New energy motor energy efficiency optimization method under dynamic adjustment

Abstract

The invention discloses a new energy motor energy efficiency optimization method under dynamic regulation, and relates to the technical field of electronic control, and the method comprises the steps: monitoring the vehicle load, navigation information, vehicle exterior temperature, environment humidity and current motor temperature distribution in a preset future time period when an electric vehicle runs; predicting driving speed change according to the navigation information to obtain a speed prediction sequence; predicting temperature distribution of the permanent magnet synchronous motor in combination with the data, and generating a motor temperature prediction distribution field; and calculating temperature difference distribution of the motor, analyzing a heat dissipation scheme by taking the temperature difference distribution as a heat dissipation demand, generating a global liquid cooling heat dissipation control scheme containing a plurality of local control parameters, and performing heat dissipation control on the permanent magnet synchronous motor in a predetermined future time period. The technical problems that in the prior art, heat dissipation requirements of a liquid cooling system and a motor are not matched, so that the heat dissipation efficiency is low, and the performance and energy efficiency of the motor of the electric automobile are affected are solved, and the technical effects of improving the heat dissipation efficiency, optimizing the energy utilization efficiency and prolonging the service life of the motor are achieved.

Description

Technical Field

[0001] This application relates to the field of electronic control technology, and particularly to an energy efficiency optimization method for new energy motors under dynamic regulation. Background Art

[0002] With the continuous enhancement of global environmental awareness and the in-depth implementation of the concept of sustainable development, electric vehicles, as a clean and efficient means of transportation, are experiencing a rapid growth in market size. Among the key technologies of electric vehicles, the performance of the motor system plays a decisive role in the power performance, driving range, and reliability of the whole vehicle. Permanent magnet synchronous motors have been widely used in electric vehicles due to their high power density, high efficiency, and good speed regulation performance. However, during actual operation, a large amount of heat is generated in the motor during the working process due to factors such as winding resistance, iron loss, and mechanical friction. Once the motor temperature is too high, it will not only affect the magnetism of the permanent magnet, reduce the output power and efficiency of the motor, but also accelerate the aging of the internal insulation material of the motor, shortening the service life of the motor. At the same time, the uneven distribution of the motor temperature will also cause internal thermal stress, affecting the structural stability of the motor. Currently, the liquid cooling system is a commonly used cooling method for electric vehicle motors. However, the traditional liquid cooling system has a problem of mismatch with the motor cooling demand. It adopts a fixed cooling strategy and cannot be flexibly adjusted according to the real-time operating state and environmental conditions of the motor, which often leads to insufficient cooling or over-cooling in actual applications. In addition, with the continuous progress of sensor technology, communication technology, and data processing technology, and the gradual popularization of intelligent control technology in the automotive field, new possibilities and directions are provided for solving the cooling problem of electric vehicle motors. Under this background, how to optimize the cooling system of electric vehicle motors has become a key problem urgently needed to be solved in the industry.

[0003] In the related technologies at the present stage, there are technical problems that the liquid cooling system does not match the motor cooling demand, resulting in low cooling efficiency and affecting the performance and energy efficiency of electric vehicle motors. Summary of the Invention

[0004] This application solves the technical problems in the prior art that the liquid cooling system does not match the motor cooling demand, resulting in low cooling efficiency and affecting the performance and energy efficiency of electric vehicle motors by providing an energy efficiency optimization method for new energy motors under dynamic regulation.

[0005] This application provides an energy efficiency optimization method for new energy motors under dynamic regulation, including: During the operation of an electric vehicle, monitor and obtain the vehicle load, navigation information, outside temperature, environmental humidity, and current motor temperature distribution within a predetermined future period. Predict the change in driving speed based on the navigation information to obtain a speed prediction sequence. Predict the motor temperature distribution of a permanent magnet synchronous motor based on the vehicle load, outside temperature, environmental humidity, current motor temperature distribution, and speed prediction sequence, and generate a motor temperature prediction distribution field. Calculate and obtain the motor temperature difference distribution based on the standard motor temperature distribution and the motor temperature prediction distribution field, and use the motor temperature difference distribution as the heat dissipation requirement to analyze the motor heat dissipation solution, generate a global liquid cooling heat dissipation control solution, and perform heat dissipation control on the permanent magnet synchronous motor within the predetermined future period. Among them, the global liquid cooling heat dissipation control solution includes multiple local liquid cooling heat dissipation control parameters.

[0006] It is intended to adopt the new energy motor energy efficiency optimization method under dynamic regulation proposed in this application. First, when the electric vehicle is running, monitor the vehicle load, navigation information, outside temperature, environmental humidity, and current motor temperature distribution within a predetermined future period, and predict the change in driving speed based on the navigation information to obtain a speed prediction sequence. Then, combine these data to predict the temperature distribution of the permanent magnet synchronous motor and generate a motor temperature prediction distribution field. Calculate the motor temperature difference distribution based on the standard and predicted temperature distributions, and use this as the heat dissipation requirement to analyze the heat dissipation solution, generate a global liquid cooling heat dissipation control solution containing multiple local control parameters, and perform heat dissipation control on the permanent magnet synchronous motor within a predetermined future period. By precisely matching the liquid cooling system with the motor heat dissipation requirement, the technical effects of improving the heat dissipation efficiency, optimizing the energy utilization efficiency, and extending the service life of the motor are achieved. Description of the Drawings

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0008] Figure 1 It is a schematic flowchart of the new energy motor energy efficiency optimization method under dynamic regulation provided by the embodiment of the present application; Figure 2 It is a schematic flowchart of the speed prediction sequence output of the new energy motor energy efficiency optimization method under dynamic regulation provided by the embodiment of the present application. Detailed Embodiments

[0009] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically exemplified below.

[0010] In order to make the purpose, technical solution and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0011] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0012] The embodiment of this application provides a method for optimizing the energy efficiency of a new energy motor under dynamic adjustment, as Figure 1 shown, the method includes: Step S100, while the electric vehicle is driving, monitor and obtain the vehicle load, navigation information, outside temperature, ambient humidity and current motor temperature distribution within a predetermined future period, predict the driving speed change according to the navigation information, and obtain the speed prediction sequence. Specifically, during the driving of the electric vehicle, the scheme firstly uses pressure sensors, weighing sensors and other equipment installed in key parts such as chassis and suspension to accurately sense the load change of the vehicle in real time, because the load size of the vehicle is directly related to the working intensity and heat generation of the motor, and its accurate data is the basis for subsequent analysis; at the same time, the vehicle navigation system is connected to the satellite positioning system to obtain navigation information of the predetermined future period with rich features such as road type, slope, curve curvature and traffic conditions; in addition, temperature and humidity sensors are installed at appropriate locations outside the vehicle to monitor the outside temperature and ambient humidity in real time, which respectively affect the heat dissipation efficiency and internal insulation performance of the motor, and can provide reference for subsequent analysis; multiple temperature sensors are also arranged on key components such as the stator winding, rotor, and casing of the motor, and combined with the layout of the motor components of the electric vehicle, the temperature of different parts of the motor is monitored in real time, so as to intuitively understand the current heating condition of the motor. After completing data monitoring, the driving speed change prediction phase begins. First, the acquired navigation information is preprocessed, the road type classification is encoded, the road slope and curve curvature are converted into numerical form, and the traffic condition information is quantified to make it structured data suitable for model processing. Then, a large amount of sample data is collected based on the historical driving records of electric vehicles. The data contains different navigation information features and the corresponding actual driving speeds. Then, the sample data is used to train the speed change prediction model using a machine learning algorithm (such as a random forest algorithm). The model learns the complex relationship between navigation information features and driving speed during training and adjusts parameters to improve prediction accuracy. Finally, the preprocessed navigation information is input into the trained speed change prediction model. After calculation and analysis, the model outputs a speed prediction sequence within a predetermined future time period. This sequence can reflect the changing trend of the vehicle's future driving speed and provide important input parameters for subsequent motor temperature distribution prediction.

[0013] In one possible implementation, Figure 2As described above, during the driving of an electric vehicle, the vehicle load, navigation information, outside vehicle temperature, environmental humidity, and current motor temperature distribution within a predetermined future period are monitored and obtained. According to the navigation information, a driving speed change prediction is made to obtain a speed prediction sequence. Step S100 further includes step S110 of extracting road features from the navigation information according to a predetermined distance and predetermined feature indicators to obtain a road feature sequence. Specifically, the road feature extraction process is to obtain key road features for subsequent analysis and prediction through systematic processing of the navigation information. First, the predetermined distance and predetermined feature indicators need to be clarified. Based on actual requirements and application scenarios, a suitable fixed road section distance is selected as the interval scale for feature extraction. For example, every 200 meters. The selection of the distance needs to be comprehensively considered to ensure that the extracted features are coherent and representative, and at the same time, the data volume will not be too large to cause an excessive computational burden. At the same time, set the key feature content to be extracted from the navigation information, including road type (highway, aisle, etc.), slope, traffic lights, etc. The road type affects the vehicle driving speed and rules, the slope is related to the vehicle power demand and energy consumption, and the traffic lights will cause the vehicle to start and stop frequently, having an important impact on the driving speed and rhythm. Then, the navigation information is parsed. With the help of an in-vehicle navigation system or a relevant positioning service interface, the navigation information during the vehicle driving process is obtained in real time. The information is presented in the form of electronic map data, positioning data, etc. Then, professional data parsing algorithms and tools are used to deeply analyze and process it, classify and extract the road information according to a predetermined rule, and convert the complex navigation data into a structured and easy-to-process format for preparing for subsequent feature extraction. Finally, the road features are extracted according to the predetermined distance and indicators. Starting from the current position of the vehicle, feature extraction points are set on the driving route determined by the navigation information at a predetermined distance interval. At each extraction point, the road information is extracted and recorded according to the predetermined feature indicators, the road type is judged and recorded, the slope information is obtained and recorded through terrain data or a slope sensor, and the number and position information of traffic lights within a certain range nearby are counted and recorded. As the vehicle moves forward, the feature extraction points are continuously advanced, and each feature is extracted in turn and combined into a sequence in order to finally obtain a road feature sequence.

[0014] Step S120: According to the historical driving records of the electric vehicle, collect a sample road feature sequence set, and label the vehicle driving speeds under different sample road feature sequences to obtain a sample speed sequence set. Specifically, valuable sample data is mined from the historical driving records of the electric vehicle. First, the data sources of the historical driving records need to be determined, mainly obtained from the vehicle's on-board data recorder, vehicle computer system, and relevant cloud data storage platforms. The on-board data recorder can record key parameters such as time, location, and speed in real time. The vehicle computer system can provide vehicle operation status data. The cloud data storage platform aggregates a large amount of historical data at different times and in different scenarios. Then, data samples that meet the requirements are screened from the large amount of historical driving records obtained, abnormal data caused by sensor failures, emergencies, etc. are removed, the screened data is sorted in chronological order, and data from different sources is integrated to form a complete and organized historical driving record data set. Next, according to the previously determined predetermined distance and predetermined feature indicators, road feature extraction is performed on the navigation information in the sorted historical driving records. According to a fixed road section distance (such as every 200 meters), each driving route segment is analyzed in turn, and key feature information such as road type, slope, traffic lights, etc. is extracted and combined into a road feature sequence. The road features of each historical driving record are extracted in this way to obtain a series of road feature sequences, which together constitute the sample road feature sequence set. After that, the collected sample road feature sequence set is properly stored using a suitable data structure and database management system, a unique identifier is added to each sequence, and relevant information such as driving time and driving route is recorded for easy traceability and management. Finally, while collecting the sample road feature sequences, the vehicle driving speed corresponding to each sample road feature sequence is labeled. According to the timestamp information in the historical driving records, the vehicle driving speed corresponding to each feature extraction point is accurately matched, and a suitable method is used to determine the representative speed of each feature extraction point, such as taking the average speed within a certain period before and after the feature extraction point. The labeled driving speed is associated with the corresponding sample road feature sequence to ensure the accuracy and consistency of the data. Then, all the sample road feature sequences with labeled driving speeds are sorted and arranged in a certain order to form a sample speed sequence set. This set contains the actual driving speed data of the vehicle under a large number of different road features, reflecting the speed change law of the vehicle under various driving conditions.

[0015] Step S130: Train a random forest using the sample road feature sequence set and the sample speed sequence set to obtain a converged speed change prediction model, and input the road feature sequence into the speed change prediction model to output the speed prediction sequence. Specifically, the training and application of the speed change prediction model are completed by means of the random forest algorithm to achieve accurate prediction of the vehicle driving speed. First, carry out data preprocessing work. Carefully clean the collected sample road feature sequence set and sample speed sequence set, check and process missing values and outliers, select appropriate filling or correction methods according to the data characteristics, and at the same time verify the data accuracy to ensure that it truly reflects the actual driving situation. Since different feature dimensions and value ranges are different, in order to prevent some features from having an unbalanced impact on model training, it is necessary to normalize the data, map all feature values to a unified interval, make the model training more stable, and improve the convergence speed and prediction accuracy. Then perform random forest model training. Select a suitable random forest algorithm library, and set key hyperparameters when initializing the model, such as the number of decision trees, the maximum depth, the number of features considered for splitting nodes, etc. The setting of hyperparameters needs to determine the optimal combination through experiments and tuning. Then use the preprocessed sample road feature sequence set as the input feature and the sample speed sequence set as the target variable to input into the model for training. During training, the random forest model constructs multiple decision trees by randomly selecting some samples and features from the sample data according to the decision tree construction principle. Each decision tree splits the samples according to the node features during the growth process to distinguish samples with different speeds as much as possible. Through the ensemble learning of multiple decision trees, the model continuously adjusts the parameters to improve the fitting ability to the sample data. During training, continuously monitor the model performance indicators. When the performance indicators no longer decrease significantly or the decrease amplitude is less than the set threshold in consecutive multiple training iterations, it is determined that the model has reached the convergence state. At this time, the model has fully mastered the laws of the sample data and can better predict the vehicle driving speed. After that, generate the speed prediction sequence. Perform the same preprocessing operations on the road feature sequence to be predicted as the training data, including cleaning, normalization, etc., to ensure that the input data format and range are consistent with the training data. Then input the processed road feature sequence into the trained and converged model. The model analyzes and calculates according to the learned relationship, outputs the speed prediction values and arranges them into a speed prediction sequence, reflecting the possible future driving speed changes of the vehicle. Finally, conduct model evaluation and optimization. Evaluate the model with an independent test data set. Input the road feature sequence of the test data into the model to obtain the predicted speed sequence, compare it with the actual speed sequence, and measure the prediction error by calculating the evaluation index. If the index is not ideal, it means that the model has overfitting or underfitting problems and needs to be further optimized. If there is overfitting, the number of decision trees can be reduced and the maximum depth can be decreased to simplify the model and improve the generalization ability; if there is underfitting, the number of decision trees can be increased and the training data volume can be expanded to enhance the fitting ability. After multiple evaluations and optimizations, the model reaches the best prediction performance.

[0016] Step S200: Predict the motor temperature distribution of the permanent magnet synchronous motor based on the vehicle load, outside vehicle temperature, ambient humidity, current motor temperature distribution, and speed prediction sequence, and generate a motor temperature prediction distribution field. Specifically, the accurate prediction of the permanent magnet synchronous motor temperature distribution is carried out to provide a strong basis for the subsequent formulation of the heat dissipation scheme and ensure the stable operation and performance of the motor. First is data collection and integration. Various sensors installed on the electric vehicle are used to collect data such as vehicle load, outside vehicle temperature, ambient humidity, and current motor temperature distribution in real time and accurately. The vehicle load sensor is installed at key parts such as the chassis, the outside vehicle temperature and ambient humidity sensors are installed at well-ventilated places outside the vehicle, and the current motor temperature distribution is collected by multiple temperature sensors arranged on key components of the motor. At the same time, combined with the speed prediction sequence obtained from the speed change prediction model, the data is integrated according to the time series, a unified data structure is established for storage, and quality inspection is carried out during this period to process missing or abnormal data. Next is model selection and construction. Research and evaluate various existing motor temperature prediction models, such as heat conduction models based on physical principles, empirical formula models, and neural network models based on machine learning. Considering factors such as accuracy, computational efficiency, and data requirements comprehensively, select the most suitable model, and then construct a motor temperature prediction model according to the selected model type. If a neural network model is selected, determine the network structure, training parameters, etc.; if a heat conduction model based on physical principles is selected, obtain the physical parameters of the motor, establish a reasonable heat conduction equation, and fully consider the actual situation of the electric vehicle operation during construction. Subsequently, model training and optimization are carried out. The integrated data is divided into a training set and a test set according to a certain proportion. The training set is input into the constructed model to start training. During training, the model adjusts the parameters according to the input data to reduce the error between the predicted value and the actual value, regularly monitors the training effect, and optimizes the model according to the evaluation results. If overfitting occurs, methods such as regularization techniques are used to reduce the model complexity and improve the generalization ability; if underfitting occurs, methods such as increasing the model complexity are tried to improve the fitting ability. After multiple trainings and optimizations, the model reaches the best prediction performance. Finally, the motor temperature prediction distribution field is generated. The integrated and preprocessed data is input into the trained and optimized model, ensuring that the input data format and range are the same as those during training. The model predicts the temperature distribution of the permanent magnet synchronous motor for a period of time in the future according to the input data, outputs a matrix or array containing the temperature prediction values of each part of the motor, and then combines the layout of the motor components to map the temperature prediction values to the actual three-dimensional space structure of the motor, and uses visualization technology to generate an intuitive motor temperature prediction distribution field, providing a clear reference for the subsequent formulation of the heat dissipation scheme.

[0017] In a possible implementation, the motor temperature distribution of the permanent magnet synchronous motor is predicted based on the vehicle load, the outside temperature, the ambient humidity, the current motor temperature distribution, and the speed prediction sequence to generate a motor temperature prediction distribution field. Step S200 further includes step S210 of pre-training a temperature distribution prediction plug-in, where the temperature distribution prediction plug-in is embedded with Q temperature distribution prediction branches, and Q is an integer greater than 10. Specifically, pre-training the temperature distribution prediction plug-in and embedding multiple temperature distribution prediction branches in the plug-in are key steps to improve the accuracy and comprehensiveness of the motor temperature distribution prediction. In terms of plug-in design and construction, first, the overall architecture of the plug-in should be clarified, a framework that can accommodate multiple branches should be built to ensure its good scalability and compatibility, and at the same time, the data interaction mechanism and coordinated work process between branches should be designed. According to different prediction principles and methods, select temperature distribution prediction branches covering various types such as physical principles, machine learning, and empirical formulas, and combine multiple types of branches to give play to the advantages of different methods. Set the number of branches Q as an integer greater than 10 according to requirements, and the specific number needs to be determined by comprehensively considering factors such as prediction accuracy requirements, computing resource limitations, and data volume. In the pre-training data preparation stage, widely collect information such as vehicle load, outside temperature, ambient humidity, and current motor temperature distribution recorded by vehicle on-board sensors, as well as driving route and speed information provided by the navigation system and various operating condition data in historical driving records. The collected data should cover different driving scenarios, weather conditions, and load conditions. After collection, clean the data to remove outliers and noise data, then perform preprocessing operations such as normalization and standardization to make the data have the same scale and distribution range, and also label the data to clarify the true motor temperature distribution corresponding to each sample. Finally, divide the preprocessed data into a training set, a validation set, and a test set in an appropriate proportion. Enter the pre-training process. For each temperature distribution prediction branch, initialize the corresponding model parameters according to its model type and structure, then select a suitable training algorithm and optimizer according to the model type of different branches, and then use the training set data to pre-train each branch. During training, continuously calculate the loss function between the prediction result and the true value, update the model parameters according to the training algorithm and optimizer, and regularly evaluate the model performance with the validation set and adjust the hyperparameters during this period. Stop training when the performance of the model on the validation set no longer improves or reaches the preset target. After pre-training is completed, use the test set to evaluate the performance of each branch. If the performance of a certain branch does not meet the standard, further adjustment and optimization are required until all branches reach the expected performance indicators.

[0018] Step S220, perform speed mean calculation and speed fluctuation analysis according to the speed prediction sequence, determine the speed mean and speed variance, and configure the number of branch calls of the temperature distribution prediction branch according to the speed mean and speed variance. Specifically, by deeply analyzing the speed prediction sequence, the number of calls of the temperature distribution prediction branch is scientifically and reasonably configured to improve the accuracy and efficiency of the motor temperature distribution prediction. First, the speed mean is calculated. Before the calculation, it is necessary to ensure that the acquired speed prediction sequence is complete and accurate. The sequence is based on the previous prediction model or algorithm and can reflect the trend of vehicle speed changes in the future. Before the calculation, a preliminary inspection is required to eliminate abnormal data points caused by sensor failure or data transmission errors. If abnormal data is found, it must be corrected or eliminated according to the actual situation to ensure the reliability of the calculation results. Then the common arithmetic mean calculation method is used to determine the speed mean. All speed values ​​in the speed prediction sequence are added and then divided by the total number of speed values. The mathematical formula is: , the speed mean can reflect the average speed level of the vehicle in the future, providing an important reference for subsequent analysis and decision-making. Then, the speed fluctuation analysis is carried out. The speed variance is used to measure the degree of dispersion of each speed value in the speed prediction sequence relative to the speed mean, reflecting the speed fluctuation. When calculating, first find the difference between each speed value and the speed mean, then square the difference, and finally find the average of all the squared differences. The mathematical formula is: , the larger the speed variance, the more violent the speed fluctuation, and vice versa, the smaller the speed fluctuation and the more stable the vehicle speed. According to this formula, the difference, square operation, sum and divide by the total number are calculated in sequence to obtain the value of the speed variance. The calculation can be assisted by computer software or programming language related functions to improve efficiency and accuracy. Finally, the number of calls to the temperature distribution prediction branch is configured. According to actual needs and experience, the association rules between the speed mean, speed variance and the number of calls to the temperature distribution prediction branch are established. Usually, when the speed mean is high and the speed variance is large, the vehicle driving state is complex and changeable, and the motor operating conditions are diverse. More branches need to be called to improve the prediction accuracy; when the speed mean and variance are small, the vehicle driving state is stable and the motor operating conditions are single. The number of branch calls can be appropriately reduced to reduce the calculation cost and improve efficiency. The specific number of calls can be determined by setting a series of thresholds, substituting the calculated speed mean and speed variance into the rules, determining the final number of calls, and ensuring that the number is within a reasonable range. The association rules can also be adjusted and optimized according to the characteristics and requirements of the actual application scenarios, laying a good foundation for more accurate and efficient motor temperature distribution prediction in the future.

[0019] Step S230: Randomly select the number of temperature distribution prediction branches within the Q temperature distribution prediction branches. Based on the vehicle load, outside temperature, ambient humidity, current motor temperature distribution, and speed prediction sequence, predict the motor temperature distribution. After calculating the mean of the multiple prediction results output, output the motor temperature prediction distribution field. Specifically, by means of multi-branch prediction and result fusion, the accuracy and reliability of the motor temperature distribution prediction are improved. First, recall the number of branches called determined according to the speed mean and speed variance, and ensure that it is within a reasonable range, neither exceeding the total number of branches Q nor being too small to affect the prediction accuracy and diversity. Then use a random number generation algorithm to randomly select among the Q temperature distribution prediction branches. The random number function libraries in common programming languages can assist in setting the value range and generating non-repeating random numbers equal to the number of branches called. Each random number corresponds to a branch index, thereby determining the branches participating in the prediction, avoiding the bias caused by fixed branch selection, and increasing the reliability and diversity of the prediction results. Then carry out the independent motor temperature distribution prediction work for each branch. First, organize data such as the vehicle load, outside temperature, ambient humidity, current motor temperature distribution, and speed prediction sequence into the input format required by each branch. Different types of branches have different requirements for data format and preprocessing, and it is necessary to ensure the accuracy and completeness of the input data. Subsequently, input the prepared data into the randomly selected branches respectively. The branches based on physical principles calculate the temperature distribution according to physical laws such as heat conduction in combination with motor parameters and operating conditions. The branches based on machine learning extract features through neural network models for prediction. The branches based on empirical formulas estimate the temperature distribution according to empirical formulas. Each branch outputs independent prediction results. Then calculate the mean of the multiple prediction results. First, collect and organize the prediction results of each branch and unify the format. Then, for the temperature prediction value of each part of the motor, add up the temperature values of all branches for this part and divide by the number of branches called to obtain the average prediction value, integrating the prediction advantages of multiple branches, reducing the error and uncertainty of a single branch prediction, and improving the accuracy and stability of the final prediction result. Finally, before outputting the motor temperature prediction distribution field, verify and optimize the results after mean calculation. Compare with historical data or actual measurement data. If a large deviation from the actual situation is found, analyze the reasons and make adjustments, such as evaluating the prediction model of abnormal branches or adjusting parameter settings. After verification and optimization, output the motor temperature prediction distribution field as the final result, which can be presented in the form of two-dimensional or three-dimensional temperature distribution diagrams, data tables, etc.

[0020] In a possible implementation, there is a pre-trained temperature distribution prediction plug-in. The temperature distribution prediction plug-in is embedded with Q temperature distribution prediction branches, where Q is an integer greater than 10. Step S210 further includes step S211 of collecting a sample data set with the predetermined future time period as a constraint according to the historical driving records of the electric vehicle. The sample data includes sample input data and sample supervision data. The sample input data includes sample load, sample temperature, sample humidity, sample initial motor temperature distribution, and sample speed sequence. The sample supervision data includes sample motor temperature distribution. Specifically, accurately and comprehensively collect a sample data set that meets the constraints of the predetermined future time period from the historical driving records of the electric vehicle to lay a solid data foundation for subsequent model training. First, clarify the application requirements, deeply analyze the application scenario and objectives of the entire project, and determine the predetermined future time period according to the time scale requirements for predicting the motor temperature of the electric vehicle. If it is to adjust the electric vehicle's cooling system in real time to ensure the stable operation of the motor in a short time, the time period can be set between 5 and 15 minutes; if it is to evaluate and optimize the motor performance during a longer journey of the electric vehicle, the time period can be extended to 30 minutes or even several hours. At the same time, it is necessary to comprehensively consider the driving characteristics of the electric vehicle. The working state and temperature change of the motor vary greatly under different driving conditions; the thermal characteristics of the motor itself, such as its heat capacity and heat dissipation efficiency, determine the temperature change rate; and the timeliness and availability of the data. If the time period is too long, the timeliness of the data decreases, and if it is too short, insufficient effective information can be obtained. After weighing, determine a suitable predetermined future time period. Then, determine the source of the historical driving records of the electric vehicle, mainly including the on-vehicle data recording system, which can record key vehicle driving parameters in real time; the cloud data storage platform, where the data is complete and reliable; and third-party data collection devices or platforms, but it is necessary to ensure the accuracy and legality of the data. Then formulate a collection strategy based on the data source. For the on-vehicle data recording system, understand its data storage format and reading method, and develop a reading tool or interface; for the cloud data storage platform, communicate with the provider to obtain access rights and download the data according to the specified interface and specifications. Set a reasonable time range during collection, collect enough records to ensure data diversity and representativeness, and initially screen and filter to remove incorrect or abnormal data. After that, start to extract sample data. Regarding the sample input data, obtain the sample load from the historical driving records through an on-vehicle weighing sensor or estimation to ensure accurate and consistent data; extract the sample temperature using an external vehicle temperature sensor, pay attention to the sensor accuracy and calibration, and record the collection time; obtain the sample humidity with the help of a humidity sensor, evaluate and calibrate the sensor performance, and record the collection time; obtain the sample initial motor temperature distribution through the temperature sensors at key parts of the motor to ensure the normal operation of the sensors and accurate data; extract the sample speed sequence from the vehicle speed sensor or the navigation system, calibrate and verify the speed sensor, and organize the data in chronological order.In terms of sample supervision data, at the end of a predetermined future period, motor temperature distribution data is obtained through a motor temperature sensor, ensuring that the measurement range and accuracy of the sensor meet the requirements, and the acquisition time corresponds to the end time of the period. Finally, the extracted sample input data and sample supervision data are uniformly processed in format, converting data with different formats and units into a unified format and unit, such as unifying temperature to degrees Celsius and speed to kilometers per hour. The sample input data and sample supervision data are aligned and associated based on the timestamp information to ensure that the input and supervision data for each sample correspond to the same time period and driving state, forming a complete sample data pair, checking the integrity and consistency of the data, and processing missing or incorrect data. The sorted sample data is organized in a certain structure and format, and a sample data set is constructed using common data storage formats such as CSV files and database tables. A unique identifier is added to each sample for easy management and query, and at the same time, the data set is backed up to prevent data loss and damage.

[0021] Step S212: Divide the sample data set into Q equal parts, and perform supervised training on the BP neural network respectively until convergence, obtaining Q temperature distribution prediction branches, and combining them to generate the temperature distribution prediction plug-in. Specifically, use the sample data set to perform supervised training on multiple BP neural networks, generate multiple temperature distribution prediction branches, and then combine them to form a temperature distribution prediction plug-in, providing a powerful tool for motor temperature distribution prediction. First, perform the equal division of the sample data set. Before the operation, clarify the total amount of the sample data set. Assume there are N samples in total and they are to be divided into Q equal parts, with the number of samples in each part n = N / Q. When calculating, it is necessary to consider whether the number of samples can be evenly divided. If not, the extra samples can be randomly assigned to each part to ensure that the number of samples in each data set is as balanced as possible. Subsequently, use the data processing tools of the programming language to distribute the samples to Q different subsets in order or by random sampling. When distributing, ensure that the data distribution in each subset is similar, avoiding special or deviated data from the overall distribution, providing representative data for subsequent model training. Next, perform the initialization of the BP neural network. Initialize a BP neural network for each equal-divided sample data set. When initializing, determine the network structure. The number of neurons in the input layer is the same as the dimension of the sample input data. The number of layers and neurons in the hidden layer are determined based on experience or experiments. Increasing the hidden layer can improve the fitting ability, but it will also increase the training time and the risk of overfitting. The number of neurons in the output layer is the same as the dimension of the sample supervised data. At the same time, set the network parameters. For example, the learning rate determines the step size of parameter update, the activation function introduces non-linearity, and the number of iterations determines the number of learning rounds. Then enter the supervised training process. Input the sample input data in each sample data set into the corresponding BP neural network. The neural network performs forward propagation. The data goes from the input layer through the hidden layer to the output layer. After the multiplication operation of each layer of data with the weight matrix and adding the bias term, it passes through the activation function for non-linear transformation to obtain the output result, that is, the predicted value for the current sample. Then compare the predicted value with the sample supervised data and calculate the error. Commonly used error functions such as mean square error are used. According to the error, perform backpropagation. Propagate the error signal layer by layer in the reverse direction from the output layer, calculate the gradients of the neuron errors with respect to the weights and biases, and update the weights and biases through the gradient descent algorithm to reduce the error. During training, continuously judge whether the convergence condition is reached. An error threshold or the maximum number of iterations can be set, and check whether it is satisfied after each iteration. If not, continue the next round of training.Finally, there is the combination and plug-in generation of the temperature distribution prediction branch. After all the BP neural networks converge in training, these Q trained neural networks are collected as the temperature distribution prediction branches. Each branch has the ability to predict the motor temperature distribution, and their focuses may be different. Then, a plug-in architecture is designed, including an input interface to receive external input data and transfer it to each branch, an output interface to collect the prediction results of each branch, fuse them according to rules, and then output the predicted temperature distribution field of the motor. The internal call logic coordinates the work of each branch. Finally, the Q branches are integrated according to the designed architecture to generate a temperature distribution prediction plug-in. After generation, it is tested and optimized using sample data not involved in training or new actual data. If the prediction results have large errors or are unstable, the fusion rules are further adjusted, and some neural networks are retrained, etc.

[0022] In a possible implementation, based on the speed prediction sequence, speed mean calculation and speed fluctuation analysis are performed to determine the speed mean and speed variance. And according to the speed mean and speed variance, the number of branch calls of the temperature distribution prediction branch is configured. Step S220 further includes step S221, which calculates the ratios of the speed mean to the maximum speed limit of the vehicle and the speed variance to the historical maximum speed variance respectively. After the mean calculation, the scale of speed demand analysis is obtained. Specifically, by deeply analyzing speed-related parameters and comprehensively considering the relationship between the speed mean and the maximum speed limit of the vehicle, and the relationship between the speed variance and the historical maximum speed variance, the scale of speed demand analysis, which is of crucial guiding significance for subsequent decisions, is obtained. Before calculating the scale of speed demand analysis, first clarify the way to obtain the speed mean. It is based on the speed prediction sequence and is obtained by adding all the speed values in the sequence and then dividing by the total number. When calculating, it is necessary to ensure the accuracy and integrity of the sequence to avoid result deviations caused by data anomalies or missing data. After that, the speed mean is properly recorded and stored. Then, determine the maximum speed limit of the vehicle. Since the speed limits of different road types are different, the maximum speed limits of various roads can be obtained by consulting traffic regulations documents, consulting traffic management departments, or using professional traffic information query platforms. Then, combined with the real-time location information obtained by the vehicle navigation system, vehicle-mounted positioning devices, etc., judge the road type where the vehicle is located to determine the maximum speed limit of the current road, and pay attention to temporary speed limit adjustments caused by special situations such as road construction and bad weather. After clarifying the speed mean and the maximum speed limit of the vehicle, divide the speed mean by the maximum speed limit to obtain a ratio that can intuitively reflect their relative relationship. The smaller the ratio, the farther the average driving speed of the vehicle is from the maximum speed limit, the more stable the driving state, and the lower the possible requirement for prediction accuracy. Subsequently, record the result of this ratio. To determine the historical maximum speed variance, a large amount of historical driving speed data covering different driving scenarios, times, and weather conditions is collected from the vehicle on-board data recorder, driving data management platform, etc. The data is preliminarily sorted and screened to remove abnormal and incorrect data, and then the formula is used. Calculate the velocity variance of each group of data, find the maximum value among them as the historical maximum velocity variance, and record and store it. Then divide the current velocity variance by the historical maximum velocity variance to obtain a ratio that reflects the relative relationship between the current velocity fluctuation degree and the historical maximum fluctuation degree. The smaller the ratio, the smaller the current velocity fluctuation, the more stable the driving state, and the lower the possible requirement for prediction accuracy. Record this ratio. Finally, calculate the mean value of the ratio of the velocity mean to the maximum speed limit of the vehicle and the ratio of the velocity variance to the historical maximum velocity variance to obtain the scale of speed demand analysis. This scale comprehensively reflects the average level and fluctuation of the vehicle driving speed. According to its size, corresponding decisions can be made. A small scale indicates a stable driving state and a low requirement for prediction accuracy, and the computing resource input can be reduced to improve efficiency; a large scale indicates a complex driving state and a high requirement for prediction accuracy, and more computing resources need to be invested to ensure accuracy.

[0023] Step S222: Multiply the speed requirement analysis scale by Q and round down to obtain the number of branch calls. Specifically, determining the number of branch calls of the temperature distribution prediction plug-in based on the speed requirement analysis scale can reasonably allocate computing power resources and improve prediction efficiency while ensuring prediction accuracy. First, clarify the basic data. One is to ensure the accuracy and effectiveness of the speed requirement analysis scale data, which is obtained by calculating the average value of the comprehensive speed mean and the maximum vehicle speed limit ratio, and the ratio of the speed variance to the historical maximum speed variance and then taking the average value, reflecting the degree of demand for prediction accuracy by the current vehicle driving speed. It needs to be checked again before use to detect and correct incorrect or abnormal data. The other is to clearly know the total number Q of branches in the temperature distribution prediction branch of the temperature distribution prediction plug-in. Q is an integer greater than 10 and has been determined in the plug-in design and construction stage, which limits the upper limit of the number of branches available for motor temperature distribution prediction. Then perform the multiplication operation, multiply the confirmed speed requirement analysis scale by Q to dynamically adjust the number of branch calls according to the speed requirement analysis scale. Since the multiplication result may be a decimal, and the actual number of called branches needs to be an integer, rounding operations are required. Appropriate rounding methods such as rounding down, rounding up, or rounding to the nearest integer can be selected according to the actual situation and project requirements. For example, when rounding down, if the multiplication result is 8.3, the number of branch calls after rounding is 8; when rounding to the nearest integer, if the multiplication result is 8.6, the number of branch calls after rounding is 9. The result after rounding is the finally determined number of branch calls. Finally, verify and adjust the result. After obtaining the number of branch calls, verify its rationality, check whether it is within the reasonable range of greater than 0 and less than or equal to Q. If it exceeds the range, recheck the calculation steps and data. At the same time, combine the actual prediction requirements and computing power resources to judge whether the number of branch calls can meet the prediction accuracy requirements. If the prediction accuracy is too low or the computing power resources are wasted seriously, adjust the rounding method or the calculation method of the speed requirement analysis scale. For example, if the number of branch calls is too small to meet the prediction accuracy standard, consider changing to rounding up or increasing the calculation weight of the speed requirement analysis scale; if the number of branch calls is too large resulting in waste of computing power resources, try changing to rounding down or reducing the calculation weight of the speed requirement analysis scale. Through continuous verification and adjustment, ensure that the determined number of branch calls can not only meet the prediction accuracy requirements but also reasonably utilize computing power resources and improve prediction efficiency.

[0024] Step S300: Calculate the temperature difference distribution of the motor based on the standard motor temperature distribution and the predicted motor temperature distribution field, and use the motor temperature difference distribution as the heat dissipation requirement to analyze the motor heat dissipation solution, generate a global liquid cooling heat dissipation control solution, and perform heat dissipation control on the permanent magnet synchronous motor during the predetermined future period. The global liquid cooling heat dissipation control solution includes multiple local liquid cooling heat dissipation control parameters. Specifically, calculate the motor temperature difference distribution by analyzing the difference between the standard motor temperature distribution and the predicted motor temperature distribution field, and use this as the basis for heat dissipation requirements to formulate a global liquid cooling heat dissipation control solution for separate local heat dissipation of specific heat-generating parts of the permanent magnet synchronous motor, so as to achieve efficient heat dissipation control during the predetermined future period. First, calculate the motor temperature difference distribution. Obtain the standard temperature range of each key part during normal operation of the motor from the motor manufacturer's technical documents, and verify and supplement the standard with past experimental test and actual operation experience data to ensure reliable and comprehensive data; refer to the previously generated predicted motor temperature distribution field to check its integrity and accuracy; compare the standard motor temperature distribution with the predicted distribution field point by point, and for key parts such as the stator winding, rotor, and motor controller, calculate the temperature difference by subtracting the standard temperature value from the predicted temperature value to clarify the degree of temperature deviation of each part from the standard and the urgent heat dissipation area. Then, conduct heat dissipation requirement analysis. Identify the high heat-generating areas based on the motor temperature difference distribution, focus on the parts where electromagnetic conversion generates heat quickly due to high-speed rotation or high-load operation, and evaluate the heat dissipation requirement degree in combination with the motor working characteristics, operating conditions, and the sensitivity of each part to temperature, and reasonably allocate heat dissipation resources. Then, design a global liquid cooling heat dissipation control solution. Plan the cooling source location according to the high heat-generating areas to ensure effective coverage of the cooling source without interfering with the normal operation of the motor; design an independent cooling circuit for each high heat-generating area, customize the cooling circuit parameters, and equip each circuit with an independent control device; determine the local liquid cooling heat dissipation control parameters for each independent cooling module, monitor the temperature change in real time and adjust dynamically, and optimize the parameters according to different operating conditions and environmental conditions to ensure the efficient operation of the system. Finally, implement heat dissipation control. Install the components of the liquid cooling heat dissipation system according to the solution, ensure accurate installation position, firm and sealed pipe connection, reasonably arrange the pipes to reduce resistance, install sensors to monitor the temperature of each part of the motor and the operating parameters of the cooling system; monitor the data in real time after starting the system, and the control system automatically adjusts the control parameters according to the preset strategy to ensure that the high heat-generating areas are within the appropriate temperature range; continuously collect and analyze the motor operation data and the operation effect of the heat dissipation system during the heat dissipation control process, optimize the solution according to the actual situation, and reduce energy consumption while ensuring the heat dissipation effect.

[0025] In a possible implementation manner, a motor temperature difference distribution is calculated and obtained according to a standard motor temperature distribution and the motor temperature prediction distribution field, and taking the motor temperature difference distribution as a heat dissipation requirement, a motor heat dissipation scheme analysis is carried out to generate a global liquid cooling heat dissipation control scheme, and the permanent magnet synchronous motor is subjected to heat dissipation control within the predetermined future time period. Among them, the global liquid cooling heat dissipation control scheme includes a plurality of local liquid cooling heat dissipation control parameters. Step S300 further includes step S310 of configuring a predetermined future period and obtaining cycle navigation information of the predetermined future period, where the time interval of the predetermined future period is greater than the predetermined future time period. Specifically, configuring a predetermined future period and obtaining its navigation information is the key basis for subsequent analysis and decision-making. Reasonably setting the period and comprehensively obtaining information can provide strong data support for accurate prediction and effective control. First, it is necessary to clarify the configuration basis and deeply study the actual use scenario of the electric vehicle. If it is used for urban commuting, the road is complex and the vehicle starts and stops frequently. To respond to emergencies in a timely manner and adjust the motor heat dissipation and performance in real time, the predetermined future period can be set to 15 - 30 minutes; if it is used for long-distance transportation and the driving environment is stable, the period can be extended to 1 - 2 hours. At the same time, consider the thermal characteristics and thermal stability of the motor. Motors with a small heat capacity, weak heat dissipation ability, and fast temperature rise require more frequent monitoring and adjustment of heat dissipation measures, and the predetermined future period should be short; motors with good thermal stability and slow temperature change can have an appropriately extended period. Also, combine the response time and working efficiency of the heat dissipation system. For a heat dissipation system with a rapid response, the predetermined future period can be slightly shorter; for a system with a long response time, the period needs to be extended accordingly. Then determine the time interval of the predetermined future period. Refer to the length of the predetermined future time period and combine the above factors to ensure that the time interval is greater than the predetermined future time period. For example, if the predetermined future time period is 10 minutes, considering the situation of urban commuting, general motor thermal stability, and short response time of the heat dissipation system, the time interval can be set to 30 minutes. After determination, verify its rationality, check whether it meets the actual requirements, and whether it can effectively monitor and control the motor operating state. If the time interval is unreasonable, readjust it. Then select the method for obtaining cycle navigation information. The on-vehicle navigation system can be used to obtain information such as the driving route plan, estimated driving time, and real-time road conditions. When interacting with the on-vehicle navigation system, ensure its accuracy and stability, and update the map and road condition data in a timely manner; third-party map data services can also be used. Select a reliable provider and obtain information according to the interface specifications. At the same time, pay attention to data security and privacy protection. Finally, collect and sort out the cycle navigation information, and obtain information such as the driving route, estimated driving time, road type, and real-time traffic conditions within the predetermined future period. The driving route affects the vehicle driving speed, time, motor working state, and heat dissipation requirements. The estimated driving time helps to reasonably arrange the operation of the heat dissipation system. The road type and real-time traffic conditions affect the motor working load and heat dissipation requirements. Obtaining this information in a timely manner can adjust the heat dissipation strategy in advance to ensure the normal operation of the motor.

[0026] Step S320: Using the speed change prediction model, predict and obtain a cycle speed prediction sequence based on the periodic navigation information, and set a heat dissipation time constraint according to the cycle speed prediction sequence.Specifically, before using the speed change prediction model for prediction, the model must be fully checked and confirmed: if the model is trained based on a machine learning algorithm, the generalization ability must be verified to prevent overfitting or underfitting; if it is based on a physical model and empirical formula, it is necessary to check whether the model assumptions are in line with reality and whether the parameters are accurately calibrated to ensure that the model is complete and accurate, the parameters are reasonable, and the training data is sufficient and representative; at the same time, the acquired periodic navigation information is sorted and preprocessed. The periodic navigation information includes the driving route, estimated driving time, road type, real-time traffic conditions, etc. The format conversion and data cleaning are performed according to the model input requirements to remove noise and outliers, correct and supplement incomplete data, and encode road type information to ensure that it can be accurately input. Enter the model; then make a prediction to obtain the cycle speed prediction sequence, input the sorted cycle navigation information into the model, and combine or input them separately according to the model type and requirements. For example, the machine learning model needs to extract features and combine them into vector input, and the physical model needs to input the relevant information into the corresponding formula separately. Ensure that the information sequence and format are correct when entering, and then start the model calculation prediction. The model analyzes the impact of various factors on vehicle speed based on the internal algorithm logic and outputs the sequence. Pay close attention to the operating status during the prediction, and handle errors and exceptions in time. If problems such as long running time or memory overflow occur, optimize the model or adjust the input data scale; after obtaining the prediction sequence, verify and evaluate the results, and compare the prediction results with the actual historical data or Reliable prediction data is compared, and the prediction error is quantified using indicators such as mean square error (MSE) and mean absolute error (MAE). If the error is large, analyze the cause and take corresponding measures to improve it, such as adjusting model parameters, optimizing input data or improving model structure; then analyze the periodic speed prediction sequence, perform statistical analysis, calculate the mean of the predicted driving speed, that is, add up all speed values ​​and divide by the total number to get the average driving speed to reflect the approximate driving speed level, and then calculate the predicted speed fluctuation information, and measure the speed fluctuation degree by variance or standard deviation. The larger the variance or standard deviation, the more violent the speed fluctuation and the more unstable the driving. At the same time, observe the sequence change trend, draw a curve of speed change over time, and judge the vehicle driving status. The driving state will affect the motor workload and heat dissipation requirements; finally, the heat dissipation time constraint is set. When setting, the motor thermal characteristics and the heat dissipation system performance must be fully considered. Different motors have different thermal characteristic parameters, and the heat dissipation system performance indicators are also different. These all affect the setting of the heat dissipation time constraint. According to the predicted average driving speed, predicted speed fluctuation information and speed change trend, a reasonable heat dissipation time constraint is set. When the speed average is high and the fluctuation is large, the motor workload is large and the heat generation is high. It is necessary to shorten the heat dissipation time interval and increase the working time of the cooling system. Conversely, the heat dissipation time interval can be extended and the working time can be reduced. For the case of unstable speed change trend, dynamic adjustments are made according to specific changes to ensure that the motor remains within the appropriate temperature range.

[0027] Step S330: Based on the heat dissipation time constraint, taking the motor temperature difference distribution as the heat dissipation requirement, conduct an analysis of the motor heat dissipation solution and output the global liquid cooling heat dissipation control solution. Specifically, organize the heat dissipation requirements, sort out the motor temperature difference distribution, clarify the temperature difference magnitude and distribution of each part, record and analyze the temperature difference data of each part, and judge which parts have high temperatures and large heat dissipation requirements. For key parts such as stator windings and rotors, a large temperature difference means more heat generation and requires key attention, providing a basis for the subsequent heat dissipation solution. At the same time, study the heat dissipation time constraint, understand the working requirements of the heat dissipation system at different times, and clarify the working intensity and duration of the heat dissipation system at different times based on factors such as the cycle speed prediction sequence. For example, when the vehicle is traveling fast and the motor load is large, a large amount of heat dissipation is required in a short time, and when the vehicle is traveling stably and the load is small, the working intensity and time can be appropriately reduced. Next, plan the heat dissipation strategy. Divide different heat dissipation time periods according to the heat dissipation time constraint, ensuring that the heat dissipation requirements in each time period are relatively consistent. It can be divided according to time intervals or changes in driving conditions. Then, combine with the motor temperature difference distribution and formulate heat dissipation strategies for each time period. When the heat dissipation requirement is large, increase the working intensity of the heat dissipation system, increase the coolant flow rate and velocity and reduce the temperature for rapid heat dissipation; when the requirement is small, reduce the working intensity, reduce the flow rate and velocity and increase the temperature to save energy. Different measures should also be taken according to the differences in heat dissipation requirements of different parts. Then, determine the local liquid cooling heat dissipation control parameters. According to the heat dissipation strategies of each time period, set appropriate control parameters for each key part of the motor. For example, when the stator winding has a large heat dissipation requirement, set a high flow rate and low temperature, and when the rotor has a small requirement, appropriately reduce the flow rate, pressure and increase the temperature. At the same time, use sensors to monitor the motor temperature and coolant flow in real time, and dynamically adjust the parameters according to the monitoring data to meet the heat dissipation requirements. Finally, integrate to form a global liquid cooling heat dissipation control solution, summarize the control parameters of each time period and part, ensure accuracy and consistency, record and organize the solution in detail for implementation and adjustment, formulate the implementation process and control logic, clarify the operation steps and parameter adjustment methods for starting, stopping, and adjusting the heat dissipation system. After the solution is formed, evaluate its heat dissipation effect and energy consumption through simulation, experimental testing, etc. If there are problems, analyze the reasons in time, optimize the set values of the control parameters, and improve the structural layout of the heat dissipation system to enhance the system performance and efficiency.

[0028] In a possible implementation, the cycle speed prediction sequence is predicted and obtained based on the cycle navigation information by using the speed change prediction model, and the heat dissipation time constraint is set according to the cycle speed prediction sequence. Step S320 further includes step S321 of calculating the speed mean and speed variance of the cycle speed prediction sequence to obtain the cycle speed mean and cycle speed variance. Specifically, before calculating the cycle speed mean and cycle speed variance, it is necessary to first check the data of the cycle speed prediction sequence, check for missing values and outliers, clarify the positions and quantities of the missing values. Outliers often occur due to data acquisition equipment failures, signal interference, etc. For example, when the normal speed range is 30 - 60 kilometers per hour, a speed value of 200 kilometers per hour suddenly appears. If there are few missing values, they can be filled with the average value of adjacent data. If there are many and regular missing values, more complex methods are used for estimation; if outliers are due to acquisition errors, they need to be corrected. If they are extreme data and have a large impact, statistical methods are used for adjustment. After the data inspection and processing, calculate the cycle speed mean. Add up the sequence speed values and then divide by the total number of speed values to obtain the mean, which can reflect the approximate driving speed of the vehicle. After calculating the mean, calculate the variance. First, find the difference between each speed value and the mean and square it, then add up the squared differences, and finally divide by the total number of speed values to obtain the variance. The size of the variance reflects the fluctuation of the vehicle's driving speed. After calculating the mean and variance, record them in detail, indicating the calculation time, data source, calculation method, etc. It can be recorded in the form of a table or a document. After recording, analyze the results. The mean reflects the overall driving speed, and the variance reflects the stability of the driving speed.

[0029] Step S322: Input the average cycle speed and the cycle speed variance into the speed - heat dissipation time mapping library, and match to obtain the heat dissipation time constraint, where the heat dissipation time constraint is negatively correlated with the average cycle speed and the cycle speed variance. Specifically, before inputting data into the speed - heat dissipation time mapping library, it is necessary to carefully check the average cycle speed and the cycle speed variance, and re - check the calculation process to ensure that the calculation method is correct, the data processing is rigorous, and the cycle speed prediction sequence used in the calculation is complete and accurate without data omission or error. For example, when calculating the average value, ensure that all speed values are involved in the summation. When calculating the variance, ensure that the difference between each speed value and the average value, the square operation, and the summation operation are all accurate. At the same time, check whether the formats of these two data conform to the requirements of the mapping library. Different mapping libraries may have specific regulations on the number of decimal places of numerical values, data types, etc. It is also necessary to ensure that the data units are consistent with the preset of the mapping library. When they are inconsistent, perform unit conversion to ensure that the input data format and unit are compatible with the mapping library. Then, it is necessary to deeply understand the structure and characteristics of the speed - heat dissipation time mapping library. The mapping library may be stored in the form of a table, a database, a hash table, etc. If it is stored in a database, it is necessary to master its table structure and query method, and also analyze the characteristics of the mapping relationship. Since the heat dissipation time constraint is negatively correlated with the average cycle speed and the cycle speed variance, that is, the larger the average cycle speed and variance, the smaller the heat dissipation time constraint, and vice versa. When using the mapping library, it is necessary to understand the data distribution law based on this characteristic. Subsequently, accurately input the average cycle speed and the cycle speed variance after checking and processing according to the requirements of the mapping library. If it is implemented through programming, ensure that the code logic is correct and the data can be accurately transmitted to the query interface. If it is a manual operation, carefully fill in the data input box to avoid errors. After inputting the data, start the matching query function of the mapping library. According to the storage structure and query algorithm, find the most matching record in the data. If there is a completely matching record, directly obtain the corresponding heat dissipation time constraint value. If not, according to the design of the mapping library, use interpolation methods, nearest neighbor algorithms, etc. to estimate an appropriate heat dissipation time constraint value. For example, the interpolation method can be calculated based on adjacent known data points. After obtaining the heat dissipation time constraint, check its rationality. Judge whether the obtained value meets the expectation based on the negative correlation relationship. For example, if the input average cycle speed and variance are both large, but the heat dissipation time constraint value is also large, it does not conform to the characteristic and there may be problems. At the same time, combined with the actual motor heat dissipation requirements and the system operation conditions, judge whether this constraint can meet the heat dissipation requirements at different driving speeds. If it is found to be unreasonable, adjustments need to be made. The reasons may be inaccurate mapping library data, defective matching algorithms, or errors in input data. If it is a mapping library data problem, the mapping library can be updated and improved. If it is an algorithm problem, it may be necessary to optimize or select a more appropriate algorithm. If it is an input data error, re - check and correct the calculation process and data of the average cycle speed and the cycle speed variance.

[0030] In a possible implementation manner, based on the heat dissipation time constraint, with the temperature difference distribution of the motor as the heat dissipation requirement, an analysis of the motor heat dissipation solution is carried out, and the global liquid cooling heat dissipation control solution is output. Step S330 further includes step S331 of obtaining the global liquid cooling heat dissipation structure of the permanent magnet synchronous motor, where the global liquid cooling heat dissipation structure includes a plurality of local liquid cooling heat dissipation components. Specifically, first, consult technical materials and documents. Collect technical materials and documents from the manufacturer, which contain key contents such as the overall motor design scheme, detailed description of the heat dissipation system, and specification parameters of each component. The technical manual can comprehensively and professionally introduce the global liquid cooling heat dissipation structure, clarify the functions, positions, and connection relationships of each local liquid cooling heat dissipation component. Product manuals, installation guides, etc. can also be consulted to supplement information from different perspectives. At the same time, refer to relevant industry standards and specifications, which have clear regulations on the design and performance requirements of the permanent magnet synchronous motor heat dissipation system, covering all aspects of the liquid cooling heat dissipation structure. By consulting, the general design principles, component selection requirements, and performance testing methods in the industry can be understood to ensure that the obtained information is accurate and meets industry standards. Then, when conditions permit, observe the physical motor on-site and disassemble the heat dissipation system on-site, which is an effective way to obtain intuitive and accurate information. When disassembling, it is necessary to operate in order and method to avoid damaging the motor and heat dissipation components. When disassembling each component, carefully observe its appearance, structural characteristics, and connection method with other components, and mark and record each local liquid cooling heat dissipation component in detail, using numbers, labels, etc. to mark, record the component name, model, specification parameters, installation position, and connection method, and photos or sketches can also be taken to assist in recording. This information will provide a basis for subsequent analysis. Then, use professional detection equipment to obtain more in-depth information. Use an ultrasonic flaw detector to detect the cooling pipes and check for defects such as cracks and holes inside to ensure the tightness and reliability of the pipes. Use an infrared thermal imager to monitor the temperature distribution of the motor during operation, understand the heat generation situation of each part, and judge the heat dissipation effect. Obtain information that cannot be observed by the naked eye through non-destructive testing equipment, and then analyze the test data. Based on the results, evaluate the performance and operating status of the global liquid cooling heat dissipation structure, and optimize and improve the heat dissipation structure targeted. Finally, if problems are encountered during the information acquisition process, consult motor design experts. With their professional knowledge and practical experience, they can analyze and interpret the global liquid cooling heat dissipation structure from a professional perspective, answer questions, and provide improvement suggestions. You can also communicate with motor maintenance technicians. They are familiar with the motor heat dissipation system in their daily work, can share the problems encountered in maintenance and solutions, and provide practical experience in the actual use and maintenance of components, thereby obtaining practical information and further deepening the understanding of the global liquid cooling heat dissipation structure.

[0031] Step S332: With the heat dissipation time constraint, taking the motor temperature difference distribution as the heat dissipation requirement and minimizing the heat dissipation energy consumption as the goal, optimize and analyze the heat dissipation control parameters of the multiple local liquid cooling heat dissipation components, and output multiple local liquid cooling control parameters. Specifically, first, sort out and analyze the basic data, clarify the heat dissipation time constraint, and based on the motor load under different driving conditions, understand the working requirements and time limits of the heat dissipation system to provide a time dimension limit for subsequent optimization; deeply analyze the motor temperature difference distribution, determine the heat dissipation priorities of key parts such as the stator winding and rotor, and focus on the parts with large temperature differences; summarize information such as the models, specifications, performance parameters and position functions of the local liquid cooling heat dissipation components to lay a foundation for parameter optimization. Next, establish a heat dissipation energy consumption model, with the goal of minimizing the heat dissipation energy consumption, analyze factors affecting heat dissipation energy consumption such as the power of the cooling water pump, the heat dissipation efficiency of the radiator, the coolant flow rate and temperature, find out their internal relationships with heat dissipation energy consumption, construct a specific heat dissipation energy consumption calculation model, quantify the relationship between each factor and heat dissipation energy consumption, and provide a quantitative basis for parameter optimization. Then, set the initial control parameter range. According to the component performance and working characteristics, combined with the actual operation of the motor, determine the initial value range of the control parameters of each component to avoid poor heat dissipation effect or excessive energy consumption caused by unreasonable parameters. After that, use appropriate optimization algorithms such as genetic algorithms and particle swarm algorithms, take the heat dissipation time constraint, the motor temperature difference distribution, the heat dissipation energy consumption model and the initial control parameter range as inputs, adjust the control parameters of each component during operation, calculate the heat dissipation effect and energy consumption under different parameter combinations, screen the optimal parameter combination, and monitor the algorithm operation in real time. Then evaluate and verify the optimization results, check whether the parameters can meet the motor heat dissipation requirements, and verify whether the motor temperature distribution is reasonable through simulation or testing; calculate the optimized energy consumption based on the energy consumption model, compare the energy consumption before and after optimization, and evaluate whether the minimization goal is achieved. If the effect is not good, readjust the parameters; at the same time, consider the stability and reliability of the heat dissipation system under the optimized parameters to ensure the normal operation of each component. Finally, sort out and record the multiple local liquid cooling control parameters finally determined, and record the control parameter values, applicable conditions and time ranges in detail, and output them in the form of a report. The report covers parameter descriptions, optimization process results, heat dissipation effects, energy consumption evaluations and system stability analyses, etc.

[0032] In the embodiment of the present application, when the electric vehicle is running, the vehicle load, navigation information, outside vehicle temperature, environmental humidity and current motor temperature distribution within a predetermined future period are monitored, and a speed prediction sequence is obtained by predicting the change in the driving speed based on the navigation information; then, these data are combined to predict the temperature distribution of the permanent magnet synchronous motor, and a motor temperature prediction distribution field is generated; the motor temperature difference distribution is calculated according to the standard and the predicted temperature distribution, and based on this, the heat dissipation solution is analyzed according to the heat dissipation requirement, and a global liquid cooling heat dissipation control solution including multiple local control parameters is generated to perform heat dissipation control on the permanent magnet synchronous motor within a predetermined future period, achieving the technical effects of improving the heat dissipation efficiency, optimizing the energy utilization efficiency and prolonging the service life of the motor by accurately matching the liquid cooling system with the motor heat dissipation requirement.

[0033] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for optimizing the energy efficiency of a new energy motor under dynamic adjustment, characterized in that, The method includes: During the running of the electric vehicle, monitoring and obtaining the vehicle load, navigation information, outside vehicle temperature, environmental humidity, and current motor temperature distribution within a predetermined future period, predicting the change in driving speed according to the navigation information, and obtaining a speed prediction sequence; Predicting the motor temperature distribution of the permanent magnet synchronous motor according to the vehicle load, outside vehicle temperature, environmental humidity, current motor temperature distribution, and speed prediction sequence, and generating a motor temperature prediction distribution field; Calculating and obtaining the motor temperature difference distribution according to the standard motor temperature distribution and the motor temperature prediction distribution field, using the motor temperature difference distribution as the heat dissipation requirement, analyzing the motor heat dissipation scheme, generating a global liquid cooling heat dissipation control scheme, and performing heat dissipation control on the permanent magnet synchronous motor within the predetermined future period, wherein the global liquid cooling heat dissipation control scheme includes a plurality of local liquid cooling heat dissipation control parameters.

2. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 1, characterized in that Predicting the change in driving speed according to the navigation information and obtaining a speed prediction sequence, including: Extracting road features from the navigation information according to a predetermined distance and predetermined feature indicators to obtain a road feature sequence; Collecting a sample road feature sequence set according to the historical driving records of the electric vehicle, and labeling the vehicle driving speeds under different sample road feature sequences to obtain a sample speed sequence set; Training a random forest using the sample road feature sequence set and the sample speed sequence set to obtain a converged speed change prediction model, and inputting the road feature sequence into the speed change prediction model to output the speed prediction sequence.

3. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 2, characterized in that, Predicting the motor temperature distribution of the permanent magnet synchronous motor according to the vehicle load, outside vehicle temperature, environmental humidity, current motor temperature distribution, and speed prediction sequence, and generating a motor temperature prediction distribution field, including: Pre-training a temperature distribution prediction plug-in, wherein the temperature distribution prediction plug-in is embedded with Q temperature distribution prediction branches, and Q is an integer greater than 10; Calculating the speed mean value and analyzing the speed fluctuation according to the speed prediction sequence to determine the speed mean value and speed variance, and configuring the number of branch calls of the temperature distribution prediction branch according to the speed mean value and speed variance; Randomly selecting the number of temperature distribution prediction branches of the branch calls within the Q temperature distribution prediction branches, predicting the motor temperature distribution according to the vehicle load, outside vehicle temperature, environmental humidity, current motor temperature distribution, and speed prediction sequence, and calculating the mean value of the multiple prediction results output and then outputting the motor temperature prediction distribution field.

4. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 3, characterized in that, Pre-training a temperature distribution prediction plug-in, including: Collecting a sample data set according to the historical driving records of the electric vehicle with the predetermined future period as a constraint, wherein the sample data includes sample input data and sample supervision data, the sample input data includes sample load, sample temperature, sample humidity, sample initial motor temperature distribution, and sample speed sequence, and the sample supervision data includes sample motor temperature distribution; Dividing the sample data set into Q equal parts, respectively performing supervised training on the BP neural network until convergence, obtaining Q temperature distribution prediction branches, and combining them to generate the temperature distribution prediction plug-in.

5. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 3, characterized in that, Configuring the number of branch calls for the temperature distribution prediction branch according to the mean speed and speed variance, including: Calculating the ratios of the mean speed to the maximum speed limit of the vehicle and the speed variance to the historical maximum speed variance respectively, and obtaining the scale of speed demand analysis after the mean calculation; Multiplying the scale of speed demand analysis by Q and taking the integer to obtain the number of branch calls.

6. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 2, characterized in that, Taking the motor temperature difference distribution as the heat dissipation demand, analyzing the motor heat dissipation scheme, and generating a global liquid cooling heat dissipation control scheme, including: Configuring a predetermined future period and obtaining the periodic navigation information of the predetermined future period, wherein the time interval of the predetermined future period is greater than the predetermined future time period; Using the speed change prediction model to predict and obtain a periodic speed prediction sequence according to the periodic navigation information, and setting the heat dissipation time constraint according to the periodic speed prediction sequence; Based on the heat dissipation time constraint, taking the motor temperature difference distribution as the heat dissipation demand, analyzing the motor heat dissipation scheme, and outputting the global liquid cooling heat dissipation control scheme.

7. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 6, characterized in that, Setting the heat dissipation time constraint according to the periodic speed prediction sequence, including: Calculating the mean speed and speed variance of the periodic speed prediction sequence to obtain the periodic speed mean and periodic speed variance; Inputting the periodic speed mean and periodic speed variance into the speed-heat dissipation time mapping library to match and obtain the heat dissipation time constraint, wherein the heat dissipation time constraint is negatively correlated with the periodic speed mean and periodic speed variance.

8. The new energy motor energy efficiency optimization method under dynamic adjustment according to claim 6, wherein Based on the heat dissipation time constraint, taking the motor temperature difference distribution as the heat dissipation demand, analyzing the motor heat dissipation scheme, including: Obtaining the global liquid cooling heat dissipation structure of the permanent magnet synchronous motor, wherein the global liquid cooling heat dissipation structure includes a plurality of local liquid cooling heat dissipation components; Taking the heat dissipation time constraint, taking the motor temperature difference distribution as the heat dissipation demand, and aiming at minimizing the heat dissipation energy consumption, optimizing and analyzing the heat dissipation control parameters of the plurality of local liquid cooling heat dissipation components, and outputting a plurality of local liquid cooling heat dissipation control parameters.

Images