Method, device and equipment for establishing current torque corresponding relation of vehicle motor

Abstract

The invention discloses a method, device and equipment for establishing a current torque corresponding relation of a vehicle motor, and belongs to the technical field of automobiles. The method for establishing the current torque corresponding relation of the vehicle motor comprises the steps that under the condition that bus voltage, motor rotating speed and motor current are set values, target reward values corresponding to all current angles in a calibration period are determined by utilizing a reward function of a reinforcement learning model for all the current angles in a current angle array; determining the maximum reward value in all the target reward values; after the maximum reward value is substituted into the reward function, inverse operation is carried out on the reward function so as to establish the corresponding relation between the motor current and the motor torque, reinforcement learning and automatic calibration are combined, the subjective judgment influence of motor current and motor torque calibration is reduced, and subjective parameter judgment is materialized and digitalized; and the technical problems of establishment of a complex multi-dimensional motor model, poor environmental adaptability and the like are avoided.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a method, device, equipment and computer-readable storage medium for establishing a current-torque correspondence relationship of a vehicle motor. Background Art

[0002] In the vehicle motor control system, the motor's current-torque correspondence is calibrated to ensure the normal operation of the motor and improve system performance. In the related technology, there are many calibration methods. The first is that the engineering and technical personnel calibrate based on their personal experience; the second is to test the motor, measure the motor's output power, speed, current, voltage and other parameters, and use these parameters to determine the current-torque correspondence; the third is to establish a motor model to simulate current, voltage, power and other parameters, and use these parameters to determine the current-torque correspondence. However, the first and second methods rely on the subjective judgment of technicians, the test process consumes a lot of human resources, and the calibration precision is low; in the third method, establishing a motor model requires a lot of experiments to realize the calibration and verification of the system's own parameters. The process is complicated and the cost is high. In addition, the actual motor is affected by the environment when it is working, and the motor model cannot simulate the interaction with the environment. Summary of the invention

[0003] The present application provides a method, device, equipment and computer-readable storage medium for establishing a current-torque correspondence relationship of a vehicle motor, which can solve technical problems existing in the prior art, such as high human resource consumption, low calibration precision, and the inability of the motor model to simulate the interaction with the environment.

[0004] In a first aspect, an embodiment of the present application provides a method for establishing a current-torque correspondence relationship of a vehicle motor, the method for establishing a current-torque correspondence relationship of a vehicle motor comprising:

[0005] When the bus voltage, motor speed and motor current are set to set values, for each current angle in the current angle array, the reward function of the reinforcement learning model is used to determine the target reward value corresponding to each current angle in the calibration period;

[0006] Determine the maximum reward value among all target reward values;

[0007] After substituting the maximum reward value into the reward function, an inverse operation is performed on the reward function to establish a corresponding relationship between the motor current and the motor torque.

[0008] In combination with the first aspect, in one implementation, the formula corresponding to the reward function of the reinforcement learning model is:

[0009]

[0010] Among them, R is the reward value, α1, α2, α3 are weight coefficients, i is the motor current, imax is the maximum current of the motor, T is the motor torque, Temp is the motor temperature, and t0 is the optimal motor temperature.

[0011] In combination with the first aspect, in one implementation, for each current angle in the current angle array, using a reward function of a reinforcement learning model to determine a target reward value corresponding to each current angle within a calibration period includes:

[0012] The bench test collects the motor torque corresponding to the current angle;

[0013] The motor temperature is collected in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period;

[0014] Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

[0015] In combination with the first aspect, in one implementation, determining the target reward value corresponding to the current angle within a calibration period based on the motor current, the motor torque, and the motor temperature using a reward function of a reinforcement learning model includes:

[0016] Calculating a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature;

[0017] All first reward values ​​are combined to determine a target reward value corresponding to the current angle within a calibration period.

[0018] In combination with the first aspect, in one implementation, all first reward values ​​are integrated to determine the target reward value corresponding to the current angle within the calibration period, and the corresponding formula is:

[0019]

[0020] Among them, Rtotal(θ n ) is when the current angle is θ n The target reward value, R i is the first reward value calculated using the reward function of the reinforcement learning model in the i-th sampling period, and S is the number of sampling periods.

[0021] In a second aspect, an embodiment of the present application provides a device for establishing a current-torque correspondence relationship of a vehicle motor, the device for establishing a current-torque correspondence relationship of a vehicle motor comprising:

[0022] A first determination module is used to determine the target reward value corresponding to each current angle in the calibration period by using the reward function of the reinforcement learning model for each current angle in the current angle array when the bus voltage, the motor speed and the motor current are set values;

[0023] A second determination module is used to determine the maximum reward value among all target reward values;

[0024] An establishing module is used for substituting the maximum reward value into the reward function and then performing an inverse operation on the reward function to establish a corresponding relationship between the motor current and the motor torque.

[0025] In conjunction with the second aspect, in one implementation, the first determining module is specifically configured to:

[0026] The bench test collects the motor torque corresponding to the current angle;

[0027] The motor temperature is collected in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period;

[0028] Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

[0029] In conjunction with the second aspect, in one implementation, the first determining module is specifically configured to:

[0030] Calculating a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature;

[0031] All first reward values ​​are combined to determine a target reward value corresponding to the current angle within a calibration period.

[0032] In a third aspect, an embodiment of the present application provides a device for establishing a current-torque correspondence relationship of a vehicle motor, the device comprising a processor, a memory, and a program for establishing a current-torque correspondence relationship of a vehicle motor stored in the memory and executable by the processor, wherein when the program for establishing a current-torque correspondence relationship of a vehicle motor is executed by the processor, the steps of the method for establishing a current-torque correspondence relationship of a vehicle motor as described in any one of the first aspects are implemented.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program for establishing a current-torque correspondence relationship of a vehicle motor is stored. When the program for establishing a current-torque correspondence relationship of a vehicle motor is executed by a processor, the steps of the method for establishing a current-torque correspondence relationship of a vehicle motor as described in any one of the first aspects are implemented.

[0034] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0035] By taking the bus voltage, motor speed and motor current as set values, for each current angle in the current angle array, and then using the reward function of the reinforcement learning model, the target reward value corresponding to each current angle in the calibration period is determined; the maximum reward value among all target reward values ​​is determined; the maximum reward value is further substituted into the reward function, and the reward function is inverted to establish the corresponding relationship between the motor current and the motor torque. This combines reinforcement learning with automatic calibration, reduces the influence of subjective judgment on the calibration of motor current and motor torque, and concretizes and digitizes subjective parameter judgment. It avoids technical problems such as establishing a complex and multi-dimensional motor model and its poor adaptability to the environment. At the same time, the sensitivity of the motor to temperature during operation is quantified, and thermal management control and service life are optimized from the perspective of temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic flow chart of a first embodiment of a method for establishing a current-torque correspondence relationship of a vehicle motor of the present application;

[0037] Figure 2 A schematic diagram of a process for constructing a multidimensional array provided in one embodiment of the present application;

[0038] Figure 3 A schematic diagram of functional modules of an embodiment of a device for establishing a current-torque correspondence relationship of a vehicle motor of the present application;

[0039] Figure 4 A schematic diagram of the hardware structure of a device for establishing a current-torque correspondence relationship of a vehicle motor involved in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0042] Reinforcement learning: also known as incentive learning or enhanced learning, is one of the methodologies of machine learning, used to describe and solve the problem of maximizing rewards by learning strategies in the process of interaction between an agent and the environment;

[0043] Reward function: Sets a greedy goal in reinforcement learning to motivate reinforcement learning to find the quantitative expression of the best plan;

[0044] Reward term: a factor or component that has a positive influence in the reward function;

[0045] Penalty term: a factor or component that has a positive influence in the reward function;

[0046] Agent: A decision-making agent for reinforcement learning.

[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0048] In a first aspect, an embodiment of the present application provides a method for establishing a current-torque correspondence relationship of a vehicle motor.

[0049] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for establishing the current-torque correspondence relationship of the vehicle motor of the present application. Figure 1 As shown, the method for establishing the current-torque correspondence relationship of the vehicle motor includes:

[0050] Step 110: When the bus voltage, motor speed, and motor current are set values, for each current angle in the current angle array, a reward function of the reinforcement learning model is used to determine a target reward value corresponding to each current angle within a calibration period;

[0051] Among them, the bus voltage, motor speed, motor current and current angle each have their own corresponding arrays, and the arrays can be determined by their corresponding numerical ranges and their corresponding gradients. For example, taking the motor speed as an example, assuming that the numerical range corresponding to the motor speed is 0 to 3000r / min, assuming that the gradient corresponding to the motor speed is 1000r / min, then the array corresponding to the motor speed is [0,1000,2000,3000]. The array corresponding to the bus voltage is [v1,v2…vr], the array corresponding to the motor speed is [n1,n2…nq], the array corresponding to the motor current is [i1,i2…im], and the array corresponding to the current angle is [θ1,θ2…θn].

[0052] When implementing it specifically, Figure 2A schematic diagram of a process for constructing a multidimensional array is provided for an embodiment of the present application, wherein each multidimensional array is composed of values ​​corresponding to bus voltage, motor speed, motor current and current angle. Figure 2 The steps are as follows:

[0053] S1. Run the vehicle motor according to the set initial current, speed, bus voltage and current angle, and calculate the initial torque;

[0054] S2, increasing the current angle value according to the set current angle gradient;

[0055] S3, calculate the real-time torque; if the reward function value corresponding to the real-time torque calculated in step S3 is greater than the reward function value corresponding to the torque at the previous moment, return to step S2; otherwise, execute step S4;

[0056] S4, reducing the current angle value according to the set current angle gradient;

[0057] S5, calculate the real-time torque; if the reward function value corresponding to the calculated real-time torque is greater than the reward function value corresponding to the torque at the previous moment, return to step S4; otherwise, record the bus voltage, motor speed, motor current, current angle and the calculated real-time torque of the vehicle motor at the current moment, and execute step S6;

[0058] S6, increasing the current value according to the set current gradient; if the current value does not reach the set peak value, returning to step S3; otherwise, executing step S7;

[0059] S7, increasing the speed value according to the set speed gradient; if the speed value does not reach the set peak value, returning to step S3; otherwise, executing step S8;

[0060] S8. Increase the bus voltage value according to the set bus voltage gradient; if the bus voltage value does not reach the set peak value, return to step S3; otherwise, end the test.

[0061] Finish Figure 2 In each step, first increase the current angle according to the current angle gradient, and the multidimensional array can be obtained as follows:

[0062] [v1,n1,i1,θ1], [v1,n1,i1,θ2]……[v1,n1,i1,θn];

[0063] After increasing the motor current according to the current gradient, the multidimensional array is as follows:

[0064] [v1,n1,i2,θ1], [v1,n1,i2,θ2]……[v1,n1,i2,θn];

[0065] [v1,n1,i3,θ1], [v1,n1,i3,θ2]……[v1,n1,i3,θn];

[0066] …

[0067] Until [v1,n1,im,θ1], [v1,n1,im,θ2]...[v1,n1,im,θn];

[0068] After increasing the motor speed according to the gradient, the multidimensional array is as follows:

[0069] [v1,n2,i1,θ1], [v1,n2,i1,θ2]……[v1,n2,i1,θn];

[0070] [v1,n2,i2,θ1], [v1,n2,i2,θ2]……[v1,n2,i2,θn];

[0071] …

[0072] Until [v1,nq,im,θ1], [v1,nq,im,θ2], … [v1,nq,im,θn];

[0073] After increasing the bus voltage according to the gradient, the multidimensional array is as follows:

[0074] [v2,n1,i1,θ1], [v2,n1,i1,θ2]……[v2,n1,i1,θn];

[0075] [v2,n1,i2,θ1], [v2,n1,i2,θ2]……[v2,n1,i2,θn];

[0076] …

[0077] Until [vr,nq,im,θ1], [vr,nq,im,θ2]…[vr,nq,im,θn].

[0078] The above process of constructing a multidimensional array can be automatically calibrated through a software algorithm, which overcomes the technical problem in the prior art that technical personnel calibrate based on experience, resulting in a large consumption of human resources and low calibration precision.

[0079] Furthermore, after obtaining the multidimensional array, the values ​​of the bus voltage, motor speed and motor current in each array can be used as preset values, and then the motor operation is controlled for each current angle in the current angle array, and the motor temperature is collected at the same time. Based on the bus voltage, the motor speed, the motor current and each current angle, the motor torque corresponding to each current angle is calculated respectively; then the motor current, motor torque and motor temperature are substituted into the reward function of the reinforcement learning model to calculate the target reward value corresponding to each current angle within the calibration period.

[0080] The formula corresponding to the reward function of the reinforcement learning model is:

[0081]

[0082] Among them, R is the reward value, α1, α2, α3 are weight coefficients, i is the motor current, imax is the maximum current of the motor, T is the motor torque, Temp is the motor temperature, and t0 is the optimal motor temperature.

[0083] The reward function takes the motor temperature as one of the variables and incorporates it into temperature control and life management, quantifying the motor's sensitivity to temperature during operation and optimizing thermal management control and service life from a temperature perspective. Preferably, the optimal motor temperature in the reward function can be set to 65°. At the same time, the reward function takes into account that the larger the motor torque, the better, and the smaller the motor current, the better.

[0084] Step 120: determine the maximum reward value among all target reward values;

[0085] In specific implementation, the maximum reward value in the target reward value can be determined by the following formula:

[0086] Rbest=arg max(Rtotal(θ1), Rtotal(θ2)...Rtotal(θn));

[0087] Among them, Rbest is the maximum reward value, and Rtotal(θn) is the target reward value when the current angle is θn. The maximum reward value can be determined by the above formula, and the current angle corresponding to the maximum reward value can also be determined.

[0088] Step 130: After substituting the maximum reward value into the reward function, an inverse operation is performed on the reward function to establish a corresponding relationship between the motor current and the motor torque.

[0089] Furthermore, after determining the maximum reward value in the target reward value, the maximum reward value is substituted into the formula corresponding to the reward function. Under a certain motor temperature, only two variables, motor current and motor torque, remain in the formula corresponding to the reward function. By inverting the reward function, the corresponding relationship between motor current and motor torque can be established.

[0090] In this embodiment, when the bus voltage, motor speed and motor current are set values, for each current angle in the current angle array, the target reward value corresponding to each current angle in the calibration period is determined by using the reward function of the reinforcement learning model; the maximum reward value among all target reward values ​​is determined; the maximum reward value is further substituted into the reward function, and the reward function is inverted to establish the correspondence between the motor current and the motor torque, thereby combining reinforcement learning and automatic calibration, reducing the influence of subjective judgment on the calibration of motor current and motor torque, and concretizing and digitizing subjective parameter judgment; avoiding technical problems such as establishing a complex and multi-dimensional motor model and its poor adaptability to the environment, and at the same time quantifying the sensitivity of the motor to temperature during operation, optimizing thermal management control and service life from the perspective of temperature.

[0091] Furthermore, in one embodiment, for each current angle in the current angle array, the reward function of the reinforcement learning model is used to determine the target reward value corresponding to each current angle in the calibration period, including:

[0092] Step 210: collecting the motor torque corresponding to the current angle by bench testing;

[0093] Step 220: collecting the motor temperature in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period;

[0094] Assuming that the calibration period of bus voltage, motor current, motor speed and current angle is 10s, the sampling period can be 1s, 2s, or 5s. For example, taking the sampling period of 1s as an example, the motor temperature is collected every 1s using a temperature sensor arranged at the motor.

[0095] Step 230: Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

[0096] In a specific implementation, the motor current, the motor torque and the motor temperature collected in each sampling period are combined, and the reward function of the reinforcement learning model is used to determine the target reward value corresponding to the current angle within the calibration period.

[0097] In this embodiment, the motor torque corresponding to the current angle is collected through bench testing; the motor temperature is collected in each sampling period, and the sampling period is obtained by dividing the calibration period into equal parts; based on the motor current, the motor torque and the motor temperature, the reward function of the reinforcement learning model is used to determine the target reward value corresponding to the current angle in the calibration period. This embodiment provides a method for determining the motor torque and motor temperature in the reward function, which lays a foundation for determining the target reward value corresponding to the current angle in the calibration period.

[0098] Further, in one embodiment, the target reward value corresponding to the current angle within the calibration period is determined based on the motor current, the motor torque and the motor temperature using a reward function of a reinforcement learning model, including:

[0099] Step 310: Calculate a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature;

[0100] In specific implementation, in each sampling period, the motor current, the motor torque and the motor temperature collected in the sampling period are respectively input into the reward function of the reinforcement learning model to obtain a first reward value, that is, the first reward value calculated using the reward function of the reinforcement learning model in the first sampling period, the first reward value calculated using the reward function of the reinforcement learning model in the second sampling period... and the first reward value calculated using the reward function of the reinforcement learning model in the Sth sampling period.

[0101] Step 320: Comprehensively combine all first reward values ​​to determine a target reward value corresponding to the current angle within a calibration period.

[0102] Furthermore, after obtaining the first reward value calculated in each sampling period, all the first reward values ​​are integrated to determine the target reward value corresponding to the current angle in the calibration period, which can improve the accuracy of the determined target reward value.

[0103] Determine the target reward value corresponding to the current angle within the calibration period, and the corresponding formula is:

[0104]

[0105] Among them, Rtotal(θ n ) is when the current angle is θ n The target reward value, R i is the first reward value calculated using the reward function of the reinforcement learning model in the i-th sampling period, and S is the number of sampling periods.

[0106] In this embodiment, the first reward value is first calculated based on the motor current, the motor torque and the motor temperature using the reward function of the reinforcement learning model, and then all the first reward values ​​are combined to determine the target reward value corresponding to the current angle within the calibration period, thereby improving the accuracy of the determined target reward value.

[0107] In a second aspect, an embodiment of the present application also provides a device for establishing a current-torque correspondence relationship of a vehicle motor.

[0108] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of a device for establishing a current-torque correspondence relationship of a vehicle motor of the present application. Figure 3 As shown, the current-torque correspondence establishment device 300 of the vehicle motor includes:

[0109] A first determination module 310 is used to determine a target reward value corresponding to each current angle in a calibration period by using a reward function of a reinforcement learning model for each current angle in the current angle array when the bus voltage, the motor speed and the motor current are set values;

[0110] A second determination module 320 is used to determine the maximum reward value among all target reward values;

[0111] The establishing module 330 is used to substitute the maximum reward value into the reward function and then perform an inverse operation on the reward function to establish a corresponding relationship between the motor current and the motor torque.

[0112] Furthermore, in one embodiment, the formula corresponding to the reward function of the reinforcement learning model is:

[0113]

[0114] Among them, R is the reward value, α1, α2, α3 are weight coefficients, i is the motor current, imax is the maximum current of the motor, T is the motor torque, Temp is the motor temperature, and t0 is the optimal motor temperature.

[0115] Further, in one embodiment, the first determining module is specifically configured to:

[0116] The bench test collects the motor torque corresponding to the current angle;

[0117] The motor temperature is collected in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period;

[0118] Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

[0119] Further, in one embodiment, the first determining module is specifically configured to:

[0120] Calculating a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature;

[0121] All first reward values ​​are combined to determine a target reward value corresponding to the current angle within a calibration period.

[0122] Further, in one embodiment, the first determination module is specifically used to determine the target reward value corresponding to the current angle within the calibration period using the following formula, and the corresponding formula is:

[0123]

[0124] Among them, Rtotal(θ n ) is when the current angle is θ n The target reward value, R i is the first reward value calculated using the reward function of the reinforcement learning model in the i-th sampling period, and S is the number of sampling periods.

[0125] Among them, the functional implementation of each module in the above-mentioned current-torque correspondence establishment device for the vehicle motor corresponds to the various steps in the above-mentioned current-torque correspondence establishment method embodiment for the vehicle motor, and its functions and implementation processes will not be repeated here one by one.

[0126] In a third aspect, an embodiment of the present application provides a device for establishing a current-torque correspondence relationship of a vehicle motor. The device for establishing a current-torque correspondence relationship of a vehicle motor may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0127] Reference Figure 4 , Figure 4 The hardware structure diagram of the current-torque correspondence establishment device of the vehicle motor involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the current-torque correspondence establishment device of the vehicle motor may include a processor, a memory, a communication interface and a communication bus.

[0128] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0129] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to interconnect the devices inside the vehicle motor current torque correspondence establishment device, and an interface used to interconnect the vehicle motor current torque correspondence establishment device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0130] The 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.

[0131] The processor may be a general-purpose processor, which may call the current-torque correspondence establishment program of the vehicle motor stored in the memory, and execute the current-torque correspondence establishment method of the vehicle motor provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the current-torque correspondence establishment program of the vehicle motor is called may refer to the various embodiments of the current-torque correspondence establishment method of the vehicle motor of the present application, which will not be repeated here.

[0132] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0133] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0134] The computer-readable storage medium of the present application stores a program for establishing a current-torque correspondence relationship of a vehicle motor, wherein when the program for establishing a current-torque correspondence relationship of a vehicle motor is executed by a processor, the steps of the method for establishing a current-torque correspondence relationship of a vehicle motor as described above are implemented.

[0135] Among them, the method implemented when the current-torque correspondence establishment program of the vehicle motor is executed can refer to the various embodiments of the current-torque correspondence establishment method of the vehicle motor of the present application, and will not be repeated here.

[0136] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0137] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0138] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0139] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0140] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the 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 in sequence or in parallel, and these operations or steps may be combined.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0142] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for establishing a current-torque correspondence relationship of a vehicle motor, It is characterized in that The method for establishing the current-torque correspondence relationship of the vehicle motor includes: When the bus voltage, motor speed and motor current are set to set values, for each current angle in the current angle array, the reward function of the reinforcement learning model is used to determine the target reward value corresponding to each current angle in the calibration period; Determine the maximum reward value among all target reward values; After substituting the maximum reward value into the reward function, an inverse operation is performed on the reward function to establish a corresponding relationship between the motor current and the motor torque.

2. The method for establishing the current-torque correspondence relationship of a vehicle motor as claimed in claim 1, It is characterized in that The formula corresponding to the reward function of the reinforcement learning model is: Among them, R is the reward value, α 1 , α 2 , α 3 is the weight coefficient, i is the motor current, imax is the maximum current of the motor, T is the motor torque, Temp is the motor temperature, t 0 is the optimum motor temperature.

3. The method for establishing the current-torque correspondence relationship of a vehicle motor as claimed in claim 2, It is characterized in that The method of determining the target reward value corresponding to each current angle in the current angle array by using the reward function of the reinforcement learning model in the calibration period includes: The bench test collects the motor torque corresponding to the current angle; The motor temperature is collected in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period; Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

4. The method for establishing the current-torque correspondence relationship of a vehicle motor as claimed in claim 3, It is characterized in that The step of determining a target reward value corresponding to the current angle within a calibration period based on the motor current, the motor torque, and the motor temperature by using a reward function of a reinforcement learning model includes: Calculating a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature; All first reward values ​​are combined to determine a target reward value corresponding to the current angle within a calibration period.

5. The method for establishing the current-torque correspondence relationship of a vehicle motor as claimed in claim 4, It is characterized in that The target reward value corresponding to the current angle within the calibration period is determined by integrating all the first reward values, and the corresponding formula is: Among them, Rtotal(θ n ) is when the current angle is θ n The target reward value, R i is the first reward value calculated using the reward function of the reinforcement learning model in the i-th sampling period, and S is the number of sampling periods.

6. A device for establishing a current-torque correspondence relationship of a vehicle motor, It is characterized in that The current-torque correspondence establishment device of the vehicle motor comprises: A first determination module is used to determine the target reward value corresponding to each current angle in the calibration period by using the reward function of the reinforcement learning model for each current angle in the current angle array when the bus voltage, the motor speed and the motor current are set values; A second determination module is used to determine the maximum reward value among all target reward values; An establishing module is used for substituting the maximum reward value into the reward function and then performing an inverse operation on the reward function to establish a corresponding relationship between the motor current and the motor torque.

7. The current-torque correspondence establishing device of a vehicle motor as claimed in claim 6, It is characterized in that The first determining module is specifically used for: The bench test collects the motor torque corresponding to the current angle; The motor temperature is collected in each sampling period, wherein the sampling period is obtained by equally dividing the calibration period; Based on the motor current, the motor torque and the motor temperature, a target reward value corresponding to the current angle within a calibration period is determined using a reward function of a reinforcement learning model.

8. The device for establishing a current-torque correspondence relationship of a vehicle motor as claimed in claim 7, It is characterized in that The first determining module is specifically used for: Calculating a first reward value using a reward function of a reinforcement learning model based on the motor current, the motor torque, and the motor temperature; All first reward values ​​are combined to determine a target reward value corresponding to the current angle within a calibration period.

9. A device for establishing a current-torque correspondence relationship of a vehicle motor, It is characterized in that The device for establishing the current-torque correspondence relationship of the vehicle motor includes a processor, a memory, and a current-torque correspondence relationship establishment program for the vehicle motor stored in the memory and executable by the processor, wherein when the current-torque correspondence relationship establishment program for the vehicle motor is executed by the processor, the steps of the current-torque correspondence relationship establishment method for the vehicle motor as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a program for establishing a current-torque correspondence relationship of a vehicle motor, wherein when the program for establishing a current-torque correspondence relationship of a vehicle motor is executed by a processor, the steps of the method for establishing a current-torque correspondence relationship of a vehicle motor as described in any one of claims 1 to 5 are implemented.

Images