Temperature control method and device of motor system, electronic equipment and storage medium

Abstract

The application provides a temperature control method and device of a motor system, an electronic device and a storage medium, only the flow of the cooling liquid flowing through the analog control component corresponding to each control target needs to be determined, required parameters are less and easy to determine, and the predicted temperature of the analog control component corresponding to the control target is described through heat exchange calculation on the flow, and the flow through all the analog control components is calculated to simultaneously reflect the temperature corresponding to all the control targets. Then, the LOSS value corresponding to each predicted temperature is determined by looking up a loss function LOSS table constructed according to the relationship between the temperature and the loss function value. Finally, the control input is changed in the direction of continuously reducing the sum of the LOSS values of all the control targets through multiple iterations until the end condition is met, and the control input obtained through the last iteration and capable of reflecting all the control targets is output.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, electronic device and storage medium for temperature control of an electric motor system. Background Technology

[0002] Thermal management control of automotive motor systems is a complex process. For the numerous control objectives of the motor system, policy-based control is commonly used. Predictive control methods, represented by MPC (Model Predictive Control), are increasingly being applied to the automotive control field. However, for multiple control objectives and complex flow and heat transfer processes, some parameters of the state-space equation model are difficult to determine, making it challenging to use the state-space equation model to solve for the control inputs that reflect all control objectives. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a temperature control method, device, electronic device and storage medium for an electric motor system to solve the above problems.

[0004] To achieve the above objectives, the first aspect of this application provides a temperature control method for a motor system, characterized in that it includes:

[0005] Based on the received control input, the predicted temperature of each analog control component is obtained by performing heat exchange calculations on the flow rate of the coolant flowing through each analog control component; wherein, each control component in the motor system corresponds to one analog control component, and each analog control component corresponds to one control target;

[0006] The LOSS value corresponding to each predicted temperature is determined by looking up the LOSS table, which is constructed based on the relationship between temperature and the loss function value.

[0007] If the termination condition is not met, update the control input and iterate through the heat transfer calculation steps again.

[0008] When the termination condition is met, output the control input obtained from the last iteration;

[0009] The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than a preset minimum difference.

[0010] Optionally, the method for constructing the LOSS table includes:

[0011] Determine the temperature threshold for each of the control components;

[0012] Determine the boundary loss value corresponding to the temperature threshold;

[0013] Based on the preset extrapolation value, the extrapolated temperature value is determined with the temperature threshold as the boundary.

[0014] Based on the preset extrapolation value, the extrapolation temperature value is determined with the temperature threshold as the boundary.

[0015] Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein the extrapolated LOSS value is greater than the boundary LOSS value;

[0016] Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein the extrapolated LOSS value is less than the boundary LOSS value.

[0017] Optionally, determining the LOSS value for each predicted temperature by searching a loss function LOSS table constructed based on the relationship between temperature and loss function values ​​includes:

[0018] A line chart of LOSS values ​​is constructed based on the LOSS table, with temperature on the x-axis and LOSS values ​​on the y-axis.

[0019] Based on the predicted temperature, the LOSS value corresponding to the predicted temperature is determined in the LOSS line graph.

[0020] Optionally, updating the control input when the termination condition is not met includes:

[0021] When the termination condition is not met, the control input is optimized by using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all the control objectives.

[0022] Optionally, optimizing the control input using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all the control objectives includes:

[0023] The solution space of the particle swarm optimization algorithm is determined based on a pre-constructed solution set;

[0024] Initialize the position and velocity of each particle, and determine the individual historical best position and the group historical best position;

[0025] Based on the individual's historical best position and the group's historical best position, the particle state of each particle is adjusted in the direction of decreasing the fitness value; wherein, the fitness value is the sum of the LOSS values ​​corresponding to all the control objectives.

[0026] Optionally, adjusting the particle state of each particle based on the individual's historical best position and the group's historical best position in the direction of decreasing fitness includes:

[0027] Update the inertia coefficient, the position and velocity of each particle;

[0028] The updated fitness value for each particle is calculated based on the LOSS value corresponding to all the control objectives.

[0029] The individual historical best position of each particle is updated based on the updated fitness value;

[0030] The population historical best position of the particle swarm is updated based on the updated fitness value, and the control input corresponding to the updated population historical best position is used as the new control input.

[0031] Optionally, updating the population historical optimal position of the particle swarm based on the updated fitness value includes:

[0032] Determine the historical optimal fitness value of the population corresponding to the historical optimal position of the population;

[0033] If the fitness value obtained in this iteration is less than the group's historical best fitness value, the group's historical best position is replaced with the group's best position in this iteration, and the group's historical best fitness value is updated.

[0034] If the fitness value obtained in this iteration is less than the historical best fitness value of the population, the historical best position and the historical best fitness value of the population are retained.

[0035] A second aspect of this application provides a temperature control device for an electric motor system, comprising:

[0036] The temperature prediction module is configured to: based on the received control input, calculate the heat exchange of the coolant flow rate through each analog control component to obtain the predicted temperature of each analog control component; wherein, each control component in the motor system corresponds to one analog control component, and each analog control component corresponds to a control target;

[0037] The loss measurement module is configured to: determine the LOSS value corresponding to each predicted temperature by looking up the LOSS table of the loss function constructed based on the relationship between temperature and loss function value;

[0038] The rolling optimization module is configured to update the control input and iterate the heat transfer calculation steps again when the termination condition is not met.

[0039] When the termination condition is met, output the control input obtained from the last iteration;

[0040] The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than a preset minimum difference.

[0041] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method provided in the first aspect of this application.

[0042] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method provided in the first aspect of this application.

[0043] The fifth aspect of this application provides a temperature control device for an electric motor system as described in the second aspect of this application, an electronic device as described in the third aspect of this application, or a non-transitory computer-readable storage medium as described in the fourth aspect of this application.

[0044] As can be seen from the above, the temperature control method, device, electronic equipment, and storage medium for the motor system provided in this application only require determining the flow rate of the coolant flowing through the simulated control component corresponding to each control target. The required parameters are few and easy to determine. The predicted temperature of the simulated control component corresponding to the control target is described by performing heat transfer calculations on the flow rate. Here, the simulated control component corresponds to the control component in the motor system. In the motor system, the coolant needs to flow through all the control components. Therefore, the process of calculating the predicted temperature simulates the flow of coolant through all the control components. Based on the control input, the flow rate of coolant flowing through all the simulated control components can be calculated. Performing heat transfer calculations on the flow rate through all the simulated control components simultaneously reflects the temperature corresponding to all control targets. Then, the LOSS value corresponding to each predicted temperature is determined by looking up the LOSS table constructed based on the relationship between temperature and the loss function value. Finally, the control input is continuously updated through multiple iterations until the termination condition is met, and the control input obtained from the last iteration, which reflects all control targets, is output. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of a temperature control method for a motor system according to an embodiment of this application;

[0047] Figure 2 This is a schematic diagram of the motor system framework according to an embodiment of this application;

[0048] Figure 3 This is a LOSS line graph of the single-ended boundary control target in an embodiment of this application;

[0049] Figure 4 This is a line graph showing the loss of the boundary control targets at both ends in an embodiment of this application.

[0050] Figure 5 A flowchart illustrating the construction of the loss function LOSS table for embodiments of this application;

[0051] Figure 6 This is a flowchart illustrating the process of obtaining the optimal control output in an embodiment of this application.

[0052] Figure 7 This is a logical schematic diagram of the particle swarm optimization algorithm in an embodiment of this application;

[0053] Figure 8 A flowchart for finding the optimal solution for embodiments of this application;

[0054] Figure 9 This is a flowchart illustrating the determination of the predicted temperature in an embodiment of this application;

[0055] Figure 10 This is a LOSS line graph of the main circuit coolant temperature in an embodiment of this application.

[0056] Figure 11 This is a schematic diagram of the structure of the temperature control device for the motor system in an embodiment of this application;

[0057] Figure 12 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0059] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] In some embodiments, such as Figure 1 As shown, the temperature control method for the motor system includes:

[0061] Step 100: Based on the received control input, the predicted temperature of each analog control component is obtained by performing heat exchange calculations on the flow rate of the coolant flowing through each analog control component.

[0062] In the motor system, each control component corresponds to a simulation control component, and each simulation control component corresponds to a control target.

[0063] In this step, for example, a flow-based physical model can be used to calculate the predicted temperature of each analog control unit after the execution of the control input. The physical model is configured to: receive and execute the control input, first calculate the flow rate through each analog control unit in the physical model, and then obtain the predicted temperature for each analog control unit by performing heat transfer calculations on the flow rate of coolant through each analog control unit.

[0064] Among them, in such Figure 2 In the illustrated motor system framework, the arrows indicate the direction of coolant flow. The electric water pump powers the coolant flow, and the electronic three-way valve controls the flow rate of coolant participating in heat exchange within the motor system. The components outside the arrows represent other parts of the entire thermal management system, providing a certain amount of cooling to the motor system. This cooling amount represents the heat removed from the motor system. After passing through the electric water pump, the coolant splits into two paths: one passes through the dual-motor controller, generator, and front motor components; the other passes through the autopilot controller, DC-DC converter, OBC, rear motor controller and rear motor, and rear oil cooler. The two coolant paths mix and then enter other circuits of the vehicle's thermal management system via the electronic three-way valve.

[0065] The motor system proposes several control objectives, including but not limited to the following:

[0066] 1. The coolant temperature in the main circuit is lower than the temperature threshold A;

[0067] 2. The temperature of the insulated gate bipolar transistor (IGBT) in the front motor controller is lower than the temperature threshold B1;

[0068] 3. The temperature of the NTC temperature sensor of the front motor controller is lower than the temperature threshold B2;

[0069] 4. The temperature of the front motor is lower than the temperature threshold B3;

[0070] 5. The temperature of the IGBT in the rear motor controller is less than the temperature threshold C1;

[0071] 6. The temperature of the coolant at the outlet of the rear motor controller is less than the temperature threshold C2;

[0072] 7. The temperature of the rear motor is less than the temperature threshold C3;

[0073] 8. The temperature of the generator controller is lower than the temperature threshold D1;

[0074] 9. The generator temperature is less than the temperature threshold D2;

[0075] 10. The temperature of the on-board charger (OBC) is lower than the temperature threshold E;

[0076] 11. The temperature of the DC-DC converter is less than the temperature threshold F;

[0077] 12. The temperature of the fully automated driving controller (FSD) is less than the temperature threshold H;

[0078] 13. Minimize the cooling requirements proposed by other parts of the thermal management system.

[0079] The specific temperature threshold values ​​for different control objectives are set according to actual usage. Given the above control objectives and complex flow heat transfer processes, it is difficult to establish a linear state-space equation model that reflects all the physical quantities corresponding to all objectives. Therefore, a flow-based physical model can be chosen. The physical model is a simplified Widmanstätke equation established for flow rate, describing the coolant flow process. Then, for each simulated control component, a simplified heat transfer calculation is performed to obtain the predicted temperature describing the temperature of that simulated control component. Furthermore, this physical model has a simple structure and is easy to model and solve. The method provided in this application embodiment is based on a model predictive control strategy. Model predictive control includes three elements: a predictive model, rolling optimization, and feedback control. A physical model is constructed to calculate the elements of the predictive model corresponding to the predicted temperature in the model predictive control.

[0080] Step 200: Determine the LOSS value corresponding to each predicted temperature by looking up the LOSS table constructed based on the relationship between temperature and the loss function value.

[0081] The LOSS table is configured to determine the LOSS value for each predicted temperature.

[0082] In this step, control of all control objectives is achieved by establishing a corresponding LOSS table for each control objective. Taking the temperature threshold A of the coolant in the main circuit as an example, where the coolant can be water, the LOSS table is shown in Table 1:

[0083] Table 1 Main Circuit Loss Table

[0084]

[0085] The temperature threshold A for the main circuit coolant is 65℃ as shown in the table. This temperature threshold represents the highest temperature at which the main circuit operates normally. If this temperature threshold is exceeded, significant damage will occur during operation. However, this temperature threshold is not the optimal operating temperature for the main circuit. The optimal temperature is generally the temperature at which the LOSS value first reaches 0 or is close to 0, such as 58℃ in Table 1. The LOSS value 180 corresponding to the temperature threshold is preset and determined through analysis of material properties, component characteristics, and testing methods. Therefore, the corresponding control objective is to keep the main circuit coolant temperature below 65℃. Table 1 shows the LOSS table for a single-end boundary control objective. Figure 3 As shown, a single-end boundary control target indicates that only the upper or lower limit temperature of the target component needs to be controlled, such as... Figure 4 As shown, the two boundary control targets need to simultaneously control the upper and lower temperature limits of the target components.

[0086] Step 300: If the termination condition is not met, update the control input and iterate through the heat transfer calculation steps again;

[0087] Step 400: When the termination condition is met, output the control input obtained from the last iteration.

[0088] The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than the preset minimum difference.

[0089] In this step, for example, when the maximum number of iterations is not reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is greater than or equal to a preset minimum difference, the control input can be changed through an optimization algorithm to reduce the sum of the LOSS values ​​corresponding to all control objectives. After one optimization, a new control input is determined, and steps 100 and 200 are executed again based on this new control input until the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than the preset minimum difference. The control input obtained in the last iteration is output as the control input of the motor system. This control input simultaneously balances all control objectives, ensuring that all control components of the motor system operate at a favorable temperature. Step 300 corresponds to the elements of rolling optimization and feedback control in model predictive control.

[0090] The control inputs of the motor system include:

[0091] 1. Duty cycle (pump speed) of electronic water pump;

[0092] 2. Valve opening degree of the electronic three-way valve;

[0093] 3. Temperature at the inlet of the electronic water pump.

[0094] The non-control inputs of the motor system are:

[0095] 1. Ambient temperature;

[0096] 2. Power consumption of each component;

[0097] 3. Effective power of each component;

[0098] 4. Vehicle speed and wind speed.

[0099] In some embodiments, such as Figure 5 As shown, based on the temperature threshold corresponding to the control objective, a loss function LOSS table is constructed for each control objective, including:

[0100] Step 210: Determine the temperature threshold for each control component.

[0101] In this step, it is necessary to determine the temperature threshold for each control component in the motor system during normal operation, in order to optimize the control input so that each control component operates below the temperature threshold.

[0102] Step 220: Determine the boundary LOSS value corresponding to the temperature threshold.

[0103] In this step, for example as shown in Table 1, the position of the temperature threshold is first determined in the table, generally selected to be recorded in the second or third row of the LOSS table, such as 65℃ in Table 1. Recording it in the second or third row of the LOSS table reserves certain space for extrapolation and internal extrapolation. Then, the boundary LOSS value 180 corresponding to the temperature threshold is determined by analyzing material properties, component properties, experiments, etc., and recorded below 65℃.

[0104] Step 230: Based on the preset extrapolation value, determine the extrapolated temperature value with the temperature threshold as the boundary.

[0105] In this step, for example, as shown in Table 1, the control target for the coolant temperature of the motor main circuit is below 65°C. This temperature threshold is used as the boundary, and a certain extrapolation value is extrapolated based on this boundary, such as 10%, which is rounded to 72°C.

[0106] Step 240: Based on the preset extrapolation value, determine the extrapolated temperature value using the temperature threshold as the boundary.

[0107] In this step, for the single-end boundary control target LOSS table as shown in Table 1, optionally, with 65°C as the boundary, two values ​​can be extrapolated, such as 95% and 90%, which are rounded to 61°C and 58°C.

[0108] Step 250: Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein the extrapolated LOSS value is greater than the boundary LOSS value.

[0109] In this step, for example, as shown in Table 1, the LOSS value after the main circuit coolant temperature exceeds the limit can be determined by the linear difference algorithm based on the line connecting the two points. The very large LOSS value of 500 is given in order to increase the slope of the line connecting the two points, so that when the temperature exceeds the temperature threshold, a larger LOSS value is determined, thereby increasing the priority of reducing the main circuit coolant temperature and ensuring the safety of the main circuit.

[0110] Step 260: Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein, the extrapolated LOSS value is less than the boundary LOSS value.

[0111] In this step, for example, as shown in Table 1, the LOSS values ​​180 and 2 are given during the extrapolation as a relaxation region where the main circuit coolant temperature is close to the temperature threshold. The purpose of giving the LOSS values ​​is to gradually reduce the slope of the line connecting the two points, thereby slowing down the rate of increase of the LOSS value when the temperature is close to the temperature threshold and avoiding exceeding the threshold temperature.

[0112] Each temperature control target has a similar LOSS table established. Under suitable conditions, this ensures that the temperature of each temperature control target in the motor system is maintained within its optimal temperature range while minimizing energy consumption. The optimal temperature range is determined based on temperature thresholds; for example, in Table 1, the optimal temperature range is 10-58℃. When the overall vehicle temperature is high, the temperature of the control target may not fall within the optimal temperature range, in which case the temperature will be maintained between 58-65℃.

[0113] In some embodiments, updating the control input when the termination condition is not met includes:

[0114] When the termination condition is not met, the control input is optimized by using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all control objectives.

[0115] In this embodiment, an improved particle swarm optimization algorithm is used to perform multiple rolling optimizations on the control input until the optimal solution of the particle swarm optimization algorithm is found. At this point, the termination condition is met, and the control input obtained in the last iteration can be determined based on the optimal solution.

[0116] In some embodiments, such as Figure 6 As shown, the control input is optimized using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all control objectives, including:

[0117] Step 310: Determine the solution space of the particle swarm optimization algorithm based on the pre-constructed solution set.

[0118] In this step, the logic of the particle swarm optimization algorithm is as follows: Figure 7 As shown, the large box represents the solution space, including all solutions in the pre-constructed solution set. Each position in the solution space corresponds to a control input. Each circle represents a particle, and the arrow connecting the circle represents the particle's velocity, which is a vector. The circles in the large box represent the local solution space of a control target. Triangles of different sizes represent different fitness values. The position of the largest triangle in the circle represents the individual optimal solution, which is the control input that keeps the single control target in the optimal temperature range. The largest triangle in the entire box represents the group optimal solution, which is the control input output when the termination condition is met.

[0119] Step 320: Initialize the position and velocity of each particle, and determine the individual historical best position and the group historical best position.

[0120] In this step, for example, the position and velocity of particle i are randomly initialized within the solution space. The velocity represents the direction and distance the particle moves in the next iteration, and the position is a solution to the problem. The individual historical best position and the swarm historical best position of particle i are also set. During initialization, a well-chosen initialization range can shorten the convergence time of the optimization. This needs to be analyzed based on the specific problem. For example, if experience suggests that the optimal solution lies within a certain range, then the particles are initialized within that range. If this cannot be determined, the boundary values ​​of the particles are used as the initialization range. The optimal position found by an individual particle in the solution space is its individual historical best position, and the optimal position found by the swarm in the solution space is its swarm historical best position.

[0121] Step 330: Adjust the particle state of each particle in the direction of decreasing fitness based on the individual's historical best position and the group's historical best position.

[0122] The fitness value is the sum of the LOSS values ​​corresponding to all control targets.

[0123] In this step, the position of the particle in the solution space is changed by initializing its position and velocity. As the position changes, the range searched by each particle in the solution space becomes larger and larger, which in turn changes the individual historical best position and the group historical best position. When the fitness value corresponding to the newly searched position of the particle is worse than the individual historical best position or the group historical best position, the individual historical best position or the group historical best position is retained; when the fitness value corresponding to the newly searched position of the particle is better than the individual historical best position or the group historical best position, the individual historical best position or the group historical best position is replaced, so that the sum of the LOSS values ​​corresponding to the control input becomes smaller and smaller.

[0124] In some embodiments, such as Figure 8 As shown, the particle state is adjusted for each particle based on its individual historical best position and the group's historical best position, in the direction of decreasing fitness. This includes:

[0125] Step 321: Update the inertia coefficient, the position and velocity of each particle.

[0126] Step 322: Calculate the updated fitness value for each particle based on the LOSS values ​​corresponding to all control objectives.

[0127] Step 323: Update the individual historical best position of each particle based on the updated fitness value.

[0128] Step 324: Update the population historical best position of the particle swarm based on the updated fitness value, and use the control input corresponding to the updated population historical best position as the new control input.

[0129] Among them, updating the population's historical best position based on the updated fitness value includes:

[0130] Determine the population's historical best fitness value corresponding to the population's historical best position; if the fitness value obtained in this iteration is less than the population's historical best fitness value, replace the population's historical best position with the population's best position in this iteration and update the population's historical best fitness value; if the fitness value obtained in this iteration is less than the population's historical best fitness value, retain the population's historical best position and population's historical best fitness value.

[0131] For example, let's illustrate this using a particle i from a particle swarm. The objective function of MPC is given by the formula J = (RY). T Q(RY)+ΔU T As shown in RΔU, J is the optimization objective of the rolling optimization, consisting of two parts: the distance of the control output to the reference target and the rate of change of the control quantity; Y is the matrix composed of the control outputs, Q is the weight coefficient matrix of the control outputs, which is a diagonal matrix; is the matrix of the change in the control quantity, and R is the weight coefficient matrix of the change in the control quantity, also a diagonal matrix, composed of the reference target for each objective. The optimization objective process is min(J), which means minimizing the average value of the LOSS value of all control objectives. In the embodiments of this application, an improved particle swarm optimization algorithm is used for rolling optimization:

[0132] Randomly initialize the position x of particle i in the solution space. i (t) and particle velocity v i (t), where velocity represents the direction and distance the particle moves in the next iteration, position is a solution to the problem, and the individual best historical position pbest of particle i is set. i and the group's historical best position gbest i During initialization, a well-chosen initialization range for particles can shorten the convergence time of optimization. This needs to be analyzed based on the specific problem. For example, if experience suggests that the optimal solution must be within a certain range, then the particles should be initialized within that range. If this cannot be determined, then the boundary values ​​of the particles should be used as the initialization range.

[0133] If the initial position of particle i satisfies the optimization termination condition, directly output the swarm's historical best position, gbest. i As the optimal solution; if the termination condition is not met, the particle state is adjusted according to the following formula:

[0134] x i (t+1)=x i (t)+v i (t+1)

[0135]

[0136]

[0137] Where t represents the number of iterations, T max Here, c1 represents the global optimization coefficient, c2 represents the local optimization coefficient, r1 represents the global variation factor, r2 represents the local variation factor, and ω represents the inertia coefficient. i = 1, 2, ..., N; N is the particle swarm size, with a recommended range of 20-1000. For example, 20-40 is suitable when there are few control objectives, and 100-200 when there are many. Smaller swarm sizes are prone to getting trapped in local optima; larger swarm sizes can improve convergence and find the global optimum faster, but the computational cost per iteration also increases accordingly. When the swarm size increases to a certain level, further increases will no longer have a significant improvement effect. The recommended range for the number of iterations t is 50-100, with typical values ​​of 60, 70, and 100. The specific value needs to be adjusted according to the actual situation during optimization. Too few iterations lead to unstable solutions, while too many iterations increase the time consumption.

[0138] Compared to traditional particle swarm optimization algorithms, the improvement made in this embodiment involves updating the inertia coefficient ω. The inertia coefficient undergoes adaptive inertia updates with each iteration. The update formula for the inertia coefficient is a non-linear, exponentially decreasing function. It maintains a large value at the beginning of the iteration, thereby increasing the global search time and intensity in the early stages; while maintaining a small value for a longer period in the later stages, thus increasing the local search time and intensity and accelerating convergence. The particle velocity v... i The (t+1) update method can avoid particle aggregation and expand the search range. The introduced perturbation factors r3 and r4 are random numbers uniformly distributed between [0, 1], which randomly adjust the individual optimal solution (individual optimal position) pbest and the group optimal solution (group optimal position) gbest, so that the particles can search in a larger range and increase the probability of the particles finding the optimal solution.

[0139] The adjusted position of particle i is x i (t+1), at this point, the fitness value f(x) of particle i in iteration t+1 is calculated based on the LOSS table and the physical model. i ), where the fitness value is the value of the optimization objective function, used to evaluate the quality of the particle's position, determine whether to update the historical best position of the individual particle and the historical best position of the group, and ensure that the particle searches in the direction of the optimal solution.

[0140] Then, compare f(x)i ) and f(pbest i )(f(pbest i ) represents the individual's historical best position pbest i (fit value at x), if f(x) i )<f(pbest i ), indicating that f(x) i ) is better than f(pbest) i ), and set the individual historical best position pbest of particle i. i Updated to x i If f(x) i )>f(pbest i ), indicating that f(pbest) i ) is better than f(x) i ), and set the individual historical best position pbest of particle i. i reserve.

[0141] Then, compare f(x) i ) and f(gbest i )(f(gbest i ) represents the group's historical best position gbest i (fit value at x), if f(x) i )<f(gbest i ), indicating that f(x) i ) is better than f(gbest) i ), and the group's historical best position gbest i Updated to x i If f(x) i )>f(gbest i ), indicating that f(gbest) i ) is better than f(x) i ), and the group's historical best position gbest i Retain. Continuously perform rolling optimization loops until the maximum number of iterations is reached, and output the group's historical best position (gbest) from the last iteration. i If gbest is the swarm optimal solution, then the control input corresponding to gbest is the optimal solution.

[0142] In some embodiments, calculating the fitness value of each particle based on the LOSS table and the physical model includes: determining the control input of the physical model based on the control input corresponding to the particle's current position; inputting the control input into the physical model to obtain the predicted temperature; determining the LOSS value corresponding to the predicted temperature based on the predicted temperature and the LOSS table; and calculating the sum of the LOSS values ​​of different control targets as the fitness value.

[0143] Among them, such as Figure 9 As shown, determining the LOSS value corresponding to the predicted temperature includes:

[0144] Step 201: Construct a LOSS line chart based on the LOSS table, with temperature as the x-axis and LOSS value as the y-axis.

[0145] Step 202: Determine the LOSS value corresponding to the predicted temperature in the LOSS line graph based on the predicted temperature.

[0146] For example, Table 1 will be used for explanation. The current position x of the particle... i The corresponding control input is input into the physical model. Assuming the physical model executes this control input, the predicted coolant temperature in the main loop is 63℃. Figure 10 As shown, a LOSS line graph constructed based on the LOSS table, with temperature as the x-axis and LOSS value as the y-axis, calculates a LOSS value of 140 for 63℃ as the x-axis. The other control objectives use the same algorithm to calculate their respective predicted temperature LOSS values, then perform summation to obtain fitness values. The average of these sums is used as the value of the objective function min(J). An improved particle swarm optimization algorithm is used to continuously balance the temperatures of each control objective to minimize the objective function value; the control input at this point is the optimal solution.

[0147] like Figure 3 and Figure 4 As shown, the process of calculating the LOSS value reveals that for extrapolated or internalized temperatures exceeding the temperature threshold, given an extrapolated or internalized LOSS value with a large difference from the LOSS boundary, when calculating the LOSS value corresponding to the predicted temperature, the LOSS value increases very rapidly with temperature as long as the predicted temperature exceeds the temperature threshold. The improved particle swarm optimization algorithm, in order to reduce the sum of LOSS values, quickly searches for temperature control inputs that can reduce the temperature of the control target during the iteration process, achieving the effect of temperature control. Furthermore, when moving away from the temperature threshold from a direction below it, a gradually decreasing relaxation region is provided, causing the LOSS value to increase faster with temperature as it approaches the threshold. This allows the improved particle swarm optimization algorithm to avoid further increasing the control input near the temperature threshold, thereby maintaining the temperature of each control target within the optimal temperature range, preventing high-temperature operation of the vehicle's motor system, and protecting the vehicle's motor system.

[0148] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0149] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0150] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a temperature control device for a motor system.

[0151] refer to Figure 11 The temperature control device for the motor system includes:

[0152] The temperature prediction module 10 is configured to: based on the received control input, calculate the heat transfer of the coolant flow rate through each analog control component to obtain the predicted temperature of each analog control component; wherein, each control component in the motor system corresponds to one analog control component, and each analog control component corresponds to one control target;

[0153] The loss measurement module 20 is configured to determine the LOSS value corresponding to each predicted temperature by looking up the LOSS table of the loss function constructed based on the relationship between temperature and loss function value.

[0154] The rolling optimization module 30 is configured to update the control input and iterate the heat transfer calculation again when the termination condition is not met.

[0155] When the termination condition is met, output the control input obtained from the last iteration;

[0156] The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than the preset minimum difference.

[0157] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0158] The apparatus described above is used to implement the temperature control method of the corresponding motor system in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0159] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the temperature control method of the motor system described in any of the above embodiments.

[0160] Figure 12 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0161] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0162] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0163] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0164] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0165] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0166] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0167] The electronic devices described above are used to implement the temperature control method of the corresponding motor system in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0168] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the temperature control method of the motor system as described in any of the above embodiments.

[0169] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0170] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the temperature control method of the motor system as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0171] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0172] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0173] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0174] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A temperature control method for a motor system, characterized in that, include: Based on the received control input, the predicted temperature of each analog control component is obtained by performing heat exchange calculations on the flow rate of the coolant flowing through each analog control component; wherein, each control component in the motor system corresponds to one analog control component, and each analog control component corresponds to one control target; The LOSS value corresponding to each predicted temperature is determined by looking up the LOSS table, which is constructed based on the relationship between temperature and the loss function value. The LOSS table includes the boundary LOSS value corresponding to the temperature threshold of the control component, the extrapolated temperature value and the corresponding extrapolated LOSS value determined based on the preset extrapolated value with the temperature threshold as the boundary, and the extrapolated temperature value and the corresponding extrapolated LOSS value determined based on the preset extrapolated value with the temperature threshold as the boundary. If the termination condition is not met, update the control input and iterate through the heat transfer calculation steps again. When the termination condition is met, output the control input obtained from the last iteration; The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than a preset minimum difference.

2. The method according to claim 1, characterized in that, The method for constructing the LOSS table includes: Determine the temperature threshold for each of the control components; Determine the boundary loss value corresponding to the temperature threshold; Based on the preset extrapolation value, the extrapolated temperature value is determined with the temperature threshold as the boundary. Based on the preset extrapolation value, the extrapolation temperature value is determined with the temperature threshold as the boundary. Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein the extrapolated LOSS value is greater than the boundary LOSS value; Determine the extrapolated LOSS value corresponding to the extrapolated temperature value in the LOSS table; wherein the extrapolated LOSS value is less than the boundary LOSS value.

3. The method according to claim 1, characterized in that, The step of determining the LOSS value for each predicted temperature by searching a loss function LOSS table constructed based on the relationship between temperature and loss function values ​​includes: A line chart of LOSS values ​​is constructed based on the LOSS table, with temperature on the x-axis and LOSS values ​​on the y-axis. Based on the predicted temperature, the LOSS value corresponding to the predicted temperature is determined in the LOSS line graph.

4. The method according to claim 1, characterized in that, When the termination condition is not met, updating the control input includes: When the termination condition is not met, the control input is optimized by using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all the control objectives.

5. The method according to claim 4, characterized in that, The optimization of the control input using the particle swarm optimization algorithm in the direction of reducing the sum of the LOSS values ​​corresponding to all the control objectives includes: The solution space of the particle swarm optimization algorithm is determined based on a pre-constructed solution set; Initialize the position and velocity of each particle, and determine the individual's historical best position and the group's historical best position; Based on the individual's historical best position and the group's historical best position, the particle state of each particle is adjusted in the direction of decreasing the fitness value; wherein, the fitness value is the sum of the LOSS values ​​corresponding to all the control objectives.

6. The method according to claim 5, characterized in that, The process of adjusting the particle state of each particle based on the individual's historical best position and the group's historical best position in the direction of decreasing fitness includes: Update the inertia coefficient, the position and velocity of each particle; The updated fitness value for each particle is calculated based on the LOSS value corresponding to all the control objectives. The individual historical best position of each particle is updated based on the updated fitness value; The population historical best position of the particle swarm is updated based on the updated fitness value, and the control input corresponding to the updated population historical best position is used as the new control input.

7. The method according to claim 6, characterized in that, The process of updating the population's historical best position based on the updated fitness value includes: Determine the historical optimal fitness value of the population corresponding to the historical optimal position of the population; If the fitness value obtained in this iteration is less than the group's historical best fitness value, the group's historical best position is replaced with the group's best position in this iteration, and the group's historical best fitness value is updated. If the fitness value obtained in this iteration is less than the historical best fitness value of the population, the historical best position and the historical best fitness value of the population are retained.

8. A temperature control device for a motor system, characterized in that, include: The temperature prediction module is configured to: based on the received control input, calculate the heat exchange of the coolant flow rate through each analog control component to obtain the predicted temperature of each analog control component; wherein, each control component in the motor system corresponds to one analog control component, and each analog control component corresponds to a control target; The loss measurement module is configured to: determine the LOSS value corresponding to each predicted temperature by looking up the LOSS table of the loss function constructed based on the relationship between temperature and loss function value; The LOSS table includes the boundary LOSS value corresponding to the temperature threshold of the control component, the extrapolated temperature value and the corresponding extrapolated LOSS value determined based on the preset extrapolated value with the temperature threshold as the boundary, and the extrapolated temperature value and the corresponding extrapolated LOSS value determined based on the preset extrapolated value with the temperature threshold as the boundary. The rolling optimization module is configured to update the control input and iterate the heat transfer calculation steps again when the termination condition is not met. When the termination condition is met, output the control input obtained from the last iteration; The termination condition is that the maximum number of iterations is reached or the difference between the sum of the LOSS values ​​of two adjacent iterations is less than a preset minimum difference.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as claimed in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.

11. A vehicle, characterized in that, This includes a temperature control device for a motor system as described in claim 8, an electronic device as described in claim 9, or a non-transitory computer-readable storage medium as described in claim 10.

Images