New Energy Vehicle Gear Decision Method and Control System Based on Deep Reinforcement Learning

Abstract

The present invention relates to the field of intelligent control technology, and particularly to a gear shifting decision-making method and control system for new energy vehicles based on deep reinforcement learning. The method includes the following steps: by deploying a vehicle speed sensor, a motor speed sensor, and a battery state sensor on a new energy vehicle and performing real-time vehicle state acquisition and vehicle data fusion processing, a driving fusion data set of the new energy vehicle is obtained; the current gear of the new energy vehicle is acquired, and the state space vector is determined by combining the corresponding driving vehicle speed, motor speed, battery power, road gradient, and curvature at the current time, so as to be used as the state input corresponding to a preset deep reinforcement learning model, and the gear shifting action space is defined to generate a selection of the gear shifting action space for the new energy vehicle, and a corresponding vehicle gear shifting decision-making reward function is designed and the vehicle driving gear shifting decision-making control is performed to generate an optimal gear shifting decision-making control strategy. The present invention can achieve more intelligent and efficient gear shifting decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a gear shifting decision-making method and control system for new energy vehicles based on deep reinforcement learning. Background Art

[0002] As an important direction for future transportation development, the improvement of intelligent control technology for new energy vehicles is crucial. In the power system of new energy vehicles, the selection of gears has a crucial impact on energy efficiency, driving performance, and the lifespan of the power system. In recent years, deep reinforcement learning (DRL), as a powerful machine learning method, has gradually been applied in the field of intelligent control. Deep reinforcement learning can continuously optimize the decision-making strategy according to the feedback signal by simulating the interaction between the environment and the agent. In the gear shifting decision-making of new energy vehicles, deep reinforcement learning can adaptively adjust the gear selection by real-time obtaining information such as the vehicle speed, acceleration, and battery state of the vehicle, and based on this information, so as to achieve the best balance between energy efficiency and driving performance. However, the existing gear shifting decision-making methods mainly rely on preset control rules and lack intelligence and adaptability. Such methods cannot make personalized and real-time gear adjustments for different driving environments, resulting in waste of energy. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a gear shifting decision-making method and control system for new energy vehicles based on deep reinforcement learning to solve at least one of the above technical problems.

[0004] To achieve the above object, a gear shifting decision-making method for new energy vehicles based on deep reinforcement learning includes the following steps:

[0005] Step S1: Deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on the new energy vehicle, and use the vehicle speed sensor, the motor speed sensor, and the battery state sensor to collect the vehicle state in real time during the corresponding real-time driving process of the new energy vehicle, so as to obtain the driving vehicle speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and perform vehicle data fusion processing on the driving vehicle speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, so as to obtain a driving fusion data set of the new energy vehicle;

[0006] Step S2: Obtain the current gear of the new energy vehicle and determine the state space vector by combining the corresponding driving speed, motor speed, battery power, road slope, and curvature in the new energy vehicle driving fusion dataset at the current time, so as to obtain the new energy vehicle state space vector; use the new energy vehicle state space vector as the state input corresponding to the preset deep reinforcement learning model, and use the deep reinforcement learning model to define the gear action space for the new energy vehicle state space vector, so as to generate the new energy vehicle gear shift action space selection, including the upshift, downshift, and maintaining the current gear actions corresponding to the new energy vehicle;

[0007] Step S3: Design the corresponding vehicle gear decision reward function through the new energy vehicle gear shift action space selection corresponding to the deep reinforcement learning model;

[0008] Step S4: Based on the vehicle gear decision reward function, use the deep reinforcement learning model to perform vehicle driving gear decision control on the corresponding new energy vehicle state space vector, so as to select the optimal gear shift action from the action space corresponding to the model according to the real-time collected vehicle state information, and generate the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: Deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on the new energy vehicle, and use the vehicle speed sensor to collect the real-time driving speed of the new energy vehicle during the corresponding real-time driving process, so as to obtain the new energy vehicle driving speed;

[0011] Step S12: Use the motor speed sensor to collect the real-time motor speed of the new energy vehicle during the corresponding real-time driving process, so as to obtain the new energy vehicle motor speed;

[0012] Step S13: Use the battery state sensor to collect the real-time battery power of the new energy vehicle during the corresponding real-time driving process, so as to obtain the new energy vehicle battery power;

[0013] Step S14: Obtain the road slope and curvature corresponding to the new energy vehicle at different driving road sites;

[0014] Step S15: Based on the road slope and curvature corresponding to the new energy vehicle at different driving road sites, perform vehicle data fusion processing on the new energy vehicle driving speed, the new energy vehicle motor speed, and the new energy vehicle battery power to obtain the new energy vehicle driving fusion dataset.

[0015] Further, step S15 includes the following steps:

[0016] Step S151: Perform Kalman filtering on the vehicle data of the new energy vehicle's driving speed, motor speed, and battery power to obtain the vehicle's noise-reduced driving speed, motor's noise-reduced speed, and battery's noise-reduced power;

[0017] Step S152: By constructing the vehicle dynamics model and battery model corresponding to the new energy vehicle, and based on the vehicle dynamics model and battery model, conduct an analysis of the correlation of the driving state for the vehicle's noise-reduced driving speed, motor's noise-reduced speed, and battery's noise-reduced power to obtain the new energy vehicle's driving state correlation data set;

[0018] Step S153: Obtain the corresponding vehicle driving road space sites through the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and based on the vehicle driving road space sites, perform a synchronous mapping of the driving space on the new energy vehicle's driving state correlation data set to obtain the corresponding vehicle driving state data set at the same driving road site, including driving speed, motor speed, and battery power;

[0019] Step S154: Based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, perform vehicle data fusion processing on the corresponding vehicle driving state data set at the same driving road site to obtain the new energy vehicle's driving fusion data set.

[0020] Furthermore, Step S2 includes the following steps:

[0021] Step S21: Obtain the current gear of the new energy vehicle;

[0022] Step S22: Determine the state space vector by combining the current gear of the new energy vehicle with the corresponding driving speed, motor speed, battery power, road slope, and curvature in the new energy vehicle's driving fusion data set at the current time to obtain the new energy vehicle's state space vector;

[0023] Step S23: Divide the new energy vehicle's state space vector into individual vehicle state discrete space vectors according to the corresponding time intervals, and determine the corresponding vehicle speed state values, rotation speed state values, power state values, slope state values, and curvature state values for each time range based on the individual vehicle state discrete space vectors;

[0024] Step S24: Take the vehicle speed status value, rotation speed status value, power status value, slope status value, and curvature status value corresponding to each time range as the state input of a preset deep reinforcement learning model, and perform gear power and energy consumption evaluation calculations on the current gear of the new energy vehicle based on the vehicle speed status value, rotation speed status value, power status value, slope status value, and curvature status value corresponding to each time range to obtain the gear power performance status value of the new energy vehicle and the energy loss of the new energy vehicle gear;

[0025] Step S25: Use the deep reinforcement learning model to define the gear action space for the gear power performance status value of the new energy vehicle and the energy loss of the new energy vehicle gear to generate a gear shift action space selection for the new energy vehicle, including actions such as upshifting, downshifting, and maintaining the current gear corresponding to the new energy vehicle.

[0026] Further, the gear power and energy consumption evaluation calculation of the current gear of the new energy vehicle based on the vehicle speed status value, rotation speed status value, power status value, slope status value, and curvature status value corresponding to each time range in Step S24 includes the following steps:

[0027] Perform gear power evaluation calculation on the current gear of the new energy vehicle using the gear power performance evaluation calculation formula based on the vehicle speed status value, rotation speed status value, and power status value corresponding to each time range to obtain the gear power performance status value of the new energy vehicle;

[0028] Simulate and calculate the vehicle gear power output of the new energy vehicle in the corresponding time range according to the gear power performance status value of the new energy vehicle, and calculate the vehicle gear power peak value of the new energy vehicle according to the vehicle gear power output;

[0029] Perform an analysis of the impact of energy consumption on the current gear of the new energy vehicle based on the slope status value and the curvature status value to obtain the energy consumption impact coefficient of the new energy vehicle gear;

[0030] Perform energy consumption evaluation calculation on the current gear of the new energy vehicle using the vehicle energy loss evaluation calculation formula based on the vehicle gear power peak value and the energy consumption impact coefficient of the new energy vehicle gear to obtain the energy loss of the new energy vehicle gear;

[0031] Among them, the specific vehicle energy loss evaluation calculation formula is:

[0032] ;

[0033] In the formula, is the energy loss of the new energy vehicle gear, is the initial value of the time range, is the termination value of the time range, is the time variable parameter, is the vehicle speed status value of a new energy vehicle at time , is the rotational speed status value of a new energy vehicle at time , is the power status value of a new energy vehicle at time , is the influence weight coefficient of power energy loss, is the power peak value of the vehicle gear, is the influence coefficient of energy consumption of a new energy vehicle gear, is the correction coefficient of energy loss of a new energy vehicle gear.

[0034] Further, the calculation formula for evaluating the gear power performance is specifically:

[0035] ;

[0036] In the formula, is the gear power performance status value of a new energy vehicle, is the initial value of the time range, is the termination value of the time range, is the time variable parameter, is the vehicle speed status value of a new energy vehicle at time , is the maximum vehicle speed of a new energy vehicle in the current gear, is the vehicle speed power contribution coefficient, is the rotational speed status value of a new energy vehicle at time , is the maximum motor rotational speed of a new energy vehicle in the current gear, is the motor rotational speed power contribution coefficient, is the power status value of a new energy vehicle at time , is the maximum battery power of a new energy vehicle in the current gear, is the battery power contribution coefficient, is the power decay time constant of a new energy vehicle in the current gear, is the time exponential decay factor, is the correction coefficient of the gear power performance status value of a new energy vehicle.

[0037] Further, the definition of the gear shifting action space described in step S25 is specifically as follows: when the power performance state value is large and the gear energy loss is within an acceptable range, the action space corresponding to the new energy vehicle is defined as an upshift action using the deep reinforcement learning model; when the power performance state value is insufficient and the gear energy loss is large, the action space corresponding to the new energy vehicle is defined as a downshift action using the deep reinforcement learning model; when the power performance state value and the gear energy loss are in a balanced state, the action space corresponding to the new energy vehicle is defined as maintaining the current gear action using the deep reinforcement learning model.

[0038] Further, the vehicle gear decision reward function described in step S3 is specifically as follows: when the action gear selected by the deep reinforcement learning model results in reduced energy consumption and enhanced power performance, a positive gear decision reward is given; when the action gear selected by the deep reinforcement learning model causes excessive energy consumption and weakened power performance, affecting the driving smoothness of the new energy vehicle, a negative gear decision reward is given.

[0039] Further, the optimal gear decision control strategy corresponding to different driving conditions described in step S4 is specifically as follows: when the vehicle is driving in congested traffic, the model determines whether to downshift to maintain the corresponding power output and smoothness of the vehicle based on insufficient vehicle speed and motor speed; when the vehicle is driving on the highway, the model determines whether to upshift to reduce the motor speed and improve energy utilization efficiency based on sufficient battery power and excessive energy consumption; when the vehicle is driving on a flat road, the model determines whether to maintain the current gear to maintain the stable operation of the vehicle and avoid unnecessary power fluctuations and motor losses based on normal battery power consumption and no obvious power increase or energy consumption reduction caused by gear shifting.

[0040] Further, the present invention also provides a new energy vehicle gear decision control system based on deep reinforcement learning for executing the new energy vehicle gear decision method based on deep reinforcement learning as described above. The new energy vehicle gear decision control system based on deep reinforcement learning includes:

[0041] A vehicle driving state data fusion module, which is used to deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on the new energy vehicle, and use the vehicle speed sensor, the motor speed sensor, and the battery state sensor to collect the vehicle state in real time during the real-time driving process of the new energy vehicle to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, so as to obtain the driving fusion data set of the new energy vehicle;

[0042] A vehicle gear operation model analysis module, which is used to obtain the current gear of a new energy vehicle and determine the state space vector by combining the corresponding driving vehicle speed, motor speed, battery power, road gradient and curvature in the new energy vehicle driving fusion data set at the current time, so as to obtain the state space vector of the new energy vehicle; taking the state space vector of the new energy vehicle as the state input corresponding to a preset deep reinforcement learning model, and using the deep reinforcement learning model to define the gear operation space of the new energy vehicle state space vector, so as to generate the gear shift operation space selection of the new energy vehicle, including the upshift, downshift and maintaining the current gear operations corresponding to the new energy vehicle;

[0043] A model decision reward function design module, which is used to design the corresponding vehicle gear decision reward function through the gear shift operation space selection of the new energy vehicle corresponding to the deep reinforcement learning model;

[0044] A vehicle driving gear decision control module, which is used to perform vehicle driving gear decision control on the corresponding state space vector of the new energy vehicle by using the deep reinforcement learning model based on the vehicle gear decision reward function, so as to select the optimal gear shift operation from the action space corresponding to the model according to the real-time collected vehicle state information, thereby generating the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

[0045] The beneficial effects of the present invention:

[0046] 1. The gear shifting decision-making method for new energy vehicles based on deep reinforcement learning proposed by the present invention, compared with the prior art, the beneficial effects of the present application are as follows: By deploying a vehicle speed sensor, a motor speed sensor, and a battery state sensor on a new energy vehicle and collecting real-time data, it can provide key data support for subsequent vehicle control. The vehicle speed sensor can monitor the driving speed of the vehicle in real time, the motor speed sensor can reflect the operating state of the motor, and the battery state sensor provides the remaining power and health state of the battery. Through the data of these sensors, the current operating state of the new energy vehicle can be accurately grasped. These data not only reflect the current driving state of the vehicle but can also be further combined with road information, especially changes in road slope and curvature. This step can obtain a comprehensive vehicle driving data set by monitoring the road slope and curvature in real time and fusing them with the vehicle's driving data. The fused data set not only includes vehicle speed, motor speed, and battery power but can also be dynamically adjusted according to road changes, enabling the vehicle to better adapt to different driving conditions, thereby improving driving efficiency and energy efficiency and enhancing the vehicle's adaptability and safety in complex conditions. Secondly, by obtaining the current gear of the new energy vehicle and combining real-time driving data and road information, an accurate state input can be provided for the deep reinforcement learning model. The gear of the new energy vehicle directly determines the characteristics of power output and the vehicle's response speed. A reasonable gear selection can effectively improve the vehicle's power performance and fuel efficiency. Through the vectorized representation of the current state space, multi-dimensional data such as vehicle speed, motor speed, battery power, road slope, and curvature can be integrated into a unified input as the state input of the deep reinforcement learning model. This method can not only cover all key state variables of the vehicle but also enable the model to automatically select the most appropriate gear action according to different working conditions, thereby reducing human intervention and gradually optimizing its decision-making ability for gear selection. As the training progresses, the model will gradually master the optimal gear shifting strategy under different driving conditions, improving the vehicle's driving comfort, power response, and energy efficiency performance. Then, designing a reasonable vehicle gear shifting decision-making reward function is the key to the effective application of deep reinforcement learning. The design of the reward function directly affects the training effect and decision-making accuracy of the model. A reasonable reward function can help the model clarify the optimization goal, such as improving driving efficiency, reducing energy consumption, extending battery life, and ensuring driving safety. By defining the reward function, the deep reinforcement learning model can be guided to develop in the optimal decision-making direction, encouraging the model to make gear shifting decisions that are most beneficial to the vehicle's performance under changing conditions. When designing the reward function, multiple factors are usually considered, such as the vehicle's energy consumption and driving smoothness. A well-designed reward function can not only enable the model to learn how to make reasonable gear selections according to the real-time vehicle state but also provide real-time feedback in a complex environment to optimize the vehicle's performance.Finally, through the deep reinforcement learning model and the designed reward function, new energy vehicles can perform precise gear shifting decision control. The vehicle continuously selects the optimal gear shifting strategy from the action space defined by the model according to real-time state information. This process can not only maximize the energy efficiency of the vehicle but also ensure the smooth operation of the vehicle under different driving conditions. Through the deep reinforcement learning model, the vehicle can make intelligent decisions based on different road conditions, driving styles, and energy requirements, thus achieving an optimized driving experience and energy efficiency management. Under different driving conditions, the model can judge whether to upshift, downshift, or maintain the current gear according to the input state space information. Each gear shifting decision is based on a comprehensive analysis of the current environment and vehicle state. Through this intelligent control strategy, new energy vehicles can achieve lower energy consumption and higher safety during actual driving, enabling them to make personalized and real-time gear adjustments in different driving environments, thereby avoiding energy loss in the gears of new energy vehicles.

[0047] 2. The new energy vehicle gear shifting decision control system based on deep reinforcement learning proposed by the present invention is generally composed of a vehicle driving state data fusion module, a vehicle gear shifting action model analysis module, a model decision reward function design module, and a vehicle driving gear shifting decision control module, and can implement any new energy vehicle gear shifting decision method described in the present invention. It is used to realize the new energy vehicle gear shifting decision method based on the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient new energy vehicle gear shifting decision control process based on deep reinforcement learning, thereby simplifying the operation process of the new energy vehicle gear shifting decision control system based on deep reinforcement learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objects, and advantages of the present invention will become more apparent:

[0049] Figure 1 It is a schematic flow chart of the steps of the new energy vehicle gear shifting decision method based on deep reinforcement learning of the present invention;

[0050] Figure 2 is Figure 1 a detailed schematic flow chart of step S1 in

[0051] Figure 3 is Figure 2 a detailed schematic flow chart of step S15 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0053] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus the repeated description thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0054] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0055] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a new energy vehicle gear shifting decision-making method based on deep reinforcement learning, and the method includes the following steps:

[0056] Step S1: By deploying a vehicle speed sensor, a motor speed sensor, and a battery state sensor on a new energy vehicle, and using the vehicle speed sensor, the motor speed sensor, and the battery state sensor to collect the vehicle state in real time during the corresponding real-time driving process of the new energy vehicle, so as to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, so as to obtain a driving fusion data set of the new energy vehicle;

[0057] Step S2: Obtain the current gear of the new energy vehicle and determine the state space vector by combining the corresponding driving speed, motor speed, battery power, road slope, and curvature in the new energy vehicle driving fusion dataset at the current time, so as to obtain the state space vector of the new energy vehicle; use the state space vector of the new energy vehicle as the state input corresponding to the preset deep reinforcement learning model, and use the deep reinforcement learning model to define the gear action space for the state space vector of the new energy vehicle, so as to generate the gear shifting action space selection of the new energy vehicle, including the upshift, downshift, and maintaining the current gear actions corresponding to the new energy vehicle;

[0058] Step S3: Design a corresponding vehicle gear decision reward function through the gear shifting action space selection of the new energy vehicle corresponding to the deep reinforcement learning model;

[0059] Step S4: Based on the vehicle gear decision reward function, use the deep reinforcement learning model to perform vehicle driving gear decision control on the corresponding state space vector of the new energy vehicle, so as to select the optimal gear shifting action from the action space corresponding to the model according to the real-time collected vehicle state information, and generate the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

[0060] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the step flow of the new energy vehicle gear decision method based on deep reinforcement learning of the present invention. In this example, the new energy vehicle gear decision method based on deep reinforcement learning includes the following steps:

[0061] Step S1: Deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on the new energy vehicle, and use the vehicle speed sensor, the motor speed sensor, and the battery state sensor to collect the vehicle state in real time during the real-time driving process of the new energy vehicle, so as to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, so as to obtain the new energy vehicle driving fusion dataset;

[0062] In the embodiments of the present invention, by installing a vehicle speed sensor, a motor speed sensor, and a battery state sensor, the operating data of a new energy vehicle is collected in real time. The output shaft of the gearbox is monitored by the vehicle speed sensor, and the vehicle speed is calculated in combination with the wheel speed sensor, so that the driving speed of the new energy vehicle can be accurately monitored. The motor speed is monitored by the motor speed sensor, and the resolver signal corresponding to the monitored motor speed is decoded into the motor speed for real-time collection of the motor speed. The battery state sensor (such as BMS) is installed inside the battery pack and is used to monitor the power state, charge and discharge rate, and battery health of the battery. Through these sensors, the real-time data of the vehicle speed, motor speed, and battery power can be collected during the vehicle driving. In addition to the real-time data collection of the vehicle, it is also necessary to obtain the slope and curvature information of the current driving section through external measuring devices, such as a ground slope sensor or a navigation system. The slope reflects the degree of rise or fall of the road, while the curvature reflects the bending condition of the road. These factors directly affect the power demand of the vehicle. These information is fused with the driving data of the vehicle according to the corresponding vehicle driving road sites to generate a fusion data set including the vehicle speed, motor speed, battery power, road slope, and curvature, providing important input data for subsequent gear decisions, and finally obtaining the driving fusion data set of the new energy vehicle.

[0063] Step S2: Obtain the current gear of the new energy vehicle and determine the state space vector by combining the corresponding driving vehicle speed, motor speed, battery power, road slope, and curvature in the driving fusion data set of the new energy vehicle at the current time to obtain the state space vector of the new energy vehicle; use the state space vector of the new energy vehicle as the state input corresponding to a preset deep reinforcement learning model, and use the deep reinforcement learning model to define the gear action space for the state space vector of the new energy vehicle to generate a gear shift action space selection for the new energy vehicle, including actions such as upshifting, downshifting, and maintaining the current gear of the new energy vehicle;

[0064] In an embodiment of the present invention, by obtaining the current gear state of a new energy vehicle, the current gear information is usually read through the vehicle's gear control system, and combined with the real-time driving data obtained previously, a state space vector of the new energy vehicle is constructed. The state space vector contains input data in multiple dimensions, such as the current vehicle speed, motor speed, battery power, road slope and curvature, etc. By combining this information, a complete state description vector is formed as the input of the deep reinforcement learning model. The deep reinforcement learning model is trained and inferred through these state space vectors. The goal of the model is to generate a gear selection suitable for the current driving condition by observing the state space. According to the current vehicle driving state (such as low speed or low battery power), the model will evaluate the matching degree between the current gear and the vehicle performance, and select the most appropriate action according to the set reward mechanism. The action space includes upshifting, downshifting, and maintaining the current gear. The deep reinforcement learning model finds the optimal decision among these choices, and finally generates a gear shifting action space selection for the new energy vehicle.

[0065] Step S3: Design a corresponding vehicle gear decision reward function through the gear shifting action space selection of the new energy vehicle corresponding to the deep reinforcement learning model;

[0066] In an embodiment of the present invention, the advantages and disadvantages of each decision-making action are evaluated by the performance of the gear shifting action space selection of the new energy vehicle in different states. Specifically, when the gear action selected by the deep reinforcement learning model can reduce energy consumption and improve power performance, the reward function will give a positive reward. The positive reward appears, for example, when the vehicle speed is low and downshifting is required to improve the motor efficiency, or in the efficient operation state, upshifting to reduce the motor speed, thereby improving the energy utilization efficiency. On the contrary, when the gear action selected by the deep reinforcement learning model results in excessive energy consumption or power performance decline, the reward function will give a negative reward. For example, during high-speed driving, due to low battery power or high motor speed, the model selects downshifting, which will lead to excessive energy consumption and affect the power output, thus bringing a negative reward. Through this positive and negative reward mechanism, the model can gradually learn how to optimize gear selection under different driving conditions, and finally design and generate a corresponding vehicle gear decision reward function.

[0067] Step S4: Based on the vehicle gear decision reward function, use the deep reinforcement learning model to perform vehicle driving gear decision control on the corresponding state space vector of the new energy vehicle, so as to select the optimal gear shifting action from the action space corresponding to the model according to the real-time collected vehicle state information, and generate the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

[0068] In the embodiments of the present invention, a deep reinforcement learning model is used to make actual gear decisions based on the real-time state information of the vehicle and a designed reward function. The model evaluates possible gear selections based on the current vehicle state vector, combines the reward function, and selects the optimal gear shifting action. For example, in congested traffic conditions, due to the low vehicle speed, the model determines whether to downshift based on the insufficient vehicle speed and motor speed to ensure sufficient power output and maintain driving smoothness. When the vehicle is driving on a highway, with a high vehicle speed, sufficient battery power, and high energy consumption, the model will select to upshift to reduce the motor speed, thereby improving the energy utilization efficiency of the vehicle and avoiding unnecessary energy consumption. In flat road conditions, when the vehicle speed is moderate, the battery power consumption is normal, and gear shifting does not have an obvious impact on power output, the model may choose to maintain the current gear to maintain the stable operation of the vehicle and avoid unnecessary power fluctuations and motor losses. Through this gear decision control strategy based on deep reinforcement learning, new energy vehicles can automatically select the optimal gear according to the real-time driving environment and state information, thereby optimizing the power performance and energy efficiency performance, and finally generating the optimal gear decision control strategy for new energy vehicles under different driving conditions.

[0069] Further, step S1 includes the following steps:

[0070] Step S11: Deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on the new energy vehicle, and use the vehicle speed sensor to collect the real-time driving speed of the new energy vehicle during the corresponding real-time driving process to obtain the driving speed of the new energy vehicle;

[0071] Step S12: Use the motor speed sensor to collect the real-time motor speed of the new energy vehicle during the corresponding real-time driving process to obtain the motor speed of the new energy vehicle;

[0072] Step S13: Use the battery state sensor to collect the real-time battery power of the new energy vehicle during the corresponding real-time driving process to obtain the battery power of the new energy vehicle;

[0073] Step S14: Obtain the road slope and curvature corresponding to different driving road points of the new energy vehicle;

[0074] Step S15: Perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road points of the new energy vehicle to obtain the driving fusion data set of the new energy vehicle.

[0075] As an embodiment of the present invention, refer to Figure 2 as shown, for Figure 1Schematic diagram of the detailed step flow of step S1. In this embodiment, step S1 includes the following steps:

[0076] Step S11: Deploy a vehicle speed sensor, a motor speed sensor, and a battery status sensor on a new energy vehicle, and use the vehicle speed sensor to collect the real-time driving speed of the new energy vehicle during the corresponding real-time driving process to obtain the driving speed of the new energy vehicle.

[0077] In the embodiment of the present invention, corresponding vehicle speed sensors, motor speed sensors, and battery status sensors are installed and deployed on a new energy vehicle to collect the corresponding data during the driving process of the new energy vehicle in real time, and the deployed vehicle speed sensor is used to collect the real-time driving speed data. For example, by monitoring the output shaft of the transmission through the vehicle speed sensor and combining with the wheel speed sensor to calculate the vehicle speed, the driving speed of the new energy vehicle can be accurately monitored. The vehicle speed sensor transmits the data to the vehicle-mounted control system through the CAN bus, providing the driving speed data to the vehicle-mounted system every second. During the vehicle driving process, the sensor can update the vehicle speed value in real time and transmit the data to the central computing unit for processing, and finally obtain the driving speed of the new energy vehicle.

[0078] Step S12: Use the motor speed sensor to collect the real-time motor speed of the new energy vehicle during the corresponding real-time driving process to obtain the motor speed of the new energy vehicle.

[0079] In the embodiment of the present invention, the motor speed is monitored by the motor speed sensor, and the resolver signal corresponding to the monitored motor speed is decoded into the motor speed for real-time collection of the motor speed. It obtains the real-time speed of the motor by monitoring the magnetic field change generated by the rotation of the motor shaft. The data acquisition system transmits the real-time motor speed to the control unit through the vehicle-mounted CAN bus. The real-time data of the motor speed is an important basis for evaluating the motor power output, driving efficiency, and energy consumption. Through the motor speed information collected by the sensor, the control system can evaluate the working state of the motor in real time, and thus provide a basis for gear shift adjustment or energy optimization, and finally obtain the motor speed of the new energy vehicle.

[0080] Step S13: Use the battery status sensor to collect the real-time battery power of the new energy vehicle during the corresponding real-time driving process to obtain the battery power of the new energy vehicle.

[0081] In the embodiment of the present invention, in order to monitor the battery power of a new energy vehicle in real time, a battery status sensor (BMS, battery management system) is used to collect the real-time battery power. The battery status sensor evaluates the remaining battery power by monitoring key parameters such as the voltage, current, and temperature of the battery pack. The battery management system processes these parameters through algorithms, calculates the percentage of the remaining battery power of the current battery, and transmits it to the central control unit via the in-vehicle CAN bus. This power data can not only reflect the charging status of the battery in real time, but also evaluate the battery health status under different working conditions, and finally obtain the battery power of the new energy vehicle.

[0082] Step S14: Obtain the road slope and curvature corresponding to different driving road points of the new energy vehicle.

[0083] In the embodiment of the present invention, the slope and curvature information of the driving road is obtained through in-vehicle sensors. The road slope can be calculated by combining the installed acceleration sensor and gyroscope with the geographical location information in the in-vehicle navigation system. The curvature is obtained by combining the in-vehicle GPS system and the real-time positioning data of the road surface marking points with sensors to evaluate the turning radius and road curvature during vehicle driving. These information are integrated into the in-vehicle computing platform through the high-precision map and road condition data interface. As the vehicle drives on different road sections, the real-time obtained road slope and curvature data can reflect the driving difficulty of different sections, and finally obtain the road slope and curvature corresponding to different driving road points of the new energy vehicle.

[0084] Step S15: Perform vehicle data fusion processing on the driving speed, motor speed, and battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road points of the new energy vehicle to obtain a driving fusion data set of the new energy vehicle.

[0085] In the embodiment of the present invention, vehicle data fusion processing is performed on the data collected by multiple sensors (including vehicle speed, motor speed, battery power, road slope, and curvature) to obtain a more comprehensive driving fusion data set of the new energy vehicle. First, the in-vehicle control system performs time synchronization processing on the data from each sensor to ensure that the data collected by each sensor corresponds to the driving state at the same moment. Then, through a fusion algorithm (such as Kalman filtering or weighted average method), the collected data is weighted and integrated to obtain a fused vehicle driving data set. This data set contains information such as the driving speed, motor speed, battery power, road slope, and curvature of the vehicle, which is used for decision-making training by the deep reinforcement learning model. Data fusion processing not only improves the accuracy of the data, but also effectively eliminates noise interference, providing accurate input data for subsequent gear decision optimization, and finally obtaining a driving fusion data set of the new energy vehicle.

[0086] Further, step S15 includes the following steps:

[0087] Step S151: Perform vehicle data Kalman filtering on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle to obtain the noise-reduced driving speed of the vehicle, the noise-reduced motor speed of the vehicle, and the noise-reduced battery power of the vehicle;

[0088] Step S152: By constructing a vehicle dynamics model and a battery model corresponding to the new energy vehicle, and based on the vehicle dynamics model and the battery model, perform driving state correlation analysis on the noise-reduced driving speed of the vehicle, the noise-reduced motor speed of the vehicle, and the noise-reduced battery power of the vehicle to obtain a set of new energy vehicle driving state correlation data;

[0089] Step S153: Obtain the corresponding vehicle driving road space sites through the road gradient and curvature corresponding to different driving road sites of the new energy vehicle, and based on the vehicle driving road space sites, perform driving space synchronous mapping on the set of new energy vehicle driving state correlation data to obtain the corresponding vehicle driving state data set at the same driving road site, including driving speed, motor speed, and battery power;

[0090] Step S154: Based on the road gradient and curvature corresponding to different driving road sites of the new energy vehicle, perform vehicle data fusion processing on the corresponding vehicle driving state data set at the same driving road site to obtain the new energy vehicle driving fusion data set.

[0091] As an embodiment of the present invention, referring to Figure 3 shown, it is Figure 2 a detailed step flow diagram of step S15 in

[0092] Step S151: Perform vehicle data Kalman filtering on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle to obtain the noise-reduced driving speed of the vehicle, the noise-reduced motor speed of the vehicle, and the noise-reduced battery power of the vehicle;

[0093] In an embodiment of the present invention, Kalman filtering is performed on the driving speed, motor speed, and battery power of a new energy vehicle. To this end, various data of the new energy vehicle during driving are first collected. These data are affected by noises such as environmental factors and sensor errors. Kalman filtering is an optimal recursive filtering method that can suppress the noises of these data and accurately estimate the actual driving state of the vehicle. The specific operation is as follows: First, a Kalman filter model is established, and the driving speed, motor speed, and battery power of the vehicle are input into the filter as state variables. Through the Kalman gain matrix, the observed values input each time are weighted and updated to filter out the noises therein, and more accurate predicted values of the vehicle speed, motor speed, and battery power are obtained. At this time, the filter continuously updates the prediction result according to the input current state and measurement data, and the output vehicle speed, motor speed, and battery power are the "noise-reduced" data, that is, the smoothed data after removing the noises, and finally the noise-reduced driving speed of the vehicle, the noise-reduced speed of the vehicle motor, and the noise-reduced power of the vehicle battery are obtained.

[0094] Step S152: By constructing a vehicle dynamics model and a battery model corresponding to the new energy vehicle, and performing a driving state correlation analysis on the noise-reduced driving speed of the vehicle, the noise-reduced speed of the vehicle motor, and the noise-reduced power of the vehicle battery based on the vehicle dynamics model and the battery model, a set of new energy vehicle driving state correlation data is obtained;

[0095] In an embodiment of the present invention, based on the dynamics model and battery model of the new energy vehicle, it is necessary to analyze and process the previously obtained "noise-reduced" data to further establish a set of vehicle driving state correlation data. Specifically, first, a dynamics model of the new energy vehicle is established, including relevant parameters such as the vehicle's acceleration, braking, and traction force. Secondly, a battery model is constructed to describe the relationships between the charge and discharge characteristics, voltage, current, and capacity of the battery. Through these two models, the relationships between the vehicle's driving state and its dynamics and battery state can be established in combination with the vehicle speed, motor speed, and battery power. For example, at a given driving speed and motor speed, the energy consumption rate of the vehicle can be predicted using the dynamics model; in combination with the battery model, the change in battery power and the battery discharge efficiency can be evaluated. Through these steps, a detailed set of vehicle driving state correlation data can be obtained, including the specific relationships between various dynamic behaviors of the vehicle and battery performance, and finally a set of new energy vehicle driving state correlation data is obtained.

[0096] Step S153: Obtain the corresponding vehicle driving road space sites through the road gradient and curvature corresponding to different driving road sites of the new energy vehicle, and perform a driving space synchronous mapping on the set of new energy vehicle driving state correlation data based on the vehicle driving road space sites to obtain a set of vehicle driving states corresponding to the same driving road site, including the driving speed, motor speed, and battery power;

[0097] In an embodiment of the present invention, based on the driving position of a new energy vehicle on different road sections and in combination with the slope and curvature information of the road, the spatial position points of the vehicle during driving are obtained. For this purpose, the specific position of the vehicle can be obtained through a real-time positioning system (such as GPS) and road terrain data (including parameters such as road slope and curvature). At each position point, in combination with the slope and curvature of the road, the real-time driving state of the vehicle is calculated, especially the vehicle speed, motor speed, and battery power. In this process, it is first necessary to determine the slope and curvature of the road, and use this information to correct the dynamic behavior and energy consumption of the vehicle. For example, when the vehicle is driving on a slope, additional traction is required, and the discharge rate of the battery will be different; while at a turning point, the stability and driving strategy of the vehicle will be affected. By comprehensively considering these factors, an accurate driving data set at the same road position is obtained, including vehicle speed, motor speed, and battery power, and these data are mapped to the corresponding spatial position points, and finally a vehicle driving state data set corresponding to the same driving road position point is obtained.

[0098] Step S154: Based on the road slope and curvature corresponding to different driving road position points of the new energy vehicle, perform vehicle data fusion processing on the vehicle driving state data set corresponding to the same driving road position point to obtain a new energy vehicle driving fusion data set.

[0099] In an embodiment of the present invention, by fusing the above-mentioned vehicle driving state data set based on the slope and curvature information of the new energy vehicle on different driving road position points. Specifically, first, information such as vehicle speed, motor speed, and battery power needs to be extracted from the driving data of different road sections, and data weighted fusion is performed in combination with the slope and curvature of the road. Through weighted fusion, the influence of the road can be comprehensively considered, the state values in each data set can be adjusted, the deviation caused by the change of road conditions can be eliminated, and more accurate overall driving state data can be obtained. In the process of fusion processing, weighted average, Kalman filter or other data fusion algorithms can be used to adjust the weight of each data point according to the influence of road slope and curvature. For example, when the vehicle is driving on a steep slope or a section with a large curvature, the weights of vehicle speed, motor speed, and battery power need to be increased to reflect the actual energy consumption and performance state of the vehicle under these conditions. Through this method, the obtained fusion data set not only contains accurate vehicle speed, motor speed, and battery power data, but also can reflect the influence of road slope and curvature on the vehicle state, and finally a new energy vehicle driving fusion data set is obtained.

[0100] Further, step S2 includes the following steps:

[0101] Step S21: Obtain the current gear of the new energy vehicle;

[0102] In an embodiment of the present invention, the current gear of a new energy vehicle is obtained in real time through in-vehicle sensors and a control system. A gear sensor is provided in the vehicle's power transmission system, which can accurately detect the current gear of the vehicle. After the vehicle's in-vehicle computer system receives the sensor signal, it will automatically identify the current gear state and record it in the system for subsequent operations and evaluations. In this process, the acquisition of the gear mainly depends on the electronic control unit (ECU) embedded in the vehicle and its cooperation with the transmission system. The goal of this step is to ensure the real-time and accurate acquisition of the current gear information as the input for subsequent calculations and decisions, and finally obtain the current gear of the new energy vehicle.

[0103] Step S22: Determine the state space vector by combining the current gear of the new energy vehicle with the corresponding driving speed, motor speed, battery power, road slope, and curvature in the new energy vehicle driving fusion data set at the current time, so as to obtain the state space vector of the new energy vehicle;

[0104] In an embodiment of the present invention, by combining the driving fusion data set of the new energy vehicle, information such as the vehicle speed, motor speed, battery power, road slope, and curvature of the vehicle at the current time is obtained. The new energy vehicle driving fusion data is processed by the foregoing steps and combined with a communication system (such as GPS) to provide vehicle driving road condition information. The battery power is calculated by the battery management system (BMS), and the road slope and curvature can be obtained through a high-precision map and a GPS module. Combine these real-time obtained values with the current gear to form the state space vector of the new energy vehicle. Specifically, the state space vector is formed by arranging each state value (vehicle speed, motor speed, battery power, road slope, curvature, etc.) in a certain time sequence to form a multi-dimensional vector describing the current vehicle state, and finally obtain the state space vector of the new energy vehicle.

[0105] Step S23: Divide the state space vector of the new energy vehicle into each discrete vehicle state space vector according to the corresponding time interval, and determine the corresponding vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value in each time range according to each discrete vehicle state space vector;

[0106] In an embodiment of the present invention, the previously determined state space vector of the new energy vehicle is discretized according to a predetermined time interval. Specifically, the system divides the state space vector into discrete time periods according to the time step. For example, each few seconds or each few minutes is a time interval. The state space vector within each time interval represents the exact state of the vehicle at that moment. According to these discrete state space vectors, the corresponding vehicle speed state value, motor speed state value, battery power state value, road slope state value, and curvature state value in each time period are calculated. For the vehicle speed, motor speed, and battery power, etc., the state value represents the measured value of these variables within a specific time period; for the slope and curvature, the state value represents the environmental information of the vehicle driving route. This discretization process enables the dynamic behavior of the vehicle to be quantified and further evaluated and decision-making to finally determine the corresponding vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value in each time range.

[0107] Step S24: Take the vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value corresponding to each time range as the state input corresponding to the preset deep reinforcement learning model, and perform gear power and energy consumption evaluation calculations on the current gear of the new energy vehicle based on the vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value corresponding to each time range to obtain the gear power performance state value of the new energy vehicle and the gear energy loss of the new energy vehicle;

[0108] In an embodiment of the present invention, by using the previously obtained vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value as the input of the deep reinforcement learning model, the preset deep reinforcement learning model is applied to perform power and energy consumption evaluation on the current gear of the new energy vehicle. Specifically, when implemented, the deep reinforcement learning model is designed to process through a multi-layer neural network according to the real-time state input of the vehicle (i.e., each state value) to obtain the gear power performance state value and energy loss value. The gear power performance state value mainly reflects the power output ability of the vehicle in the current gear and evaluates whether the vehicle can meet the current driving conditions. The energy loss reflects the energy consumption situation in the current gear, considering factors such as vehicle power demand, driving environment (such as slope and curvature), and battery efficiency. This process requires training the deep reinforcement learning model so that it can output the corresponding gear power performance and energy consumption evaluation results according to the state space vector of the vehicle, and finally obtain the gear power performance state value of the new energy vehicle and the gear energy loss of the new energy vehicle.

[0109] Step S25: Define the gear action space for the power performance state value of the new energy vehicle gear and the energy loss of the new energy vehicle gear by using a deep reinforcement learning model, so as to generate the gear shifting action space selection of the new energy vehicle, including the upshift, downshift and maintaining the current gear actions corresponding to the new energy vehicle.

[0110] In the embodiment of the present invention, by defining the gear shifting action space of the new energy vehicle according to the gear power performance state value and energy loss calculated above. First, the model uses the gear power performance state value and energy loss as the basis for decision-making, and sets the action space as upshift, downshift and maintaining the current gear. Specifically, when the gear power performance state value is large and the gear energy loss is within an acceptable range, the deep reinforcement learning model determines that the vehicle is suitable for upshifting to improve driving efficiency; when the gear power performance state value is small and the energy loss is large, the model determines that downshifting should be performed to reduce unnecessary energy consumption; when the gear power and energy loss reach a balance, the model determines that the current gear should be maintained to avoid additional energy waste caused by frequent gear shifting. Each time a decision is made, the model will evaluate the current power demand, energy consumption and driving environment, and select the optimal gear action. Through this decision-making process based on deep reinforcement learning, intelligent control of gear shifting can be achieved under different driving conditions, optimizing the energy efficiency and driving experience of the new energy vehicle, and finally generating the gear shifting action space selection of the new energy vehicle, including the upshift, downshift and maintaining the current gear actions corresponding to the new energy vehicle.

[0111] Further, the evaluation calculation of the gear power and energy consumption of the current gear of the new energy vehicle based on the vehicle speed state value, rotation speed state value, battery state value, slope state value and curvature state value corresponding to each time range in step S24 includes the following steps:

[0112] Based on the vehicle speed state value, rotation speed state value and battery state value corresponding to each time range, use the gear power performance evaluation calculation formula to perform the gear power evaluation calculation on the current gear of the new energy vehicle, and obtain the gear power performance state value of the new energy vehicle;

[0113] In the embodiment of the present invention, by combining the initial value of the time range, the termination value of the time range, the vehicle speed state value, the rotation speed state value, the battery state value, the maximum vehicle speed of the new energy vehicle in the current gear, the maximum rotation speed of the motor, the maximum battery power, the vehicle speed power contribution coefficient, the motor rotation speed power contribution coefficient, the battery power contribution coefficient, the power decay time constant, the time exponential decay factor and related parameters, a suitable gear power performance evaluation calculation formula is constructed to perform the gear power evaluation calculation, so as to quantitatively calculate the power performance state value of the vehicle in the current gear, that is, the energy output ability of the vehicle in this gear, and finally obtain the gear power performance state value of the new energy vehicle.

[0114] Preferably, according to the power performance state value of the new energy vehicle gear, simulate and calculate the vehicle gear power output of the new energy vehicle in the corresponding time range, and calculate the vehicle gear power peak corresponding to the new energy vehicle according to the vehicle gear power output.

[0115] In the embodiment of the present invention, based on the gear power performance state value calculated in the previous step and combined with the current gear of the vehicle, simulate and calculate the vehicle gear power output of the new energy vehicle in this time range. The vehicle gear power output usually represents the power output value that the vehicle can provide in a specific gear. The calculation of this output requires combining the vehicle's power transmission system and real-time control system. The specific calculation method can be carried out through dynamic simulation software. According to the change of the power output, further calculate the power peak of the vehicle in the current gear. This process mainly depends on the actual driving state and power output curve of the vehicle. When simulating and calculating, it is necessary to comprehensively consider the vehicle speed change, acceleration and load conditions to determine the maximum power output at different time points, and finally obtain the vehicle gear power peak corresponding to the new energy vehicle.

[0116] Preferably, based on the slope state value and the curvature state value, analyze the influence of the current gear of the new energy vehicle on energy consumption, and obtain the energy consumption influence coefficient of the new energy vehicle gear.

[0117] In the embodiment of the present invention, by obtaining the current slope state value and curvature state value, these values are usually collected and calculated in real time by in-vehicle sensors and navigation systems. The slope state value describes the slope condition of the road section where the vehicle is located, and the curvature state value reflects the degree of curvature of the vehicle's driving route. According to these data, analyze the influence of the current gear of the new energy vehicle on energy consumption. Through a mathematical model, analyze the influence degree of the slope and curvature on the vehicle's energy consumption. When the slope is large, the vehicle needs to overcome greater gravity resistance. When the curvature is large, the vehicle needs more power to maintain steering stability. Therefore, these factors will affect the energy consumption of the vehicle in the current gear. Combining these analysis results, obtain an energy consumption influence coefficient of the gear. This coefficient specifically represents the energy consumption change rate of the vehicle in this gear under a specific driving environment, that is, this coefficient is specifically , where is the slope state value, is the energy consumption of the vehicle in this gear, is the total energy consumption of the vehicle during the whole driving process, is the curvature state value, and finally obtain the energy consumption influence coefficient of the new energy vehicle gear.

[0118] Preferably, based on the power peak of the vehicle gear and the energy consumption influence coefficient of the new energy vehicle gear, the energy consumption of the new energy vehicle in the current gear is evaluated and calculated using the vehicle energy loss evaluation calculation formula to obtain the energy loss of the new energy vehicle gear.

[0119] In the embodiment of the present invention, by combining the initial value of the time range, the termination value of the time range, the termination value of the time range, the vehicle speed state value, the rotational speed state value, the battery state value, the power energy loss influence weight coefficient, the power peak of the vehicle gear, the energy consumption influence coefficient of the new energy vehicle gear, and related parameters, a suitable vehicle energy loss evaluation calculation formula is formed for evaluating and calculating the energy loss, so as to quantitatively calculate the energy loss value of the new energy vehicle in the current gear, and finally obtain the energy loss of the new energy vehicle gear.

[0120] Among them, the vehicle energy loss evaluation calculation formula is specifically:

[0121] ;

[0122] In the formula, is the energy loss of the new energy vehicle gear, is the initial value of the time range, is the termination value of the time range, is the time variable parameter, is the vehicle speed state value of the new energy vehicle at time ; is the rotational speed state value of the new energy vehicle at time ; is the battery state value of the new energy vehicle at time ; is the power energy loss influence weight coefficient, is the power peak of the vehicle gear, is the energy consumption influence coefficient of the new energy vehicle gear, is the correction coefficient of the energy loss of the new energy vehicle gear.

[0123] The present invention obtains a calculation formula for evaluating vehicle energy loss through the use of a specific mathematical model and verification, which is used to calculate the energy consumption of a new energy vehicle in the current gear. By considering dynamic states such as vehicle speed, rotational speed, and battery power within different time ranges, this calculation formula for vehicle energy loss can more accurately simulate the energy consumption of new energy vehicles during actual driving. It is not only based on static data, but also evaluates energy consumption by considering the dynamic performance (such as vehicle speed and rotational speed) and battery power changes of the vehicle at specific time points. This can help analyze the energy consumption of the vehicle under actual working conditions and be more in line with the actual driving scenario. In this formula, the mutual relationships of multiple factors such as the power peak value of the vehicle, vehicle speed, rotational speed, and battery power state are considered. Through the comprehensive calculation of these variables, a more accurate energy consumption evaluation can be obtained, avoiding the one-sidedness of using a single parameter for energy consumption evaluation. For example, vehicle speed and rotational speed directly affect power output, while the battery power state affects the actual consumption of the battery. In this formula, the time variable and the weighting factor reflect the weighted influence on the states at different moments in the time series. This weighting takes into account the changes in energy consumption over time, making the evaluation of vehicle energy consumption more accurate, especially for working conditions where energy consumption is concentrated or concentrated in specific time periods. In this way, the actual energy consumption of new energy vehicles under different working conditions can be analyzed in more detail. Through the analysis of the influence of the slope state value and the curvature state value on vehicle energy consumption, the formula can capture the influence of the driving environment on energy consumption. For example, when going uphill, the vehicle needs more power to overcome gravity, resulting in increased energy consumption; while a section with a larger curvature will cause frequent acceleration and deceleration, thus affecting the power consumption of the vehicle. The energy consumption influence coefficient in the formula reflects the influence of these external factors on energy consumption, thus evaluating energy consumption more comprehensively. In addition, the introduction of a correction coefficient can finely adjust the calculation process in actual applications to ensure that the calculation results are more in line with the actual situation. Through this correction coefficient, the deviation between theoretical calculation and actual test can be corrected, making the evaluation results more accurate. In summary, this formula can fully consider the energy loss of new energy vehicle gears Initial value of the time range End value of the time range Time variable parameter At time Vehicle speed state value of the new energy vehicle At time Rotational speed state value of the new energy vehicle At time Battery power state value of the new energy vehicle Power energy loss influence weight coefficient Vehicle gear power peak value New energy vehicle gear energy consumption influence coefficient Correction coefficient for new energy vehicle gear energy loss , according to the energy loss of new energy vehicle gears and the mutual correlation relationship with the above parameters constitutes a functional relationship , this formula can realize the energy consumption evaluation calculation process of the current gear of new energy vehicles. At the same time, through the correction coefficient of the energy loss of new energy vehicle gears the introduction of can be adjusted according to the error situation in the calculation process, so as to improve the accuracy and applicability of the vehicle energy loss evaluation calculation formula.

[0124] Furthermore, the calculation formula for evaluating the power performance of the gear is specifically as follows:

[0125] ;

[0126] In the formula, is the power performance state value of the new energy vehicle gear, is the initial value of the time range, is the termination value of the time range, is the time variable parameter, is the vehicle speed state value of the new energy vehicle at time , is the maximum vehicle speed of the new energy vehicle in the current gear, is the vehicle speed power contribution coefficient, is the rotational speed state value of the new energy vehicle at time , is the maximum motor rotational speed of the new energy vehicle in the current gear, is the motor rotational speed power contribution coefficient, is the battery state value of the new energy vehicle at time , is the maximum battery charge of the new energy vehicle in the current gear, is the battery charge power contribution coefficient, is the power decay time constant of the new energy vehicle in the current gear, is the time exponential decay factor, is the correction coefficient of the power performance state value of the new energy vehicle gear.

[0127] The present invention has obtained a gear power performance evaluation calculation formula through the use of a specific mathematical model and verification, which is used to calculate the gear power evaluation of the current gear of a new energy vehicle. This gear power performance evaluation calculation formula takes into account multiple key parameters, including vehicle speed, rotational speed, and state of charge. Through this multi-dimensional evaluation, the power performance of a new energy vehicle at a specific gear can be more accurately reflected, avoiding errors that may be caused by a single indicator. For example, the influence of vehicle speed and rotational speed reflects the actual effect of power output, while the state of charge represents the available energy of the battery. Time integration is used in the formula, and a time decay factor and a power decay time constant are introduced, which enables the formula to consider the change of time and the decay effect of the battery / motor. For electric vehicles, as the usage time increases, the battery charge and motor efficiency may decay. Therefore, this weighted time decay can better simulate the actual power performance. By normalizing the vehicle speed, rotational speed, and state of charge with their maximum values, the formula can accurately reflect the actual contribution of each parameter. This processing method helps to avoid performance differences among different vehicles under different parameters, making the evaluation process universal and comparable. The energy efficiency of an electric vehicle is usually closely related to power output. Through the coefficients in the formula, the contributions of vehicle speed, rotational speed, and state of charge to power output can be quantified, and the evaluation results provide data support for subsequent energy consumption analysis, helping to optimize energy efficiency management. By analyzing the power output amount of the vehicle and the influence coefficients in subsequent steps, the energy loss of an electric vehicle under different driving conditions can be predicted, which has very important guiding significance for the optimization of the energy management system, especially in the case of long-term high load or low battery charge. The formula includes multiple adjustment coefficients, which can be adjusted individually according to specific driving conditions. Therefore, this calculation method can not only provide power performance evaluation for different vehicle models, but also be adjusted and optimized in real time according to different driving environments, road conditions, and battery states, thereby improving the accuracy of the evaluation results. In summary, the formula fully considers the gear power performance state value of a new energy vehicle , the initial value of the time range , the termination value of the time range , the time variable parameter , the vehicle speed state value of the new energy vehicle at time , the maximum vehicle speed of the new energy vehicle in the current gear , the vehicle speed power contribution coefficient , the rotational speed state value of the new energy vehicle at time , the maximum motor rotational speed of the new energy vehicle in the current gear , the motor rotational speed power contribution coefficient , the state of charge value of the new energy vehicle at time ​​​ , the maximum battery power of the new energy vehicle in the current gear , the power contribution coefficient of the battery power , the power decay time constant of the new energy vehicle in the current gear , the time exponential decay factor , the correction coefficient of the power performance state value of the new energy vehicle gear , according to the power performance state value of the new energy vehicle gear and the mutual correlation relationships between the above parameters constitute a functional relationship , this formula can realize the gear power evaluation calculation process of the new energy vehicle in the current gear. At the same time, through the correction coefficient of the power performance state value of the new energy vehicle gear the introduction of can be adjusted according to the error situation that appears in the calculation process, so as to improve the accuracy and applicability of the gear power performance evaluation calculation formula.

[0128] Further, the definition of the gear action space described in step S25 is specifically that when the power performance state value is large and the gear energy loss is within an acceptable range, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as an upshift action; when the power performance state value is insufficient and the gear energy loss is large, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as a downshift action; when the power performance state value and the gear energy loss are in a balanced state, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as maintaining the current gear action.

[0129] Further, the vehicle gear decision reward function described in step S3 is specifically that when the action gear selected by the deep reinforcement learning model causes a reduction in energy consumption and an enhancement in power performance, a positive gear decision reward is given; when the action gear selected by the deep reinforcement learning model causes excessive energy consumption and a weakening in power performance, affecting the driving smoothness of the new energy vehicle, a negative gear decision reward is given.

[0130] Further, the optimal gear decision control strategy corresponding to different driving conditions described in step S4 is specifically that when the vehicle is driving in a congested road condition, the model judges whether to downshift to maintain the corresponding power output and smoothness of the vehicle according to the insufficient vehicle speed and motor speed; when the vehicle is driving in a high-speed road condition, the model judges whether to upshift to reduce the motor speed and improve the energy utilization efficiency according to the sufficient battery power and excessive energy consumption; and when the vehicle is driving in a gentle road condition, the model judges whether to maintain the current gear to maintain the stable operation of the vehicle and avoid unnecessary power fluctuations and motor losses according to the normal battery power consumption and the fact that gear shifting will not bring obvious power improvement or energy consumption reduction.

[0131] Furthermore, the present invention also provides a new energy vehicle gear shifting decision control system based on deep reinforcement learning, which is used to execute the new energy vehicle gear shifting decision method based on deep reinforcement learning as described above. The new energy vehicle gear shifting decision control system based on deep reinforcement learning includes:

[0132] A vehicle driving state data fusion module, which is used to deploy a vehicle speed sensor, a motor speed sensor, and a battery state sensor on a new energy vehicle, and use the vehicle speed sensor, the motor speed sensor, and the battery state sensor to collect the vehicle state in real time during the corresponding real-time driving process of the new energy vehicle, so as to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to different driving road sites of the new energy vehicle, and perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle, and the battery power of the new energy vehicle based on the road slope and curvature corresponding to different driving road sites of the new energy vehicle, so as to obtain a driving fusion data set of the new energy vehicle;

[0133] A vehicle gear action model analysis module, which is used to obtain the current gear of the new energy vehicle and determine the state space vector by combining the driving speed, motor speed, battery power, road slope, and curvature corresponding to the driving fusion data set of the new energy vehicle at the current time, so as to obtain the state space vector of the new energy vehicle; use the state space vector of the new energy vehicle as the state input corresponding to a preset deep reinforcement learning model, and use the deep reinforcement learning model to define the gear action space for the state space vector of the new energy vehicle, so as to generate a gear shifting action space selection for the new energy vehicle, including upshifting, downshifting, and maintaining the current gear actions corresponding to the new energy vehicle;

[0134] A model decision reward function design module, which is used to design a corresponding vehicle gear shifting decision reward function through the gear shifting action space selection corresponding to the deep reinforcement learning model;

[0135] A vehicle driving gear shifting decision control module, which is used to perform vehicle driving gear shifting decision control on the corresponding state space vector of the new energy vehicle based on the vehicle gear shifting decision reward function by using the deep reinforcement learning model, so as to select the optimal gear shifting action from the action space corresponding to the model according to the real-time collected vehicle state information, thereby generating an optimal gear shifting decision control strategy corresponding to the new energy vehicle under different driving conditions.

[0136] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0137] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A new energy vehicle gear decision method based on deep reinforcement learning, characterized in that: The following steps are involved: Step S1: by deploying a vehicle speed sensor, a motor speed sensor and a battery status sensor on the new energy vehicle, and using the vehicle speed sensor, the motor speed sensor and the battery status sensor to collect the vehicle status of the real-time driving process of the new energy vehicle in real time, so as to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle; obtaining the road slope and curvature corresponding to the new energy vehicle at different driving road locations, and performing vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle based on the road slope and curvature corresponding to the new energy vehicle at different driving road locations, so as to obtain a new energy vehicle driving fusion data set; Step S2: obtaining the current gear of the new energy vehicle and determining the state space vector in combination with the corresponding driving speed, motor speed, battery power, road slope and curvature in the new energy vehicle driving fusion data set at the current time, so as to obtain the state space vector of the new energy vehicle; using the state space vector of the new energy vehicle as the state input corresponding to the preset deep reinforcement learning model, and using the deep reinforcement learning model to define the gear action space of the state space vector of the new energy vehicle, so as to generate the gear switching action space selection of the new energy vehicle, including the corresponding upshift, downshift and keeping current gear actions of the new energy vehicle; Step S3: Designing a corresponding vehicle gear decision reward function through the gear switching action space selection of the new energy vehicle corresponding to the deep reinforcement learning model; wherein the vehicle gear decision reward function is specifically that when the action gear selected by the deep reinforcement learning model results in reduced energy consumption and enhanced power performance, a positive reward is given to the gear decision; when the action gear selected by the deep reinforcement learning model results in excessive energy consumption and weakened power performance to affect the driving smoothness of the new energy vehicle, a negative reward is given to the gear decision; Step S4: Based on the vehicle gear decision reward function, the deep reinforcement learning model is used to perform vehicle gear decision control on the corresponding new energy vehicle state space vector, so as to select the optimal gear switching action from the action space corresponding to the model according to the real-time collected vehicle state information, and generate the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

2. The gear decision method for new energy vehicles based on deep reinforcement learning according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: by deploying a vehicle speed sensor, a motor speed sensor and a battery status sensor on the new energy vehicle, and using the vehicle speed sensor to collect the driving speed of the new energy vehicle in real time during the real-time driving process, so as to obtain the driving speed of the new energy vehicle; Step S12: using a motor speed sensor to collect the motor speed of the new energy vehicle in real time during the real-time driving process to obtain the motor speed of the new energy vehicle; Step S13: using a battery status sensor to collect the battery power of the new energy vehicle in real time during the real-time driving process to obtain the battery power of the new energy vehicle; Step S14: Obtaining the road slope and curvature corresponding to different driving road locations of the new energy vehicle; Step S15: Based on the road slope and curvature corresponding to different driving road locations of the new energy vehicle, the vehicle data fusion processing is performed on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle to obtain a new energy vehicle driving fusion data set.

3. The gear decision method for new energy vehicles based on deep reinforcement learning according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: Perform vehicle data Kalman filtering on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle to obtain the driving noise reduction speed of the vehicle, the motor noise reduction speed of the vehicle and the battery noise reduction power of the vehicle; Step S152: constructing a vehicle dynamics model and a battery model corresponding to the new energy vehicle, and performing driving state correlation analysis on the vehicle driving noise reduction speed, the vehicle motor noise reduction speed, and the vehicle battery noise reduction power based on the vehicle dynamics model and the battery model, to obtain a new energy vehicle driving state correlation data set; Step S153: Obtain the corresponding vehicle driving road space location through the road slope and curvature corresponding to the new energy vehicle at different driving road locations, and perform driving space synchronization mapping on the new energy vehicle driving state associated data set based on the vehicle driving road space location to obtain the corresponding vehicle driving state data set at the same driving road location, including the driving speed, motor speed and battery power; Step S154: Based on the road slope and curvature corresponding to the new energy vehicle at different driving road locations, vehicle data fusion processing is performed on the vehicle driving state data set corresponding to the same driving road location to obtain a new energy vehicle driving fusion data set.

4. The gear decision method for new energy vehicles based on deep reinforcement learning according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: obtaining the current gear position of the new energy vehicle; Step S22: determining the state space vector of the new energy vehicle by combining the current gear position of the new energy vehicle with the corresponding driving speed, motor speed, battery power, road slope and curvature in the new energy vehicle driving fusion data set at the current time, so as to obtain the state space vector of the new energy vehicle; Step S23: dividing the new energy vehicle state space vector into individual vehicle state discrete space vectors according to corresponding time intervals, and determining the corresponding vehicle speed state value, rotation speed state value, power state value, slope state value and curvature state value in each time range according to each vehicle state discrete space vector; Step S24: using the vehicle speed state value, rotation speed state value, power state value, slope state value and curvature state value corresponding to each time range as the state input corresponding to the preset deep reinforcement learning model, and performing gear power and energy consumption evaluation calculation on the current gear of the new energy vehicle based on the vehicle speed state value, rotation speed state value, power state value, slope state value and curvature state value corresponding to each time range, to obtain the gear power performance state value of the new energy vehicle and the gear energy loss of the new energy vehicle; Step S25: Use the deep reinforcement learning model to define the gear action space of the new energy vehicle gear power performance state value and the new energy vehicle gear energy loss to generate the new energy vehicle gear switching action space selection, including the corresponding upshift, downshift and maintain current gear actions of the new energy vehicle.

5. The gear decision method for new energy vehicles based on deep reinforcement learning according to claim 4 is characterized in that: The step S24 includes the following steps: performing gear power and energy consumption evaluation calculation for the current gear of the new energy vehicle based on the corresponding vehicle speed state value, rotation speed state value, power state value, slope state value, and curvature state value in each time range: Based on the corresponding vehicle speed state value, rotation speed state value and power state value in each time range, the gear power performance evaluation calculation formula is used to perform gear power evaluation calculation on the current gear of the new energy vehicle to obtain the gear power performance state value of the new energy vehicle; The vehicle gear power output of the new energy vehicle in the corresponding time range is simulated and calculated according to the gear power performance state value of the new energy vehicle, and the vehicle gear power peak value corresponding to the new energy vehicle is calculated according to the vehicle gear power output; Based on the slope state value and the curvature state value, the energy consumption impact of the current gear of the new energy vehicle is analyzed to obtain the energy consumption impact coefficient of the gear of the new energy vehicle; Based on the vehicle gear power peak and the new energy vehicle gear energy consumption impact coefficient, the vehicle energy loss evaluation calculation formula is used to evaluate and calculate the energy consumption of the current gear of the new energy vehicle, and the gear energy loss of the new energy vehicle is obtained; Among them, the vehicle energy loss assessment calculation formula is as follows: ； In the formula, The energy loss of new energy vehicles during gear shifting. is the initial value of the time range, is the end value of the time range, is the time variable parameter, For new energy vehicles in time The vehicle speed state value at For new energy vehicles in time The speed state value at For new energy vehicles in time The power state value at is the weight coefficient of power energy loss, is the peak power of the vehicle gear, is the energy consumption impact coefficient of gear position of new energy vehicles, It is the correction coefficient for energy loss during gear shift of new energy vehicles.

6. The gear decision method for new energy vehicles based on deep reinforcement learning according to claim 5 is characterized in that: The gear dynamic performance evaluation calculation formula is specifically as follows: ； In the formula, is the gear power performance status value of new energy vehicles, is the initial value of the time range, is the end value of the time range, is the time variable parameter, For new energy vehicles in time The vehicle speed state value at is the maximum speed of the new energy vehicle in the current gear, is the vehicle speed power contribution coefficient, For new energy vehicles in time The speed state value at is the maximum motor speed of the new energy vehicle in the current gear, is the motor speed power contribution coefficient, For new energy vehicles in time The power state value at It is the maximum battery capacity of the new energy vehicle in the current gear. is the battery power contribution coefficient, is the power attenuation time constant of the new energy vehicle in the current gear, is the time exponential decay factor, It is the correction coefficient of the gear power performance status value of new energy vehicles.

7. The new energy vehicle gear decision method based on deep reinforcement learning according to claim 4 is characterized in that: The gear action space definition described in step S25 is specifically as follows: when the power performance state value is large and the gear energy loss is within an acceptable range, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as an upshift action; when the power performance state value is insufficient and the gear energy loss is large, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as a downshift action; when the power performance state value and the gear energy loss are in a balanced state, the deep reinforcement learning model is used to define the action space corresponding to the new energy vehicle as a maintain current gear action.

8. The new energy vehicle gear decision method based on deep reinforcement learning according to claim 1 is characterized in that: The optimal gear decision control strategy corresponding to different driving conditions described in step S4 is specifically that when the vehicle is driving on congested roads, the model determines whether it is necessary to downshift to maintain the corresponding power output and smoothness of the vehicle based on the vehicle speed and insufficient motor speed; when the vehicle is driving on high-speed roads, the model determines whether it is necessary to upshift to reduce the motor speed and improve energy utilization efficiency based on sufficient battery power and excessive energy consumption; and when the vehicle is driving on smooth roads, the model determines whether it is necessary to maintain the current gear to maintain the smooth operation of the vehicle and avoid unnecessary power fluctuations and motor losses based on normal battery power consumption and the fact that gear switching will not bring obvious power improvement or energy consumption reduction.

9. A new energy vehicle gear position decision control system based on deep reinforcement learning, characterized in that: Used to execute the new energy vehicle gear decision method based on deep reinforcement learning as claimed in claim 1, the new energy vehicle gear decision control system based on deep reinforcement learning includes: The vehicle driving status data fusion module is used to deploy a vehicle speed sensor, a motor speed sensor and a battery status sensor on the new energy vehicle, and use the vehicle speed sensor, the motor speed sensor and the battery status sensor to collect the vehicle status of the new energy vehicle in real time during the real-time driving process, so as to obtain the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle; obtain the road slope and curvature corresponding to the new energy vehicle at different driving road locations, and perform vehicle data fusion processing on the driving speed of the new energy vehicle, the motor speed of the new energy vehicle and the battery power of the new energy vehicle based on the road slope and curvature corresponding to the new energy vehicle at different driving road locations, so as to obtain the new energy vehicle driving fusion data set; The vehicle gear action model analysis module is used to obtain the current gear of the new energy vehicle and determine the state space vector in combination with the corresponding driving speed, motor speed, battery power, road slope and curvature in the new energy vehicle driving fusion data set at the current time to obtain the new energy vehicle state space vector; the new energy vehicle state space vector is used as the state input corresponding to the preset deep reinforcement learning model, and the deep reinforcement learning model is used to define the gear action space of the new energy vehicle state space vector to generate the new energy vehicle gear switching action space selection, including the corresponding upshift, downshift and keep current gear actions of the new energy vehicle; The model decision reward function design module is used to design the corresponding vehicle gear decision reward function through the gear switching action space selection of the new energy vehicle corresponding to the deep reinforcement learning model; The vehicle gear decision control module is used to perform vehicle gear decision control on the corresponding new energy vehicle state space vector based on the vehicle gear decision reward function using a deep reinforcement learning model, so as to select the optimal gear switching action from the action space corresponding to the model according to the real-time collected vehicle state information, thereby generating the optimal gear decision control strategy corresponding to the new energy vehicle under different driving conditions.

Images