Multi-physical field simulation method for motor cooling device

Abstract

The invention relates to the technical field of motor cooling, and discloses a multi-physical field simulation method for a motor cooling device. According to the method, a multi-physics field coupling layer, an optimization layer and a simulation verification model are included, and the multi-physics field coupling layer and the optimization layer are connected to form an end-to-end numerical calculation model. In the first simulation stage, first experimental data, real cooling strategy information, an adjustment instruction, verification feedback information and the like of motor operation are obtained, corresponding models are input to obtain prediction results, and model parameters are adjusted based on the results. Future experimental data can be obtained to further optimize parameters, and a second simulation stage is set. The method can accurately simulate multiple physical fields of the motor cooling device, optimize a cooling strategy, improve simulation precision and model adaptability, save research and development cost, and improve motor performance and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of motor cooling, and in particular to a multi-physics field simulation method for a motor cooling device. Background Art

[0002] In modern industry and technology, electric motors, as core power components, are widely used in numerous industries, including automotive, aerospace, and new energy. As motors develop toward higher power density, higher speeds, and smaller sizes, the heat they generate during operation is increasing dramatically. If this heat cannot be dissipated promptly and effectively, the motor's temperature will continue to rise, leading to a series of serious problems.

[0003] Excessive temperatures can degrade the insulation of motor windings, shortening the motor's lifespan and potentially causing short circuits and motor damage. Furthermore, uneven temperature distribution can lead to inconsistent thermal expansion of motor components, creating additional stress that can affect the motor's structural stability and operating accuracy. Furthermore, poor motor cooling can reduce efficiency and increase energy consumption, a significant disadvantage for modern industry, which strives for energy efficiency.

[0004] Traditional motor cooling system design and optimization methods rely primarily on experience and trial and error. This approach not only consumes significant manpower, material resources, and time, but also, due to the complex and ever-changing operating environment of motors, which involves the interaction of multiple physical fields such as temperature, flow, and stress, relying solely on experience and experimentation makes it difficult to fully and deeply understand the cooling system's performance under various operating conditions.

[0005] In the early days, researchers primarily focused on a single physical field within the motor, studying only the impact of the temperature field on motor cooling, while ignoring the coupling effects of other factors such as flow and stress fields. With technological advancements, the concept of multi-physics has gradually been introduced, but the lack of effective simulation methods and tools has made it difficult to accurately simulate the complex interrelationships between these multiple physical fields. For example, when simulating the flow of the cooling medium, it is impossible to accurately consider its impact on the temperature distribution, or the effect of temperature changes on the stress field.

[0006] Existing simulation methods often suffer from insufficient accuracy. On the one hand, simplified models fail to accurately reflect actual physical processes. For example, the simplified processing of complex internal motor structures can lead to significant deviations between simulation results and actual conditions. On the other hand, in data processing and model training, there is a lack of effective strategies to fully utilize experimental data, resulting in weak model generalization and difficulty adapting to different motor operating conditions and cooling device designs.

[0007] Furthermore, developing a reasonable cooling strategy based on actual operating conditions is a pressing issue during the design of motor cooling devices. Currently, cooling strategies are mostly based on fixed rules or simple empirical formulas, and are unable to dynamically adjust based on the motor's real-time operating status and multi-physics field information, making it difficult to optimize the cooling effect. In summary, existing motor cooling technologies have many shortcomings in multi-physics field simulation and cooling strategy optimization. There is an urgent need for a more advanced, efficient, and accurate multi-physics field simulation method for motor cooling devices to meet actual engineering needs. Summary of the Invention

[0008] The object of the present invention is to provide a multi-physics field simulation method for a motor cooling device to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a multi-physics field simulation method for a motor cooling device, the method comprising: The simulation method includes a multi-physics coupling layer, an optimization layer, and a simulation verification model. The multi-physics coupling layer and the optimization layer are connected to form an end-to-end numerical calculation model, so that the optimization layer directly generates cooling strategy information based on the output of the multi-physics coupling layer. The method includes a first simulation stage, The first simulation stage includes: Acquire a plurality of first experimental data during operation of the motor, first real cooling strategy information corresponding to the first experimental data, and a first adjustment instruction and first verification feedback information for the first real cooling strategy information, wherein the first experimental data include first operating parameters of the motor and first measured physical field information for a cooling device, the first measured physical field information including current measurement data and historical measurement data of a temperature field, a flow field, and a stress field; Inputting a first input sample including the first experimental data into the multiphysics coupling layer to obtain a first implicit field representation output by the multiphysics coupling layer; Inputting a first intermediate sample including the first implicit field representation into the optimization layer to obtain first predicted cooling strategy information output by the optimization layer; Inputting the first intermediate sample into a simulation verification model to obtain a first prediction adjustment instruction and first prediction verification feedback information output by the simulation verification model; Parameters of the simulation verification model are adjusted based on the first adjustment instruction, the first prediction adjustment instruction, the first verification feedback information, and the first prediction verification feedback information.

[0010] Preferably, the parameters of the multi-physics coupling layer and the optimization layer are adjusted based on the first prediction adjustment instruction, the first prediction verification feedback information, the first prediction cooling strategy information and the first actual cooling strategy information. The first adjustment instruction and the first prediction adjustment instruction are respectively used to indicate whether manual correction strategy and correction timing are required during the simulation process, and the first verification feedback information and the first prediction verification feedback information respectively include manually marked and cooling efficiency evaluation results generated by the simulation model; The first verification feedback information includes at least one of the following: Temperature distribution uniformity information, flow field stability information, cooling efficiency, structural stress peak, number of thermal cycles, and material deformation threshold.

[0011] Preferably, the first simulation stage further includes: Acquire first future experimental data for the operating environment of the cooling device, The output of the optimization layer also includes first future predicted physical field information for the operating environment of the cooling device. Adjusting the parameters of the multi-physics coupling layer and the optimization layer based on the first prediction adjustment instruction, the first prediction verification feedback information, the first prediction cooling strategy information, and the first actual cooling strategy information includes: Based on the first future experimental data, the first future predicted physical field information, the first predicted adjustment instruction, the first predicted verification feedback information, the first predicted cooling strategy information and the first real cooling strategy information, the parameters of the multi-physical field coupling layer and the optimization layer are adjusted.

[0012] Preferably, the first future experimental data includes future temperature field measured data, future flow field measured data and / or future implicit field representation corresponding to the future measured data.

[0013] Preferably, the method further includes a second simulation phase after the first simulation phase. The second simulation stage includes: Acquire a plurality of second experimental data during operation of the motor, second real cooling strategy information corresponding to the second experimental data, and a second adjustment instruction and second verification feedback information for the second real cooling strategy information, wherein the second experimental data includes a second operating parameter of the motor and second measured physical field information for the cooling device; Inputting a second input sample including the second experimental data into the multiphysics coupling layer to obtain a second implicit field representation output by the multiphysics coupling layer; inputting a second intermediate sample including the second implicit field representation into the optimization layer to obtain second predicted cooling strategy information output by the optimization layer; Inputting the second intermediate sample into the simulation verification model to obtain a second prediction adjustment instruction and second prediction verification feedback information output by the simulation verification model; adjusting parameters of the simulation verification model based on the second adjustment instruction, the second prediction adjustment instruction, the second verification feedback information, and the second prediction verification feedback information; and Based on the second prediction adjustment instruction, the second prediction verification feedback information, the second prediction cooling strategy information and the second actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

[0014] Preferably, the adjustment instruction includes adjustment decision information, which indicates whether manual correction of the strategy is required and the specific time node for correction; the prediction adjustment instruction includes prediction adjustment decision information, which indicates whether correction is triggered during the simulation process and the predicted triggering time.

[0015] Preferably, the adjustment instruction includes an adjustment identifier, which is used to indicate whether the first real cooling strategy information has been adjusted through external intervention, and the predicted adjustment instruction includes a predicted adjustment identifier, which is used to indicate whether the predicted cooling strategy information requires external intervention adjustment.

[0016] Preferably, inputting a first input sample including the first experimental data into the multi-physics field coupling layer to obtain a first implicit field representation output by the multi-physics field coupling layer comprises: Based on the first verification feedback information, classify the plurality of first experimental data into working conditions; Based on the classification result, sampling is performed from the plurality of first experimental data in equal proportion according to categories to obtain a plurality of first input sample data; and A first input sample including the first input sample data is input into the multiphysics coupling layer to obtain the first implicit field representation.

[0017] Preferably, the experimental data is divided into a plurality of working condition categories according to the verification feedback information, and the difference in the number of samples corresponding to each category in the plurality of first input sample data does not exceed a preset threshold.

[0018] Preferably, the method further comprises: Before the first simulation stage, pre-calculating the multi-physics coupling layer and the optimization layer offline so that the simulation model can generate the first predicted cooling strategy information based on the first input sample; The first simulation stage further includes: An initial simulation is performed using a simulation model obtained by offline pre-calculation, and during the simulation process, the first experimental data and corresponding first real cooling strategy information, as well as a first adjustment instruction and first verification feedback information for the first real cooling strategy information are obtained.

[0019] Preferably, the offline pre-calculation includes: Acquire third experimental data and third real cooling strategy information corresponding to the third experimental data, wherein the third experimental data includes historical operating parameters of the test motor and historical physical field information for the cooling device; Inputting a third input sample including the third experimental data into the multiphysics coupling layer to obtain a third implicit field representation output by the multiphysics coupling layer; Inputting a third intermediate sample including the third implicit field representation into the optimization layer to obtain third predicted cooling strategy information output by the optimization layer; and Based on the third predicted cooling strategy information and the third actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

[0020] Preferably, the third experimental data further includes third verification feedback information for the third true cooling strategy information. Wherein, adjusting the parameters of the multi-physics field coupling layer and the optimization layer based on the third predicted cooling strategy information and the third actual cooling strategy information includes: Based on the third verification feedback information, the third predicted cooling strategy information and the third actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

[0021] Preferably, the present invention further includes a multi-physics field simulation device for a motor cooling device, the device comprising: An experimental data acquisition unit is configured to acquire experimental data during the operation of the motor, corresponding actual cooling strategy information, adjustment instructions, and verification feedback information; a coupling layer processing unit configured to input experimental data into the multiphysics coupling layer and output an implicit field representation; an optimization layer processing unit configured to input the implicit field representation into the optimization layer to generate predicted cooling strategy information; a verification model processing unit configured to input the implicit field representation into the simulation verification model to output prediction adjustment instructions and prediction verification feedback information; A parameter adjustment unit is configured to adjust the simulation verification model parameters based on the adjustment instructions, the predicted adjustment instructions, the verification feedback information and the predicted verification feedback information, and to adjust the coupling layer and optimization layer parameters based on the predicted adjustment instructions, the predicted verification feedback information, the predicted cooling strategy information and the actual cooling strategy information.

[0022] Compared with the prior art, the present invention has the following beneficial effects: In terms of improving simulation accuracy, this method uses a multi-physics coupling layer to comprehensively process multi-physics field information such as temperature field, flow field, and stress field during motor operation. It not only takes into account current measurement data, but also incorporates historical measurement data, and can more comprehensively and accurately reflect the complex interactions between multiple physical fields. Compared with traditional simulation methods, it avoids the loss of accuracy caused by ignoring certain physical field factors or simplifying models. For example, in the simulation of motor cooling, it can accurately calculate the impact of cooling medium flow on temperature distribution and stress changes caused by temperature changes, making the simulation results closer to the actual situation and providing reliable data support for the design and optimization of motor cooling devices.

[0023] In terms of optimizing the cooling strategy, the optimization layer directly generates cooling strategy information based on the output of the multi-physics field coupling layer. Furthermore, this process combines multiple data points, such as actual cooling strategy information, predicted adjustment instructions, and verification feedback information, to adjust parameters. This enables the cooling strategy to be dynamically optimized based on the motor's real-time operating status and multi-physics field information. For example, when the motor load changes and causes the temperature to rise, the optimized cooling strategy can promptly adjust the flow rate and flow velocity of the cooling medium to ensure that the motor always operates within the appropriate temperature range, effectively improving the motor's cooling efficiency and operational stability.

[0024] In terms of model training and adaptability, by acquiring a large amount of experimental data, including motor operating parameters and measured physical field information of the cooling device under different operating conditions, and combining it with corresponding adjustment instructions and verification feedback information, the multi-physics field coupling layer, optimization layer, and simulation verification model are continuously trained and parameterized. This approach improves the model's generalization capabilities, enabling it to adapt to different motor operating conditions and cooling device designs. Whether under high motor load and low speed conditions or facing cooling devices with different structures and materials, the model can accurately simulate and optimize strategies.

[0025] In terms of cost savings, traditional motor cooling device design relies on extensive testing, requiring significant manpower, material resources, and time. However, the simulation method of the present invention performs simulation and optimization in a virtual environment, significantly reducing the number of actual tests. For example, during the development of a new motor cooling device, multiple design options can be evaluated and screened using simulation methods, and then a few optimized options can be verified through actual testing, effectively reducing R&D costs and shortening the product development cycle.

[0026] In terms of improving motor performance and reliability, precise simulation and optimized cooling strategies have resulted in more uniform temperature distribution, more stable flow fields, and effectively controlled structural stress. This helps improve the motor's insulation performance, reduce the number of thermal cycles, and lower the risk of material deformation, significantly enhancing motor performance and reliability, extending its service life, and providing strong support for the stable development of related industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a working principle diagram of the multi-physics field simulation method for a motor cooling device according to the present invention; Figure 2 Construct a flow chart for the first future experimental data; Figure 3 This is the flow chart of the second simulation stage; Figure 4 Flowchart for offline pre-computation and initialization of the first simulation stage. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] See also Figures 1-4 The present invention provides a multi-physics field simulation method for a motor cooling device, and the specific implementation steps are as follows: During motor operation, multiple first experimental data are collected. These data include first operating parameters of the motor, such as the motor speed and load, as well as first measured physical field information for the cooling device, including current and historical measurement data for temperature, flow, and stress fields. Simultaneously, first actual cooling strategy information corresponding to the first experimental data is obtained, such as the flow setting of the cooling medium and the on / off control of the cooling channels, as well as first adjustment instructions and first verification feedback information for the first actual cooling strategy information.

[0030] The first input sample, containing the first experimental data, is fed into the multiphysics coupling layer. The multiphysics coupling layer analyzes and processes the input data, taking into account the interactions among the temperature, flow, and stress fields, and outputs a first implicit field representation. This implicit field representation provides a comprehensive description of the current state of the motor cooling system, including information about the relationships between the various physical fields.

[0031] The first intermediate sample containing the first implicit field representation is input to the optimization layer. Based on the first implicit field representation, the optimization layer applies specific algorithms and strategies, taking into account the motor's operating requirements and the performance limitations of the cooling device, and outputs first predicted cooling strategy information. This predicted cooling strategy information is the optimized cooling solution provided by the optimization layer based on the current motor operating state and cooling device status.

[0032] The first intermediate sample is input into the simulation verification model. Based on the input first intermediate sample, the simulation verification model simulates the operation of the motor cooling device under the predicted cooling strategy and outputs a first prediction adjustment instruction and first prediction verification feedback information. The first prediction adjustment instruction indicates whether and when manual corrections to the cooling strategy are required during the simulation process. The first prediction verification feedback information includes cooling performance evaluation results, such as temperature distribution uniformity and flow field stability.

[0033] Parameters of the simulation verification model are adjusted based on the first adjustment instruction, the first prediction adjustment instruction, the first verification feedback information, and the first prediction verification feedback information. By continuously adjusting the parameters of the simulation verification model, the actual operation of the motor cooling device can be more accurately simulated, thereby improving the accuracy and reliability of the simulation.

[0034] The present invention will be further described below in conjunction with Examples 1 to 6: Example 1

[0035] In practical applications, the first simulation phase requires consideration of more factors beyond the basic steps described above. After obtaining the first experimental data, the first actual cooling strategy information, the first adjustment instructions, and the first verification feedback information, the parameters of the multiphysics coupling layer and the optimization layer are adjusted based on the first predicted adjustment instructions, the first predicted verification feedback information, the first predicted cooling strategy information, and the first actual cooling strategy information.

[0036] The first adjustment instruction and the first prediction adjustment instruction are used to indicate whether manual strategy correction is required during the simulation process and when to correct the correction. For example, when the load of the motor suddenly changes significantly, the first adjustment instruction may indicate that manual intervention is required to adjust the cooling strategy to ensure that the motor can operate normally under the new load conditions. The first prediction adjustment instruction is the simulation verification model predicting whether the strategy needs to be corrected based on the simulation results and the time to trigger the correction. If the simulation verification model predicts that the temperature of the motor will exceed the safety threshold at a certain point in the future, it will output the first prediction adjustment instruction, indicating that the cooling strategy needs to be adjusted in advance.

[0037] The first verification feedback information and the first prediction verification feedback information include the cooling efficiency evaluation results manually marked and generated by the simulation model, respectively. The first verification feedback information includes at least one of the following items: temperature distribution uniformity information, flow field stability information, cooling efficiency, structural stress peak, number of thermal cycles, material deformation threshold, etc. Taking the temperature distribution uniformity information as an example, during the operation of the motor, if the design of the cooling device is unreasonable, it may cause large temperature differences in different parts of the motor, affecting the performance and life of the motor. By analyzing the temperature distribution uniformity information, the effectiveness of the cooling strategy can be evaluated. If the first verification feedback information shows that the temperature distribution is uneven, the cooling strategy needs to be adjusted, such as changing the flow path of the cooling medium or increasing the flow rate of the cooling medium. At the same time, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted according to these feedback information, so that the model can better adapt to the actual situation and improve the accuracy of the prediction.

[0038] When acquiring first-time future experimental data for the cooling system's operating environment, it's crucial to fully consider various potential variables. Future temperature field measurements may be affected by fluctuations in ambient temperature, which can vary with season and time of day if the motor is used outdoors. Future flow field measurements may be affected by wear or blockage of internal cooling system components, leading to changes in the flow of the cooling medium. The future implicit field representation corresponding to the future measured data comprehensively reflects the impact of these changes on the motor cooling system.

[0039] In addition to the first predicted cooling strategy information, the optimization layer outputs first future predicted physical field information specific to the cooling device's operating environment. Based on the first future experimental data, the first future predicted physical field information, the first predicted adjustment instructions, the first predicted verification feedback information, the first predicted cooling strategy information, and the first actual cooling strategy information, the parameters of the multi-physics coupling layer and the optimization layer are adjusted. This allows the model to not only make predictions and adjustments based on current experimental data but also consider possible future scenarios, proactively optimizing the cooling strategy and improving the performance and reliability of the motor cooling device. Example 2

[0040] In the first simulation phase, data acquisition and processing are crucial. Obtaining the first future experimental data for the cooling device's operating environment is crucial for improving the accuracy and foresight of the simulation.

[0041] The first future experimental data includes future temperature field measured data, future flow field measured data, and / or future implicit field representations corresponding to the future measured data. The future temperature field measured data can be obtained by placing temperature sensors around the cooling device. These sensors can monitor changes in ambient temperature and temperature trends in key parts of the motor in real time. For example, high-precision temperature sensors can be installed near the motor windings, on the surface of the core, and other locations to record temperature data over a period of time in the future. By analyzing this data, we can understand the temperature variation patterns of the motor under different operating conditions, providing a basis for subsequent simulations and strategy adjustments.

[0042] Acquiring future flow field data will require specialized measurement equipment, such as particle image velocimetry (PIV) or hot-wire anemometers. These devices can measure parameters such as the velocity, flow rate, and direction of the coolant within the cooling channel. By monitoring future flow field data, anomalies in the coolant flow process, such as low velocity or uneven flow, can be promptly detected.

[0043] Assume that the flow rate of the cooling medium is , the flow rate is , the cross-sectional area of the cooling channel is , which satisfy the formula ,in Indicates the volume of cooling medium passing through a certain cross section of the cooling channel per unit time, in cubic meters per second ( ); Indicates the flow rate of the cooling medium in meters per second ( ); Indicates the cross-sectional area of the cooling channel in square meters ( If the flow rate in a certain area of the cooling channel is significantly lower than that in other areas, there may be blockage or excessive resistance in that area. This requires inspection and maintenance of the cooling device. At the same time, this factor should be taken into account in the simulation model and relevant parameters should be adjusted.

[0044] The future implicit field representation corresponding to future measured data is a comprehensive, abstract representation of information such as the future temperature and flow fields. It integrates the relationships between multiple physical quantities, providing a more comprehensive reflection of changes in the cooling device's operating environment. Advanced data processing methods, such as principal component analysis (PCA) in machine learning algorithms or autoencoders in deep learning, can be used to obtain this future implicit field representation. These methods can extract key features from large amounts of future measured data, generating a concise and effective future implicit field representation.

[0045] In order to measure the degree to which the future implicit field representation retains the original data features, the information retention rate is introduced , the calculation formula is ,in represents the number of principal components extracted, represents the number of features of the original data, Indicates the The eigenvalues corresponding to the principal components are Indicates the The eigenvalues corresponding to the original features. The value range is arrive The closer It indicates that the future implicit field representation retains the characteristics of the original data to a higher degree.

[0046] After obtaining these first future experimental data, they are integrated into the simulation process. When generating the first predicted cooling strategy information, the optimization layer will fully consider the trends and changes reflected by these future experimental data. If the future temperature field measured data shows that the ambient temperature will rise in the future, the optimization layer may increase the flow rate of the cooling medium in advance to ensure that the motor can still operate normally in a high temperature environment. At the same time, based on the first future experimental data, the first future predicted physical field information, the first predicted adjustment instructions, the first predicted verification feedback information, the first predicted cooling strategy information and the first real cooling strategy information, the parameters of the multi-physical field coupling layer and the optimization layer are adjusted so that the model can better adapt to future changes and improve the accuracy and reliability of the simulation. Example 3

[0047] After completing the first simulation phase, the present invention further includes a second simulation phase. In the second simulation phase, a plurality of second experimental data during the operation of the motor, second actual cooling strategy information corresponding to the second experimental data, a second adjustment instruction for the second actual cooling strategy information, and second verification feedback information are first obtained.

[0048] The second experimental data includes the second operating parameters of the motor and the second measured physical field information for the cooling device. Similar to the first simulation stage, the second operating parameters of the motor cover information such as the speed and load of the motor when it is running in this stage. These parameters will change with the actual use of the motor. For example, in different working scenarios, the motor may need to run at different speeds and loads. The second measured physical field information for the cooling device also includes relevant data on the temperature field, flow field, and stress field. By real-time monitoring of these data, the working status of the cooling device in the second stage can be understood.

[0049] A second input sample, consisting of the second experimental data, is fed into the multiphysics coupling layer. The multiphysics coupling layer analyzes and processes the second input sample, taking into account the interactions between the temperature, flow, and stress fields, and outputs a second implicit field representation. This process is identical to the multiphysics coupling layer in the first simulation phase, but due to the different input data, the output of this second implicit field representation reflects the specific state of the current motor and cooling system.

[0050] The second intermediate sample, including the second implicit field representation, is input into the optimization layer. Based on the second implicit field representation, the optimization layer combines the motor's operating requirements with the cooling device's performance limitations to output second predicted cooling strategy information. For example, if the second implicit field representation indicates an increasing temperature trend at a particular motor location, the optimization layer might adjust the cooling strategy by increasing the coolant flow rate at that location or rerouting the coolant flow path.

[0051] The second intermediate sample is input into the simulation verification model. Based on the input second intermediate sample, the simulation verification model simulates the operation of the motor cooling device under the predicted cooling strategy and outputs a second prediction adjustment instruction and second prediction verification feedback information. The second prediction adjustment instruction indicates whether and when manual corrections to the cooling strategy are required during the simulation. The second prediction verification feedback information includes cooling performance evaluation results, such as temperature distribution uniformity and flow field stability.

[0052] The parameters of the simulation verification model are adjusted based on the second adjustment instruction, the second prediction adjustment instruction, the second verification feedback information, and the second prediction verification feedback information. By continuously adjusting the parameters of the simulation verification model, the model can more accurately simulate the actual operating conditions of the motor cooling device. For example, if the second verification feedback information indicates a significant deviation between the simulation results and the actual conditions, the parameters of the simulation verification model need to be adjusted to optimize the model's algorithm and structure to improve the simulation accuracy.

[0053] Based on the second prediction adjustment instructions, the second prediction verification feedback information, the second predicted cooling strategy information, and the second actual cooling strategy information, the parameters of the multiphysics coupling layer and the optimization layer are adjusted. This allows the multiphysics coupling layer and the optimization layer to better adapt to the operating conditions of the motor and cooling device in the second phase, improves the accuracy of the prediction, and provides more reliable support for subsequent cooling strategy optimization. Example 4

[0054] Adjustment instructions and predicted adjustment instructions play a crucial role throughout the simulation process. Adjustment instructions include adjustment decision information, which indicates whether manual strategy correction is required and the specific timeframe for such correction. Predictive adjustment instructions include predicted adjustment decision information, which indicates whether a correction should be triggered during the simulation and the predicted triggering time.

[0055] In real-world applications, significant changes in the motor's operating conditions, such as a sudden increase in load, can cause the motor to generate more heat, and the existing cooling strategy may not be able to meet these requirements. In these cases, the adjustment decision information may indicate the need for manual correction of the cooling strategy, specifying the specific time point for this correction, such as immediately increasing the coolant flow rate. After manually correcting the cooling strategy, the corresponding first-stage real cooling strategy information is generated, which serves as the basis for subsequent simulations and model adjustments.

[0056] The simulation verification model generates predictive adjustment decision information based on simulation results. The model predicts the future operation of the motor cooling system. If it predicts that the motor temperature will exceed a safety threshold at some point in the future, or if the flow field shows signs of instability, it will output predictive adjustment decision information. For example, if the simulation verification model predicts that the motor winding temperature will reach a warning value within the next five minutes, the predictive adjustment decision information will indicate triggering a cooling strategy correction before the next five minutes, such as increasing the cooling fan speed in advance.

[0057] By comparing the adjustment decision information and the predicted adjustment decision information, the accuracy of the simulation verification model can be evaluated. If the two indicators are basically consistent, it means that the simulation verification model can well predict the operation of the motor cooling device; if there is a significant difference, the simulation verification model needs to be adjusted and optimized. At the same time, these adjustment instructions and predicted adjustment instructions will also affect the parameter adjustments of the multi-physics coupling layer and the optimization layer. Based on the adjustment decision information and the predicted adjustment decision information, combined with the verification feedback information and the predicted verification feedback information, the parameters of the multi-physics coupling layer and the optimization layer are adjusted, so that the model can more accurately predict the cooling strategy and improve the performance and reliability of the motor cooling device.

[0058] The adjustment instruction also includes an adjustment flag, and the predicted adjustment instruction includes a predicted adjustment flag. The adjustment flag is used to characterize whether the first real cooling strategy information has been adjusted through external intervention, and the predicted adjustment flag is used to characterize whether the predicted cooling strategy information requires external intervention adjustment. When an abnormal situation occurs during the operation of the motor, such as excessive temperature or unstable flow field, the operator may manually adjust the cooling strategy, and the adjustment flag will record this external intervention behavior. In the subsequent simulation process, by analyzing the adjustment flag, it can be understood in which cases external intervention is required, and the impact of external intervention on the cooling effect. The predicted adjustment flag helps determine whether the predicted cooling strategy information requires further manual intervention. If the predicted adjustment flag shows that the predicted cooling strategy information requires external intervention, you can prepare in advance and adjust the cooling strategy at the appropriate time to ensure the normal operation of the motor cooling device. Example 5

[0059] In the process of inputting the first experimental data into the multi-physics field coupling layer, some data processing operations need to be performed. Based on the first verification feedback information, the working conditions of multiple first experimental data are classified. The first verification feedback information contains rich information about the operating status of the motor cooling device, such as temperature distribution uniformity information, flow field stability information, etc. By analyzing this information, the operating conditions of the motor can be divided into different categories. For example, if the temperature distribution of the motor is uniform, the flow field is stable, and the cooling efficiency is high within a certain period of time, then this working condition can be classified as a normal working condition; if the temperature of the motor is locally too high, there is a certain degree of disorder in the flow field, and the cooling efficiency is reduced, it can be classified as an abnormal working condition.

[0060] Based on the classification results, multiple first experimental data are sampled in equal proportion by category to obtain multiple first input sample data. The purpose of this is to ensure that each operating condition category is reasonably representative in the input samples, and to prevent a certain operating condition category from dominating the data set, thereby affecting the training and prediction effects of the model. For example, if the amount of data for normal operating conditions is much larger than the amount of data for abnormal operating conditions, when training the model, the model may be more inclined to learn the data features under normal operating conditions, while having weaker prediction capabilities for abnormal operating conditions. By sampling in equal proportion by category, the model can better learn the features under different operating conditions and improve the generalization ability of the model.

[0061] During the sampling process, it is necessary to ensure that the difference in the number of samples corresponding to each category in the multiple first input sample data does not exceed the preset threshold. The setting of the preset threshold needs to be adjusted according to the actual situation. Generally speaking, the preset threshold should not be too large, otherwise the balance of data in each category cannot be guaranteed; nor should it be too small, otherwise the training effect of the model may be affected due to the small amount of data. The first input sample including the first input sample data is input into the multi-physics field coupling layer to obtain the first implicit field representation. After the above-mentioned data processing steps, the first input sample input to the multi-physics field coupling layer can more comprehensively reflect the different operating conditions of the motor cooling device, so that the first implicit field representation output by the multi-physics field coupling layer is more accurate and reliable. This provides a good foundation for the subsequent optimization layer to generate accurate first predicted cooling strategy information, and also helps to improve the accuracy of the simulation verification model and the performance of the entire simulation system. Example 6

[0062] Before performing the first simulation phase, it is necessary to perform offline pre-calculation on the multi-physics field coupling layer and the optimization layer so that the simulation model can generate first predicted cooling strategy information based on the input first input sample.

[0063] Offline pre-calculation first requires obtaining the third experimental data and the third real cooling strategy information corresponding to the third experimental data. The third experimental data includes the historical operating parameters of the test motor and the historical physical field information of the cooling device. The historical operating parameters of the test motor record the speed, load, and other information of the motor under different operating times and working conditions in the past. This data reflects the various operating states of the motor. The historical physical field information of the cooling device includes the past measurement data of the temperature field, flow field, and stress field. By analyzing this historical data, the performance of the cooling device under different working conditions can be understood.

[0064] The third input sample, consisting of the third experimental data, is fed into the multiphysics coupling layer. The multiphysics coupling layer analyzes and processes the input data, taking into account the interactions between the temperature, flow, and stress fields, and outputs a third implicit field representation. This process is similar to how the multiphysics coupling layer processes the first input sample in the first simulation phase: both layers analyze the input data to obtain a comprehensive implicit field representation.

[0065] Next, the third intermediate sample including the third implicit field representation is input to the optimization layer. The optimization layer applies a specific algorithm and strategy based on the third implicit field representation, taking into account the operating requirements of the motor and the performance limitations of the cooling device, and outputs third predicted cooling strategy information.

[0066] If the third experimental data also includes third verification feedback information for the third real cooling strategy information, then when adjusting the parameters of the multi-physics coupling layer and the optimization layer, it is necessary to base the adjustment on the third verification feedback information, the third predicted cooling strategy information, and the third real cooling strategy information. The third verification feedback information includes the evaluation results of the cooling efficiency, such as the evaluation of the temperature distribution uniformity, the flow field stability, etc. For example, if the third verification feedback information shows that the temperature distribution of the cooling device is uneven under a certain working condition, and the third predicted cooling strategy information fails to effectively solve this problem, it is necessary to adjust the parameters of the multi-physics coupling layer and the optimization layer. By adjusting the parameters, the model can better learn the rules in the historical data, improve the model's prediction accuracy for the cooling strategy under different working conditions, and provide a more reliable model foundation for the subsequent first simulation stage. In the first simulation stage, the simulation model obtained by offline pre-calculation is used to perform the initial simulation, and the first experimental data and the corresponding first real cooling strategy information, as well as the first adjustment instructions and the first verification feedback information for the first real cooling strategy information, are obtained during the simulation process, thereby continuously optimizing the simulation model and improving the accuracy and reliability of the multi-physics simulation of the motor cooling device.

[0067] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0068] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A multi-physics field simulation method for a motor cooling device, characterized in that: The simulation method includes a multi-physics coupling layer, an optimization layer, and a simulation verification model. The multi-physics coupling layer and the optimization layer are connected to form an end-to-end numerical calculation model, so that the optimization layer directly generates cooling strategy information based on the output of the multi-physics coupling layer. The method includes a first simulation stage, The first simulation stage includes: Acquire a plurality of first experimental data during operation of the motor, first real cooling strategy information corresponding to the first experimental data, and a first adjustment instruction and first verification feedback information for the first real cooling strategy information, wherein the first experimental data include first operating parameters of the motor and first measured physical field information for a cooling device, the first measured physical field information including current measurement data and historical measurement data of a temperature field, a flow field, and a stress field; Inputting a first input sample including the first experimental data into the multiphysics coupling layer to obtain a first implicit field representation output by the multiphysics coupling layer; Inputting a first intermediate sample including the first implicit field representation into the optimization layer to obtain first predicted cooling strategy information output by the optimization layer; Inputting the first intermediate sample into a simulation verification model to obtain a first prediction adjustment instruction and first prediction verification feedback information output by the simulation verification model; Parameters of the simulation verification model are adjusted based on the first adjustment instruction, the first prediction adjustment instruction, the first verification feedback information, and the first prediction verification feedback information.

2. The multi-physics field simulation method for a motor cooling device according to claim 1, characterized in that: Adjusting the parameters of the multi-physics coupling layer and the optimization layer based on the first prediction adjustment instruction, the first prediction verification feedback information, the first prediction cooling strategy information, and the first actual cooling strategy information; The first adjustment instruction and the first prediction adjustment instruction are respectively used to indicate whether manual correction strategy and correction timing are required during the simulation process, and the first verification feedback information and the first prediction verification feedback information respectively include manually marked and cooling efficiency evaluation results generated by the simulation model; The first verification feedback information includes at least one of the following: Temperature distribution uniformity information, flow field stability information, cooling efficiency, structural stress peak, number of thermal cycles, and material deformation threshold.

3. The multi-physics field simulation method for a motor cooling device according to claim 1, characterized in that: The first simulation stage further includes: Acquire first future experimental data for the operating environment of the cooling device, The output of the optimization layer also includes first future predicted physical field information for the operating environment of the cooling device. Adjusting the parameters of the multi-physics coupling layer and the optimization layer based on the first prediction adjustment instruction, the first prediction verification feedback information, the first prediction cooling strategy information, and the first actual cooling strategy information includes: Based on the first future experimental data, the first future predicted physical field information, the first predicted adjustment instruction, the first predicted verification feedback information, the first predicted cooling strategy information and the first real cooling strategy information, the parameters of the multi-physical field coupling layer and the optimization layer are adjusted.

4. The multi-physics field simulation method for a motor cooling device according to claim 3, characterized in that: The first future experimental data includes future temperature field measured data, future flow field measured data and / or future implicit field representation corresponding to the future measured data.

5. The multi-physics field simulation method for a motor cooling device according to any one of claims 1 to 4, characterized in that: Also included is a second simulation phase after the first simulation phase, The second simulation stage includes: Acquire a plurality of second experimental data during operation of the motor, second real cooling strategy information corresponding to the second experimental data, and a second adjustment instruction and second verification feedback information for the second real cooling strategy information, wherein the second experimental data includes a second operating parameter of the motor and second measured physical field information for the cooling device; Inputting a second input sample including the second experimental data into the multiphysics coupling layer to obtain a second implicit field representation output by the multiphysics coupling layer; inputting a second intermediate sample including the second implicit field representation into the optimization layer to obtain second predicted cooling strategy information output by the optimization layer; Inputting the second intermediate sample into the simulation verification model to obtain a second prediction adjustment instruction and second prediction verification feedback information output by the simulation verification model; adjusting parameters of the simulation verification model based on the second adjustment instruction, the second prediction adjustment instruction, the second verification feedback information, and the second prediction verification feedback information; and Based on the second prediction adjustment instruction, the second prediction verification feedback information, the second prediction cooling strategy information and the second actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

6. The multi-physics field simulation method for a motor cooling device according to any one of claims 1 to 4, characterized in that: The adjustment instruction includes adjustment decision information, which indicates whether manual correction of the strategy is required and the specific time node for correction. The prediction adjustment instruction includes prediction adjustment decision information, which indicates whether correction is triggered during the simulation process and the predicted triggering time.

7. The multi-physics field simulation method for a motor cooling device according to any one of claims 1 to 4, characterized in that: The adjustment instruction includes an adjustment flag, which is used to indicate whether the first real cooling strategy information has been adjusted through external intervention. The prediction adjustment instruction includes a prediction adjustment flag, which is used to indicate whether the prediction cooling strategy information requires external intervention adjustment.

8. The multi-physics field simulation method for a motor cooling device according to any one of claims 1 to 4, characterized in that: Inputting a first input sample including the first experimental data into the multiphysics field coupling layer to obtain a first implicit field representation output by the multiphysics field coupling layer includes: Based on the first verification feedback information, classify the plurality of first experimental data into working conditions; Based on the classification result, sampling is performed from the plurality of first experimental data in equal proportion according to categories to obtain a plurality of first input sample data; and A first input sample including the first input sample data is input into the multiphysics coupling layer to obtain the first implicit field representation.

9. The multi-physics field simulation method for a motor cooling device according to claim 8, characterized in that: The experimental data is divided into a plurality of working condition categories according to the verification feedback information, and the difference in the number of samples corresponding to each category in the plurality of first input sample data does not exceed a preset threshold.

10. The multi-physics field simulation method for a motor cooling device according to any one of claims 1 to 4, characterized in that: Also includes: Before the first simulation stage, pre-calculating the multi-physics coupling layer and the optimization layer offline so that the simulation model can generate the first predicted cooling strategy information based on the first input sample; The first simulation stage further includes: An initial simulation is performed using a simulation model obtained by offline pre-calculation, and during the simulation process, the first experimental data and corresponding first real cooling strategy information, as well as a first adjustment instruction and first verification feedback information for the first real cooling strategy information are obtained.

11. The multi-physics field simulation method for a motor cooling device according to claim 10, characterized in that: The offline pre-calculation includes: Acquire third experimental data and third real cooling strategy information corresponding to the third experimental data, wherein the third experimental data includes historical operating parameters of the test motor and historical physical field information for the cooling device; Inputting a third input sample including the third experimental data into the multiphysics coupling layer to obtain a third implicit field representation output by the multiphysics coupling layer; Inputting a third intermediate sample including the third implicit field representation into the optimization layer to obtain third predicted cooling strategy information output by the optimization layer; and Based on the third predicted cooling strategy information and the third actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

12. The multi-physics field simulation method for a motor cooling device according to claim 11, characterized in that: The third experimental data also includes third verification feedback information for the third true cooling strategy information. Wherein, adjusting the parameters of the multi-physics field coupling layer and the optimization layer based on the third predicted cooling strategy information and the third actual cooling strategy information includes: Based on the third verification feedback information, the third predicted cooling strategy information and the third actual cooling strategy information, the parameters of the multi-physics field coupling layer and the optimization layer are adjusted.

13. A multi-physics field simulation device for a motor cooling device, characterized in that: include: An experimental data acquisition unit is configured to acquire experimental data during the operation of the motor, corresponding actual cooling strategy information, adjustment instructions, and verification feedback information; a coupling layer processing unit configured to input experimental data into the multiphysics coupling layer and output an implicit field representation; an optimization layer processing unit configured to input the implicit field representation into the optimization layer to generate predicted cooling strategy information; a verification model processing unit configured to input the implicit field representation into the simulation verification model to output prediction adjustment instructions and prediction verification feedback information; A parameter adjustment unit is configured to adjust the simulation verification model parameters based on the adjustment instructions, the predicted adjustment instructions, the verification feedback information and the predicted verification feedback information, and to adjust the coupling layer and optimization layer parameters based on the predicted adjustment instructions, the predicted verification feedback information, the predicted cooling strategy information and the actual cooling strategy information.

Images