Use the k-means algorithm to cluster the eigenvalues ​​of a large amount of historical working condition data, analyze the center and width parameters of the hidden layer neurons, and thus determine the structure of the adaptive neural network model.

[0041] 2. Neural network establishment: A hybrid neural network model is established by combining the radial basis function (RBF) neural network and the long short-term memory (LSTM) network. This model can learn the time series characteristics in historical data and adaptively modify the model structure according to the input data for iterative optimization to improve the prediction accuracy.

[0042] 3. Neural network model training and prediction: Using a large amount of historical data, the established hybrid neural network model is optimized and trained through Bayesian optimization for hyperparameters, and the global operating condition is predicted based on the characteristic values ​​of short-distance operating conditions through cross-validation.

[0043] 4. Real-time iterative prediction and model optimization: Through transfer learning technology, the prediction results are updated in real time, and the neural network is optimized using new operating data to adapt to new operating conditions.

[0044] 5. Establishment of energy consumption model of thermal management system: Using the thermal management data of the whole vehicle, a nonlinear autoregressive neural network (NARX) with external input is established and trained to make it an energy consumption model that can predict the energy consumption of the thermal management system in real time according to the input vehicle speed and temperature control target.

[0045] 6. Global optimization using genetic algorithm: Establish a fitness function based on the energy consumption model, write a genetic algorithm operator, and use the genetic algorithm to optimize the battery temperature control target trajectory under global working conditions.

[0046] The method of this embodiment can provide high-precision global operating condition prediction with good real-time and adaptability. Through iterative optimization and model updating, the accuracy of prediction can be continuously improved. The energy consumption model modeled by neural network and genetic algorithm can accurately and quickly complete global optimization.

[0047] The specific implementation of this embodiment:

[0048] Step 1: Cluster analysis of big data operating condition characteristic values;

[0049] Collect historical operating data and extract eigenvalues. Use the k-means algorithm to perform cluster analysis on the data to facilitate the subsequent construction of the RBF adaptive neural network model.

[0050] 1. Data reading and preprocessing: First, read the data and create a data set D = {(x1, y1), (x2, y2), …, (x n ,y n )}where x i is the eigenvector, y i is the target variable.

[0051] 2. Standardized features: Standardize the feature values ​​to facilitate subsequent classification training and division. The specific method is as follows:

[0052] make Where μ is the mean of the eigenvalues ​​and σ is the standard deviation.

[0053] 3. Divide the training set and test set:

[0054] Set the randomness and divide the data set into training set and test set, that is, X test ,X train ,Y test ,Y train .

[0055] 4. K-means clustering initialization;

[0056] 1) Using the K-means++ initialization method, first randomly select a point from the data set as the cluster center c1.

[0057] 2) Then for each data point x, calculate its distance to the cluster center D(x) = min j ||xc j || 2 .

[0058] 3) Select a new cluster center based on the ratio of the square of the distance D(x). Specifically, take the square of the distance of each point as the probability and select the new center:

[0059] 4) Repeat steps 2) and 3) until k cluster centers are selected.

[0060] 5. Cluster analysis;

[0061] 1) For each data point x i Assign to the nearest cluster center c j ;

[0062] 2) Update the cluster center c of each cluster j , calculate the mean of all points in each cluster: Among them, N j is the number of samples assigned to cluster j;

[0063] 3) Repeat 1) and 2) above until the cluster center no longer changes or the maximum number of iterations is reached.

[0064] Step 2: Combine the cluster analysis method in step 1 to create an RBF class, implement adaptive neural network structure, and automatically adjust its parameters (such as center position, width, and weight) according to the changes in input data to better approximate real data. Combine the RBF and LSTM models through keras, and use the Ad am optimizer to perform gradient descent on the model.

[0065] The first step is to create an RBF class to implement adaptive adjustment of the neural network structure:

[0066] 1. Define the basic parameters of the RBF layer;

[0067] Output dimension: d;

[0068] Center: Set to c i represents the center of each output, i=1,2,…,d;

[0069] beta value: set to β, controls the width of the function, i = 1, 2, …, d.

[0070] 2. Initialization;

[0071] During the initialization phase, the center and beta values ​​are initialized:

[0072] Initialization of the center: c i ~U(0,1), for i = 1, 2, ..., d where U(0,1) means randomly generated from a uniform distribution;

[0073] Beta value initialization: βi =1.0 for i=1,2,…,d.

[0074] 3. Forward propagation calculation;

[0075] Given an input x∈R n (where n is the dimension of the input), the output layer calculates the output value by the following steps:

[0076] 1) Extension Center: Each center unfolds in a new dimension;

[0077] 2) Calculate the distance: Calculate the distance between the input sample and each center: H = Cx;

[0078] 3) Calculate output: The calculation formula for output is: Here, ||c i -x|| 2 Indicates c i The square of the Euclidean distance from the input x.

[0079] Then combine the RBF and LSTM models:

[0080] 1. Preprocess the input;

[0081] Given input time series data: x = {x1, x2, …x T}.

[0082] 2. Create LSTM layer;

[0083] The input of LSTM is the output of RBF, and the sequence representation is:

[0084] Assume that the RBF output is y RBF , the output after input to the LSTM layer is h(t)=LSTM(y RBF (t),h(t-1),c(t-1)), where h(t) is the hidden state of LSTM at time step t and c(t-1) is the memory cell state of LSTM.

[0085] The core formula of LSTM is:

[0086] 3. Output layer;

[0087] The output layer is usually a fully connected layer that outputs the prediction y pred =W out ·h(T)+b out Here, W out is the output layer weight, b out is bias.

[0088] 4. Loss function;

[0089] Use mean square error (MSE) as the loss function:

[0090] 5.Adam optimizer;

[0091] Use the Adam optimizer to update the network weight parameter θ. The steps are:

[0092] 1) Calculate the gradient:

[0093] 2) Update the first-order momentum and second-order momentum:

[0094] 3) Correction deviation:

[0095] 4) Update parameters:

[0096] Step 3: Using a large amount of historical data, the established hybrid neural network model is optimized and trained through Bayesian optimization, and the global operating condition prediction is obtained based on the characteristic values ​​of short-distance operating conditions through cross-validation.

[0097] 1. Define hyperparameters: Let the model be f(x;h), where x is the input and h is the hyperparameter. The performance of the input model is optimized by adjusting the hyperparameter h.

[0098] 2. Objective function: The input of hyperparameter optimization is the hybrid neural network model obtained in step 2. The objective function L(h) is defined as the validation loss of the model f(x; h) under the hyperparameter h: L(h) = E[L val (h)] where L val (h) is the validation loss obtained by cross-validation when the hyperparameter h is given.

[0099] 3. Bayesian optimization: Bayesian optimization uses a surrogate model to model the objective function and selects hyperparameters based on the model.

[0100] 1) Surrogate model: Use Gaussian process GP to model the objective function L(h)~GP(m(h),k(h,h')) where m(h) is the mean function and k(h,h') is the covariance function.

[0101] 2) Selection criterion: In Bayesian optimization, the selection criterion is Expected Improvement (EI): Where L * is the best currently known validation loss and p(z|h) is the distribution of Gaussian process predictions.

[0102] 4. Hyperparameter update: Find the next hyperparameter h by maximizing the selection criterion EI(h) next = argmax h EI(h).

[0103] 5. Update and Iterate: After selecting new hyperparameters, evaluate model performance and update the surrogate model, iterate this process, and evaluate the updates until the performance metric no longer improves or the maximum number of iterations is reached.

[0104] 6. Obtain the hybrid neural network model with the best hyperparameters based on the results of Bayesian optimization and train the best model.

[0105] 7. Use the test set to perform testing, complete cross-validation, and obtain a hybrid neural network model that can predict global operating conditions through short-distance characteristic values.

[0106] Step 4: Use transfer learning to iterate predictions in real time, update prediction results, and use new working condition data to optimize the neural network and collect new working condition data in real time. Use transfer learning technology to integrate new data into the existing model for real-time prediction. Adjust and optimize the neural network based on the prediction results and actual working conditions.

[0107] 1. Model layer freezing, freezing all layers except the last few layers, is used to update the model, which is essentially training similar models with the same logic but different details:

[0108] For each layer i = (1, 2, ..., N-1), set trainable = 0, where N is the total number of layers in the model, and the last layer l N is a trainable layer.

[0109] 2. Add a new output layer to adapt and learn from new data;

[0110] y=f(x;W,b)=W·x+bHere y is the output, W is the new weight parameter, b is the bias term, and x is the input data.

[0111] 3. Model compilation, you need to use a smaller learning rate to quickly compile similar models:

[0112] Loss = L(y ture ,y pred ) = huber_loss(y ture ,f(x;W,b)), optimizer=Adam(α=1×10 -5 )

[0113] 4. Model training, continue training the model using the new data set:

[0114]

[0115] 5. Model prediction, use the test set to make predictions to test the model, and use R 2 Make an evaluation:

[0116] in, Yes true The mean of .

[0117] Step 5: Using the vehicle thermal management data of historical operating conditions, a nonlinear autoregressive neural network model (NARX) with external input is established and trained so that it can predict the energy consumption of the global thermal management system in real time through the global operating conditions predicted in steps 3 and 4 and the given temperature control targets.

[0118] 1. Adjust the vehicle thermal management data of historical conditions to conform to the NARX model:

[0119] The input data X1 is the global temperature trajectory controlled by the thermal management system, the input data X2 is the global operating condition, i.e., the vehicle speed, and the output y is the energy consumption of the thermal management system under the corresponding temperature control trajectory. X1 and X2 are concatenated in the second dimension (time T) to form the new input data X.

[0120] 2. Build the NARX model:

[0121] Define the model f(X; W, b), where W is the weight of the model and b is the bias;

[0122] Define the hidden layer h = ReLU (XW1 + b1), define the output layer y pred =hW2+b2, where W1 and W2 are the weight matrices of the corresponding layers, and b1 and b2 are biases.

[0123] 3. Compile the model: the loss function is the mean square error:

[0124] 4. Train the model, train the model, update the weights W1, W2 and biases b1, b2:

[0125] W,b←train_model(X,y) is trained for E=100 rounds, with each batch size being B=10.

[0126] Step 6: Based on the energy consumption model established in step 5, build a fitness function, which should be the weighted value of global energy consumption and mean temperature offset. Write a genetic algorithm to optimize the fitness function to the minimum value. Due to the input variable requirements of the genetic algorithm, the generated initial temperature trajectory and the optimal temperature rule are both scattered points, which will serve as the global staged temperature control target of the thermal management system.

[0127] 1. Determine genetic individuals: Let P be a population consisting of N individuals, each of which can be represented by a chromosome x i :P={x1,x2,…,x N The information carried by each individual is the global temperature trajectory scatter point row matrix, that is, x i =T i ,

[0128] 2. Build a fitness function. In order to ensure low thermal management energy consumption while making the battery work more generally at a more suitable temperature, the fitness function should limit both thermal management energy consumption and average battery temperature. Specifically:

[0129] in, is the global average temperature, y i is the output of the energy consumption model constructed in step 5, and W1 and W2 are the corresponding weights.

[0130] 3. Generate new populations through selection, crossover and mutation:

[0131] 1) Select an operation:

[0132] The selection operation adopts roulette selection, and the individual probability Select x i The probability is proportional to its fitness.

[0133] 2) Crossover operation: For the two selected parents x a and x b , perform a single-point crossover operation to generate two new individuals xc hild1 and x child2 , x child1 =[t1,t2,…,t c ,t' c+1 ,…,t' m ], x child2 =[t'1,t'2,…,t' c ,t c+1 ,…,t m ], where c is the selected intersection point.

[0134] 3) Mutation operation: Using non-uniform mutation, randomly generate the variation ∈ and uniformly distributed random numbers u, set the mutation probability p, then the individual after mutation

[0135] 4. Genetic termination: When the maximum number of iterations is reached or the fitness change is less than the threshold, the genetic process terminates. At this time, the individual with the highest fitness in the population is the best individual, and the global temperature trajectory formed by the scattered row matrix of the global temperature trajectory it carries is the global optimal temperature trajectory under the current working conditions.

[0136] This embodiment provides an effective method for global operating condition prediction and global optimization of battery temperature trajectory. By combining k-means clustering analysis, RBF and LSTM neural networks, and transfer learning technology, high-precision, high-real-time, and highly adaptable operating condition prediction is achieved. The energy consumption model of the thermal management system is established through the NARX neural network, and the global optimization of the predicted global operating condition is achieved using a genetic algorithm. Overall, it is possible to use short-distance driving data combined with historical operating condition data to predict global operating conditions and optimize global thermal management temperature trajectories.

[0137] A global trajectory optimization system for battery temperature of an electric vehicle, comprising:

[0138] Data acquisition module, used to obtain historical operating data and global temperature trajectory of electric vehicles;

[0139] The working condition prediction module is used to construct an initial working condition prediction model by combining a radial basis function neural network and a long short-term memory network, train and optimize the initial working condition prediction model based on the historical working condition data in combination with a Bayesian optimization algorithm to obtain a trained working condition prediction model; perform real-time iterative prediction and optimization on the trained working condition prediction model based on a transfer learning algorithm to obtain an optimized working condition prediction model; perform real-time working condition prediction based on the optimized working condition prediction model to obtain working condition prediction data;

[0140] The thermal management system energy consumption prediction module is used to construct an initial thermal management system energy consumption prediction model based on a nonlinear autoregressive neural network; the initial thermal management system energy consumption prediction model is trained based on the operating condition prediction data and the preset temperature control target, and the real-time energy consumption prediction of the thermal management system is performed based on the trained thermal management system energy consumption prediction model to obtain the thermal management system energy consumption prediction data;

[0141] The global optimization module is used to construct a fitness function with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the mean temperature offset value; construct a population with the global temperature trajectory as an individual, and perform iterative optimization within the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm. After the iteration is completed, the optimal global temperature trajectory is output.

[0142] An electronic device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the method for optimizing the global trajectory of the battery temperature of an electric vehicle. A computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for optimizing the global trajectory of the battery temperature of an electric vehicle is implemented.

[0143] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for optimizing the global trajectory of electric vehicle battery temperature, characterized in that: include: Obtain historical operating data and global temperature trajectory of electric vehicles; An initial operating condition prediction model is constructed by combining a radial basis function neural network and a long short-term memory network, and the initial operating condition prediction model is trained and optimized based on the historical operating condition data combined with a Bayesian optimization algorithm to obtain a trained operating condition prediction model; Based on the transfer learning algorithm, the trained working condition prediction model is predicted and optimized in real time to obtain the optimized working condition prediction model; Execute real-time working condition prediction based on the optimized working condition prediction model to obtain working condition prediction data; Construct an initial thermal management system energy consumption prediction model based on nonlinear autoregressive neural network; The initial thermal management system energy consumption prediction model is trained based on the operating condition prediction data and the preset temperature control target, and the real-time energy consumption prediction of the thermal management system is performed based on the trained thermal management system energy consumption prediction model to obtain the thermal management system energy consumption prediction data; The fitness function is constructed with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the average temperature offset value; A population is constructed with the global temperature trajectory as an individual, and an iterative search is performed within the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm, and the optimal global temperature trajectory is output after the iteration is completed.

2. The method for optimizing the global trajectory of battery temperature of an electric vehicle according to claim 1, characterized in that: Before building the initial operating condition prediction model by combining the radial basis function neural network and the long short-term memory network, it also includes: Performing cluster analysis on the historical operating condition data, and using the cluster analysis results as model structure parameters; Based on the model structure parameters, a radial basis function neural network and a long short-term memory network are combined to construct an initial operating condition prediction model.

3. The method for optimizing the global trajectory of battery temperature of an electric vehicle according to claim 1, characterized in that: The training and optimization of the initial operating condition prediction model based on the historical operating condition data in combination with a Bayesian optimization algorithm specifically includes: The objective function is to minimize the verification loss of the initial working condition prediction model under hyperparameters; Based on the Bayesian optimization algorithm and the objective function, the initial operating condition prediction model is optimized for hyperparameters to obtain the optimal hyperparameters, and the operating condition prediction model corresponding to the optimal hyperparameters is trained based on the historical operating condition data to obtain the trained operating condition prediction model.

4. The method for optimizing the global trajectory of battery temperature of an electric vehicle according to claim 1, characterized in that: The real-time iterative prediction and optimization of the trained working condition prediction model based on the transfer learning algorithm specifically includes: The trained working condition prediction model is frozen based on the preset number of freezing layers, and a new output layer is added to the working condition prediction model after the model freezing is completed. The working condition prediction model with the new output layer added is trained and iterated based on real-time working condition data, and an optimized working condition prediction model is obtained after the iteration is completed.

5. The method for optimizing the global trajectory of battery temperature of an electric vehicle according to claim 1, characterized in that: The iterative optimization in the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm specifically includes: Based on the genetic optimization algorithm, each individual is iteratively updated. In each iterative update process, the fitness value corresponding to each individual is calculated, and the population is iteratively updated based on the fitness value corresponding to each individual until the number of iterations reaches a preset value, and the optimal individual is output to obtain the optimal global temperature trajectory.

6. An electric vehicle battery temperature global trajectory optimization system, characterized in that: include: Data acquisition module, used to obtain historical operating data and global temperature trajectory of electric vehicles; The working condition prediction module is used to construct an initial working condition prediction model by combining a radial basis function neural network and a long short-term memory network, train and optimize the initial working condition prediction model based on the historical working condition data in combination with a Bayesian optimization algorithm to obtain a trained working condition prediction model; perform real-time iterative prediction and optimization on the trained working condition prediction model based on a transfer learning algorithm to obtain an optimized working condition prediction model; perform real-time working condition prediction based on the optimized working condition prediction model to obtain working condition prediction data; The thermal management system energy consumption prediction module is used to construct an initial thermal management system energy consumption prediction model based on a nonlinear autoregressive neural network; the initial thermal management system energy consumption prediction model is trained based on the operating condition prediction data and the preset temperature control target, and the real-time energy consumption prediction of the thermal management system is performed based on the trained thermal management system energy consumption prediction model to obtain the thermal management system energy consumption prediction data; A global optimization module is used to construct a fitness function with the goal of minimizing the weighted value of the thermal management system energy consumption prediction data and the average temperature offset value; A population is constructed with the global temperature trajectory as an individual, and an iterative search is performed within the population based on the fitness value corresponding to each individual combined with a genetic optimization algorithm, and the optimal global temperature trajectory is output after the iteration is completed.

7. An electronic device, characterized in that: It comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute a method for optimizing the global trajectory of the battery temperature of an electric vehicle according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: It stores a computer program, and when the computer program is executed by a processor, it implements a method for optimizing the global trajectory of the battery temperature of an electric vehicle as described in any one of claims 1-5.

Images