Actuator load reduction control method, apparatus, and storage medium

Abstract

The application discloses an actuator load reduction control method and device and a storage medium, and relates to the technical field of vehicle chassis thermal management. The method comprises the following steps: collecting multi-source data of each actuator of a vehicle chassis; acquiring a physical predicted temperature of the actuator by using a forward Euler method according to the multi-source data; acquiring a data predicted temperature of the actuator by using a pre-trained LSTM network model according to the multi-source data; performing weighted summation on the physical predicted temperature and the data predicted temperature to acquire a final predicted temperature of the actuator; and when the final predicted temperature of the actuator is greater than a corresponding safety temperature, performing load migration on the actuator and performing performance compensation with a dynamic balance as a target. The application can provide a temperature reference for the advance regulation and control of the actuator, realize the cooperative load reduction of the actuator through load migration, avoid the decline of the overall performance of the vehicle through the performance compensation mode, and effectively ensure the safety of vehicle driving.

Description

Technical Field

[0001] This application relates to the field of vehicle chassis thermal management technology, specifically to an actuator unloading control method, device, and storage medium. Background Technology

[0002] New energy vehicle chassis actuators (such as brake-by-wire, steering-by-wire, and active suspension) are prone to thermal overload under high-frequency response demands, leading to performance degradation or safety risks. Traditional actuator thermal overload protection mainly relies on passive temperature protection mechanisms (such as threshold protection mechanisms), which have the following drawbacks: It only triggers when the temperature reaches a set threshold, which results in a response lag. Furthermore, when overload protection is triggered, the overall performance of the vehicle may deteriorate, affecting the safety of vehicle operation. Summary of the Invention

[0003] In view of the deficiencies in the existing technology, the technical problem to be solved by this application is: how to achieve preventive control of the actuator to ensure the safety of vehicle operation.

[0004] To achieve the above objectives, in a first aspect, embodiments of this application provide an actuator unloading control method, the method comprising the following steps: Collect multi-source data from various actuators in the vehicle chassis; Based on multi-source data, the physical predicted temperature of the actuator is obtained using the forward Euler method. Based on multi-source data, a pre-trained LSTM network model is used to obtain actuator data to predict temperature; The physical predicted temperature and the data predicted temperature are weighted and summed to obtain the final predicted temperature of the actuator. When the final predicted temperature of the actuator is determined to be greater than the corresponding safe temperature, the actuator is subjected to load shifting, and performance compensation is performed with the goal of dynamic balance.

[0005] In conjunction with the first aspect, in one embodiment, the multi-source data includes chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature.

[0006] In conjunction with the first aspect, in one embodiment, the formula for calculating the physical prediction temperature of the actuator using the forward Euler method is: ; In the formula, for Physically predicted temperature at any given time for The temperature of the chassis actuator at any given time. The equivalent thermal conductivity coefficient, For actuator heat capacity, For ambient temperature, This represents the total thermal power of the actuator.

[0007] In conjunction with the first aspect, in one embodiment, the LSTM network model takes chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature as inputs, and outputs the actuator's data-predicted temperature.

[0008] In conjunction with the first aspect, in one embodiment, the formula for calculating the final predicted temperature of the actuator by weighted summing of the physical predicted temperature and the data predicted temperature is as follows: ; In the formula, for The final predicted temperature at that moment, To predict temperature based on data, These are the weighting coefficients for physically predicted temperatures.

[0009] In conjunction with the first aspect, in one embodiment, the weighting coefficient of the physically predicted temperature is determined based on the chassis actuator temperature and the ambient temperature, and the determination logic is as follows: ; In the formula, This is the absolute difference between the chassis actuator temperature and the ambient temperature.

[0010] In conjunction with the first aspect, in one embodiment, after obtaining the final predicted temperature of the actuator, incremental compensation is periodically performed on the final predicted temperature of the actuator to obtain an updated final predicted temperature. The formula for calculating the updated final predicted temperature is as follows: ; In the formula, The updated final predicted temperature, To ultimately predict the temperature, This is the proportional gain coefficient. The actual actuator temperature in the previous prediction cycle. This is the final predicted temperature output from the previous prediction cycle.

[0011] In conjunction with the first aspect, in one embodiment, the process of load migration for the actuator when the final predicted temperature of the actuator is determined to be greater than the corresponding safe temperature includes: The total load adjustment is calculated using the following formula: ; In the formula, This is the total load adjustment amount. For migration coefficient, To ultimately predict the temperature, The safe temperature for the actuator; The load adjustment allocated to the actuator is determined based on the total load adjustment, and the formula for calculating this load adjustment is as follows: ; In the formula, For the first The load adjustment amount assigned to each actuator For the first The thermal coupling coefficient of each actuator For the first The efficiency factor of each actuator for The highest actuator temperature among all actuators For the first The temperature of each actuator; The output of the corresponding actuator is controlled according to the load adjustment amount.

[0012] Secondly, embodiments of this application provide an actuator load reduction control device, which includes a processor, a memory, and an actuator load reduction control program stored in the memory and executable by the processor, wherein when the actuator load reduction control program is executed by the processor, it implements the method provided in the first aspect.

[0013] Thirdly, embodiments of this application provide a computer-readable storage medium storing an actuator deload control program, which, when executed, implements the method provided in the first aspect.

[0014] Compared with the prior art, the advantages of this application are: (1) The final predicted temperature is obtained by weighted fusion of physical predicted temperature and data predicted temperature, providing a temperature reference for the early control of actuators, effectively solving the lag defect of traditional actuator thermal overload protection, avoiding long-term overheating of a single actuator through load migration, realizing coordinated load reduction of actuators, and avoiding the decline of overall vehicle performance through performance compensation, effectively ensuring the safety of vehicle driving.

[0015] (2) Based on the absolute difference between the actuator temperature and the ambient temperature, the weights of the physical predicted temperature and the data predicted temperature are dynamically adjusted to improve the prediction accuracy of the final predicted temperature. While having greater applicability, the prediction deviation is continuously corrected by periodic incremental compensation to avoid the accumulation of prediction errors and improve the stability of the actuator's long-term operation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the method flow in the embodiments of this application; Figure 2 This is a schematic diagram of the hardware structure of the actuator unloading control device involved in the embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] In a first aspect, embodiments of this application provide an actuator unloading control method, referring to... Figure 1 The method includes the following steps: S1. Collect multi-source data from various actuators in the vehicle chassis (chassis actuator temperature, acquisition frequency 100Hz; actuator operating current, acquisition frequency 1kHz; coolant flow rate, acquisition frequency 50Hz; chassis ambient temperature, acquisition frequency 10Hz). S2. Based on multi-source data, the physical predicted temperature of the actuator is obtained using the forward Euler method; Based on multi-source data, a pre-trained LSTM (Long Short-Term Memory) network model is used to obtain actuator data to predict temperature; S3. Perform a weighted summation of the physical predicted temperature and the data predicted temperature to obtain the final predicted temperature of the actuator; S4. When the final predicted temperature of the actuator is determined to be greater than the corresponding safe temperature, the actuator is subjected to load shifting, and performance compensation is performed with the goal of dynamic balance.

[0022] This method obtains the final predicted temperature by weighted fusion of physical and data-based temperature predictions, providing a temperature reference for the early adjustment of actuators. This effectively solves the lag defect of traditional actuator thermal overload protection. Furthermore, by using load transfer and performance compensation, it avoids the degradation of the overall vehicle performance and effectively ensures the safety of vehicle operation.

[0023] In one embodiment, the formula for calculating the physical prediction temperature of the actuator using the forward Euler method based on multi-source data is as follows: ; In the formula, for Physically predicted temperature at any given time for The temperature of the chassis actuator at any given time. The equivalent thermal conductivity coefficient, For actuator heat capacity, For ambient temperature, The total thermal power of the actuator is calculated as follows: ; ; ; In the formula, For the Joule heating of the actuator, The mechanical losses and heat generated by the actuator (such as the heat generated by the friction of the motor rotation, are calibrated by the no-load current-speed characteristic test). For the actuator operating current, For example, the resistance of a motor coil, calibrated to 0.18Ω by a constant temperature DC impedance test at 25℃.

[0024] Therefore, the consideration for obtaining the physical predicted temperature is as follows: obtain the predicted temperature change based on the total thermal power and total heat dissipation power of the actuator, and then obtain the physical predicted temperature based on the predicted temperature change.

[0025] The formula for calculating the total heat dissipation power of the aforementioned actuator is: ; In the formula, Total heat dissipation power of the actuator The effective heat dissipation area of ​​the actuator (fixed setting: 0.025m²) 2 ), The convective heat transfer coefficient (calibrated by wind tunnel heat dissipation experiments) is calculated as follows: ; In the formula, This refers to the coolant flow rate.

[0026] By obtaining the temperature change based on the difference between the actuator's total thermal power and total heat dissipation power, and then using the forward Euler method to iterate the temperature, the desired result can be obtained. The predicted temperature change after a given time.

[0027] The formula for predicting temperature changes is: ; In the formula, To predict the amount of temperature change, The time step is 0.01s.

[0028] Therefore, the formula for calculating the physical predicted temperature of the actuator can be understood as follows: .

[0029] In one embodiment, the LSTM network model described above takes chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature as inputs, and outputs the actuator's predicted temperature based on data.

[0030] The pre-training process for LSTM network models includes: Multi-source data (chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature) were collected from the actuator under continuous steering frequency sweep condition (2 hours of continuous operation), emergency braking cycle condition (1.5 hours of continuous operation), and high and low temperature environment chamber condition (3 hours of continuous operation). After data cleaning, the data was used as the dataset. Extract multi-source data from the dataset for a continuous set number of steps (e.g., 30 steps, with a step length of 0.01s) and the chassis actuator temperature corresponding to the next step (as the future temperature) to generate time series samples and obtain a pre-training dataset; The pre-training dataset is divided into a training set and a validation set according to a set ratio (8:2); Train the LSTM network model using the training set; When the accuracy of the LSTM network model in predicting temperature no longer improves, the accuracy of the LSTM network model in predicting temperature is verified using a validation set. When the accuracy of the temperature prediction is greater than a preset threshold, the pre-trained LSTM network model is obtained.

[0031] Based on this, and using multi-source data, a pre-trained LSTM network model can be used to obtain actuator data to predict temperature.

[0032] In one embodiment, the formula for calculating the final predicted temperature of the actuator by weighted summing of the physical predicted temperature and the data predicted temperature is as follows: ; In the formula, for The final predicted temperature at that moment, To predict temperature based on data, These are the weighting coefficients for physically predicted temperatures.

[0033] The weighting coefficient for the physically predicted temperature is determined based on the chassis actuator temperature and the ambient temperature. The specific determination logic is as follows: ; In the formula, This is the absolute difference between the chassis actuator temperature and the ambient temperature.

[0034] Thus, in the low-temperature range (<30℃), the weighting coefficient of the physical prediction temperature is set to 0.2, with the data prediction temperature as the main factor, which can better capture the nonlinear fluctuations of temperature; in the transition temperature range (30℃-60℃), the weighting coefficient of the physical prediction temperature is linearly increased; in the high-temperature range (≥60℃), heat conduction dominates the temperature rise, with the physical prediction temperature as the main factor.

[0035] Therefore, it can be seen that dynamically adjusting the weights of physical predicted temperature and data predicted temperature based on the absolute difference between the actuator temperature and the ambient temperature can improve the prediction accuracy of the final predicted temperature and make it more applicable.

[0036] In one embodiment, after obtaining the final predicted temperature, the final predicted temperature of the actuator is incrementally compensated periodically (e.g., every 100ms) to obtain an updated final predicted temperature. The formula for calculating the updated final predicted temperature is as follows: ; In the formula, The updated final predicted temperature, To ultimately predict the temperature, This is the proportional gain coefficient (initial value is 0.5, and it is adjusted according to the error method between the final predicted temperature and the actual actuator temperature at the corresponding time to ensure that the calibrated predicted temperature matches the actual actuator temperature). The actual actuator temperature in the previous prediction cycle. This is the final predicted temperature output from the previous prediction cycle.

[0037] Regularly correcting the final predicted temperature can compensate for the inherent calculation deviations between the physical predicted temperature and the data-based predicted temperature calculation, prevent the continuous accumulation of errors, make the temperature prediction results more accurate, and thus improve the long-term stability of the actuator.

[0038] In one embodiment, after obtaining the final predicted temperature of the actuator, it is determined whether the final predicted temperature of the actuator is greater than the corresponding safe temperature (taking the steering motor actuator and the brake caliper actuator as examples, the safe temperature of the steering motor actuator is 150°C and the safe temperature of the brake caliper actuator is 200°C). If so, the load is transferred to the actuator (as a high-temperature actuator); otherwise, the load is not transferred.

[0039] The above-mentioned process for load migration of the actuator includes: The formula for calculating the total load adjustment (such as redundant tasks) is as follows: ; In the formula, This is the total load adjustment amount. The migration coefficient is taken as 0.1A / ℃. The safe temperature for the actuator; The load adjustment allocated to the actuator (i.e., the normal actuator not operating at high temperature) is determined based on the total load adjustment. The formula for calculating this load adjustment is as follows: ; In the formula, For the first The load adjustment amount assigned to each actuator For the first The thermal coupling coefficient of each actuator For the first The efficiency factor of each actuator for The highest actuator temperature among all actuators For the first The temperature of each actuator; The output of the corresponding actuator is controlled according to the load adjustment amount. This achieves load shifting of the actuator.

[0040] This quantitative allocation of load based on thermal coupling coefficient, working efficiency, and real-time temperature difference can distribute the redundant tasks of high-temperature actuators to normal actuators, achieve a balanced distribution of actuator thermal load, avoid long-term overheating of a single actuator, and realize coordinated load reduction of actuators.

[0041] Based on this, during load transfer, to ensure stable vehicle operation and maintain overall vehicle dynamic balance, the output of actuators that have not performed load adjustment is adjusted to achieve performance compensation. For example: When the steering torque is the target of load reduction, the performance compensation is achieved by increasing the ESC yaw moment in order to maintain the steering wheel control force unchanged. When the braking force is the load reduction target, the performance compensation is carried out by increasing the regenerative braking torque, with the total deceleration change rate being <0.05g as the target. When the suspension damping is the target for load reduction, the performance compensation is achieved by activating the active anti-roll bar torque, with the goal of reducing the body roll angle deviation to <0.5° (based on the current body roll angle).

[0042] Therefore, by utilizing the performance compensation mechanism, while adjusting the load transfer and load reduction of the actuators, the output capacity of the remaining actuators can be optimized, which can ensure the stability of the vehicle's dynamic performance such as steering and braking, and achieve a balance between thermal protection and overall vehicle handling performance.

[0043] Secondly, embodiments of this application provide an actuator unloading control device, which can be a device with data processing capabilities such as a personal computer (PC), a laptop computer, or a server.

[0044] Reference Figure 2 , Figure 2 This is a schematic diagram of the hardware structure of the actuator load reduction control device involved in the embodiments of this application. In the embodiments of this application, the actuator load reduction control device may include a processor, a memory, a communication interface, and a communication bus.

[0045] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0046] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting devices within the actuator unloading control equipment, as well as interfaces used for interconnecting the actuator unloading control equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0047] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0048] The processor can be a general-purpose processor, which can call the actuator deload control program stored in memory and execute the actuator deload control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the actuator deload control program is called can be referred to in various embodiments of the actuator deload control method of this application, and will not be repeated here.

[0049] Those skilled in the art will understand that Figure 2 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] Thirdly, embodiments of this application also provide a computer-readable storage medium.

[0051] The computer-readable storage medium of this application stores an actuator deload control program, wherein when the actuator deload control program is executed by a processor, it implements the steps of the actuator deload control method as described above.

[0052] The method implemented when the actuator load reduction control program is executed can be referred to in various embodiments of the actuator load reduction control method of this application, and will not be repeated here.

[0053] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0054] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0055] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0056] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0057] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0059] The above are merely specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the scope of the claims.

Claims

1. An actuator unloading control method, characterized in that, The method includes the following steps: Collect multi-source data from various actuators in the vehicle chassis; Based on multi-source data, the physical predicted temperature of the actuator is obtained using the forward Euler method. Based on multi-source data, a pre-trained LSTM network model is used to obtain actuator data to predict temperature; The physical predicted temperature and the data predicted temperature are weighted and summed to obtain the final predicted temperature of the actuator. When the final predicted temperature of the actuator is determined to be greater than the corresponding safe temperature, the actuator is subjected to load shifting, and performance compensation is performed with the goal of dynamic balance.

2. The actuator unloading control method as described in claim 1, characterized in that: The multi-source data includes chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature.

3. The actuator unloading control method as described in claim 2, characterized in that: The formula for calculating the physical prediction temperature of the actuator using the forward Euler method is as follows: ； In the formula, for Physically predicted temperature at any given time for The temperature of the chassis actuator at any given time. The equivalent thermal conductivity coefficient, For actuator heat capacity, For ambient temperature, This represents the total thermal power of the actuator.

4. The actuator unloading control method as described in claim 3, characterized in that: The LSTM network model takes chassis actuator temperature, actuator operating current, coolant flow rate, and chassis ambient temperature as inputs, and outputs the actuator data to predict the temperature.

5. The actuator unloading control method as described in claim 4, characterized in that: The formula for calculating the final predicted temperature of the actuator by weighted summing of the physical predicted temperature and the data predicted temperature is as follows: ； In the formula, for The final predicted temperature at that moment, To predict temperature based on data, These are the weighting coefficients for the physically predicted temperature.

6. The actuator unloading control method as described in claim 5, characterized in that: The weighting coefficient for the physically predicted temperature is determined based on the chassis actuator temperature and the ambient temperature, and the determination logic is as follows: ； In the formula, This is the absolute difference between the chassis actuator temperature and the ambient temperature.

7. The actuator unloading control method as described in claim 1, characterized in that: After obtaining the final predicted temperature of the actuator, incremental compensation is periodically performed on the final predicted temperature to obtain an updated final predicted temperature. The formula for calculating the updated final predicted temperature is as follows: ； In the formula, The updated final predicted temperature, To ultimately predict the temperature, This is the proportional gain coefficient. The actual actuator temperature in the previous prediction cycle. This is the final predicted temperature output from the previous prediction cycle.

8. The actuator unloading control method as described in claim 1, characterized in that: When the final predicted temperature of the actuator is determined to be greater than the corresponding safe temperature, the process of load migration for the actuator includes: The total load adjustment is calculated using the following formula: ； In the formula, This is the total load adjustment amount. For migration coefficient, To ultimately predict the temperature, The safe temperature for the actuator; The load adjustment allocated to the actuator is determined based on the total load adjustment, and the formula for calculating this load adjustment is as follows: ； In the formula, For the first The load adjustment amount assigned to each actuator For the first The thermal coupling coefficient of each actuator For the first The efficiency factor of each actuator for The highest actuator temperature among all actuators For the first The temperature of each actuator; The output of the corresponding actuator is controlled according to the load adjustment amount.

9. An actuator unloading control device, characterized in that, The actuator load reduction control device includes a processor, a memory, and an actuator load reduction control program stored in the memory and executable by the processor, wherein when the actuator load reduction control program is executed by the processor, it implements the steps of the actuator load reduction control method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an actuator deload control program, wherein when the actuator deload control program is executed, it implements the steps of the actuator deload control method as described in any one of claims 1 to 8.

Images