Vehicle control device

Abstract

To provide a vehicle control device capable of suppressing reverse rotation of an engine when the engine is being stopped.SOLUTION: A vehicle control device includes: a learning unit that performs machine learning with engine rotation speeds and crank positions being input; an estimation unit that estimates MG torque for engine stop control on the basis of the machine learning; and a restriction unit that restricts the MG torque applied to a motor generator not to allow a value of the MG torque to become negative when the engine rotation speed is equal to or lower than a predetermined value.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a control device mounted on a vehicle. [Background technology]

[0002] Patent Document 1 discloses a vehicle control device that estimates noise by machine learning using as input one or more parameters of the crank angle before the start of an internal combustion engine, the engine speed, and the engine load. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-076162 Summary of the Invention [Problem to be solved by the invention]

[0004] When stopping the engine in a hybrid (HV) system, it is desirable to stop it quickly, quietly, and at the target crank position. For example, to stop the engine quickly, a negative torque that stops the engine may be applied by the torque of a motor generator (MG) (hereinafter referred to as "MG torque").

[0005] However, if the negative MG torque is too large or if a negative MG torque is applied until just before the engine stops, the engine may reverse from forward rotation to reverse rotation, which must be avoided from the perspectives of noise, vibration, and durability.

[0006] The present disclosure has been made in consideration of the above-mentioned problems, and aims to provide a vehicle control device that can prevent the engine from rotating in reverse when the engine is stopped. [Means for solving the problem]

[0007] In order to solve the above problem, one aspect of the disclosed technology is a vehicle control device that includes a learning unit that inputs engine speed and crank position and performs machine learning, an estimation unit that estimates MG torque for engine stop control based on the machine learning, and a limiting unit that limits the MG torque applied to the motor generator to prevent it from becoming a negative value when the engine speed is below a predetermined value. [Effects of the Invention]

[0008] According to the vehicle control device of the present disclosure, when the engine speed is equal to or lower than a predetermined value, the MG torque is restricted so as not to become a negative value, thereby suppressing the occurrence of reverse rotation of the engine when the engine is stopped. [Brief explanation of the drawings]

[0009] [Figure 1] Functional block diagram of a vehicle control device according to an embodiment of the present disclosure. [Figure 2] Processing flowchart of MG torque control executed by a vehicle control device [Figure 3] Timing chart explaining the relationship between engine speed and MG torque DETAILED DESCRIPTION OF THE INVENTION

[0010] <Embodiment> [composition] Fig. 1 is a functional block diagram showing an outline of a vehicle control device 100 according to an embodiment of the present disclosure. The control device 100 illustrated in Fig. 1 includes a learning unit 110, an estimation unit 120, and a restriction unit 130. The control device 100 of this embodiment can be mounted on vehicles such as hybrid electric vehicles (HEVs) and plug-in hybrid electric vehicles (PHEVs).

[0011] The learning unit 110 of the control device 100 is configured to input information on the rotation speed of an internal combustion engine (not shown) mounted on a vehicle and crank position indicating the rotation angle of the crankshaft, and to perform predetermined learning (machine learning, reinforcement learning, etc.) on this input information. Information on the engine rotation speed can be acquired from an engine rotation sensor or the like provided on the vehicle. Information on the crank position can be acquired from a crank angle sensor or the like provided on the vehicle. The learning method or algorithm performed by the learning unit 110 is not particularly limited, and the concept includes all methods and algorithms that learn optimal behavior by trial and error by repeating a cycle of deciding on an action, acting based on the decision, evaluating the results of the action, evaluating the action, and deciding on the next action based on the results of the evaluation.

[0012] The estimation unit 120 of the control device 100 is configured to estimate the MG torque to be applied (commanded) to a motor generator mounted on a vehicle (not shown) based on the current engine speed and the current crank position. This MG torque estimation is performed, for example, using a predetermined map created by learning. The estimation unit 120 can also acquire information on the state of fuel injection into the engine. The fuel injection state can be acquired from a device (not shown) mounted on the vehicle (not shown) that controls the amount of fuel injected.

[0013] The limiting unit 130 of the control device 100 is configured to limit (not allow negative values) the MG torque to be applied (instructed) to the motor generator based on the MG torque estimated by the estimating unit 120 when the current engine speed is equal to or lower than a predetermined value. An example of a limiting method is to replace the MG torque, which is a negative value, with zero torque.

[0014] Note that part or all of the above-described control device 100 may be configured by an electronic control unit (ECU) that typically includes a processor such as a microcomputer, a memory, an input / output interface, etc. This electronic control unit can realize part or all of the functions performed by the above-described learning unit 110, estimation unit 120, and restriction unit 130 by having the processor read and execute a program stored in the memory.

[0015] [control] Next, control performed by the vehicle control device 100 according to an embodiment of the present disclosure will be described with further reference to Figures 2 and 3. Figure 2 is a flowchart illustrating the procedure for MG torque control performed by each component of the vehicle control device 100. Figure 3 is a timing chart illustrating the relationship between engine speed and MG torque.

[0016] (Step S201) The learning unit 110 acquires the engine speed (NE) and crank position of the vehicle. Once the engine speed (NE) and crank position have been acquired by the learning unit 110, the process proceeds to step S202.

[0017] (Step S202) The learning unit 110 performs learning using the engine speed (NE) and crank position acquired in step S201 as inputs.

[0018] Typically, when stopping the engine of an HV system, a motor generator is used to achieve engine shutdown that takes into account factors such as quickly reducing the engine speed so that the engine speed does not stagnate in the resonance band, and stopping the engine at a crank position where compression is light so that the engine speed can quickly pass through the resonance band the next time the engine is started. Because MG torque control during engine shutdown must be designed to meet various requirements, a significant amount of work is required for repeated evaluation to adapt it to each vehicle. In this embodiment, to reduce this adaptation work, the engine is automatically and repeatedly shut down, and reinforcement learning is used to design reward values ​​for each shutdown requirement, thereby deriving the optimal value for MG torque control.

[0019] Once learning is performed by learning unit 110 using the engine speed (NE) and crank position as input, the process proceeds to step S203.

[0020] (Step S203) The estimation unit 120 determines whether fuel injection into the engine has stopped (whether the engine has stopped). For example, fuel injection is stopped when the engine speed falls below a predetermined value (such as 1000 rpm). If the estimation unit 120 determines that fuel injection has stopped (Yes in step S203), the process proceeds to step S204. On the other hand, if the estimation unit 120 determines that fuel injection has not stopped (No in step S203), the process proceeds to step S201.

[0021] (Step S204) The estimation unit 120 estimates the MG torque based on the current engine speed (NE) and the current crank position. The learning unit 110 can estimate the MG torque using, for example, the map learned in step S202. Once the MG torque is estimated by the learning unit 110, the process proceeds to step S205.

[0022] (Step S205) The limiting unit 130 determines whether the current engine speed (NE) is equal to or less than a predetermined value. This predetermined value is set, for example, to a predetermined speed (experimental value, simulation value, etc.) at which the engine may rotate in reverse. If the limiting unit 130 determines that the engine speed (NE) is equal to or less than the predetermined value (step S205, Yes), the process proceeds to step S206. On the other hand, if the limiting unit 130 determines that the engine speed (NE) exceeds the predetermined value (step S205, No), the process proceeds to step S208.

[0023] (Step S206) The limiting unit 130 determines whether the MG torque estimated in step S204 is less than zero, i.e., whether it is a negative value. If the limiting unit 130 determines that the MG torque is less than zero (step S206, Yes), the process proceeds to step S207. On the other hand, if the limiting unit 130 determines that the MG torque is greater than or equal to zero, i.e., whether it is a positive value (step S206, No), the process proceeds to step S208.

[0024] (Step S207) The limiting unit 130 sets the actual MG torque (actual MG torque) applied (instructed) to the motor generator to zero. That is, the limiting unit 130 performs torque limitation so that the actual MG torque does not become a negative value (the portion indicated by the dotted line in FIG. 3). When the limiting unit 130 sets the actual MG torque to zero, the process proceeds to step S201.

[0025] (Step S208) The limiting unit 130 sets the actual MG torque (actual MG torque) to be applied (instructed) to the motor generator to the MG torque estimated in step S204. That is, the limiting unit 130 does not limit the torque because the actual MG torque is a positive value. When the limiting unit 130 sets the actual MG torque to the estimated MG torque, the process proceeds to step S201.

[0026] <Actions and Effects> As described above, according to the vehicle control device 100 according to an embodiment of the present disclosure, when the engine speed is equal to or lower than a predetermined value, the MG torque applied (commanded) to the motor generator is limited so as not to become a negative value.

[0027] This restriction prevents the engine from reversing from forward rotation to reverse rotation if the negative value of the MG torque for stopping the engine is too large or if a negative value of MG torque is applied until just before the engine is stopped.

[0028] In the above embodiment, the control device 100 is described as being mounted on a vehicle such as a hybrid electric vehicle (HEV) or a plug-in hybrid electric vehicle (PHEV) having both an engine and a motor in its drivetrain. In addition, the control device 100 can be applied to a vehicle equipped with a system that drives and controls something with the motor using some target value (such as a target rotation speed or the output amount of an external generator), such as an electric vehicle (BEV) having only a motor in its drivetrain. [Industrial Applicability]

[0029] The vehicle control device of the present disclosure can be used in vehicles that have both an engine and a motor in their drivetrain. [Explanation of symbols]

[0030] 100 control device 110 Learning Department 120 Estimation part 130 Restricted Section

Claims

[Claim 1] A control device for a vehicle, a learning unit that inputs engine speed and crank position and performs machine learning; an estimation unit that estimates an MG torque for engine stop control based on the machine learning; a limiting unit that limits the MG torque applied to the motor generator so that it does not become a negative value when the engine rotation speed is equal to or lower than a predetermined value. Vehicle control device.

Images