Control device of vehicle

Abstract

To provide a control device of a vehicle that can execute driving-system protection control in accordance with a state of a road surface on which a vehicle is running and a habit and a character of each driver to make both reliability on a driving system and power performance compatible.SOLUTION: A control device of a vehicle inputs running data Ddat to a machine-learnt model selected in accordance with a running road surface section Rcd reflecting a state of a running road surface to calculate a maximum torque predicted value Tpr, and also estimates a driver section Lv by clustering, and performs control of setting a limit value constant Lmtv for driving-system protection control in accordance with the running road surface section Rcd and the driver section Lv. When a maximum value of generated torque Tmax exceeds the maximum torque predicted value Tpr, the control device renews the maximum torque predicted value Tpr to a maximum value of generated torque Tmax, and further renews the driver section Lv by clustering, and performs control of setting the limit value constant Lmtv for the driving-system protection control.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a vehicle control device. [Background technology]

[0002] In vehicles, drive system protection controls such as engine torque limiting, engine speed limiting, and brake hydraulic gradient suppression are generally implemented to avoid damage to the drive system or reduced reliability that can occur when excessive torque is applied to the drive system.

[0003] In the drivetrain protection control, a neural network learning model is used to predict driving operations that will place an excessive load on the vehicle and to execute avoidance processing in advance, and the driver's habits are reflected in the control to improve the prediction accuracy of the driving operations. For example, Patent Document 1 discloses a vehicle control device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2022-174435 Summary of the Invention [Problem to be solved by the invention]

[0005] In the above conventional vehicle control devices, prediction accuracy is improved by learning to reflect the driver's habits, but there is a problem that it is difficult to learn for rare situations that may cause damage to the drivetrain if they occur, such as wheel spin when driving off-road or sudden braking on snowy or muddy roads. If these situations occur before or during learning, they may not be avoided and may result in damage.

[0006] In addition, the above avoidance process also has the problem that the same control is applied to all drivers, and the control is not optimal for each driver. While the control is able to avoid events that can only occur in a very small number of drivers and ensures the reliability of the drive system, it is excessive for the majority of other drivers and sacrifices power performance.

[0007] The present invention has been made against the background of the above circumstances, and its object is to provide a vehicle control device that performs drive system protection control in accordance with the road surface conditions and the habits and characteristics of each driver, thereby optimally achieving both drive system reliability and power performance. [Means for solving the problem]

[0008] The gist of the present invention is that it includes (a) a vehicle control device that performs drivetrain protection control to suppress excessive torque generation in the drivetrain, and (b) an estimation unit that selects one of a plurality of pre-stored machine-learned models based on road surface conditions, inputs driving data for a predetermined period of time into the selected machine-learned model to calculate a maximum torque prediction value that will occur in a specific period, and estimates the driver classification of the driver by machine learning clustering using the maximum torque prediction value, the driving data for the predetermined period, and a pre-prepared driver classification, and (c) a determination unit that performs setting control of a limit value constant for the drivetrain protection control in accordance with the road surface conditions and the estimated driver classification, and, if a maximum torque generated in a specific period exceeds the maximum torque prediction value, updates the maximum torque prediction value and the driver classification, and performs setting control of the limit value constant for the drivetrain protection control.

[0009] Preferably, the accuracy of the prediction value estimation of the machine-learned model can be improved by re-learning the machine-learned model using the driving data when the maximum torque prediction value and the driver classification are updated as training data.

[0010] The machine learning model (including machine-learned models) used here refers to a learning model based on a machine learning algorithm. A specific example of a machine learning algorithm is deep learning, which uses a neural network to generate features for learning and connection weighting coefficients. Effect of the Invention

[0011] According to the present invention, the limit value constant of the drivetrain protection control is set according to the road surface condition and the estimated driver classification, and when the maximum torque generated during the specific period exceeds the maximum torque prediction value, the maximum torque prediction value and the driver classification are updated to set the limit value constant of the drivetrain protection control. This makes it possible to provide a vehicle control device that can implement the drivetrain protection control according to the road surface condition and the driver classification that reflects the habits and characteristics of each driver, and can optimally achieve both drivetrain reliability and power performance. [Brief description of the drawings]

[0012] [Figure 1] 1 is a diagram illustrating a schematic configuration of a vehicle according to an embodiment of the present invention; [Diagram 2] 2 is a diagram showing a main part of the torque suppression control of the electronic control device of FIG. 1. [Diagram 3] 3 is a block diagram for explaining the flow of processing data regarding the torque suppression control of the electronic control device of FIG. 1 and FIG. 2 and the processing in the server. FIG. [Figure 4] 3 is a flowchart illustrating a main part of a control operation example regarding the torque suppression control of the electronic control device of FIGS. 1 and 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that in the following embodiments, the drawings are appropriately simplified or modified, and the dimensional ratios and shapes of the various parts are not necessarily drawn accurately. EXAMPLES

[0014] Fig. 1 is a diagram illustrating the schematic configuration of an engine-driven, four-wheel-drive vehicle 10 to which the present invention is applied. In Fig. 1, the vehicle 10 is equipped with an engine 12, wheels 14, a brake 44, and a power transmission device 18 that transmits power from the engine 12 etc. to the wheels 14.

[0015] The power transmission device 18 includes a transmission 26 having a power distribution device and an automatic transmission, a transfer 28, a propeller shaft 30, a differential 34, and a drive shaft 38.

[0016] The vehicle 10 is equipped with an electronic control device 80 serving as a controller including a control device that controls the engine 12, the power transmission device 18, etc. The electronic control device 80 is configured to include a so-called microcomputer, and performs various controls of the vehicle 10 by a CPU performing signal processing according to a stored program. The electronic control device 80 functionally includes a drive control unit 82 and a torque suppression control unit 84.

[0017] The drive control unit 82 controls all functions related to driving. It has a function as an engine control unit that controls the operation of the engine 12 by controlling the engine control device 20 including a throttle actuator, a fuel injection device, an ignition device, etc., a function as a shift control unit that controls the shifting of the transmission 26 by controlling the transmission control mechanism 42 based on the actual vehicle speed and required output from a pre-stored AT gear stage shift map, and a function as a braking control unit that controls the braking operation of the brake 44 by controlling the brake control mechanism 48.

[0018] The torque suppression control unit 84 is a control unit that is responsible for control related to the present invention, and performs drive system protection control to suppress generation of excessive torque in the drive system through control that will be described later.

[0019] For example, in the vehicle 10, when driving off-road, one of the wheels 14 may lift off the ground on a rocky road or a mogul road. When the wheels 14 are placed on the road surface during subsequent driving, excessive torque is generated due to the inertia torque caused by the engine torque Te and the inertia Itm of the input system of the engine 12 and the transmission 26, and there is a concern that the drive system, such as the transmission 26, the transfer 28, the propeller shaft 30, and the differential 34, may be damaged. In addition, on a snowy road or a muddy road, when the wheels 14 spin and sudden braking is performed, excessive torque is generated due to the inertia torque of the input system. Since the load on the drive system from the output shaft of the transmission 26 to the axle side is severe when the gear ratio yat is low, the drive control unit 82 sets an upper limit value of the engine torque Te and an upper limit value of the engine speed Ne when the gear ratio yat of the transmission 26 and the transfer 28 is low gear, and controls so that they do not exceed those values. The upper limit value of engine torque Te, the upper limit value of engine speed Ne, etc. are stored as a map in the electronic control unit 80, and the torque suppression control unit 84 performs control to switch depending on the road surface classification Rcd and driver classification Lv described later.

[0020] The torque Ta generated in the drive system is calculated by the following equation (1). Ta = [Te + (Itm × engine rotation angular acceleration ωe)] × yat (1)

[0021] 2 shows an overview of the torque suppression control unit 84. The torque suppression control unit 84 includes an input unit 86 to which data from various sensors and other control devices in the vehicle, such as driving data Dda, a road surface image Iard, and weather information Winfo, is input, and a storage unit 88 that stores a portion of the data input to the input unit 86. Furthermore, the torque suppression control unit 84 includes an estimation unit 90 (described later), a determination unit 92 (described later), and a storage / output unit 94 that stores data determined by the determination unit 92 in the storage unit 88 or outputs the data to another control flow.

[0022] The estimation unit 90 performs the following three processes based on the input data from the input unit 86 and the storage unit 88. First, a traveling road surface division Rcd is selected based on the traveling road surface condition. Second, one of a plurality of pre-stored machine-learned models is selected according to the selected traveling road surface division Rcd, and the traveling data Ddat for a predetermined period is input to the selected machine-learned model to calculate a maximum torque prediction value Tpr that will occur in a specific period. Third, the driver classification Lv of the driver is estimated by machine learning clustering using the calculated maximum torque prediction value Tpr, the traveling data Ddat for the predetermined period, and a driver classification Lv prepared in advance.

[0023] The determination unit 92 controls the setting of the limit value constant Lmtv for drive system protection control according to the driving road surface classification Rcd and the estimated driver classification Lv output from the estimation unit 90, and also updates the maximum torque prediction value Tpr and the driver classification Lv to control the setting of the limit value constant Lmtv for drive system protection control when the maximum torque value Tmax generated in a specific period exceeds the maximum torque prediction value Tpr. Machine learning models, maps and calculation formulas created in advance by experiments, simulations, etc., required for the processing and calculations of the estimation unit 90 and the determination unit 92 are stored in the ROM.

[0024] Furthermore, the torque suppression control unit 84 (electronic control unit 80) is equipped with a transmitting unit 96 for transmitting the stored data to a server 100 provided outside the vehicle 10, and a receiving unit 98 for receiving data from the server.

[0025] Fig. 3 is a block diagram for explaining the flow of processing data regarding the torque suppression control of the torque suppression control unit 84. In Fig. 3, the inside of a parallelogram frame indicates the output result or value of each process, and the reference characters beginning with a parenthesized S indicate the corresponding steps in the flowchart of Fig. 4.

[0026] 4 is a flow chart for explaining the main control operations of the torque suppression control unit 84. Hereinafter, the control operations of the torque suppression control unit 84 will be explained along the processing steps of FIG. 4 with reference to FIG.

[0027] In step S1 (hereinafter, step will be omitted) in Fig. 4, driving data, weather data, etc. are acquired. As shown in Fig. 3, driving data Dda such as accelerator opening θacc, engine torque Te, engine speed Ne, transmission gear position Sat, right front wheel rotation speed Nfr, left front wheel rotation speed Nfl, right rear wheel rotation speed Nrr, right rear wheel rotation speed Nrl, brake oil pressure Pbcr, longitudinal acceleration Gx and lateral acceleration Gy of the vehicle 10, and shift lever operation position POSsh are acquired via the input unit 86, and these time-series driving data Ddat for a predetermined period are stored in the storage unit 88. In addition, data of road surface images Iard captured by an on-board camera and weather information Winfo received by communication with the server 100 or other external networks are also acquired via the input unit 86.

[0028] In S2 corresponding to the estimation unit 90, a traveling road surface division Rcd is selected based on the traveling road surface condition. Based on the camera captured image Iard and meteorological information Winfo acquired via the input unit 86, a traveling road surface division Rcd1 is selected from M types of traveling road surface divisions Rcd set in advance according to the traveling road surface, for example, one of rocky roads, mogul roads, snowy roads, muddy roads, etc., and the road surface condition, for example, dry or wet (Rcd=Rcd1). In addition, the selection of the traveling road surface division Rcd may be estimated using machine learning to which the traveling data Ddat is also input.

[0029] In S3 corresponding to the estimation unit 90, a machine-learned model corresponding to the traveling road surface division Rcd1 selected in S2 is selected from N types of machine-learned models for estimating the maximum torque prediction value Tpr created in advance. The machine-learned model is preferably a model created by LSTM (Long Short-Term Model).

[0030] In S4 corresponding to the estimation unit 90, a maximum torque predicted value Tpr1 is calculated from the traveling data Ddat by the machine-learned model selected in S3 (Tpr=Tpr1).

[0031] In S5 corresponding to the estimation unit 90, the maximum torque prediction value Tpr1 calculated in S4 and the driving data Ddat are input to a machine learning model that performs clustering created in advance, and the driver classification Lv1 is estimated from the driver classification Lv of P types prepared in advance (Lv=Lv1). The machine learning model that performs clustering is preferably a model created by TKSM (Time Series k-means). In addition, weighting may be performed on the input of the maximum torque prediction value Tpr1.

[0032] In S6 corresponding to the determination unit 92, it is determined whether the maximum value Tmax of the generated torque Ta calculated from the driving data Ddat acquired in S1 and equation (1) is equal to or less than the maximum torque prediction value Tpr1 calculated in S4 (Tpr1≧Tmax).

[0033] If the determination in S6 is positive, in S7 corresponding to the determination unit 92, the driver category Lv is determined to be the driver category Lv1 selected in S5 (Lv remains unchanged at Lv1).

[0034] If the determination in S6 is negative, in S8 corresponding to the decision unit 92, the value of the maximum torque prediction value Tpr is changed from Tpr1 to Tmax (Tpr=Tmax).

[0035] Next, in S9 corresponding to the determination unit 92, the maximum torque prediction value Tpr (=Tmax) and the driving data Ddat are used as input data, and the same clustering as in S5 is performed, and the driver classification Lv is updated to the updated value Lv2 (Lv=Lv2).

[0036] Next, in S10 corresponding to the determination unit 92, the re-learning flag Fml is turned ON, and in S11, the traveling data Dmlt at the time of re-learning is stored. The storage time of the traveling data Dmlt is set in advance to a suitable value, for example, 60 seconds, so that the latest value is always stored. The traveling data Dmlt 60 seconds before the timing when the re-learning flag Fml was turned ON is stored in the storage / output unit 94.

[0037] Furthermore, in S12 corresponding to the determination unit 92, a limit value constant Lmtv for driveline protection control is selected and determined according to the traveling road surface category Rcd selected in S2 and the driver category Lv estimated in S7 or S9. Preferably, a map of the upper limit value of the engine torque or the engine speed is selected and determined.

[0038] 3 shows the flow of processing data in the server 100. The maximum torque prediction value Tpr, the re-learning flag Fml, and the running data Dmlt stored in the memory / output unit 94 are transmitted from the vehicle 10 to the server 100 at an appropriate timing and received by the server input unit 102. In the machine learning execution unit 104, re-learning of the machine-learned model is performed using the received data as teacher data, and the re-learned model Mml is created and stored in the server memory / output unit 106. The accuracy of the prediction value estimation can be improved by updating the machine-learned model in the electronic control unit 80 to the re-learned model Mml via OTA (Over The Air), a dealer, or the like.

[0039] As described above, according to the electronic control device 80 of this embodiment, drive system protection control can be performed according to the driving road surface conditions and the driver classification that reflects the habits and characteristics of each driver, and a vehicle control device can be provided that can optimally achieve both drive system reliability and power performance.

[0040] It should be noted that the above is merely one embodiment of the present invention, and the present invention can be embodied in various modified forms without departing from the spirit of the present invention.

[0041] For example, the vehicle in the above embodiment is a vehicle that uses the engine 12 as its only drive source, but the vehicle may be a hybrid vehicle that has the engine 12 and a rotary machine as its drive source, or an electric vehicle that uses a rotary machine as its only drive source. In addition, the transmission in the transmission 26 may be any of a stepped transmission, a belt-type continuously variable transmission, an electric continuously variable transmission, etc.

[0042] It should be noted that the above is merely one embodiment, and the present invention can be embodied in various modified and improved forms based on the knowledge of those skilled in the art. [Explanation of symbols]

[0043] 10: vehicle, 80: electronic control device, 82: drive control unit, 84: torque suppression control unit, 86: input unit, 88: memory unit, 90: estimation unit, 92: determination unit, 94: memory / output unit, 96: transmission unit, 98: reception unit, 100: server, 102: server input unit, 104: machine learning execution unit, 106: server memory / output unit

Claims

[Claim 1] A vehicle control device that performs drive system protection control to suppress excessive torque generation in a drive system, an estimation unit that selects one of a plurality of pre-stored machine-learned models based on a traveling road surface condition, inputs traveling data for a predetermined period of time into the selected machine-learned model, calculates a predicted maximum torque value that will occur in a specific period of time, and estimates the driver classification of the driver by machine learning clustering using the predicted maximum torque value, the traveling data for the predetermined period of time, and a driver classification prepared in advance; A determination unit that performs setting control of a limit value constant of the drivetrain protection control according to the traveling road surface condition and the estimated driver classification, and when a maximum torque generated in a specific period exceeds the maximum torque prediction value, updates the maximum torque prediction value and the driver classification to perform setting control of the limit value constant of the drivetrain protection control. A vehicle control device comprising:

Images