CN117048365B - Automobile torque control method, system, storage medium and equipment - Google Patents
Automobile torque control method, system, storage medium and equipment Download PDFInfo
- Publication number
- CN117048365B CN117048365B CN202311317229.3A CN202311317229A CN117048365B CN 117048365 B CN117048365 B CN 117048365B CN 202311317229 A CN202311317229 A CN 202311317229A CN 117048365 B CN117048365 B CN 117048365B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- external environment
- torque output
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 54
- 238000013135 deep learning Methods 0.000 claims abstract description 47
- 238000012417 linear regression Methods 0.000 claims abstract description 19
- 230000002787 reinforcement Effects 0.000 claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013526 transfer learning Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L15/00—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles
- B60L15/20—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles for control of the vehicle or its driving motor to achieve a desired performance, e.g. speed, torque, programmed variation of speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/40—Drive Train control parameters
- B60L2240/42—Drive Train control parameters related to electric machines
- B60L2240/423—Torque
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/08—Electric propulsion units
- B60W2710/083—Torque
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention provides an automobile torque control method, an automobile torque control system, a storage medium and an automobile torque control device, wherein the method comprises the following steps: controlling the vehicle-mounted detection equipment to acquire external environment information, and determining environment semantic information of the current external environment through a first deep learning training model according to the external environment information; controlling an in-vehicle sensor to acquire vehicle working condition information, and determining a current driving mode through a second deep learning training model according to the vehicle working condition information and external environment information; controlling an in-vehicle sensor to acquire real-time information of the vehicle, and confirming the upper limit and the lower limit of actual torque output of each shaft motor through a linear regression model according to the real-time information of the vehicle; and determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion. The invention solves the problem that the automobile torque control method in the prior art is difficult to adapt to complex and uncertain environments.
Description
Technical Field
The present invention relates to the field of automobile control technologies, and in particular, to an automobile torque control method, system, storage medium, and apparatus.
Background
The electric automobile has the characteristics of small noise, no pollution, zero emission and high energy conversion efficiency. The electric automobile can fundamentally solve the problems of petroleum dependence, environmental pollution, greenhouse gas emission, energy safety and the like, and is the final choice for developing new energy automobiles.
In the electric vehicle control technology, there is an electric vehicle torque output control technology. The aim of the torque output control technology of the electric automobile is to realize accurate control of the motor rotation speed and the torque so as to meet the requirements of drivers and the change of road conditions.
Existing electric vehicle torque output control techniques are typically model-based methods. The model-based method refers to designing corresponding controllers, such as a proportional-integral-derivative (PID) controller, a sliding-mode variable structure controller, an adaptive controller and the like, according to a mathematical model of the motor. However, although the method is theoretically mature, the requirements on model parameters are high, the method is time-consuming and labor-consuming depending on manual design or adjustment of torque output control parameters, and is not suitable for electric vehicles driven by different shaft numbers, independent control of each shaft motor cannot be realized, so that the dynamic performance, stability and safety of the vehicle are reduced, and the torque output cannot be dynamically adjusted according to different driving modes and working conditions, so that the economical efficiency and driving comfort of the vehicle are reduced.
Disclosure of Invention
Based on the above, the invention aims to provide an automobile torque control method, an automobile torque control system, a storage medium and an automobile torque control device, which aim to solve the problem that the automobile torque control method in the prior art is difficult to adapt to complex and uncertain environments.
According to the embodiment of the invention, the method for controlling the torque of the automobile comprises the following steps:
controlling a vehicle-mounted detection device to acquire external environment information, and determining environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
controlling an in-vehicle sensor to acquire vehicle working condition information, and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information;
the vehicle-mounted sensor is controlled to acquire vehicle real-time information, the vehicle real-time information is compared with vehicle theoretical information in a database, the vehicle is subjected to fault judgment to determine fault information, and the actual torque output upper and lower limits of all shaft motors are confirmed through a linear regression model according to the fault information and the theoretical torque output upper and lower limits of all shaft motors in the database;
and determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion.
In addition, the method for controlling the torque of the automobile according to the embodiment of the invention may further have the following additional technical features:
further, the step of controlling the vehicle-mounted detection device to acquire external environment information and determining the environment semantic information of the current external environment through the first deep learning training model according to the external environment information includes:
controlling a vehicle-mounted detection device to acquire external environment information of the vehicle, wherein the vehicle-mounted detection device at least comprises a camera, a radar and a GPS, and the external environment information at least comprises road surface conditions, traffic conditions and weather conditions;
selecting a type of a first deep learning training model according to the weather conditions;
if the weather condition is a normal weather condition, determining environmental semantic information of the current external environment through a deep convolutional neural network according to the external environment information;
if the weather condition is severe weather condition, the external environment information is processed through generating an countermeasure network according to the external environment information, and then the environment semantic information of the current external environment is determined through a convolutional neural network.
Further, the step of controlling the in-vehicle sensor to obtain vehicle working condition information and determining the current proper driving mode through the second deep learning training model according to the vehicle working condition information and the external environment information includes:
controlling an in-vehicle sensor to acquire vehicle working condition information;
determining the current required working condition of the vehicle according to the external environment information;
and comparing the vehicle working condition information with the required working condition, and determining a current proper driving mode through a multi-classifier.
Further, the step of determining the optimal torque output ratio of each of the axle motors through a reinforcement learning algorithm according to the driving mode, the environmental semantic information and the upper and lower limits of the actual torque output includes:
determining multiple groups of torque output proportion data through a strong learning algorithm according to the environment semantics;
comparing the torque output proportion data with the upper limit and the lower limit of the actual torque output to screen out qualified torque output proportion data conforming to the upper limit and the lower limit of the actual torque output;
and determining the optimal torque output ratio which is optimally adapted to the current driving mode through the strong learning algorithm according to the qualified torque output ratio data and the driving mode.
Further, the step of determining an optimal torque output ratio of each of the axle motors through a reinforcement learning algorithm according to the driving mode, the environmental semantic information and the upper and lower limits of the actual torque output, and performing torque control on each of the axle motors according to the optimal torque output ratio includes:
and acquiring the running data and the control effect data of the vehicle in the journey at this time, and uploading the running data and the control effect data to a cloud server, so that the cloud server optimizes the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm according to the running data and the control effect data and generates patches.
Further, before the step of controlling the vehicle-mounted detection device to acquire external environment information and determining the environment semantic information of the current external environment through the first deep learning training model according to the external environment information, the method comprises the following steps:
and downloading the patch from the cloud server to update parameters of the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm.
Another object of the present invention is a system for controlling torque in a vehicle, said system comprising:
the environment semantic determining module is used for controlling the vehicle-mounted detecting equipment to acquire external environment information and determining the environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
the driving mode determining module is used for controlling the in-vehicle sensor to acquire vehicle working condition information and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information;
the torque output determining module is used for controlling the in-vehicle sensor to acquire vehicle real-time information, comparing the vehicle real-time information with vehicle theoretical information in the database, performing fault judgment on the vehicle to determine fault information, and determining the actual torque output upper and lower limits of each shaft motor through a linear regression model according to the fault information and the theoretical torque output upper and lower limits of each shaft motor in the database;
and the optimal torque determining module is used for determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion.
It is another object of an embodiment of the present invention to provide a storage medium having stored thereon a computer program which when executed by a processor implements the steps of the above-described vehicle torque control method.
It is another object of an embodiment of the present invention to provide an apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed implements the steps of the above-described method of controlling vehicle torque.
According to the invention, real-time external environment information, vehicle working condition information and vehicle information are acquired, the information is processed through a deep learning training model, so that environment semantic information, a current adaptive driving mode and upper and lower output limits of current actual torque are obtained, the data are processed through a reinforcement learning algorithm, the optimal torque output proportion of each current shaft motor can be determined, and further, the control of the vehicle torque is realized. Furthermore, the invention solves the problem that the automobile torque control method in the prior art is difficult to adapt to complex and uncertain environments.
Drawings
FIG. 1 is a flowchart of an automobile torque control method in a first embodiment of the invention;
FIG. 2 is a schematic diagram of the result of a system for suppressing steering wheel axial shake in a second embodiment of the invention;
FIG. 3 is a schematic view of the apparatus in a third embodiment of the present invention;
the invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, a method for controlling torque of an automobile according to a first embodiment of the present invention is shown, and the method specifically includes steps S01-S04.
Step S01, controlling a vehicle-mounted detection device to acquire external environment information, and determining environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
in specific implementation, controlling a vehicle-mounted detection device to acquire external environment information of the vehicle, wherein the vehicle-mounted detection device at least comprises a camera, a radar and a GPS, and the external environment information at least comprises road surface conditions, traffic conditions and weather conditions; selecting a type of a first deep learning training model according to the weather conditions; if the weather condition is a normal weather condition, determining environmental semantic information of the current external environment through a deep convolutional neural network according to the external environment information; if the weather condition is severe weather condition, the external environment information is processed through generating an countermeasure network according to the external environment information, and then the environment semantic information of the current external environment is determined through a convolutional neural network. Because of bad weather conditions, the image effect obtained by the vehicle-mounted detection equipment is poor, and the road surface scene changes fast, the image is enhanced and repaired through the countermeasure network, virtual data are generated to simulate different rain and snow scenes, and then the characteristic extraction and classification are carried out on the image through the convolutional neural network, so that the semantic information of the environment is obtained. In particular, it may be implemented by a variational self-encoder generating a countermeasure network (VAE-GAN), the input being the original image and the target scene, the output being the enhanced image. VAE-GAN is a deep learning method combining a variational self-encoder (VAE) and a generation countermeasure network (GAN), which can simultaneously realize reconstruction and generation of images while guaranteeing quality and diversity of images. In addition, the deep convolutional neural network may be composed of a plurality of convolutional layers, a pooling layer and a full-connection layer, and the activation function may be implemented with a ReLU function.
Step S02, controlling an in-vehicle sensor to acquire vehicle working condition information, and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information;
specifically, controlling an in-vehicle sensor to acquire vehicle working condition information; determining the current required working condition of the vehicle according to the external environment information; and comparing the vehicle working condition information with the required working condition, and determining a current proper driving mode through a multi-classifier. Firstly, determining what working condition is needed by the vehicle according to the external environment, for example, when the vehicle is on a highway and the weather is good, the working condition of high speed, stability and energy saving is needed, and then judging the driving intention and the driving state of the vehicle according to the information such as the speed, the acceleration and the accelerator pedal signal of the vehicle, and further determining that the current proper mode is a sport mode or an economic mode. When the vehicle is in an urban road section, but the weather is severe and is rainy and snowy, a low-speed, flexible and robust working condition is required. And judging the driving intention and the driving state of the vehicle according to the information such as the speed, the acceleration and the brake pedal signal of the vehicle, and selecting a proper driving mode such as a comfort mode or a safety mode. This step may be implemented with a multi-classifier, where the input is vehicle status information and the output is a class of driving patterns. The multi-classifier can be built with a fully connected layer and the activation function can be implemented with a softmax function.
Step S03, controlling the in-vehicle sensor to acquire vehicle real-time information, comparing the vehicle real-time information with vehicle theoretical information in a database, performing fault judgment on the vehicle to determine fault information, and determining the actual torque output upper and lower limits of each shaft motor through a linear regression model according to the fault information and the theoretical torque output upper and lower limits of each shaft motor in the database;
when the method is specifically implemented, the in-vehicle sensor is controlled to acquire the real-time information of the vehicle, the real-time information of the vehicle is compared with the theoretical information of the vehicle in the database, and the vehicle is subjected to fault judgment to determine fault information; and confirming the upper and lower limits of the actual torque output of each shaft motor through a linear regression model according to the fault information and the upper and lower limits of the theoretical torque output of each shaft motor in the database. Specifically, the maximum available power and the minimum available power of each shaft motor are calculated according to the maximum discharge power and the maximum recharging power provided by the BMS and the maximum torque and the minimum torque of each shaft motor provided by the MCU. Then, by analyzing and comparing the information provided by the BMS, MCU, SOC sensor and the like, whether the fault conditions such as overcharge or overdischarge of the battery, overheat or overload of the motor, too low or too high residual battery capacity and the like exist is judged, and then the maximum available power and the minimum available power of each shaft motor are corrected and adjusted according to the fault judgment result so as to ensure the safe operation of the battery and the motor. Finally, the maximum available power and the minimum available power of each shaft motor are converted into upper and lower torque output limits according to factors such as SOC and system transmission efficiency thereof. This step can be implemented with a simple linear regression model, with inputs being the various limiting factors and outputs being the torque output upper and lower limits. The linear regression model may be constructed with a fully connected layer and the activation function may be implemented with an identity function.
Step S04, determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion;
specifically, determining multiple groups of torque output proportion data through a strong learning algorithm according to the environment semantics; comparing the torque output proportion data with the upper limit and the lower limit of the actual torque output to screen out qualified torque output proportion data conforming to the upper limit and the lower limit of the actual torque output; and determining the optimal torque output ratio which is optimally adapted to the current driving mode through the strong learning algorithm according to the qualified torque output ratio data and the driving mode. And predicting the optimal torque output proportion of each shaft motor by using a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower torque output limits, and outputting the final torque. The reinforcement learning algorithm gives rewards or punishments according to indexes such as energy consumption, safety, comfort and the like through interaction with the environment, and continuously adjusts parameters of the model so as to achieve the aim of optimization. This step may be implemented with a deep actor-critics network (DACN), where the input is the current state and continuous motion space and the output is a deterministic strategy and value function for each motion. DACN is a reinforcement learning method combining a deep neural network and actor-critique algorithm, which can handle high-dimensional states and motion spaces while avoiding the problem of high variance of strategy gradient algorithm and deviation of value function method. In addition, the pre-training model in other fields (such as the automatic driving or game field) can be applied to the torque output control of the electric automobile through the transfer learning technology, and the optimal torque output proportion of each shaft motor is predicted by using the reinforcement learning algorithm, and the final torque is output. The transfer learning technology enables the model to adapt to the running working condition under severe weather through fine adjustment or adaptive training, improves the generalization capability of the model and reduces the training time. This step can be implemented with a deep reinforcement learning meta-learning (DRLML) algorithm, where the input is the current state and continuous action space, and the output is the deterministic strategy for each action. The DRLML is a method combining deep reinforcement learning and meta learning, and can quickly adapt to new working conditions or tasks by utilizing a pre-training model in other fields, and meanwhile, the stability and the expandability of the model are maintained.
In addition, after the vehicle journey is finished, the operation data and the control effect data of the vehicle in the journey are obtained and uploaded to a cloud server, so that the cloud server optimizes the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm according to the operation data and the control effect data and generates patches. And downloading the patch from the cloud server to update parameters of the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm before the vehicle journey begins. Specifically, through wireless communication or other reasonable modes, the operation data (such as battery state, motor state, torque output proportion and the like) and the control effect data (such as energy consumption, emission, safety, comfort and the like) of the vehicle under different working conditions are collected and uploaded to a cloud server or other storage devices so as to update and optimize the deep learning training model. And the collected and uploaded data are utilized to perform operations such as parameter adjustment, structure optimization, function enhancement and the like on the deep learning training model in an online learning mode or other reasonable modes so as to improve indexes such as accuracy, robustness and adaptability of the model. For example, in the invention, the collected and uploaded data can be utilized to perform incremental learning or transfer learning on the deep learning training model so as to adapt to new working conditions or requirements. And transmitting the optimized content to the vehicle system in a patch mode so as to update the deep learning training model.
It should be noted that, in order to train the deep learning model, in each training period, we need to perform the following steps: randomly extracting a batch of data from the dataset as input; calculating the output of each layer through forward propagation, and obtaining a final prediction result; calculating an error between a predicted result and a real result through a loss function, and evaluating the performance of the model; calculating the gradient of each layer through a back propagation algorithm, and updating the parameters of the model; repeating the above steps until the stop condition is met or the maximum training period is reached. During the training process, we need to pay attention to the following points: to prevent the over-fitting or under-fitting problem, we need to divide the dataset into a training set, a validation set and a test set, and monitor the performance of the model on the validation set; to improve the generalization ability of the model, we can use some regularization techniques, such as dropout, batch normalization, etc.; to improve the convergence speed and stability of the model, we can use some optimization algorithms, such as Adam, RMSProp, etc.; to improve the exploratory capacity of the model and avoid sinking into local optima, we can use some exploratory strategies like epsilon-greedy, boltzmann, etc.
In summary, according to the automobile torque control method in the above embodiment of the present invention, real-time external environment information, vehicle condition information and vehicle information are obtained, and then these information are processed through a deep learning training model, so as to obtain environment semantic information, a currently adapted driving mode and upper and lower limits of current actual torque output, and then these data are processed through a reinforcement learning algorithm, so that the optimal torque output ratio of each current shaft motor can be determined, and further, the control of the automobile torque is realized. Furthermore, the invention solves the problem that the automobile torque control method in the prior art is difficult to adapt to complex and uncertain environments.
Example two
Referring to fig. 2, a block diagram of a system for controlling torque of an automobile according to a second embodiment of the invention is shown, and the system 200 for controlling torque of an automobile includes: an environmental semantics determination module 21, a driving pattern determination module 22, a torque output determination module 23, and an optimal torque determination module 24, wherein:
the environment semantic determining module 21 is configured to control the vehicle-mounted detecting device to obtain external environment information, and determine environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
the driving mode determining module 22 is configured to control an in-vehicle sensor to obtain vehicle condition information, and determine a current suitable driving mode according to the vehicle condition information and the external environment information through a second deep learning training model;
the torque output determining module 23 is configured to control the in-vehicle sensor to obtain real-time information of the vehicle, compare the real-time information of the vehicle with theoretical information of the vehicle in the database, determine fault information by performing fault judgment on the vehicle, and confirm the upper and lower limits of actual torque output of each shaft motor through a linear regression model according to the fault information and the theoretical upper and lower limits of torque output of each shaft motor in the database;
an optimal torque determining module 24, configured to determine an optimal torque output ratio of each of the axle motors through a reinforcement learning algorithm according to the driving mode, the environmental semantic information, and the upper and lower limits of the actual torque output, and perform torque control on each of the axle motors according to the optimal torque output ratio;
further, in other embodiments of the present invention, the system 200 for controlling the torque of the vehicle comprises:
the data uploading module is used for acquiring the running data and the control effect data of the vehicle in the journey and uploading the running data and the control effect data to the cloud server, so that the cloud server optimizes the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm according to the running data and the control effect data and generates patches;
and the data downloading module is used for downloading the patch from the cloud server to update parameters of the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm.
Further, the environment semantic determining module 21 includes:
the vehicle-mounted detection equipment at least comprises a camera, a radar and a GPS, and the external environment information at least comprises road surface conditions, traffic conditions and weather conditions;
the judging and selecting unit is used for selecting the type of the first deep learning training model according to the weather conditions; if the weather condition is a normal weather condition, determining environmental semantic information of the current external environment through a deep convolutional neural network according to the external environment information; if the weather condition is severe weather condition, the external environment information is processed through generating an countermeasure network according to the external environment information, and then the environment semantic information of the current external environment is determined through a convolutional neural network.
Further, in other embodiments of the present invention, the driving mode determining module 22 includes:
the working condition acquisition unit is used for controlling the in-vehicle sensor to acquire vehicle working condition information;
the working condition determining unit is used for determining the current required working condition of the vehicle according to the external environment information;
and the driving mode determining unit is used for comparing the vehicle working condition information with the required working condition and determining a current proper driving mode through a multi-classifier.
Further, the torque output determination module 23 includes:
the fault information judging unit is used for controlling the in-vehicle sensor to acquire real-time information of the vehicle, comparing the real-time information of the vehicle with theoretical information of the vehicle in the database, and judging the fault of the vehicle to determine fault information;
and the torque determining unit is used for determining the upper and lower limits of the actual torque output of each shaft motor through a linear regression model according to the fault information and the upper and lower limits of the theoretical torque output of each shaft motor in the database.
Further, the optimal torque determination module 24 includes:
the torque output proportion determining unit is used for determining a plurality of groups of torque output proportion data through a strong learning algorithm according to the environment semantics;
the screening unit is used for comparing the torque output proportion data with the upper limit and the lower limit of the actual torque output to screen out qualified torque output proportion data which accords with the upper limit and the lower limit of the actual torque output;
and the determining unit is used for determining the optimal torque output ratio which is most suitable for the current driving mode through the strong learning algorithm according to the qualified torque output ratio data and the driving mode.
The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and are not described herein again.
Example III
In another aspect, referring to fig. 3, a schematic diagram of an electronic device according to a third embodiment of the present invention is provided, including a memory 20, a processor 10, and a computer program 30 stored in the memory and capable of running on the processor, where the processor 10 implements the method for controlling torque of an automobile according to the above-mentioned method when executing the computer program 30.
The processor 10 may be, among other things, a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip for running program code or processing data stored in the memory 20, e.g. executing an access restriction program or the like, in some embodiments.
The memory 20 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 20 may in some embodiments be an internal storage unit of the electronic device, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like. Further, the memory 20 may also include both internal storage units and external storage devices of the electronic device. The memory 20 may be used not only for storing application software of an electronic device and various types of data, but also for temporarily storing data that has been output or is to be output.
It should be noted that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and in other embodiments the electronic device may comprise fewer or more components than shown, or may combine certain components, or may have a different arrangement of components.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the automobile torque control method as described above.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (6)
1. A method of controlling torque in an automobile, the method comprising:
controlling a vehicle-mounted detection device to acquire external environment information, and determining environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
controlling an in-vehicle sensor to acquire vehicle working condition information, and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information;
the vehicle-mounted sensor is controlled to acquire vehicle real-time information, the vehicle real-time information is compared with vehicle theoretical information in a database, the vehicle is subjected to fault judgment to determine fault information, and the actual torque output upper and lower limits of all shaft motors are confirmed through a linear regression model according to the fault information and the theoretical torque output upper and lower limits of all shaft motors in the database;
determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion;
the step of controlling the vehicle-mounted detection equipment to acquire external environment information and determining the environment semantic information of the current external environment through a first deep learning training model according to the external environment information comprises the following steps:
controlling a vehicle-mounted detection device to acquire external environment information of the vehicle, wherein the vehicle-mounted detection device at least comprises a camera, a radar and a GPS, and the external environment information at least comprises road surface conditions, traffic conditions and weather conditions;
selecting a type of a first deep learning training model according to the weather conditions;
if the weather condition is a normal weather condition, determining environmental semantic information of the current external environment through a deep convolutional neural network according to the external environment information;
if the weather condition is severe weather condition, processing the external environment information by generating an countermeasure network according to the external environment information, and determining the environment semantic information of the current external environment by a convolutional neural network;
the step of controlling the in-vehicle sensor to acquire vehicle working condition information and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information comprises the following steps:
controlling an in-vehicle sensor to acquire vehicle working condition information;
determining the current required working condition of the vehicle according to the external environment information;
comparing the vehicle working condition information with the required working condition, and determining a current proper driving mode through a multi-classifier;
the step of determining the optimal torque output ratio of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output comprises the following steps:
determining multiple groups of torque output proportion data through a strong learning algorithm according to the environment semantics;
comparing the torque output proportion data with the upper limit and the lower limit of the actual torque output to screen out qualified torque output proportion data conforming to the upper limit and the lower limit of the actual torque output;
and determining the optimal torque output ratio which is optimally adapted to the current driving mode through the strong learning algorithm according to the qualified torque output ratio data and the driving mode.
2. The method according to claim 1, wherein the step of determining an optimal torque output ratio of each of the axle motors by a reinforcement learning algorithm based on the driving pattern, the environmental semantic information, and the actual torque output upper and lower limits, and performing torque control of each of the axle motors based on the optimal torque output ratio, comprises:
and acquiring the running data and the control effect data of the vehicle in the journey at this time, and uploading the running data and the control effect data to a cloud server, so that the cloud server optimizes the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm according to the running data and the control effect data and generates patches.
3. The method for controlling torque of an automobile according to claim 2, wherein the step of controlling the on-vehicle detecting device to acquire the external environment information and determining the environmental semantic information of the current external environment through the first deep learning training model according to the external environment information comprises:
and downloading the patch from the cloud server to update parameters of the first deep learning training model, the second deep learning training model, the linear regression model and the strong learning algorithm.
4. A system for controlling torque in a vehicle, characterized by implementing the method according to claim 1
The automobile torque control method according to any one of claims 3, the system comprising:
the environment semantic determining module is used for controlling the vehicle-mounted detecting equipment to acquire external environment information and determining the environment semantic information of the current external environment through a first deep learning training model according to the external environment information;
the driving mode determining module is used for controlling the in-vehicle sensor to acquire vehicle working condition information and determining a current proper driving mode through a second deep learning training model according to the vehicle working condition information and the external environment information;
the torque output determining module is used for controlling the in-vehicle sensor to acquire vehicle real-time information, comparing the vehicle real-time information with vehicle theoretical information in the database, performing fault judgment on the vehicle to determine fault information, and determining the actual torque output upper and lower limits of each shaft motor through a linear regression model according to the fault information and the theoretical torque output upper and lower limits of each shaft motor in the database;
and the optimal torque determining module is used for determining the optimal torque output proportion of each shaft motor through a reinforcement learning algorithm according to the driving mode, the environment semantic information and the upper and lower limits of the actual torque output, and controlling the torque of each shaft motor according to the optimal torque output proportion.
5. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the steps of the vehicle torque control method according to any one of claims 1 to 3.
6. An automotive torque control device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the automotive torque control method according to any one of claims 1-3 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317229.3A CN117048365B (en) | 2023-10-12 | 2023-10-12 | Automobile torque control method, system, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317229.3A CN117048365B (en) | 2023-10-12 | 2023-10-12 | Automobile torque control method, system, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117048365A CN117048365A (en) | 2023-11-14 |
| CN117048365B true CN117048365B (en) | 2024-01-26 |
Family
ID=88655846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311317229.3A Active CN117048365B (en) | 2023-10-12 | 2023-10-12 | Automobile torque control method, system, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117048365B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019180231A (en) * | 2019-06-05 | 2019-10-17 | 日産自動車株式会社 | Control device for electric vehicle and control method for electric vehicle |
| CN110936824A (en) * | 2019-12-09 | 2020-03-31 | 江西理工大学 | Electric automobile double-motor control method based on self-adaptive dynamic planning |
| CN113119753A (en) * | 2021-05-26 | 2021-07-16 | 合肥工业大学 | Distributed type electric-drive vehicle differential steering self-adaptive control method |
| CN114684202A (en) * | 2022-06-01 | 2022-07-01 | 浙江大旗新能源汽车有限公司 | Intelligent system for automatically driving vehicle and integrated control method thereof |
| CN115257819A (en) * | 2022-09-02 | 2022-11-01 | 东南大学 | Decision-making method for safe driving of large-scale commercial vehicle in urban low-speed environment |
| EP4108504A1 (en) * | 2021-06-25 | 2022-12-28 | Bosch Automotive Products (Suzhou) Co., Ltd. | Method and device for self-adaptively adjusting drive torque of two-wheeled electric vehicle |
-
2023
- 2023-10-12 CN CN202311317229.3A patent/CN117048365B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019180231A (en) * | 2019-06-05 | 2019-10-17 | 日産自動車株式会社 | Control device for electric vehicle and control method for electric vehicle |
| CN110936824A (en) * | 2019-12-09 | 2020-03-31 | 江西理工大学 | Electric automobile double-motor control method based on self-adaptive dynamic planning |
| CN113119753A (en) * | 2021-05-26 | 2021-07-16 | 合肥工业大学 | Distributed type electric-drive vehicle differential steering self-adaptive control method |
| EP4108504A1 (en) * | 2021-06-25 | 2022-12-28 | Bosch Automotive Products (Suzhou) Co., Ltd. | Method and device for self-adaptively adjusting drive torque of two-wheeled electric vehicle |
| CN114684202A (en) * | 2022-06-01 | 2022-07-01 | 浙江大旗新能源汽车有限公司 | Intelligent system for automatically driving vehicle and integrated control method thereof |
| CN115257819A (en) * | 2022-09-02 | 2022-11-01 | 东南大学 | Decision-making method for safe driving of large-scale commercial vehicle in urban low-speed environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117048365A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102019113865A1 (en) | INTELLIGENT MOTOR VEHICLES, SYSTEMS AND CONTROL LOGIC FOR REAL-TIME ROUTE GUIDANCE AND ADAPTIVE DRIVE CONTROL | |
| DE102019105874A1 (en) | Automated driving systems and control logic for cloud-based scenario planning of autonomous vehicles | |
| CN113788021B (en) | Adaptive following cruise control method combined with preceding vehicle speed prediction | |
| CN112418237A (en) | Vehicle driving decision method and device and electronic equipment | |
| DE102022123187A1 (en) | Adaptive reduction of neural network systems | |
| US11100372B2 (en) | Training deep neural networks with synthetic images | |
| CN111830962A (en) | Interpretation data for reinforcement learning agent controller | |
| CN117048365B (en) | Automobile torque control method, system, storage medium and equipment | |
| KR20220163201A (en) | Apparatus for controlling transmission of vehicle and method thereof | |
| CN114407906B (en) | Vehicle load measuring method, device, storage medium and equipment | |
| US20220170543A1 (en) | Gear stage choosing apparatus, gear stage choosing method, and simulation apparatus | |
| CN113580947B (en) | Vehicle energy recovery method and device, vehicle and storage medium | |
| DE102022125228A1 (en) | AUTOMATED DRIVING SYSTEM WITH THE DESIRED LEVEL OF DRIVING AGGRESSIVITY | |
| DE102018123652A1 (en) | METHOD AND SYSTEMS FOR TESTING COMPONENTS OF PARALLEL COMPUTER DEVICES | |
| US20220188621A1 (en) | Generative domain adaptation in a neural network | |
| US9174626B2 (en) | Methods and systems for controlling shifting between operating modes in hybrid vehicles | |
| US10977783B1 (en) | Quantifying photorealism in simulated data with GANs | |
| Zhang | Vehicle Parameters Estimation and Driver Behavior Classification for Adaptive Shift Strategy of Heavy Duty Vehicles | |
| DE102020120367A1 (en) | Method and system for controlling an electrified vehicle | |
| CN112861266A (en) | Method, apparatus, medium, and electronic device for controlling device driving mode | |
| CN117311330B (en) | Control method and system of whole vehicle controller, storage medium and electronic equipment | |
| CN116494984B (en) | Random gradient-based energy recovery control method and system and vehicle | |
| CN116384065B (en) | Method and device for optimizing combination parameters of hybrid electric vehicle | |
| CN114379554B (en) | Vehicle fuel-saving control method, control device and storage medium | |
| DE102022126139A1 (en) | SYSTEMS AND PROCEDURES FOR PROVIDING HANDLING INSTRUCTIONS FOR AN OPERATIONAL CHARGING UNIT |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |