Vehicle control device

Abstract

Provided is a vehicle control device enabling stable estimation of a vehicle state quantity with few learning patterns. This vehicle control device comprises: variable dampers (relative displacement control devices) that are provided between the body of a vehicle and each of a plurality of wheels provided, and that control relative displacement between the body and the wheels; a vehicle state calculation unit that is mounted on the vehicle and calculates the state of the vehicle; a relative wheel speed calculation unit (relative speed information calculation unit) that, with respect to signals of speed information (wheel speed) of each of the wheels and a body speed of the vehicle outputted from the vehicle state calculation unit, calculates a fluctuation component of the speed information of each of the wheels from the body speed; a state quantity estimation unit for estimating a state quantity by using a neural network that was trained so as to estimate a state quantity of the vehicle on the basis of outputs from the vehicle state calculation unit and the relative wheel speed calculation unit; and a control value calculation unit (control unit) for controlling the variable dampers on the basis of output from the state quantity estimation unit.

Description

Vehicle control device

[0001] The present disclosure relates to a vehicle control device suitable for application to a vehicle such as a four-wheeled automobile.

[0002] Patent Document 1 discloses a device for estimating the state of a vehicle such as a four-wheeled automobile, which uses a neural network (NN) to calculate vehicle state quantities (e.g., the relative speed between the vehicle body and the wheels, the speed of the vehicle body in the vertical direction, etc.) from wheel speeds and the like.

[0003] In the prior art disclosed in Patent Document 1, a vehicle state quantity is estimated using a neural network that has been trained to estimate the relative velocity between the vehicle body and wheels in the vertical direction of the vehicle and the sprung velocity, which is the vertical velocity of the vehicle body, in accordance with data related to the vehicle speed. The data related to the vehicle speed is wheel speed data, and estimation accuracy can be improved by also using yaw rate, steering angle, vehicle acceleration, and control current value (feedback current).

[0004] International Publication No. 2022 / 168683

[0005] In the above-described conventional technology, sprung velocity and relative velocity are estimated from wheel speed information, and vehicle behavior is estimated using a neural network without installing sensors that directly measure vehicle behavior. Furthermore, vehicle state quantity estimation using a neural network can estimate vehicle state quantities with relatively high accuracy on road surfaces with shapes similar to those used for learning. However, in the above-described conventional technology, wheel speeds are directly input to the neural network. Therefore, even on similar road surfaces, if the vehicle is traveling at a speed different from the learning conditions, the input signal may change significantly, potentially reducing estimation accuracy. Therefore, in order to ensure stable estimation accuracy, learning must be performed for each vehicle speed, which increases the number of learning steps.

[0006] An object of one embodiment of the present invention is to provide a vehicle control device that can stably estimate vehicle state quantities with a small number of learning patterns.

[0007] A vehicle control device according to one embodiment of the present invention includes a relative displacement control device provided between a vehicle body and each of a plurality of wheels, for controlling the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit mounted on the vehicle and calculating the state of the vehicle; a relative speed information calculation unit that calculates a fluctuation in the speed information of each wheel from the vehicle body speed in response to a signal of speed information of each wheel and vehicle body speed of the vehicle output from the vehicle state calculation unit; a state quantity estimation unit that estimates the state quantity using a neural network that has been trained to estimate a state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit; and a control unit that controls the relative displacement control device based on outputs from the state quantity estimation unit.

[0008] A vehicle control device according to one embodiment of the present invention comprises: a relative displacement control device provided between a vehicle body and each of a plurality of wheels, for controlling the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit mounted on the vehicle and calculating the state of the vehicle; a relative speed information calculation unit that calculates a fluctuation in the speed information of each wheel from an average value of wheel speeds of four or two wheels of the vehicle in response to a speed information signal of each wheel output from the vehicle state calculation unit; a state quantity estimation unit that estimates the state quantity using a neural network that has been trained to estimate a state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit; and a control unit that controls the relative displacement control device based on outputs from the state quantity estimation unit.

[0009] A vehicle control device according to one embodiment of the present invention includes a relative displacement control device that is provided between a vehicle body and each of a plurality of wheels and controls the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit that is mounted on the vehicle and calculates the state of the vehicle; a wheel acceleration calculation unit that calculates a fluctuation in the speed information of each wheel from a differential value of the speed information of each wheel output from the vehicle state calculation unit; a state quantity estimation unit that estimates the state quantity using a neural network that has been trained to estimate the state quantity of the vehicle based on outputs from the vehicle state calculation unit and the wheel acceleration calculation unit; and a control unit that controls the relative displacement control device based on outputs from the state quantity estimation unit.

[0010] A vehicle control device according to one embodiment of the present invention includes a drive unit that drives wheels of a vehicle, a vehicle state calculation unit mounted on the vehicle and that calculates the state of the vehicle, a relative speed information calculation unit that calculates a fluctuation in the speed information of each wheel from an average value of the wheel speeds of four or two wheels of the vehicle in response to a signal of speed information of each wheel output from the vehicle state calculation unit, a state quantity estimation unit that estimates the state quantity using a neural network that has been trained to estimate a state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit, and a control unit that controls the drive unit based on outputs from the state quantity estimation unit.

[0011] According to one embodiment of the present invention, vehicle state quantities can be stably estimated with a small number of learning patterns.

[0012] 10 is a block diagram showing a vehicle control device according to a first embodiment of the present invention. FIG. 11 is a block diagram showing a relative wheel speed calculation unit and a state quantity estimator in FIG. 1. FIG. 12 is an explanatory diagram showing an example of a neural network of the state quantity estimator. FIG. 13 is a characteristic line diagram showing a time change of the relative wheel speed when traveling on a similar road surface at different vehicle speeds. FIG. 14 is a characteristic line diagram showing a time change of the relative wheel speed and the sprung velocity. FIG. 15 is a block diagram showing a vehicle control device according to a second embodiment of the present invention. FIG. 16 is a block diagram showing a wheel speed average value calculation unit, a relative wheel speed calculation unit and a state quantity estimator in FIG. 6. FIG. 17 is a block diagram showing a vehicle control device according to a third embodiment of the present invention. FIG. 18 is a block diagram showing an integrator, a relative wheel speed calculation unit and a state quantity estimator in FIG. 6. FIG. 19 is a block diagram showing a vehicle control device according to a fourth embodiment of the present invention. FIG. 10 is a block diagram showing a differentiator, a relative wheel speed calculation unit and a state quantity estimator in FIG. 12. FIG. 19 is a block diagram showing a vehicle control device according to a fifth embodiment of the present invention. FIG. 19 is a block diagram showing a wheel acceleration calculation unit and a state quantity estimator in FIG. 12. FIG. 20 is a block diagram showing a vehicle control device according to a sixth embodiment of the present invention.

[0013] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A vehicle control device according to an embodiment of the present invention will be described in detail below with reference to the accompanying drawings, taking as an example a case where the vehicle control device is applied to a four-wheeled vehicle.

[0014] Fig. 1 shows a vehicle control device 1 according to a first embodiment. The vehicle control device 1 is composed of a suspension device 5 and a controller 11. In Fig. 1, for example, left and right front wheels and left and right rear wheels (hereinafter collectively referred to as wheels 3) are provided on the underside of a vehicle body 2 that constitutes the body of the vehicle. The wheels 3 are composed of tires 4, which act as springs that absorb small irregularities in the road surface. The vehicle body 2 constitutes the sprung mass, and the wheels 3 constitute the unsprung mass.

[0015] The suspension device 5 is provided between the vehicle body 2 and the vehicle wheel 3. The suspension device 5 is composed of a suspension spring 6 (hereinafter referred to as the spring 6) and an adjustable damping force shock absorber (hereinafter referred to as the variable damper 7) provided in parallel with the spring 6 between the vehicle body 2 and the wheel 3.

[0016] 1 shows a case where one set of suspension devices 5 is provided between the vehicle body 2 and the wheels 3. However, a total of four sets of suspension devices 5 are provided individually and independently between, for example, four wheels 3 and the vehicle body 2, and only one of these sets is shown schematically in FIG.

[0017] Here, the variable damper 7 of the suspension device 5 is configured using a damping force adjustable hydraulic shock absorber interposed between the vehicle body 2 and the wheel 3. The variable damper 7 is provided between the vehicle body 2 and the wheel 3, and configures a relative displacement control device that changes the force that suppresses the relative displacement between the vehicle body 2 and the wheel 3.

[0018] The variable damper 7 is provided with a variable damping force actuator 8, which is composed of a damping force adjustment valve or the like, for continuously adjusting the characteristics of the generated damping force (i.e., the damping force characteristics) from hard characteristics (hard characteristics) to soft characteristics (soft characteristics). Note that the variable damping force actuator 8 does not necessarily have to be configured to continuously adjust the damping force characteristics, and may be capable of adjusting the damping force in multiple stages, for example, two or more stages. Furthermore, the variable damper 7 may be of a pressure control type or a flow rate control type. The variable damper 7 may also be of a type that controls viscosity, such as a magnetorheological fluid or an electrorheological fluid.

[0019] The controller 11 constitutes a control device. The controller 11 is configured by, for example, a microcomputer, and serves as a control device for controlling the damping characteristics of the variable damper 7. The controller 11 is connected to, for example, a CAN 10 (Controller Area Network), which is a line network required for data communication. The controller 11 acquires data related to the vehicle behavior (hereinafter referred to as behavior information) through the CAN 10. At this time, the behavior information includes, for example, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, wheel speed, etc. Therefore, this behavior information is input to the controller 11. The output side of the controller 11 is connected to the damping force variable actuator 8 of the variable damper 7.

[0020] The controller 11 also has a storage unit 12 made up of ROM, RAM, non-volatile memory, etc. The storage unit 12 of the controller 11 stores various programs, information (vehicle information), data, etc. for controlling the variable damper 7. The controller 11 estimates the sprung velocity and relative velocity as vehicle state quantities based on the behavior information. In this case, the relative velocity is the relative velocity between the sprung and unsprung parts, and is the piston velocity of the variable damper 7. The controller 11 calculates the force to be generated by the variable damper 7 (force generating mechanism) of the suspension unit 5 based on the estimated vehicle state quantities, and outputs a control signal (command current) to the variable damping force actuator 8 of the suspension unit 5.

[0021] 1 , the controller 11 includes a damper control unit 13, a weight parameter storage unit 14, and a data reading unit 15. The damper control unit 13 includes a vehicle state calculation unit 16, a relative wheel speed calculation unit 17, a state quantity estimation unit 18, and a control value calculation unit 20. The weight parameter storage unit 14 may be a part of the storage unit 12, or may be separate from the storage unit 12.

[0022] The vehicle state calculation unit 16 is mounted on the vehicle and calculates the state of the vehicle. Specifically, the vehicle state calculation unit 16 acquires data related to the vehicle state during driving from communication data transmitted within the vehicle via the CAN 10, and calculates behavior information (vehicle state) such as wheel speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, and yaw rate based on the acquired data. The vehicle state calculation unit 16 also calculates the speed of the vehicle body 2 in the traveling direction as the vehicle body speed. Note that the behavior information calculated by the vehicle state calculation unit 16 from the CAN signal includes the wheel speed, vehicle body speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, and yaw rate, but the present invention is not limited to this. The behavior information may be any information necessary for the state quantity estimation unit 18 to estimate the sprung velocity or relative velocity, and unnecessary information may be omitted. The behavior information is not limited to the above-described information, and various information may be added, for example, to improve the estimation accuracy of the sprung velocity, etc.

[0023] The relative wheel speed calculation unit 17 constitutes a relative speed information calculation unit. As shown in FIGS. 1 and 2 , the relative wheel speed calculation unit 17 calculates the fluctuation of the speed information (wheel speed) of each wheel from the vehicle body speed based on the signal of the speed information (wheel speed) of each wheel and the vehicle body speed output from the vehicle state calculation unit 16. Specifically, the relative wheel speed calculation unit 17 calculates the difference between the wheel speed signal of each wheel and the vehicle body speed signal to calculate the relative wheel speed. Note that the wheel speed information does not necessarily have to be information on the wheel speed itself, but may include various information from which the wheel speed can be calculated. The vehicle body speed is the ground speed of the vehicle in the traveling direction.

[0024] The state quantity estimator 18 receives various types of behavior information calculated based on the CAN signal as input signals from the vehicle state calculator 16. In addition, the state quantity estimator 18 receives the relative wheel speed as an input signal from the relative wheel speed calculator 17.

[0025] The state quantity estimation unit 18 estimates the state quantities (e.g., sprung speed, relative speed) of the vehicle using a neural network that has been trained to estimate the state quantities based on the outputs from the vehicle state calculation unit 16 and the relative wheel speed calculation unit 17. Specifically, the state quantity estimation unit 18 estimates the sprung speed and relative speed using a neural network that has been trained to estimate the sprung speed and relative speed of the vehicle based on the outputs from the vehicle state calculation unit 16 and the relative wheel speed calculation unit 17.

[0026] The weight parameters of the trained neural network are stored in the weight parameter storage unit 14. Therefore, the neural network of the state quantity estimation unit 18 is configured using the weight parameters stored in the weight parameter storage unit 14. The neural network of the state quantity estimation unit 18 outputs the sprung velocity and relative velocity of each wheel in response to input signals from the vehicle state calculation unit 16 and the relative wheel speed calculation unit 17.

[0027] In this embodiment, the in-vehicle network will be described using a CAN as an example, but other in-vehicle networks such as CAN FD (CAN with Flexible Data Rate), FlexRay, or in-vehicle Ethernet may also be used.

[0028] The state quantity estimating unit 18 reads out the weight parameters stored in the weight parameter storage unit 14 via the data reading unit 15. The state quantity estimating unit 18 estimates data related to suspension control required by the control value calculating unit 20, specifically, instantaneous values ​​related to suspension control (sprung speed, relative speed), based on the behavior information calculated by the vehicle state calculating unit 16, the relative wheel speed calculated by the relative wheel speed calculating unit 17, and the weight parameters.

[0029] As shown in FIG. 2 , in this embodiment, the state quantity estimator 18 estimates data related to suspension control for each of the four wheels (sprung velocity, relative velocity) by referring to the behavior information calculated by the vehicle state calculator 16, such as longitudinal acceleration, lateral acceleration, steering angle, and yaw rate, as well as the relative wheel speed calculated by the relative wheel speed calculator 17. The estimated results are then transferred to the downstream control value calculator 20. At this time, the state quantity estimator 18 estimates sensor data related to suspension control for each of the four wheels (vehicle state quantities). The state quantity estimator 18 is configured using a neural network. Weight parameters used in the neural network are determined in advance for the vehicle through machine learning. Therefore, the state quantity estimator 18 can estimate the sprung velocity and relative velocity as vehicle state quantities, taking into account factors such as the stiffness characteristics of the entire vehicle. As a result, the control value calculator 20 controls the variable damper 7 based on the vehicle state quantities appropriately estimated by the state quantity estimator 18. Therefore, the suspension device 5 can be controlled in accordance with the behavior of the vehicle, and the accuracy of the suspension control can be improved.

[0030] Next, the configuration and learning method of the neural network of the state quantity estimating section 18 will be described with reference to FIGS.

[0031] The state quantity estimator 18 is an artificial intelligence (AI) system and is configured using a trained neural network. Weighting parameters, behavior information, and relative wheel speeds are input to the state quantity estimator 18. The neural network of the state quantity estimator 18 is configured using the weighting parameters. As shown in FIG. 3 , the state quantity estimator 18 inputs the behavior information and relative wheel speeds into the neural network to estimate sensor data such as the relative speed and sprung speed of each wheel, and outputs the sensor data. As shown in FIGS. 1 and 2 , the state quantity estimator 18 outputs the sprung speed and relative speed as vehicle state quantities to a downstream control value calculation unit 20. The neural network of the state quantity estimator 18 is configured similarly to the neural network of the vehicle behavior estimator disclosed in, for example, Japanese Patent Application Laid-Open No. 2022-191913.

[0032] As an example, a specific configuration of the neural network of the state quantity estimator 18 will be described with reference to FIG.

[0033] The neural network of the state quantity estimator 18 is a three-layer hierarchical neural network in which elements of an input layer (number of elements i) 101, a hidden layer (number of elements j) 102, and an output layer (number of elements k) 103 are hierarchically connected. Each element of the input layer 101 is connected to each element of the hidden layer 102 by a weight W1ij (i = 1 to I, j = 1 to J), and each element of the hidden layer 102 is connected to each element of the output layer 103 by a weight W2jk (j = 1 to J, k = 1 to K). Information on these weights (hereinafter referred to as weight parameters) is expressed as a determinant of the weights W1ij and W2jk. The weight parameters are calculated in advance by machine learning and stored in the weight parameter storage unit 14. Note that, in this example, a neural network with the simplest all-element-connected hidden layer 102 is shown, but this is not limiting. For example, a neural network with two or more hidden layers 102 may also be used.

[0034] As shown in Figure 3, the input layer 101 of the neural network receives time series data of relative wheel speed calculated by the relative wheel speed calculation unit 17, in addition to time series data such as longitudinal acceleration, lateral acceleration, steering angle, and yaw rate contained in the CAN signal. The output layer 103 outputs instantaneous values ​​of the sprung velocity and relative velocity of the suspension device 5 for each wheel of the vehicle. The number of elements in the hidden layer 102 is generally determined by the number of elements in the input layer 101 and the output layer 103, and is set to a number that maximizes the accuracy of state quantity estimation by the neural network. The number of elements in the output layer 103 is determined by the output specifications for state quantity estimation.

[0035] The neural network machine learning is performed based on data on vehicle state quantities (e.g., sprung speed, unsprung speed), behavior information, and relative wheel speed data previously acquired by a data acquisition vehicle. The data acquisition vehicle has the same specifications as the vehicle in which the state quantity estimation unit 18 is installed, and is equipped with various sensors (speed sensors, acceleration sensors, etc.) that acquire vehicle state quantities. The neural network machine learning adjusts weight parameters to learn the correlation between the vehicle state quantity (sprung speed, unsprung speed) data acquired by the data acquisition vehicle and the behavior information and relative wheel speed data. The weight parameters obtained as a result of learning are stored in the weight parameter memory unit 14.

[0036] In the present embodiment, the state quantity estimating unit 18 performs machine learning to determine the correlation between the vehicle state quantity data acquired by the data acquisition vehicle and the behavior information and relative wheel speed data, but the present invention is not limited to this. For example, a vehicle model corresponding to the vehicle on which the state quantity estimating unit 18 is installed may be constructed, and the state quantity estimating unit 18 may perform machine learning based on data acquired by a simulation using this vehicle model.

[0037] Next, the state quantity estimation process and estimation accuracy using the neural network of the state quantity estimator 18 will be described with reference to FIGS. 2, 4 and 5. FIG.

[0038] 2 shows a state quantity estimation process using a neural network (artificial intelligence: AI) according to the first embodiment. In the first embodiment, before the state quantity estimation process using the neural network, the relative wheel speed calculation unit 17 calculates the difference between the wheel speed signal of each wheel and the vehicle body speed signal to calculate the relative wheel speed. The relative wheel speed calculated by the relative wheel speed calculation unit 17 and the longitudinal acceleration, lateral acceleration, steering angle, and yaw rate calculated by the vehicle state calculation unit 16 are input to the neural network of the state quantity estimation unit 18.

[0039] Here, Figure 4 shows an example of the change over time in relative wheel speed when traveling on two similar but different road surfaces. The solid line in Figure 4 shows the relative wheel speed when traveling on undulating road A at 60 km / h. The dashed line in Figure 4 shows the relative wheel speed when traveling on undulating road B at 100 km / h.

[0040] 4, even if the absolute wheel speed (ground wheel speed) changes significantly, the relative wheel speed calculated by the relative wheel speed calculation unit 17 remains almost unchanged. Therefore, even if the vehicle travels on a road surface similar to a learned road surface at an unlearned vehicle speed, the input signal to the neural network is similar to the learned conditions, and the vehicle state quantity can be estimated with the same estimation accuracy as in the learned scenario.

[0041] Therefore, the conditions under which an undulating road A was traveled at approximately 60 km / h were actually learned, and the state quantities (sprung velocity, relative velocity) were estimated for the above-described conventional technology and the first embodiment (present invention) when an unlearned undulating road B was traveled at approximately 100 km / h. The estimation results are shown in Fig. 5. As shown in Fig. 5, it can be confirmed that the first embodiment (solid line in Fig. 5) is able to estimate values ​​closer to the sensor values ​​(two-dot chain lines in Fig. 5), which are the actual measured values ​​of the state quantities, compared to the above-described conventional technology (broken line in Fig. 5).

[0042] Thus, the vehicle control device 1 according to this embodiment includes a variable damper 7 (relative displacement control device) that is provided between the vehicle body 2 and each of the multiple wheels 3 of the vehicle and controls the relative displacement between the vehicle body 2 and the wheels 3, a vehicle state calculation unit 16 that is mounted on the vehicle and calculates the state of the vehicle, a relative wheel speed calculation unit 17 (relative speed information calculation unit) that calculates the fluctuation of the speed information (wheel speed) of each wheel 3 from the vehicle body speed in response to signals of speed information (wheel speed) of each wheel 3 and the vehicle body speed (ground movement speed in the direction of travel) output from the vehicle state calculation unit 16, a state quantity estimation unit 18 that estimates the state quantity using a neural network that has been trained to estimate the state quantity of the vehicle based on outputs from the vehicle state calculation unit 16 and the relative wheel speed calculation unit 17, and a control value calculation unit 20 (control unit) that controls the variable damper 7 based on the output from the state quantity estimation unit 18.

[0043] The vehicle control device 1 according to this embodiment performs processing to remove steady-state components from the wheel speed signal before input to the neural network so that fluctuations in wheel speed due to the stroke of the suspension device 5 become more noticeable. Even when traveling at different vehicle speeds, fluctuations in wheel speed due to the stroke of the suspension device 5 do not change significantly. This allows the neural network of the state quantity estimator 18 to stably estimate vehicle state quantities with fewer learning patterns. This improves the accuracy of the neural network's estimation of state quantities under unlearned conditions. As the accuracy of the state quantity estimation improves, the control value calculator 20 can appropriately control the variable damper 7, thereby improving the ride comfort of the vehicle. Furthermore, because the robustness of vehicle state quantity estimation under unlearned conditions is improved, the number of learning patterns can be reduced, thereby shortening the development man-hours required for the neural network, etc.

[0044] The vehicle speed is acquired from a CAN signal mounted on the vehicle, and the relative wheel speed calculation unit 17 can calculate the relative wheel speed, which is the variation in the wheel speed, by calculating the difference between the wheel speed acquired from the CAN signal and the vehicle speed.

[0045] 6 and 7 show a second embodiment. The second embodiment is characterized in that the relative speed information calculation unit calculates the fluctuation of the speed information of each wheel by using the wheel speed as the speed information of each wheel and the average value of the wheel speeds of four or two wheels of the vehicle. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0046] 6 and 7, a vehicle control device 21 according to the second embodiment is configured, similarly to the vehicle control device 1 according to the first embodiment, by a suspension device 5 constituting a damping force generating device and a controller 22 constituting a control device. The controller 22 is configured similarly to the controller 11 according to the first embodiment. Therefore, the controller 22 has a storage unit 12. The controller 22 also has a damper control unit 23, a weight parameter storage unit 14, and a data reading unit 15. The damper control unit 23 has a vehicle state calculation unit 24, a relative wheel speed calculation unit 25, a state quantity estimator 18, and a control value calculation unit 20.

[0047] The vehicle state calculation unit 24 is configured in the same manner as the vehicle state calculation unit 16 according to the first embodiment. Therefore, the vehicle state calculation unit 24 acquires data relating to the vehicle state during traveling from communication data transmitted within the vehicle via the CAN 10, and calculates behavior information (vehicle state) such as wheel speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, etc. However, unlike the vehicle state calculation unit 16 according to the first embodiment, the vehicle state calculation unit 24 does not output vehicle body speed.

[0048] The relative wheel speed calculation unit 25 constitutes a relative speed information calculation unit. The relative wheel speed calculation unit 25 calculates fluctuations in the speed information (wheel speed) of each wheel based on the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 24 and the average wheel speed. At this time, an average wheel speed calculation unit 26 that calculates the average wheel speed of four wheels is provided on the input side of the relative wheel speed calculation unit 25. Therefore, in addition to the wheel speed of each wheel, the average wheel speed is input to the relative wheel speed calculation unit 25 instead of the vehicle speed. The relative wheel speed calculation unit 25 calculates the difference between the wheel speed of each wheel and the average wheel speed to calculate the relative wheel speed. The relative wheel speed calculation unit 25 outputs the calculated relative wheel speed to the state quantity estimation unit 18.

[0049] The wheel speed average value calculation unit 26 is not limited to calculating the average value of the wheel speeds of all four wheels. For example, the wheel speed average value calculation unit 26 may calculate the average value of the wheel speeds of two drive wheels. In addition, in the case of a four-wheel drive vehicle, the wheel speed average value calculation unit 26 may calculate the average value of the wheel speeds of either the two front wheels or the two rear wheels.

[0050] The state quantity estimating unit 18 reads out the weight parameters stored in the weight parameter storage unit 14 via the data reading unit 15. The state quantity estimating unit 18 estimates data related to suspension control required by the control value calculating unit 20, specifically, instantaneous values ​​related to suspension control (sprung speed, relative speed), based on the behavior information calculated by the vehicle state calculating unit 24, the relative wheel speed calculated by the relative wheel speed calculating unit 25, and the weight parameters.

[0051] Thus, the second embodiment can also achieve substantially the same effects as the first embodiment. The relative wheel speed calculation unit 25 according to the second embodiment calculates the fluctuation of the speed information (wheel speed) of each wheel from the average value of the wheel speeds of four or two wheels of the vehicle, in response to the signal of the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 24. Therefore, the vehicle state calculation unit 24 according to the second embodiment does not need to calculate the vehicle body speed as in the first embodiment, and only needs to calculate the wheel speed excluding the vehicle body speed. Therefore, in the second embodiment, even if the vehicle body speed cannot be calculated directly, for example, the relative wheel speed calculation unit 25 can calculate the relative wheel speed based on the wheel speed.

[0052] 8 and 9 show a third embodiment. The third embodiment is characterized in that the relative speed information calculation unit calculates the fluctuation of the speed information of each wheel by using the wheel speed as the speed information of each wheel and an integrated value obtained by integrating the acceleration in the vehicle's traveling direction (e.g., longitudinal acceleration) as the vehicle body speed. In the third embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0053] 8 and 9, a vehicle control device 31 according to the third embodiment is configured, similarly to the vehicle control device 1 according to the first embodiment, with a suspension device 5 constituting a damping force generating device and a controller 32 constituting a control device. The controller 32 is configured similarly to the controller 11 according to the first embodiment. Therefore, the controller 32 has a storage unit 12. The controller 32 also has a damper control unit 33, a weight parameter storage unit 14, and a data reading unit 15. The damper control unit 33 has a vehicle state calculation unit 34, a relative wheel speed calculation unit 35, a state quantity estimator 18, and a control value calculation unit 20.

[0054] The vehicle state calculation unit 34 is configured in the same manner as the vehicle state calculation unit 16 according to the first embodiment. Therefore, the vehicle state calculation unit 34 acquires data relating to the vehicle state during traveling from communication data transmitted within the vehicle via the CAN 10, and calculates behavior information (vehicle state) such as wheel speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, etc. However, unlike the vehicle state calculation unit 16 according to the first embodiment, the vehicle state calculation unit 34 does not output vehicle body speed.

[0055] The relative wheel speed calculation unit 35 constitutes a relative speed information calculation unit. The relative wheel speed calculation unit 35 calculates fluctuations in the speed information (wheel speed) of each wheel based on the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 34 and the integrated value of the acceleration in the vehicle's traveling direction, which is the vehicle body speed. At this time, an integrator 36 that integrates the acceleration in the vehicle's traveling direction (e.g., longitudinal acceleration) is provided on the input side of the relative wheel speed calculation unit 35. Therefore, in addition to the wheel speed of each wheel, the integrated value of the vehicle acceleration is input to the relative wheel speed calculation unit 35 instead of the vehicle body speed. The relative wheel speed calculation unit 35 calculates the difference between the wheel speed of each wheel and the integrated value of the longitudinal acceleration to calculate the relative wheel speed. The relative wheel speed calculation unit 35 outputs the calculated relative wheel speed to the state quantity estimation unit 18.

[0056] Note that the integrator 36 is not limited to integrating the longitudinal acceleration. For example, when the vehicle is turning, the integrator 36 may integrate the acceleration in the traveling direction of the vehicle calculated based on the longitudinal acceleration and the lateral acceleration.

[0057] The state quantity estimating unit 18 reads out the weight parameters stored in the weight parameter storage unit 14 via the data reading unit 15. The state quantity estimating unit 18 estimates data related to suspension control required by the control value calculating unit 20, specifically, instantaneous values ​​related to suspension control (sprung speed, relative speed), based on the behavior information calculated by the vehicle state calculating unit 34, the relative wheel speed calculated by the relative wheel speed calculating unit 35, and the weight parameters.

[0058] Thus, the third embodiment can also achieve substantially the same effects as the first embodiment. In the third embodiment, the vehicle body speed is calculated by integrating the vehicle body longitudinal acceleration. Therefore, the vehicle state calculation unit 34 according to the third embodiment does not need to calculate the vehicle body speed as in the first embodiment, and only needs to calculate the acceleration in the vehicle's traveling direction (e.g., longitudinal acceleration) excluding the vehicle body speed. Therefore, in the third embodiment, even if the vehicle body speed cannot be calculated directly, the relative wheel speed calculation unit 35 can calculate the relative wheel speed based on the wheel speed and longitudinal acceleration, thereby reducing the number of required behavior information signals.

[0059] 10 and 11 show a fourth embodiment. The fourth embodiment is characterized in that the relative speed information calculation unit calculates fluctuations in the speed information of each wheel by using the wheel speed as the speed information of each wheel and a differential value obtained by differentiating the travel distance of the vehicle as the vehicle body speed. In the fourth embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0060] 10 and 11 , a vehicle control device 41 according to the fourth embodiment is configured, similarly to the vehicle control device 1 according to the first embodiment, by a suspension device 5 constituting a damping force generating device and a controller 42 constituting a control device. The controller 42 is configured similarly to the controller 11 according to the first embodiment. Therefore, the controller 42 has a storage unit 12. The controller 42 also includes a damper control unit 43, a weight parameter storage unit 14, and a data reading unit 15. The damper control unit 43 includes a vehicle state calculation unit 44, a relative wheel speed calculation unit 45, a state quantity estimator 18, and a control value calculation unit 20.

[0061] The vehicle state calculation unit 44 is configured in the same manner as the vehicle state calculation unit 16 according to the first embodiment. Therefore, the vehicle state calculation unit 44 acquires data relating to the vehicle state during driving from communication data transmitted within the vehicle via the CAN 10, and calculates behavior information (vehicle state) such as wheel speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, etc. based on the acquired data. In addition to receiving signals from the CAN 10, the vehicle state calculation unit 44 also receives GPS signals from the GPS receiver 47. The vehicle state calculation unit 44 calculates the travel distance of the vehicle based on the GPS signals.

[0062] The relative wheel speed calculation unit 45 constitutes a relative speed information calculation unit. The relative wheel speed calculation unit 45 calculates fluctuations in the speed information (wheel speed) of each wheel based on the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 44 and the differential value of the travel distance of the vehicle. At this time, for example, a differentiator 46 that differentiates the travel distance of the vehicle is provided on the input side of the relative wheel speed calculation unit 45. Therefore, in addition to the wheel speed of each wheel, the differential value of the travel distance of the vehicle is input to the relative wheel speed calculation unit 45 instead of the vehicle body speed. The relative wheel speed calculation unit 45 calculates the difference between the wheel speed of each wheel and the differential value of the travel distance of the vehicle to calculate the relative wheel speed. The relative wheel speed calculation unit 45 outputs the calculated relative wheel speed to the state quantity estimation unit 18.

[0063] The differentiator 46 receives the travel distance of the vehicle from the vehicle state calculation unit 44. At this time, the travel distance of the vehicle is measured using, for example, a GPS signal. Therefore, the travel distance of the vehicle may be calculated by a GPS receiver 47 that receives the GPS signal.

[0064] The state quantity estimating unit 18 reads out the weight parameters stored in the weight parameter storage unit 14 via the data reading unit 15. The state quantity estimating unit 18 estimates data related to suspension control required by the control value calculating unit 20, specifically, instantaneous values ​​related to suspension control (sprung speed, relative speed), based on the behavior information calculated by the vehicle state calculating unit 44, the relative wheel speed calculated by the relative wheel speed calculating unit 45, and the weight parameters.

[0065] Thus, the fourth embodiment can achieve substantially the same effects as the first embodiment. In the fourth embodiment, the vehicle speed is calculated from the travel distance (GPS signal). Specifically, the vehicle speed is calculated by differentiating the travel distance. Therefore, in the fourth embodiment, even if the vehicle speed cannot be calculated directly, the relative wheel speed calculation unit 45 can calculate the relative wheel speed based on the wheel speed and the travel distance.

[0066] 12 and 13 show a fifth embodiment. The fifth embodiment is characterized in that the wheel acceleration calculation unit calculates the fluctuation of the speed information of each wheel by using a differential value obtained by differentiating the wheel speed as the speed information of each wheel. In the fifth embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0067] 12 and 13 , a vehicle control device 51 according to the fifth embodiment is configured, similarly to the vehicle control device 1 according to the first embodiment, by a suspension device 5 constituting a damping force generating device and a controller 52 constituting a control device. The controller 52 is configured similarly to the controller 11 according to the first embodiment. Therefore, the controller 52 has a storage unit 12. The controller 52 also has a damper control unit 53, a weight parameter storage unit 14, and a data reading unit 15. The damper control unit 53 has a vehicle state calculation unit 54, a wheel acceleration calculation unit 55, a state quantity estimation unit 56, and a control value calculation unit 20.

[0068] The vehicle state calculation unit 54 is configured in the same manner as the vehicle state calculation unit 16 according to the first embodiment. Therefore, the vehicle state calculation unit 54 acquires data relating to the vehicle state during traveling from communication data transmitted within the vehicle via the CAN 10, and calculates behavior information (vehicle state) such as wheel speed, longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, etc. However, unlike the vehicle state calculation unit 16 according to the first embodiment, the vehicle state calculation unit 54 does not output vehicle body speed.

[0069] The wheel acceleration calculation unit 55 calculates the fluctuation of the speed information (wheel speed) of each wheel based on the differential value of the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 54. At this time, the wheel acceleration calculation unit 55 is a differentiator that differentiates the wheel speed. Therefore, the wheel speed of each wheel is input to the wheel acceleration calculation unit 55. The wheel acceleration calculation unit 55 calculates the differential value of the wheel speed of each wheel to calculate the wheel acceleration. The wheel acceleration calculation unit 55 outputs the calculated wheel acceleration to the state quantity estimation unit 56.

[0070] The state quantity estimating unit 56 is configured in the same manner as the state quantity estimating unit 18 according to the first embodiment. The state quantity estimating unit 56 estimates the state quantities using a neural network that has been trained to estimate the state quantities of the vehicle based on outputs from the vehicle state calculating unit 54 and the wheel acceleration calculating unit 55. At this time, weight parameters that are the learning results of the neural network are stored in the weight parameter storage unit 14. The state quantity estimating unit 56 reads out the weight parameters stored in the weight parameter storage unit 14 via the data reading unit 15. The state quantity estimating unit 56 estimates data related to suspension control required by the control value calculating unit 20, specifically, instantaneous values ​​related to suspension control (sprung velocity, relative velocity), based on the behavior information calculated by the vehicle state calculating unit 54, the wheel acceleration calculated by the wheel acceleration calculating unit 55, and the weight parameters.

[0071] Thus, the fifth embodiment can achieve substantially the same effects as the first embodiment. The wheel acceleration calculation unit 55 according to the fifth embodiment calculates the fluctuation in the speed information (wheel speed) of each wheel from the differential value of the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 54. Therefore, in the fifth embodiment, the wheel acceleration calculation unit 55 calculates the fluctuation in the speed information (wheel speed) of each wheel based only on the wheel speed of each wheel. Therefore, in the fifth embodiment, there is no need to calculate the vehicle speed as in the first embodiment, and the number of signals of required behavior information can be reduced.

[0072] Next, Fig. 14 shows a sixth embodiment. The sixth embodiment is characterized in that the control unit controls a drive device that drives the wheels of the vehicle based on the output from the state quantity estimator. In the sixth embodiment, the same components as those in the second embodiment are denoted by the same reference numerals, and their description will be omitted.

[0073] 14, a vehicle control device 61 according to the sixth embodiment is made up of a drive device 62 that drives the wheels of the vehicle and a controller 63 that constitutes the control device. The drive device 62 includes a braking force generating device that applies braking force to the wheels 3, such as a disc brake or drum brake, a driving force generating device that applies driving force to the wheels 3 (drive wheels), such as an engine or motor, and a steering device that controls the steering angle of the steered wheels. Alternatively, the drive force generating device, braking force generating device, and steering device may be combined.

[0074] The controller 63 is configured in the same manner as the controller 22 according to the second embodiment. Therefore, the controller 63 has a storage unit 12. The controller 63 also has a drive device control unit 64, a weight parameter storage unit 14, and a data reading unit 15. The drive device control unit 64 is configured in the same manner as the damper control unit 23 according to the second embodiment, and has a vehicle state calculation unit 24, a relative wheel speed calculation unit 25, a state quantity estimation unit 18, and a control value calculation unit 65.

[0075] The relative wheel speed calculation unit 25 calculates the fluctuation of the speed information (wheel speed) of each wheel based on the speed information (wheel speed) of each wheel output from the vehicle state calculation unit 24 and the average value of the wheel speeds of all four wheels or two drive wheels. At this time, an average wheel speed calculation unit 26 that calculates the average wheel speed is provided on the input side of the relative wheel speed calculation unit 25. Therefore, the wheel speed of each wheel and the average wheel speed are input to the relative wheel speed calculation unit 25. The relative wheel speed calculation unit 25 calculates the difference between the wheel speed of each wheel and the average wheel speed to calculate the relative wheel speed. The relative wheel speed calculation unit 25 outputs the calculated relative wheel speed to the state quantity estimation unit 18.

[0076] The state quantity estimation unit 18 estimates data related to suspension control required by the control value calculation unit 65, specifically, instantaneous values ​​related to suspension control (sprung speed, relative speed), based on the behavior information calculated by the vehicle state calculation unit 24, the relative wheel speed calculated by the relative wheel speed calculation unit 25, and the weighting parameters read out from the weighting parameter memory unit 14.

[0077] The control value calculation unit 65 is a control unit that controls the drive device 62 based on the output from the state quantity estimation unit 18. The control value calculation unit 65 calculates control values ​​(e.g., target braking force, target driving force, target steering angle, etc.) for controlling the braking force, driving force, steering angle, etc. of the drive device 62 based on the instantaneous values ​​input from the state quantity estimation unit 18. The control value calculation unit 65 outputs control signals based on the control values ​​to the drive device 62. The drive device 62 operates the brakes, engine, steering, etc. based on the control values ​​output from the control value calculation unit 65. As a result, the vehicle control device 61 controls the braking force, driving force, etc. of each wheel based on the sprung velocity, etc. estimated by the state quantity estimation unit 18, thereby controlling the up and down movement of the vehicle body 2.

[0078] Thus, the sixth embodiment can also achieve substantially the same effects as the first embodiment. In the sixth embodiment, the control value calculation unit 65 (control unit) controls the drive unit 62 based on the output from the state quantity estimator 18. Therefore, the vehicle control device 61 can be applied to vehicles in which the dampers of the suspension device are passively controlled or not passively controlled.

[0079] Although the sixth embodiment is applied to the second embodiment, the present invention is not limited to this. That is, the sixth embodiment may be applied to the first embodiment, or to the third to fifth embodiments.

[0080] In the first embodiment, the controller 11 acquires vehicle behavior information (vehicle state) including wheel speed through the CAN 10, but the present invention is not limited to this. The controller 11 may, for example, directly acquire detection values ​​from various sensors. Alternatively, various sensors that detect longitudinal acceleration (longitudinal G), lateral acceleration (lateral G), steering angle, yaw rate, wheel speed, etc. may calculate the vehicle state and input the calculated value to the controller 11. In this case, the various sensors constitute a vehicle state calculation unit. Alternatively, the controller 11 may acquire behavior information from another controller, etc. This configuration can also be applied to the second to sixth embodiments.

[0081] In the first embodiment, an example has been described in which the force generating mechanism is the variable damper 7 made of a semi-active damper. However, the present invention is not limited to this, and an active damper (either an electric actuator or a hydraulic actuator) may be used as the force generating mechanism. In the first embodiment, an example has been described in which the force generating mechanism that generates a force that can be adjusted between the vehicle body 2 side and the wheel 3 side is configured by the variable damper 7 made of a damping force adjustable hydraulic shock absorber. However, the present invention is not limited to this, and for example, the force generating mechanism may be configured by an air suspension, a stabilizer (kinesus), an electromagnetic suspension, or the like, in addition to a hydraulic shock absorber. These configurations can also be applied to the second to fifth embodiments.

[0082] In the first embodiment, a vehicle behavior control device for use in a four-wheeled automobile has been described as an example. However, the present invention is not limited to this and can also be applied to, for example, work vehicles, transport vehicles such as trucks and buses. This configuration can also be applied to the second to sixth embodiments.

[0083] This application claims priority to Japanese Patent Application No. 2023-207472, filed December 8, 2023. The entire disclosure of Japanese Patent Application No. 2023-207472, filed December 8, 2023, including the specification, claims, drawings, and abstract, is incorporated herein by reference in its entirety.

[0084] 1, 21, 31, 41, 51, 61: vehicle control device, 2: vehicle body, 3: wheel, 5: suspension device, 7: adjustable damping force shock absorber (variable damper), 8: variable damping force actuator, 11, 22, 32, 42, 52, 63: controller, 16, 24, 34, 44, 54: vehicle state calculation unit, 17, 25, 35, 45: relative wheel speed calculation unit (relative speed information calculation unit), 18, 56: state quantity estimator, 20, 65: control value calculation unit (control unit), 26: wheel speed average value calculation unit, 36: integrator, 46: differentiator, 55: wheel acceleration calculation unit, 62: drive device

Claims

1. A vehicle control device comprising: a relative displacement control device provided between a vehicle body and each of a plurality of wheels, the relative displacement control device controlling the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit mounted on the vehicle and calculating a state of the vehicle; a relative speed information calculation unit which calculates a fluctuation in the speed information of each wheel from the vehicle body speed in response to a signal of speed information of each wheel and the vehicle body speed of the vehicle output from the vehicle state calculation unit; a state quantity estimation unit which estimates the state quantity using a neural network that has been trained to estimate a state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit; and a control unit which controls the relative displacement control device based on the output from the state quantity estimation unit.

2. A vehicle control device according to claim 1, wherein the vehicle speed is obtained from a CAN signal mounted on the vehicle.

3. A vehicle control device according to claim 1, wherein the vehicle speed is calculated by integrating the vehicle longitudinal acceleration.

4. A vehicle control device according to claim 1, wherein the vehicle speed is calculated from a traveled distance.

5. A vehicle control device comprising: a relative displacement control device provided between a vehicle body and each of a plurality of wheels, the relative displacement control device controlling the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit mounted on the vehicle and calculating a state of the vehicle; a relative speed information calculation unit for calculating a fluctuation in the speed information of each wheel from an average value of the wheel speeds of two or four wheels of the vehicle in response to a signal of speed information of each wheel output from the vehicle state calculation unit; a state quantity estimation unit for estimating the state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit; and a control unit for controlling the relative displacement control device based on the output from the state quantity estimation unit.

6. A vehicle control device comprising: a relative displacement control device provided between a vehicle body and each of a plurality of wheels, the relative displacement control device controlling the relative displacement between the vehicle body and the wheels; a vehicle state calculation unit mounted on the vehicle, the vehicle state calculation unit calculating a state of the vehicle; a wheel acceleration calculation unit calculating a fluctuation in the speed information of each wheel from a differential value of the speed information of each wheel output from the vehicle state calculation unit; a state quantity estimation unit estimating the state quantity using a neural network that has been trained to estimate the state quantity of the vehicle based on outputs from the vehicle state calculation unit and the wheel acceleration calculation unit; and a control unit that controls the relative displacement control device based on the output from the state quantity estimation unit.

7. A vehicle control device comprising: a drive device that drives wheels of a vehicle; a vehicle state calculation unit mounted on the vehicle and calculating a state of the vehicle; a relative speed information calculation unit that calculates a fluctuation in the speed information of each wheel from an average value of the wheel speeds of four or two wheels of the vehicle in response to a signal of speed information of each wheel output from the vehicle state calculation unit; a state quantity estimation unit that estimates the state quantity using a neural network that has been trained to estimate a state quantity of the vehicle based on outputs from the vehicle state calculation unit and the relative speed information calculation unit; and a control unit that controls the drive device based on the output from the state quantity estimation unit.

Images