All-in-one electric drive assembly system and control method

Abstract

The invention discloses an all-in-one electric drive assembly system and a control method, and relates to the technical field of new energy automobile power system control. The system comprises an engine, a motor, a power battery, a clutch, a vehicle transmission mechanism and an electronic control system, wherein the electronic control system comprises a reinforcement learning decision module, a mode control module, an execution control module, a safety control module and a strategy management module. The system generates a power control instruction and a driving mode instruction based on operation state information, cooperative control of power output and driving modes of an engine and a motor is achieved, and switching of pure electric driving, series driving and parallel driving modes is supported. According to the method, multi-source power combined control can be executed according to the vehicle state, and the method has the parameter setting and safe takeover capacity. The energy efficiency, the self-adaptability and the operation stability of the driving control system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle power system control, and particularly to an integrated electric drive assembly system and a control method thereof. Background Art

[0002] With the rapid development of new energy vehicles, the performance of the electric drive system has become a core factor affecting the vehicle's power performance, economy, and intelligent level. To improve the power response efficiency, extend the cruising range, and adapt to complex traffic conditions, hybrid and multi-mode drive systems have gradually become one of the mainstream technical paths.

[0003] Existing integrated electric drive assembly systems usually integrate engines, electric motors, power batteries, clutches, and transmission mechanisms, supporting multiple drive modes such as pure electric, series, and parallel. However, such systems generally rely on control strategies constructed based on fixed rules or empirical logic, and have poor adaptability to complex operating environments and dynamic working conditions. The main technical problems are as follows: lack of adaptive control ability: traditional control strategies are difficult to achieve optimal power distribution and mode switching among multiple drive modes with high uncertainty and strong non-linearity; insufficient energy management optimization: fixed strategies are difficult to balance engine efficiency, battery SOC safety, motor response, and vehicle energy consumption in real time, resulting in poor performance in some operating states; rigid control path and lack of fault tolerance mechanism: when abnormal sensing, strategy failure, or actuator deviation occurs, there is no flexible takeover mechanism, and the system safety cannot be guaranteed; poor strategy deployment and migration ability: existing control systems respond slowly to changes in the operating environment, and strategy switching lags behind, unable to achieve continuous control performance maintenance and optimization.

[0004] Therefore, there is an urgent need for an electronic control system architecture that can perform joint sensing, strategy coordination, adaptive adjustment, and have fault tolerance ability under complex conditions, especially lacking an engineering system solution that introduces deep reinforcement learning into the field of vehicle drive mode control. Summary of the Invention

[0005] The purpose of the present invention is to overcome the technical deficiencies of the existing integrated electric drive system, such as strong control strategy rigidity, poor self-adaptability, low energy utilization efficiency, and lack of safety fault tolerance mechanism, and propose an integrated electric drive assembly system and a control method thereof, so as to achieve adaptive control and optimized management of core drive units such as engines, electric motors, and clutches under multiple drive modes, thereby improving the vehicle's power performance, energy consumption economy, and operating safety.

[0006] To achieve the above purpose, the present invention is realized through the following technical solutions:

[0007] On the one hand, the present invention provides an integrated electric drive assembly system for realizing the switching of multiple drive modes of a vehicle and the coordinated control of power, including:

[0008] An engine, an electric motor, a power battery, a clutch, and a vehicle transmission mechanism, wherein:

[0009] The engine can be selectively connected or decoupled from the vehicle transmission mechanism through the clutch. The electric motor is connected to the vehicle transmission mechanism to drive the vehicle, and the power battery is electrically connected to the electric motor to provide driving electric energy or recover braking energy;

[0010] It further includes an electronic control system for coordinately controlling the engine, the electric motor, and the clutch during vehicle operation. The electronic control system includes:

[0011] A reinforcement learning decision-making module for generating control instructions based on vehicle state information. The control instructions include power control instructions for controlling the power output of the engine and the electric motor, and driving mode instructions for controlling the connection state of the clutch and the start / stop state of the engine;

[0012] A mode control module for controlling the engagement or disengagement state of the clutch and the start or stop state of the engine according to the driving mode instructions to switch the operating state of the vehicle between pure electric drive, series drive, and parallel drive modes;

[0013] An execution control module for controlling the operation of the engine and the electric motor according to the power control instructions to drive the vehicle to output the target torque and speed;

[0014] A safety control module for judging whether the abnormal control conditions are met based on the vehicle state information and the execution feedback of the control instructions, and implementing a preset safety control strategy when the conditions are met, including output limitation, mode switching, or control takeover;

[0015] A strategy management module for adjusting the parameters of the safety control strategy or switching the control strategy model when the operating environment parameters change to maintain the control performance of the electronic control system under different operating conditions.

[0016] A further improvement of the present invention lies in that the reinforcement learning decision-making module includes:

[0017] A state input processing unit for collecting and processing vehicle operation state information, including but not limited to vehicle load, driving demand, state of charge (SOC) of the battery, engine speed, motor efficiency, and current driving mode, for constructing a unified state vector;

[0018] The engine control agent unit is a control policy network trained based on a deep reinforcement learning algorithm. Taking the state vector as the input, it outputs a power control command for controlling the engine power, and its optimization objectives include minimizing the fuel consumption rate and optimizing the output response performance;

[0019] The motor control agent unit is a control policy network trained based on a deep reinforcement learning algorithm. Taking the unified state vector as the input, it outputs a power control command for controlling the motor power, and the optimization objectives include improving the energy usage efficiency and maintaining the battery safety;

[0020] The drive mode decision-making unit is used to generate a drive mode command for controlling the clutch connection state and the engine start / stop state based on the unified state vector and the agent output result;

[0021] The agent collaborative optimization unit is used to establish a shared state interface and a reward coupling mechanism between the engine control agent unit and the motor control agent unit, and coordinate the consistency of the control commands through joint optimization strategy output.

[0022] A further improvement of the present invention is that the motor control agent unit includes:

[0023] The state sharing sub-unit is used to respectively provide the unified state vector to the engine control agent unit and the motor control agent unit as a common input;

[0024] The reward fusion sub-unit is used to perform weighted calculation on the immediate reward values of the engine control agent unit and the motor control agent unit according to the set reward coupling factor ρ to generate a joint reward signal, where: when ρ = 0, no reward sharing is performed; when ρ > 0, partial reward sharing is performed; when ρ is a specific non-zero value, joint optimization calculation is performed;

[0025] The conflict coordination sub-unit is used to adjust the control commands based on a preset priority, weight function or fusion rule when the power control commands or drive mode commands respectively output by the two agent units are inconsistent;

[0026] The fusion strategy output sub-unit is used to respectively output the power control command and the drive mode command processed by the conflict coordination sub-unit to the drive mode control module and the execution control module.

[0027] A further improvement of the present invention is that the drive mode decision-making unit includes:

[0028] A state discrimination sub-unit, configured to identify an operating scenario based on key parameters in the state vector, where the key parameters include the current vehicle speed, acceleration demand, state of charge of the battery, engine start / stop state, current power request, and system efficiency evaluation index;

[0029] A mode switching determination sub-unit, configured to make an optimal judgment among three driving modes of pure electric drive, series drive, and parallel drive according to the operating scenario recognition result and the target optimization strategy. The judgment process is implemented based on a policy function, and a hysteresis mechanism is provided to avoid frequent switching;

[0030] A clutch control instruction generation sub-unit, configured to generate a control instruction for controlling the engagement state of the clutch according to the mode determination result, so as to implement the mechanical connection configuration required by the selected driving mode;

[0031] An engine start / stop control instruction generation sub-unit, configured to generate an engine start / stop control signal according to the driving mode determination result, so as to enable the engine to intervene or withdraw from the power system as needed;

[0032] A safety redundancy determination sub-unit, configured to monitor the execution result of the driving mode switching instruction in real time. If it detects abnormal mode switching, execution failure, or system safety risks, it triggers a preset fault mode or degradation control strategy.

[0033] A further improvement of the present invention lies in that the execution control module includes a motor control unit for controlling the torque output of the first motor. The motor control unit adopts a field-oriented control structure, including:

[0034] A speed outer loop adjustment unit, with the input being the difference between the target speed ω ref and the actual speed ω act , and the output being the target torque current i q,ref , which is adjusted by a proportional-integral controller;

[0035] A current inner loop adjustment unit, with the input being the deviation between the target current i q,ref and the actual current i q,act , and the output being a voltage control signal or PWM duty cycle for driving a three-phase inverter;

[0036] The control structure adopts a d-q coordinate transformation method to transform the three-phase stationary coordinate system current to the rotating coordinate system;

[0037] The speed outer loop adjustment unit and the current inner loop adjustment unit form an inner-outer loop cascade PI control structure, which respectively completes the speed command calculation and the current control command adjustment.

[0038] A further improvement of the present invention is that, to enhance the operation stability and regulation accuracy of the motor control unit in the execution control module, it further includes:

[0039] A parameter tuning unit for offline tuning of the proportional gain and integral gain parameters K p , K i of the speed outer loop regulation unit and the current inner loop regulation unit in the field-oriented control structure. The tuning process uses the non-dominated sorting genetic algorithm, and the optimization objectives of the non-dominated sorting genetic algorithm are the following two functions:

[0040]

[0041] Where: T m (t) is the actual torque of the first motor; is the average value of the torque within the optimization period T0, used to calculate the steady-state torque fluctuation index;

[0042] A torque feedback regulation unit for real-time collecting the output torque T m (t) of the first motor during vehicle operation and comparing it with a preset torque fluctuation threshold:

[0043] When the fluctuation amplitude exceeds the threshold, the feedback regulation unit finely tunes the target current i q,ref , or performs gain correction on the controller parameters K p , K i . dt represents the integral with respect to time t; J1 is used to evaluate the integral of the speed tracking error of the control system within the time interval [0, T o ; J2 is used to measure the pulsation variance of the motor output torque within this interval.

[0044] A further improvement of the present invention is that the safety control module includes:

[0045] An abnormal determination unit for obtaining the vehicle speed, battery state of charge SOC, motor temperature and working current in the vehicle operation state, and respectively setting safety thresholds for the above variables; when the detected value exceeds the safety threshold, generating an abnormal state determination signal;

[0046] A control takeover unit for, after receiving the abnormal state determination signal, replacing the control path of the reinforcement learning decision module to the execution control module and performing at least one of the following control operations:

[0047] A torque limit sub-unit for outputting a motor torque limit instruction to the execution control module;

[0048] A clutch disconnection sub-unit for outputting an engine clutch disconnection control instruction to the drive mode control module;

[0049] The PID control switching sub-unit is used to call the preset power control logic based on the PID regulator and send the output signal to the execution control module.

[0050] A further improvement of the present invention is that the policy management module includes:

[0051] A standby policy library, which is configured with multiple control policy networks obtained through offline training, and each policy network corresponds to a different combination of vehicle operating environment parameters;

[0052] The policy switching determination unit is used to judge whether the policy switching condition is met based on the state of charge (SOC) of the battery, the change in battery capacity, and the environmental temperature parameters monitored during the vehicle operation, and generate a policy switching control signal when the condition is met;

[0053] The policy switching execution unit is used to load the target policy network from the standby policy library and replace the current main policy network according to the policy switching control signal, and continuously adjust the control parameters of the original main policy network with a limited amplitude during the replacement process.

[0054] On the other hand, the present invention provides a multi-in-one electric drive assembly control method, which is applied to a multi-in-one electric drive assembly system as described in any one of the above claims. The method includes the following steps:

[0055] Step 1: Collect the vehicle operation state information, where the operation state information includes vehicle speed, acceleration request, state of charge (SOC) of the battery, engine speed, motor efficiency parameters, and the current drive mode state;

[0056] Step 2: Based on the operation state information, generate control instructions through a reinforcement learning decision-making strategy, where the control instructions include an engine power instruction, a motor power instruction, and a drive mode switching instruction;

[0057] Step 3: According to the drive mode switching instruction, control the engagement or disengagement state of the clutch and the start or stop state of the engine to realize the switching of the vehicle between the pure electric drive, series drive, and parallel drive modes;

[0058] Step 4: According to the engine power instruction and the motor power instruction, respectively control the throttle opening of the engine and the current vector of the motor to realize the output of the vehicle target torque and speed;

[0059] Step 5: Monitor the key parameters during the vehicle operation, including vehicle speed, battery SOC, motor temperature, current, and execute feedback according to the control instructions to judge whether there are abnormal control conditions. If so, trigger the preset safety control strategy;

[0060] Step 6: When a change in the operating environment parameters is detected, adjust the control parameters of the safety control strategy or switch the pre-set control strategy model to ensure the control performance and stability of the electronic control system under different operating conditions.

[0061] The beneficial effects of the present invention are as follows: Through the configuration of the structurally integrated engine, motor, clutch and vehicle transmission mechanism, coordinated by the electronic control system, flexible switching between pure electric drive, series drive and parallel drive modes is achieved, thus significantly improving the adaptability of the system to complex driving conditions and the continuity of power output. The system introduces a reinforcement learning decision-making module, which generates composite control instructions including power control and drive mode switching based on vehicle operating state information, and can handle dynamic optimization problems in complex environments such as non-linearity and multi-variables, overcoming the technical shortcomings of traditional control strategies such as slow response and poor generalization ability. The electronic control system adopts a modular design, with a reinforcement learning decision-making module, a mode control module, an execution control module, a safety control module and a strategy management module respectively. The responsibilities of each module are clear and the logical connection is close, which is beneficial to the functional division and engineering deployment of the control path. By coordinating the power output of the engine and the motor and combining with real-time drive mode selection, the system can reduce fuel consumption and power consumption while ensuring power demand, and significantly improve the energy utilization efficiency of the whole vehicle. At the same time, the safety control module can perform real-time abnormal state determination based on key operating parameters and trigger fault tolerance strategies such as output limitation and control takeover when necessary, enhancing the safety and stability of the whole vehicle control; the strategy management module supports switching to a backup strategy or fine-tuning the main strategy parameters when the operating environment changes (such as battery capacity attenuation, external temperature fluctuation), thus ensuring the continuous and reliable operation of the system under diverse working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts.

[0063] Among them:

[0064] Figure 1 is the system modular diagram of the present invention;

[0065] Figure 2 is the method flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention fall within the scope of protection of the present invention.

[0067] As Figure 1 shown, this is an embodiment of the present invention, which provides an integrated electric drive assembly system for realizing the switching of multiple driving modes and power coordination control of a vehicle, including:

[0068] an engine, an electric motor, a power battery, a clutch, and a vehicle transmission mechanism, wherein:

[0069] The engine can be selectively connected or decoupled from the vehicle transmission mechanism through the clutch. The electric motor is connected to the vehicle transmission mechanism to drive the vehicle. The power battery is electrically connected to the electric motor to provide driving electric energy or recover braking energy;

[0070] It further includes an electronic control system for coordinately controlling the engine, the electric motor, and the clutch during the operation of the vehicle. The electronic control system includes:

[0071] (1) A reinforcement learning decision-making module

[0072] for generating control instructions based on vehicle state information. The control instructions include power control instructions for controlling the power output of the engine and the electric motor, and driving mode instructions for controlling the connection state of the clutch and the start / stop state of the engine;

[0073] The reinforcement learning decision-making module includes:

[0074] A state input processing unit for collecting and processing vehicle operation state information, including but not limited to vehicle load, driving demand, state of charge (SOC) of the battery, engine speed, motor efficiency, and current driving mode, for constructing a unified state vector;

[0075] An engine control agent unit, which is a control strategy network trained based on a deep reinforcement learning algorithm. Taking the state vector as input, it outputs power control instructions for controlling the power of the engine, and its optimization objectives include minimizing fuel consumption rate and optimizing output response performance;

[0076] The motor control agent unit is a control policy network trained based on the deep reinforcement learning algorithm. Taking the unified state vector as the input, it outputs a power control command for controlling the power of the motor. The optimization objectives include improving energy usage efficiency and maintaining battery safety;

[0077] The driving mode decision-making unit is used to generate a driving mode command for controlling the clutch connection state and the engine start / stop state based on the unified state vector and the agent output result;

[0078] The agent collaborative optimization unit is used to establish a shared state interface and a reward coupling mechanism between the engine control agent unit and the motor control agent unit, and coordinate the consistency of control commands by jointly optimizing the policy output.

[0079] In a specific embodiment, the motor control agent unit includes:

[0080] The state sharing sub-unit is used to provide the unified state vector to the engine control agent unit and the motor control agent unit respectively as a common input;

[0081] The reward fusion sub-unit is used to perform weighted calculation on the immediate reward values of the engine control agent unit and the motor control agent unit according to the set reward coupling factor ρ to generate a joint reward signal, where: when ρ = 0, no reward sharing is performed; when ρ > 0, partial reward sharing is performed; when ρ is a specific non-zero value, joint optimization calculation is performed;

[0082] The conflict coordination sub-unit is used to adjust the control command based on a preset priority, weight function or fusion rule when the power control commands or driving mode commands respectively output by the two agent units are inconsistent;

[0083] The fusion policy output sub-unit is used to output the power control command and the driving mode command processed by the conflict coordination sub-unit to the driving mode control module and the execution control module respectively.

[0084] In a specific embodiment, the driving mode decision-making unit includes:

[0085] The state discrimination sub-unit is used to identify the operating scenario based on the key parameters in the state vector. The key parameters include the current vehicle speed, acceleration demand, battery charge state, engine start / stop state, current power request and system efficiency evaluation index;

[0086] A mode switching determination subunit, configured to perform an optimal selection judgment among three driving modes of pure electric drive, series drive, and parallel drive according to the operation scenario recognition result and the target optimization strategy. The judgment process is implemented based on a policy function or a mode switching map, and a hysteresis mechanism is provided to avoid frequent switching;

[0087] A clutch control instruction generation subunit, configured to generate a control instruction for controlling the engagement state of the clutch according to the mode determination result, so as to implement the mechanical connection configuration required by the selected driving mode;

[0088] An engine start / stop control instruction generation subunit, configured to generate an engine start / stop control signal according to the driving mode determination result, so as to enable the engine to intervene or withdraw from the power system as needed;

[0089] A safety redundancy determination subunit, configured to monitor the execution result of the driving mode switching instruction in real time. If a mode switching abnormality, execution failure, or system safety risk is detected, a preset fault mode or degradation control strategy is triggered.

[0090] Although the "reinforcement learning decision-making module" in this embodiment does not introduce new components in terms of structure that exceed the general elements of the existing control system, its control logic organization method, agent cooperation mechanism, and decision output path all exhibit strong systematic innovation characteristics.

[0091] First, the module performs normalized modeling on multi-dimensional state information through the "state input processing unit" to form a unified state vector, which is simultaneously used to drive multiple control policy agents to achieve consistent coupling in the input space. Compared with the traditional method of separately modeling the motor and engine control paths, this embodiment realizes the fusion of the horizontal control dimensions and improves the response consistency of the model to the changes of multi-source state variables.

[0092] Second, this embodiment adopts a "dual-agent control structure", where the engine and the motor are respectively set as independent control agents. After being independently trained based on their respective reinforcement learning networks, they output control strategies, and a quantifiable and adjustable incentive sharing mechanism is introduced through the "reward fusion subunit" to dynamically adjust the proportion of the optimization objectives of the two according to the priority of the vehicle operation task. This "soft coupling - adjustable fusion" method is relatively rare in the existing multi-driving path control systems and provides a new engineering implementation path for solving the dynamic game between energy efficiency and response performance.

[0093] Furthermore, when there is a policy conflict between the power control instruction and the drive mode instruction, this embodiment is provided with a "conflict coordination subunit", which introduces a preset priority and a fusion rule to perform a balanced calculation on the conflicting instructions, ensuring that the final output behavior has functional continuity and decision stability. Compared with the existing method that only relies on fixed priority or fuzzy logic to handle conflicts, this solution clarifies the conflict resolution path through a structured module, facilitating policy deployment and expansion.

[0094] In addition, through the "fusion strategy output subunit", this embodiment uniformly coordinates and outputs the power distribution result and the drive mode selection result before the execution instruction is distributed, decoupling and then recoupling the engine, the motor, and the clutch longitudinally logically in the control path, taking into account both the system response speed and the control closed-loop consistency.

[0095] In summary, this embodiment does not expand the traditional system at the hardware level or in terms of the number of structural units, but rather conducts systematic optimization and engineering integration design on the control strategy organizational structure and path coordination mechanism. Especially, the mechanism for realizing collaborative decision-making output of multiple control objects under the reinforcement learning framework has significant non-obviousness, can effectively solve problems such as poor adaptability of the existing rule-driven system in a dynamic environment and weak consistency of conflicting strategies, and has clear technological progress significance.

[0096] (2) Mode control module

[0097] It is used to control the engaged or disengaged state of the clutch according to the drive mode instruction, and control the start or stop state of the engine, so as to switch the operating state of the vehicle among pure electric drive, series drive, and parallel drive modes;

[0098] The mode control module described in this embodiment, although similar to the control module of the existing hybrid drive system in terms of hardware structure and functional objectives, and its main role is to realize the switching between different drive modes and the execution state management, but in terms of the control trigger path organization, the clarity of the decision response logic, and the cooperation mechanism with the reinforcement learning strategy output, it constitutes a unique system implementation.

[0099] (3) Execution control module

[0100] It is used to control the operation of the engine and the motor according to the power control instruction, and drive the vehicle to output the target torque and speed;

[0101] The execution control module includes a motor control unit for controlling the torque output of the first motor. The motor control unit adopts a field-oriented control structure, including:

[0102] A speed outer loop adjustment unit, with the input being the target speed ω ref and the actual speed ω actThe difference is output as the target torque current i q,ref , and is adjusted by a proportional-integral controller;

[0103] The current inner-loop adjustment unit has an input of the target current i q,ref and the actual current i q,act The deviation between them is output as a voltage control signal or a PWM duty cycle for driving a three-phase inverter;

[0104] The control structure adopts a d-q coordinate transformation method to transform the three-phase stationary coordinate system current to the rotating coordinate system;

[0105] The speed outer-loop adjustment unit and the current inner-loop adjustment unit form an inner-outer loop cascade PI control structure to respectively complete the rotational speed command calculation and the current control command adjustment.

[0106] In one embodiment, to enhance the operation stability and adjustment accuracy of the motor control unit in the execution control module, it further includes:

[0107] A parameter tuning unit for off-line tuning of the proportional gain and integral gain parameters K p , K i in the field-oriented control structure. The tuning process uses a non-dominated sorting genetic algorithm, and the optimization objectives of the non-dominated sorting genetic algorithm are the following two functions:

[0108]

[0109] Where: T m (t) is the actual torque of the first motor; is the average value of the torque within the optimization period T0 and is used to calculate the steady-state torque fluctuation index;

[0110] A torque feedback adjustment unit for real-time collecting the output torque T m (t) of the first motor during vehicle operation and comparing it with a preset torque fluctuation threshold:

[0111] When the fluctuation amplitude exceeds the threshold, the feedback adjustment unit finely adjusts the target current i q,ref based on the current deviation value, or corrects the gain of the controller parameters K p , K i ; dt represents the integral with respect to time t; J1 is used to evaluate the integral of the speed tracking error of the control system within the time interval [0, T o ; J2 is used to measure the pulsation variance of the motor output torque within this interval.

[0112] Although the execution control module described in this embodiment adopts a mature technical path of field-oriented control strategy, its systematic innovative design in structural configuration, parameter tuning method, and dynamic adjustment mechanism significantly improves the engineering applicability and control robustness of traditional motor control schemes.

[0113] First of all, this embodiment constructs a double-loop control structure with a speed outer loop and a current inner loop connected in series. The speed loop is used to adjust the deviation between the target speed and the actual speed, and outputs the target current through an external proportional-integral controller; the current loop is based on the current deviation to control the output of the inverter, and finally realizes the fine control of the motor torque. Compared with the existing control strategies that mainly use single-loop or fixed-parameter control, this structure realizes the control target decomposition across time scales and a two-layer error correction mechanism.

[0114] Secondly, in order to ensure the stability of the controller under a wide range of operating conditions during vehicle operation, this embodiment adopts a parameter tuning method based on multi-objective optimization. By using an intelligent optimization algorithm offline to jointly adjust the proportional gain and integral gain parameters in the controller, and considering both the speed tracking accuracy of the control system and the smoothness of the motor output torque, the parameter selection that takes into account both dynamic response and driving stability is realized. This method of multi-objective evaluation and optimization breaks through the traditional mode of relying on engineering experience or single performance index to tune parameters, and reflects the actual implementation of the system performance trade-off thinking in the drive control strategy.

[0115] Furthermore, in response to the output fluctuation problem of the motor during dynamic operation, this embodiment further introduces a torque feedback regulation mechanism. This mechanism continuously monitors the output torque of the motor during vehicle operation and compares it with a preset fluctuation threshold. When the fluctuation amplitude exceeds the safe range, the system automatically triggers a fine-tuning mechanism to immediately correct the target current or controller parameters, thereby effectively suppressing the output instability caused by road disturbances, load mutations, etc. This mechanism not only improves the disturbance adaptation ability of the electric drive system, but also ensures the continuity and safety of the vehicle's power output during actual driving.

[0116] The innovation of this embodiment does not lie in the breakthrough of the control principle, but in the organization method of the control strategy in actual engineering, the feedback path design, and the optimization process structure. The formed complete control system can significantly improve the robustness, adaptability, and energy efficiency performance of the vehicle's electric drive control, and has strong technological progressiveness and practical application value.

[0117] (4) Safety control module

[0118] It is used to judge whether the abnormal control conditions are met based on the vehicle state information and the execution feedback of the control instruction, and implement the preset safety control strategy when the conditions are met, including output limitation, mode switching, or control takeover;

[0119] The safety control module includes:

[0120] An abnormality determination unit, configured to obtain the vehicle speed, the state of charge (SOC) of the battery, the motor temperature, and the working current in the vehicle running state, and respectively set safety thresholds for the above variables; when the detected value exceeds the safety threshold, generate an abnormality state determination signal;

[0121] A control takeover unit, configured to, after receiving the abnormality state determination signal, replace the control path of the execution control module by the reinforcement learning decision-making module and perform at least one of the following control operations:

[0122] A torque limit subunit, configured to output a motor torque limit instruction to the execution control module;

[0123] A clutch disconnection subunit, configured to output an engine clutch disconnection control instruction to the drive mode control module;

[0124] A PID control switching subunit, configured to call a preset power control logic based on a PID regulator and send the output signal to the execution control module.

[0125] (5) Policy management module

[0126] It is configured to adjust the parameters of the safety control policy or switch the control policy model when the operating environment parameters change, so as to maintain the control performance of the electronic control system under different operating conditions.

[0127] The policy management module includes:

[0128] A standby policy library, configured with multiple control policy networks obtained through offline training, and each policy network corresponds to a different combination of vehicle operating environment parameters;

[0129] A policy switching determination unit, configured to determine whether the policy switching condition is met based on the state of charge (SOC) of the battery, the change in battery capacity, and the environmental temperature parameters monitored during the vehicle operation, and generate a policy switching control signal when the condition is met;

[0130] A policy switching execution unit, configured to, according to the policy switching control signal, load a target policy network from the standby policy library and replace the current main policy network, and perform a limited-amplitude continuous adjustment on the control parameters of the original main policy network during the replacement process.

[0131] As Figure 2 shown, this is another embodiment of the present invention. This embodiment provides a multi-in-one electric drive assembly control method, which is applied to a multi-in-one electric drive assembly system as described in any one of the above, and the method includes the following steps:

[0132] Step 1: Collect the operating state information of the vehicle, where the operating state information includes vehicle speed, acceleration request, state of charge (SOC) of the battery, engine speed, motor efficiency parameter, and current drive mode state;

[0133] Step 2: Based on the operating state information, generate control instructions through a reinforcement learning decision-making strategy, where the control instructions include engine power instructions, motor power instructions, and drive mode switching instructions;

[0134] Step 3: According to the drive mode switching instruction, control the engagement or disengagement state of the clutch and the start or stop state of the engine to achieve the switching of the vehicle between pure electric drive, series drive, and parallel drive modes;

[0135] Step 4: According to the engine power instruction and the motor power instruction, respectively control the throttle opening of the engine and the current vector of the motor to achieve the output of the target torque and speed of the vehicle;

[0136] Step 5: Monitor the key parameters during the vehicle operation, including vehicle speed, battery SOC, motor temperature, current, and execute feedback according to the control instructions to determine whether there are abnormal control conditions. If so, trigger a preset safety control strategy;

[0137] Step 6: When detecting a change in the operating environment parameters, adjust the control parameters of the safety control strategy or switch the preset control strategy model to ensure the control performance and stability of the electronic control system under different operating conditions.

[0138] In summary, in view of the technical problems existing in the existing multi-in-one electric drive system, such as inflexible drive mode switching, low power distribution efficiency, poor adaptability, and rigid control strategy, the present invention proposes an electronic control system solution integrating deep reinforcement learning control, modular structure design, and adaptive management mechanism. Through the dynamic optimization control of the power output of the engine and the motor by the reinforcement learning agent, as well as the intelligent determination and switching of the drive mode, the global trade-off between dynamic performance and energy efficiency utilization is achieved, and the response speed and environmental adaptability of the system are improved; by setting up a safety control module and a strategy management module, the control stability and fault tolerance during operation are ensured, meeting the long-term operation requirements under complex working conditions. The system of the present invention has a complete structure and clear control logic, has good engineering realizability and scalability, and can be widely applied to various application scenarios such as hybrid electric vehicles, range-extended electric vehicles, and high-performance new energy vehicles, with significant practical value and industrialization prospects.

[0139] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0140] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where the functions may be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed.

[0141] As described above, the above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A multi-in-one electric drive assembly system for realizing the switching of multiple driving modes and the coordinated control of power of a vehicle, comprising: An engine, an electric motor, a power battery, a clutch and a vehicle transmission mechanism, wherein: The engine can be selectively connected or decoupled from the vehicle transmission mechanism through the clutch. The electric motor is connected to the vehicle transmission mechanism to drive the vehicle. The power battery is electrically connected to the electric motor to provide driving electric energy or recover braking energy. It is characterized in that it further includes an electronic control system for coordinately controlling the engine, the electric motor and the clutch during the running of the vehicle. The electronic control system includes: A reinforcement learning decision-making module for generating control instructions based on vehicle state information. The control instructions include power control instructions for controlling the power output of the engine and the electric motor, and drive mode instructions for controlling the connection state of the clutch and the start / stop state of the engine; A mode control module for controlling the engagement or disengagement state of the clutch and the start or stop state of the engine according to the drive mode instructions to switch the running state of the vehicle between pure electric drive, series drive and parallel drive modes; An execution control module for controlling the operation of the engine and the electric motor according to the power control instructions to drive the vehicle to output the target torque and speed; A safety control module for judging whether the abnormal control conditions are met based on the vehicle state information and the execution feedback of the control instructions, and implementing a preset safety control strategy when the conditions are met, including output limitation, mode switching or control takeover; A strategy management module for adjusting the parameters of the safety control strategy or switching the control strategy model when the operating environment parameters change to maintain the control performance of the electronic control system under different operating conditions.

2. The multi-in-one electric drive assembly system according to claim 1, characterized in that The reinforcement learning decision-making module includes: A state input processing unit for collecting and processing vehicle running state information, including but not limited to vehicle load, driving demand, state of charge (SOC) of the battery, engine speed, motor efficiency, current drive mode, for constructing a unified state vector; An engine control agent unit, which is a control strategy network trained based on the deep reinforcement learning algorithm, takes the state vector as input, and outputs a power control instruction for controlling the power of the engine. The optimization objectives include minimizing the fuel consumption rate and optimizing the output response performance; A motor control agent unit, which is a control strategy network trained based on the deep reinforcement learning algorithm, takes the unified state vector as input, and outputs a power control instruction for controlling the power of the motor. The optimization objectives include improving the energy use efficiency and maintaining the battery safety; A drive mode decision-making unit for generating drive mode instructions for controlling the connection state of the clutch and the start / stop state of the engine based on the unified state vector and the agent output results; An agent cooperative optimization unit for establishing a shared state interface and a reward coupling mechanism between the engine control agent unit and the motor control agent unit, and coordinating the consistency of the control instructions through joint optimization of the strategy output.

3. The multi-in-one electric drive assembly system according to claim 2, characterized in that, The motor control agent unit includes: A state sharing subunit, configured to respectively provide the unified state vector to the engine control agent unit and the motor control agent unit as a common input; A reward fusion subunit, configured to perform weighted calculation on the immediate reward values of the engine control agent unit and the motor control agent unit according to a set reward coupling factor ρ to generate a joint reward signal, where: when ρ = 0, no reward sharing is performed; when ρ > 0, partial reward sharing is performed; when ρ is a specific non-zero value, joint optimization calculation is performed; A conflict coordination subunit, configured to adjust control instructions based on a preset priority, weight function or fusion rule when the power control instructions or drive mode instructions respectively output by the two agent units are inconsistent; A fusion strategy output subunit, configured to respectively output the power control instruction and the drive mode instruction processed by the conflict coordination subunit to the drive mode control module and the execution control module.

4. The multi-in-one electric drive assembly system according to claim 2, characterized in that, The drive mode decision unit includes: A state discrimination subunit, configured to perform operation scenario recognition based on key parameters in the state vector, and the key parameters include the current vehicle speed, acceleration demand, battery state of charge, engine start / stop state, current power request and system efficiency evaluation index; A mode switching determination subunit, configured to perform a preference judgment among three drive modes of pure electric drive, series drive and parallel drive according to the operation scenario recognition result and the target optimization strategy, and the judgment process is implemented based on a policy function and is provided with a hysteresis mechanism to avoid frequent switching; A clutch control instruction generation subunit, configured to generate a control instruction for controlling the engagement state of the clutch according to the mode determination result; An engine start / stop control instruction generation subunit, configured to generate the start / stop control signal of the engine according to the drive mode determination result; A safety redundancy determination subunit, configured to monitor the execution result of the drive mode switching instruction in real time, and if a mode switching abnormality, execution failure or system safety risk is detected, trigger a preset fault mode or degradation control strategy.

5. The multi-in-one electric drive assembly system according to claim 4, characterized in that, The execution control module includes a motor control unit, configured to control the torque output of the motor, and the motor control unit adopts a field-oriented control structure, including: Speed outer loop adjustment unit, with the input being the target speed ω ref and the actual speed ω act The difference, and the output is the target torque current i q,ref , which is adjusted by a proportional-integral controller; Current inner loop regulation unit, with the input being the target current i q,ref and the actual current i q,act The deviation between them, and the output is a voltage control signal or PWM duty cycle, which is used to drive the three-phase inverter; The control structure adopts a d-q coordinate transformation method to transform the three-phase stationary coordinate system current to the rotating coordinate system; The speed outer loop adjustment unit and the current inner loop adjustment unit form an inner and outer loop cascaded PI control structure to respectively complete the speed command calculation and the current control command adjustment.

6. The multi-in-one electric drive assembly system according to claim 5, wherein To enhance the operation stability and adjustment accuracy of the motor control unit in the execution control module, it further includes: The parameter tuning unit is used to perform offline tuning on the proportional gain and integral gain parameters K p , K i of the speed outer loop adjustment unit and the current inner loop adjustment unit in the field-oriented control structure. The non-dominated sorting genetic algorithm is used in the tuning process. The optimization objectives of the non-dominated sorting genetic algorithm are the following two functions: Where: T m (t) is the actual torque of the first motor; is the average value of the torque within the optimization period T0 and is used to calculate the steady-state torque fluctuation index; A torque feedback adjustment unit for real-time collecting the output torque T of the first motor during vehicle operation m (t) and comparing it with a preset torque fluctuation threshold value: When the fluctuation amplitude exceeds the threshold value, the feedback adjustment unit finely tunes the target current i based on the current deviation value q,ref , or corrects the gain of the controller parameters K p , K i ; dt represents the integral with respect to time t; J1 is used to evaluate the integral of the speed tracking error of the control system in the time interval [0, T o ; J2 is used to measure the pulsation variance of the motor output torque in this interval.

7. The multi-in-one electric drive assembly system according to claim 1, characterized in that The safety control module includes: An abnormality determination unit, configured to obtain the vehicle speed, battery state of charge SOC, motor temperature and working current in the vehicle operation state, and respectively set safety thresholds for the above variables; when the detected value exceeds the safety threshold, generate an abnormality state determination signal; A control takeover unit, configured to, after receiving the abnormality state determination signal, replace the control path of the execution control module by the reinforcement learning decision module and execute at least one of the following control operations: A torque limit sub-unit for outputting a motor torque limit instruction to the execution control module; A clutch disconnection sub-unit for outputting an engine clutch disconnection control instruction to the drive mode control module; A PID control switching sub-unit for invoking a preset power control logic based on a PID regulator and sending an output signal to the execution control module.

8. The multi-in-one electric drive assembly system according to claim 1, characterized in that The strategy management module includes: A standby strategy library configured with multiple control strategy networks obtained through offline training, and each strategy network corresponds to a different combination of vehicle operating environment parameters; A strategy switching determination unit for judging whether the strategy switching condition is met based on the state of charge SOC of the battery, the change in battery capacity, and the environmental temperature parameters monitored during the vehicle operation, and generating a strategy switching control signal when the condition is met; A strategy switching execution unit for loading a target strategy network from the standby strategy library and replacing the current main strategy network according to the strategy switching control signal, and continuously adjusting the control parameters of the original main strategy network with a limited amplitude during the replacement process.

9. A control method for an integrated electric drive assembly, which is applied to an integrated electric drive assembly system according to any one of claims 1-8, characterized in that, The method includes the following steps: Step 1: Collect the vehicle operation state information, where the operation state information includes vehicle speed, acceleration request, state of charge SOC of the battery, engine speed, motor efficiency parameters, and the current drive mode state; Step 2: Based on the operation state information, generate control instructions through a reinforcement learning decision-making strategy, where the control instructions include an engine power instruction, a motor power instruction, and a drive mode switching instruction; Step 3: According to the drive mode switching instruction, control the engagement or disengagement state of the clutch, and the start or stop state of the engine, to realize the switching of the vehicle between the pure electric drive, series drive, and parallel drive modes; Step 4: According to the engine power instruction and the motor power instruction, respectively control the engine throttle opening and the current vector of the motor to realize the output of the vehicle target torque and speed; Step 5: Monitor the key parameters during the vehicle operation, including vehicle speed, battery SOC, motor temperature, current, and execute feedback according to the control instructions to judge whether there are abnormal control conditions. If so, trigger a preset safety control strategy; Step 6: When it is detected that the operation environment parameters change, adjust the control parameters of the safety control strategy, or switch the preset control strategy model to ensure the control performance and stability of the electronic control system under different operating conditions.

Images