Vehicle control device

Abstract

To provide a vehicle control device capable of early starting countermeasure control against resonance of a vehicle.SOLUTION: A vehicle control device comprises: a calculation section which calculates a calculated value based on a detection value of a sensor with respect to vehicle behavior; a prediction section which predicts whether a vehicle experiences resonance, based on the calculated value, using a prediction model which is subject to supervised machine learning and outputs whether the vehicle experiences the resonance with the calculated value before the vehicle experiences resonance as input; and an execution section which executes a countermeasure process against the resonance of the vehicle when the vehicle is predicted to experience the resonance.SELECTED DRAWING: Figure 3

Description

Technical Field

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

Background Art

[0002] A technique for limiting the driving force of a vehicle when resonance occurs in the vehicle is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above technique, since the driving force is limited after resonance occurs in the vehicle, there is a possibility that the start of the driving force limitation is delayed.

[0005] Therefore, an object of the present invention is to provide a vehicle control device capable of starting countermeasure control against vehicle resonance at an early stage.

Means for Solving the Problems

[0006] The above object can be achieved by a vehicle control device including: a calculation unit that calculates a calculation value based on a detection value of a sensor related to the behavior of the vehicle; a prediction unit that predicts whether or not the vehicle resonates based on the calculation value, using a machine learning-trained prediction model with a teacher that takes the calculation value before the vehicle resonates as an input and outputs whether or not the vehicle resonates; and an execution unit that executes a countermeasure process against the resonance of the vehicle when it is predicted that the vehicle resonates.

[0007] The detected value includes at least one of the longitudinal acceleration of the vehicle, the rotational speed of the wheels of the vehicle, and the rotational speed of a rotating member that rotates in conjunction with a wheel that receives power from the driving power source of the vehicle. The calculated value may include at least one of an average value, a maximum value, a minimum value, a variance value, and a standard deviation value, within a predetermined time, of at least one of the longitudinal acceleration of the vehicle, the difference in rotational speeds of two wheels of the vehicle, the integrated value of the rotational fluctuation amount of the rotating member, and the difference between the vehicle body speed of the vehicle and the rotational speed of the vehicle.

[0008] The calculated value may include the total number of peak values within a predetermined time of the waveform after band-pass filter processing of the detected value.

[0009] The motor, which is the driving power source of the vehicle, may be directly connected to any wheel of the vehicle.

[0010] When it is predicted that the vehicle will resonate, the execution unit may reduce the torque of the driving power source of the vehicle more than when it is not predicted that the vehicle will resonate, as the countermeasure process.

Advantages of the Invention

[0011] According to the present invention, it is possible to provide a control device for a vehicle that can start countermeasure control against vehicle resonance at an early stage.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Best Mode for Carrying Out the Invention

[0013] [General Configuration of Vehicle] FIG. 1 is a schematic configuration diagram of a vehicle 1. The vehicle 1 is an electric vehicle equipped with a motor 2 as a driving power source. The vehicle 1 includes a motor 2, a propeller shaft 3, a differential gear 4, drive shafts 51 and 52, a left rear wheel 61, a right rear wheel 62, a left front wheel 63, a right front wheel 64, a PCU (Power Control Unit) 7, a battery 8, and an ECU (Electric Control Unit) 10.

[0014] The motor 2 is, for example, a permanent magnet synchronous motor or an induction motor. The motor 2 has a function as a prime mover that outputs torque by power supply, and further has a function as a generator that generates electricity when the vehicle 1 is braked. The power generated by the motor 2 is supplied to the battery 8 via the PCU 7.

[0015] The motor 2 is directly connected to the left rear wheel 61 and the right rear wheel 62 via the propeller shaft 3, the differential gear 4, and the drive shafts 51 and 52. Here, the fact that the motor 2 is directly connected to the left rear wheel 61 and the right rear wheel 62 means that no transmission, clutch, torque converter, etc. are provided between the motor 2 and the left rear wheel 61 and the right rear wheel 62. When the torque of the motor 2 is transmitted to the left rear wheel 61 and the right rear wheel 62, the vehicle 1 travels. In the example shown in FIG. 1, the vehicle 1 is a rear-wheel drive vehicle in which the torque of the motor 2 is transmitted to the left rear wheel 61 and the right rear wheel 62, but it is not limited to this and may be a front-wheel drive vehicle or a four-wheel drive vehicle.

[0016] The drive shafts 51 and 52 may be connected to the rotor of the motor 2 via a gear or directly.

[0017] The battery 8 is a power storage device composed of a secondary battery such as a nickel-metal hydride battery or a lithium-ion battery. The battery 8 can be charged not only by the power generated by the motor 2 but also by the power supplied from an external power source. Note that the battery 8 is not limited to a secondary battery, and any power storage device that can generate a DC voltage and be charged is acceptable. For example, a capacitor or the like may be used.

[0018] The ECU 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and a storage device, etc., and performs various controls by executing programs stored in the ROM and the storage device. The ECU 10 is an example of a control device for the vehicle 1 and functionally realizes a prediction unit and an execution unit, which will be described in detail later.

[0019] An ignition switch 90, wheel rotation speed sensors 91 to 94, a shaft rotation speed sensor 95, and a longitudinal and lateral acceleration sensor 96 are electrically connected to the ECU 10. The ignition switch 90 detects the on / off state of the ignition. The wheel rotation speed sensors 91 to 94 detect the rotation speeds of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, and the right front wheel 64, respectively. The longitudinal and lateral acceleration sensor 96 detects the longitudinal and lateral acceleration of the vehicle 1. The wheel rotation speed sensors 91 to 94, the shaft rotation speed sensor 95, and the longitudinal and lateral acceleration sensor 96 are examples of sensors related to the behavior of the vehicle 1.

[0020] In such a vehicle 1, resonance may occur during driving. The resonance of the vehicle 1 mainly occurs during driving on a wavy road. The resonance during driving on a wavy road is considered to be caused by the overlap between the frequency at which the left rear wheel 61 etc. repeats idling and grounding due to the forced fluctuation from the wavy road and the unsprung resonance frequency or the drive system resonance frequency of the vehicle 1. In particular, in this embodiment, the motor 2, the left rear wheel 61, and the right rear wheel 62 are directly connected without passing through a clutch, a transmission, or the like. Therefore, vibration is easily transmitted from the road surface to the vehicle 1. In this embodiment, the ECU 10 predicts whether resonance will occur using the prediction model described below, and when the vehicle 1 is predicted to resonate, executes a countermeasure process against the resonance of the vehicle 1. The prediction model is stored in advance in the ROM of the ECU 10.

[0021] [Prediction Model] The prediction model is a machine learning-predicted model by supervised learning, which takes as input the calculation value described below before the vehicle 1 resonates and outputs whether the vehicle 1 resonates. The calculation value is calculated based on the detection value of the sensor related to the behavior of the vehicle 1. The sensors related to the behavior of the vehicle 1 are the above-described wheel rotation speed sensors 91 to 94, the shaft rotation speed sensor 95, and the longitudinal and lateral acceleration sensors 96. As supervised learning, for example, any one of logistic regression, random forest, support vector machine, k-nearest neighbor method, and neural network, or a plurality of these may be used.

[0022] The detection values are the longitudinal and lateral acceleration of the vehicle 1, and the rotation speeds of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, the right front wheel 64, and the propeller shaft 3. Here, the propeller shaft 3 is an example of a rotating member that rotates in conjunction with the left rear wheel 61 and the right rear wheel 62 that receive power from the motor 2, which is the driving power source of the vehicle 1. Therefore, for example, instead of the rotation speed of the propeller shaft 3, the rotation speed of the rotor of the motor 2 may be used. Also, when a gear is provided between the motor 2 and the propeller shaft 3, the rotation speed of that gear may be used.

[0023] The calculated values are the average value, maximum value, minimum value, variance value, and standard deviation value of each of the longitudinal and lateral accelerations of the vehicle 1, the rotational speed of the left rear wheel 61, the rotational speed of the right rear wheel 62, the longitudinal and lateral accelerations, the difference in rotational speeds between the left rear wheel 61 and the right rear wheel 62, the difference in rotational speeds between the left front wheel 63 and the right front wheel 64, the difference in rotational speeds between the left rear wheel 61 and the left front wheel 63, and the difference in rotational speeds between the right rear wheel 62 and the right front wheel 64 within a predetermined time period.

[0024] Furthermore, the calculated values include the average value, maximum value, minimum value, variance value, and standard deviation value of the integrated value of the rotational fluctuation amount of the propeller shaft 3 within a predetermined time period. The integrated value of the rotational fluctuation amount is calculated as follows. The rotational fluctuation amount is calculated based on a signal obtained by removing noise from the rotational speed component of the propeller shaft 3 by band-pass filter processing. The rotational fluctuation amount may be, for example, the difference between the target rotational speed and the actual rotational speed, or the difference between the maximum value and the minimum value of the rotational speed of the propeller shaft 3 while the propeller shaft 3 rotates through a predetermined angle. The integrated value is calculated by integrating such a rotational fluctuation amount within a predetermined time period. Such integrated values are calculated for each predetermined time period, and the average value, maximum value, minimum value, variance value, and standard deviation value are calculated from these multiple integrated values.

[0025] Furthermore, the calculated values include the average value, maximum value, minimum value, variance value, and standard deviation value of the difference between the vehicle body speed of the vehicle 1 and the rotational speed of any one of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, and the right front wheel 64 within a predetermined time period. The vehicle body speed is estimated based on the rotational speed of at least one of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, and the right front wheel 64. For example, the vehicle body speed may be the maximum rotational speed among the rotational speeds of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, and the right front wheel 64. Note that the vehicle body speed may be estimated not only based on the rotational speed of the wheels but also by a conventionally known method, for example, using an acceleration sensor or the like.

[0026] Furthermore, the calculated value includes the total number of peak values within a predetermined time of the waveform after the band-pass filter processing of the rotational speed of the left rear wheel 61, the total number of peak values within a predetermined time of the waveform after the band-pass filter processing of the rotational speed of the left front wheel 63, and the total number of peak values within a predetermined time of the waveform after the band-pass filter processing of the longitudinal and lateral acceleration.

[0027] FIG. 2 is an example of a waveform after the band-pass filter processing of the rotational speed of the left rear wheel 61. The band-pass filter processing is a process for removing noise from the detected value indicating the rotational speed of the left rear wheel 61, and is a process for passing a predetermined frequency band including components of the resonance frequency and removing other noise components. As shown in FIG. 2, the ECU 10 calculates, as the calculated value, the total number of peak values within a predetermined time within a predetermined reading range.

[0028] When learning the prediction model, the vehicle 1 is made to travel on a flat road, a stepped road, a cobblestone road, or a wavy road. As described above, resonance is likely to occur during travel on a wavy road. Therefore, before resonance occurs during travel on a wavy road, the detected values such as the rotational speed of the left rear wheel 61 and the longitudinal and lateral acceleration slightly fluctuate, and this fluctuation is reflected in the above-described calculated value. In this way, the prediction model can be generated. The ECU 10 predicts whether resonance will occur before resonance occurs using the prediction model as described below, and executes countermeasure processing for resonance.

[0029] [Resonance countermeasure control] FIG. 3 is a flowchart showing an example of the resonance countermeasure control. This control is repeatedly executed while the ignition is on. The ECU 10 acquires the respective detected values of the wheel speed sensors 91 to 94, the shaft speed sensor 95, and the longitudinal and lateral acceleration sensor 96 (step S1), and calculates the above-described calculated value based on these detected values (step S2).

[0030] Next, the ECU 10 determines whether or not it is predicted that resonance will occur in the vehicle 1 using the above-described prediction model (step S3). If it is determined that resonance will not occur (No in step S3), the ECU 10 turns off the resonance prediction flag (step S4) and ends this control. If it is predicted that resonance will occur (Yes in step S3), the ECU 10 turns on the resonance prediction flag (step S5), and the ECU 10 executes countermeasure processing for resonance (step S6). The countermeasure processing is, in this embodiment, processing for limiting the maximum torque of the motor 2, which will be described in detail later.

[0031] As described above, it is possible to predict the occurrence of resonance early before resonance occurs based on the prediction model, and to start countermeasure processing early if it is predicted that resonance will occur.

[0032] [Countermeasure Processing] FIG. 4 is a timing chart showing an example of countermeasure processing. FIG. 4 shows the transitions of the resonance prediction flag and the maximum torque of the motor 2. When it is predicted that resonance will occur and the resonance prediction flag is switched from off to on (time t1), the maximum torque of the motor 2 is immediately limited. In this way, the countermeasure processing is executed immediately after it is predicted that resonance will occur, and the occurrence of resonance can be avoided. The countermeasure processing shown in FIG. 4 is suitable for a vehicle in which the maximum torque of the motor 2 is relatively large. This is because even if the maximum torque of the motor 2 is immediately limited, since the margin of the motor 2 is large, the influence on drivability is small.

[0033] FIG. 5 is a timing chart showing another example of the countermeasure process. In FIG. 5, the transition of the resonance prediction flag, the integrated value of the rotational fluctuation amount described above, and the maximum torque of the motor 2 is shown. As shown in FIG. 5, when the resonance prediction flag is switched from off to on (time t1), the threshold value for the integrated value for limiting the maximum torque of the motor 2 is switched from the value α to a value β smaller than the value α. As a result, when the integrated value becomes equal to or greater than the value β (time t2), the maximum torque of the motor 2 is limited. The value α is a threshold value for limiting the maximum torque of the motor 2 based on the integrated value when it is predicted that resonance will not occur. The value β is a threshold value for limiting the maximum torque of the motor 2 based on the integrated value when it is predicted that resonance will occur.

[0034] Therefore, when it is predicted that resonance will not occur, the maximum torque of the motor 2 is limited when the integrated value becomes equal to or greater than the value α (time t3). Thus, when it is predicted by the prediction model that resonance will occur, the threshold value is switched to the value β, so that the maximum torque of the motor 2 can be limited earlier.

[0035] The countermeasure process shown in FIG. 5 is suitable for a vehicle in which the maximum torque of the motor 2 is relatively small. This is because in a vehicle with a relatively small maximum torque, the driving force is small, so when the maximum torque of the motor 2 is limited, the impact on drivability is large. Also, the maximum torque may be limited when the integrated rotational fluctuation value starts to increase.

[0036] In the above embodiment, the vehicle 1 which is an electric vehicle is described as an example, but it is not limited thereto. For example, the vehicle may be an engine vehicle equipped with an engine as a driving power source. Also, the vehicle may be a hybrid vehicle equipped with an engine and a motor as driving power sources. Even in these vehicles, by reducing the torque of these driving power sources as a countermeasure process when resonance is predicted, the occurrence of resonance can be suppressed.

[0037] In the above-described embodiment, the motor 2 is directly connected to the left rear wheel 61 and the right rear wheel 62. However, the present invention is not limited to this, and the content of the above-described embodiment can also be applied to a mechanism connected via a clutch, a transmission, or the like.

[0038] In the above-described embodiment, the detected values are the longitudinal acceleration, and the rotational speeds of the left rear wheel 61, the right rear wheel 62, the left front wheel 63, the right front wheel 64, and the propeller shaft 3. However, the present invention is not limited to this, and it may be at least one of the above values.

[0039] The calculated value may include at least one of the average value, the maximum value, the minimum value, the variance value, and the standard deviation value within a predetermined time of at least one of the longitudinal acceleration of the vehicle 1, the difference in the rotational speeds of two wheels of the vehicle 1, the integrated value of the rotational fluctuation amount of the rotating member, and the difference between the vehicle body speed of the vehicle 1 and the rotational speed of any one of the wheels of the vehicle 1.

[0040] The calculated value may include the total number of peak values within a predetermined time of the waveform after the band-pass filter processing of at least one of the detected values.

[0041] As described above, the embodiments of the present invention have been described in detail. However, the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

Description of Reference Numerals

[0042] 1 Vehicle 2 Motor (driving power source for traveling) 3 Propeller shaft (rotating member) 10 ECU (control device, prediction unit, execution unit) 61 Left rear wheel 62 Right rear wheel 63 Left front wheel 64 Right front wheel 91 to 94 Wheel rotation speed sensors (sensors) 95 Shaft rotation speed sensor (sensor) 96 Longitudinal acceleration sensor (sensor)

Claims

1. An arithmetic unit that calculates an arithmetic value based on a detection value of a sensor related to the behavior of a vehicle, A prediction unit that predicts whether the vehicle resonates based on the arithmetic value, using a machine-learned prediction model with supervised learning that takes the arithmetic value before the vehicle resonates as an input and outputs whether the vehicle resonates or not, A control device for a vehicle, comprising an execution unit that executes a countermeasure process against the resonance of the vehicle when it is predicted that the vehicle resonates.

2. The detection value includes at least one of the longitudinal acceleration of the vehicle, the rotational speed of the wheels of the vehicle, and the rotational speed of a rotating member that rotates in conjunction with a wheel that receives power from the driving power source of the vehicle. The arithmetic value includes at least one of the average value, maximum value, minimum value, variance value, and standard deviation value of at least one of the longitudinal acceleration of the vehicle, the difference in rotational speeds of two wheels of the vehicle, the integrated value of the rotational fluctuation amount of the rotating member, and the difference between the vehicle body speed of the vehicle and the rotational speed of any one of the wheels of the vehicle, within a predetermined time. The control device for a vehicle according to Claim 1.

3. The arithmetic value includes the total number of peak values within a predetermined time of the waveform after band-pass filter processing of the detection value. The control device for a vehicle according to Claim 2.

4. The motor, which is the driving power source of the vehicle, is directly connected to any one of the wheels of the vehicle. The control device for a vehicle according to Claim 3.

5. When it is predicted that the vehicle resonates, the execution unit reduces the torque of the driving power source of the vehicle more than when it is not predicted that the vehicle resonates, as the countermeasure process. The control device for a vehicle according to any one of Claims 1 to 4.

Images