WO2022168683A1 - 車両状態量推定装置 - Google Patents
車両状態量推定装置 Download PDFInfo
- Publication number
- WO2022168683A1 WO2022168683A1 PCT/JP2022/002726 JP2022002726W WO2022168683A1 WO 2022168683 A1 WO2022168683 A1 WO 2022168683A1 JP 2022002726 W JP2022002726 W JP 2022002726W WO 2022168683 A1 WO2022168683 A1 WO 2022168683A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- vehicle
- acceleration
- speed
- neural network
- Prior art date
Links
- 238000013528 artificial neural network Methods 0.000 claims abstract description 61
- 230000001133 acceleration Effects 0.000 claims description 251
- 238000001514 detection method Methods 0.000 claims description 46
- 239000006096 absorbing agent Substances 0.000 claims description 36
- 230000035939 shock Effects 0.000 claims description 36
- 238000013016 damping Methods 0.000 claims description 31
- 230000004044 response Effects 0.000 claims description 9
- 230000006403 short-term memory Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 38
- 238000000034 method Methods 0.000 description 29
- 239000000725 suspension Substances 0.000 description 12
- 230000000052 comparative effect Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000015654 memory Effects 0.000 description 5
- 230000000306 recurrent effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/107—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G17/00—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load
- B60G17/015—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G17/00—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load
- B60G17/06—Characteristics of dampers, e.g. mechanical dampers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2202/00—Indexing codes relating to the type of spring, damper or actuator
- B60G2202/40—Type of actuator
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/05—Attitude
- B60G2400/052—Angular rate
- B60G2400/0523—Yaw rate
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/10—Acceleration; Deceleration
- B60G2400/102—Acceleration; Deceleration vertical
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/10—Acceleration; Deceleration
- B60G2400/104—Acceleration; Deceleration lateral or transversal with regard to vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/10—Acceleration; Deceleration
- B60G2400/106—Acceleration; Deceleration longitudinal with regard to vehicle, e.g. braking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/20—Speed
- B60G2400/202—Piston speed; Relative velocity between vehicle body and wheel
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/20—Speed
- B60G2400/204—Vehicle speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/20—Speed
- B60G2400/208—Speed of wheel rotation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2400/00—Indexing codes relating to detected, measured or calculated conditions or factors
- B60G2400/40—Steering conditions
- B60G2400/41—Steering angle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2500/00—Indexing codes relating to the regulated action or device
- B60G2500/10—Damping action or damper
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2600/00—Indexing codes relating to particular elements, systems or processes used on suspension systems or suspension control systems
- B60G2600/18—Automatic control means
- B60G2600/187—Digital Controller Details and Signal Treatment
- B60G2600/1878—Neural Networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G2800/00—Indexing codes relating to the type of movement or to the condition of the vehicle and to the end result to be achieved by the control action
- B60G2800/70—Estimating or calculating vehicle parameters or state variables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/14—Yaw
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/28—Wheel speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/18—Steering angle
Definitions
- the embodiment of the present invention relates to a vehicle state quantity estimation device.
- the relative speed of the wheels with respect to the vehicle body in the vertical direction of the vehicle (so-called stroke speed) and the speed of the vehicle body in the vertical direction of the vehicle (so-called sprung speed) are estimated as the vehicle state, and the estimated relative speed and the speed of the vehicle body are estimated.
- Techniques for controlling the damping force of suspension shock absorbers based on velocity are known.
- a vehicle state quantity estimating apparatus includes a data acquisition unit that acquires first data that is data relating to a speed of a vehicle; Using a first neural network trained to estimate at least one of the relative speed of the wheels of the vehicle with respect to the body of the vehicle and the vehicle body speed, which is the speed of the vehicle body in the vertical direction, the data a vehicle state estimation unit that estimates at least one of the relative speed and the vehicle body speed according to the first data acquired by the acquisition unit;
- the vehicle state estimating unit detects the relative speed of the wheels with respect to the vehicle body in the vertical direction of the vehicle and the speed of the vehicle body in the vertical direction of the vehicle in response to the input of the first data. At least one of the relative speed and the vehicle body speed is estimated according to the first data acquired by the data acquisition unit using the first neural network trained to estimate at least one of the speed and the speed. , the accuracy of estimating the vehicle state (at least one of the relative speed and the vehicle body speed) can be improved.
- the first data is wheel speed data indicating the rotational speed of the wheels.
- the vehicle state estimating unit calculates the relative speed of the wheels with respect to the vehicle body in the vertical direction of the vehicle and the vehicle body speed, which is the speed of the vehicle body in the vertical direction of the vehicle. At least one of the relative speed and the vehicle body speed is estimated according to the wheel speed data acquired by the data acquisition unit using the first neural network trained to estimate at least one of the vehicle It is possible to improve the accuracy of estimating the state (at least one of relative speed and vehicle body speed).
- the data acquisition unit acquires yaw rate data indicating the yaw rate of the vehicle
- the first neural network acquires the relative speed data according to the input of the wheel speed data and the yaw rate. Learning is performed to estimate at least one of the speed and the vehicle body speed, and the vehicle state estimation unit uses the first neural network to obtain the wheel speed data and At least one of the relative velocity and the vehicle body velocity is estimated according to the yaw rate data.
- the vehicle includes a shock absorber interposed between the vehicle body and the wheel and capable of changing a damping force according to an input current
- the data acquisition unit includes: Current value data indicating the value of the current is obtained, and the first neural network estimates at least one of the relative speed and the vehicle body speed in accordance with the input of the wheel speed data and the current value data.
- the vehicle state estimation unit uses the first neural network to determine the relative speed and the vehicle body according to the wheel speed data and the current value data acquired by the data acquisition unit Estimate at least one of speed and speed.
- the data acquisition unit acquires steering angle data indicating the steering angle of the vehicle
- the first neural network inputs the wheel speed data and the steering angle data.
- learning is performed so as to estimate at least one of the relative speed and the vehicle body speed according to the data obtained by the data obtaining unit
- the vehicle state estimating unit uses the first neural network to obtain the At least one of the relative speed and the vehicle speed is estimated according to the wheel speed data and the steering angle data.
- the first data is acceleration data indicating acceleration of the vehicle
- the first neural network is trained to estimate the relative speed
- the vehicle state estimation unit estimates the relative velocity according to the acceleration data acquired by the data acquisition unit using the first neural network.
- the relative speed estimating unit is the first neural network trained so as to estimate the relative speed of the wheels of the vehicle with respect to the vehicle body in the vertical direction of the vehicle in accordance with the input of the acceleration data. is used to estimate the relative speed according to the acceleration data acquired by the data acquisition unit, so it is possible to improve the accuracy of estimating the relative speed of the wheels with respect to the vehicle body.
- the data acquiring unit acquires yaw rate data indicating the yaw rate of the vehicle
- the first neural network acquires the relative acceleration data according to the input of the acceleration data and the yaw rate data. Learning is performed to estimate speed, and the vehicle state estimation unit uses the first neural network to estimate the relative speed according to the acceleration data and the yaw rate data acquired by the data acquisition unit. to estimate
- the vehicle includes a shock absorber interposed between the vehicle body and the wheel and capable of changing a damping force according to an input current
- the data acquisition unit includes: Acquiring current value data indicating the value of the current
- the first neural network performs learning so as to estimate the relative velocity in accordance with the inputs of the acceleration data and the current value data
- the vehicle The state estimator uses the first neural network to estimate the relative velocity according to the acceleration data and the current value data acquired by the data acquisition section.
- the data acquisition unit acquires steering angle data indicating the steering angle of the vehicle
- the first neural network receives the acceleration data and the steering angle data.
- the vehicle state estimation unit uses the first neural network to estimate the relative velocity according to the acceleration data and the steering angle data acquired by the data acquisition unit. estimating the relative velocity.
- the data acquisition unit acquires wheel speed data indicating the rotational speed of the wheels
- the first neural network receives the acceleration data and the wheel speed data.
- the vehicle state estimation unit uses the first neural network to estimate the relative speed according to the acceleration data and the wheel speed data acquired by the data acquisition unit. estimating the relative velocity.
- the data acquisition unit obtains data from acceleration sensors provided only for some of a plurality of acceleration detection target locations at different positions in the vehicle. and an acquisition unit that acquires actual acceleration data indicating actual acceleration that is the acceleration of each Using a second neural network trained to estimate the actual acceleration of the acceleration detection target location detected by the acceleration sensor, the acceleration detection target location of the plurality of acceleration detection target locations according to the input of the actual acceleration data. and an estimating unit that estimates all the actual accelerations.
- the first neural network is LSTM (Long Short Term Memory).
- a vehicle state quantity estimating apparatus detects an actual acceleration at a target acceleration detection point from acceleration sensors provided only for some of a plurality of acceleration detection target points at different positions in a vehicle. and an acquisition unit that acquires actual acceleration data indicating the actual acceleration, and each of the accelerations when the acceleration sensors are provided for all of the plurality of acceleration detection target locations according to the input of the actual acceleration data.
- FIG. 1 is a schematic diagram showing a schematic configuration of an example of a vehicle according to a first embodiment
- FIG. FIG. 2 is a schematic diagram showing a schematic configuration of one example of the suspension system in the vehicle according to the first embodiment.
- FIG. 3 is an exemplary functional block diagram of a control device of the vehicle according to the first embodiment;
- FIG. 4 is an exemplary and schematic block diagram showing the configuration of the vehicle state estimation network according to the first embodiment.
- FIG. 5 is an exemplary schematic block diagram showing an example of the configuration of an encoder unit of the vehicle state estimation network according to the first embodiment;
- FIG. 6 is an exemplary schematic block diagram showing an example of the configuration of a decoder unit of the vehicle state estimation network according to the first embodiment;
- FIG. 7 is an exemplary schematic block diagram showing an example of the configuration of the LSTM block of the vehicle state estimation network according to the first embodiment.
- 8 is a flowchart showing an example of a vehicle state estimation method executed by the control device according to the first embodiment;
- FIG. 9 is an exemplary schematic diagram showing an example of a stroke speed estimation result by the technique according to the first embodiment.
- FIG. 10 is a schematic diagram showing a schematic configuration of an example of the vehicle according to the second embodiment.
- FIG. 11 is an exemplary functional block diagram of a control device for a vehicle according to a second embodiment;
- FIG. 12 is an exemplary schematic block diagram showing the configuration of a stroke speed estimation network according to the second embodiment.
- FIG. 13 is a flowchart showing an example of a relative speed estimation method executed by the control device according to the second embodiment;
- FIG. 14 is an exemplary and schematic diagram showing an example of stroke speed estimation results by the technique according to the second embodiment.
- FIG. 15 is an exemplary and schematic diagram showing an example of a stroke speed estimation result according to a technique according to a comparative example.
- FIG. 16 is an exemplary and schematic diagram showing an example of a stroke speed estimation error according to the technique according to the second embodiment.
- FIG. 17 is an exemplary and schematic diagram showing an example of a stroke speed estimation error according to the technique according to the second embodiment.
- FIG. 18 is a schematic diagram showing an example schematic configuration of a vehicle according to a third embodiment.
- FIG. 19 is an exemplary functional block diagram of a control device for a vehicle according to a third embodiment
- FIG. 20 is an exemplary schematic block diagram showing configurations of a stroke speed estimation network and a sprung acceleration estimation network according to the third embodiment.
- FIG. 21 is an exemplary and schematic diagram showing an example of the estimation result of the sprung acceleration by the technique according to the third embodiment.
- FIG. 22 is an exemplary and schematic diagram showing an example of an estimation result of the sprung mass acceleration by the technology according to the comparative example.
- FIG. 1 is a schematic diagram showing a schematic configuration of an example of a vehicle 1 according to the first embodiment.
- the vehicle 1 may be, for example, an automobile (internal combustion engine automobile) using an internal combustion engine (engine, not shown) as a drive source, or an electric motor (motor, not shown) as a drive source. It may be a vehicle (electric vehicle, fuel cell vehicle, etc.) that uses both of them as a driving source (hybrid vehicle).
- the vehicle 1 can be equipped with various transmissions, and can be equipped with various devices (systems, parts, etc.) necessary for driving the internal combustion engine and the electric motor. Further, the system, number, layout, etc.
- the vehicle 1 is a four-wheeled vehicle (four-wheeled vehicle) and has two left and right front wheels 3F and two left and right rear wheels 3R.
- the front (direction Fr) in the longitudinal direction of the vehicle is the left side.
- the vehicle control system 100 of the vehicle 1 includes a control device 10, a steering device 11, a steering angle sensor 12, a yaw rate sensor 13, a braking system 61, and the like. Further, the vehicle control system 100 includes a suspension device 4, a rotation sensor 5, a braking device 6, etc. corresponding to each of the two front wheels 3F, and a suspension device corresponding to each of the two rear wheels 3R. 4, a rotation sensor 5 and the like are provided.
- the vehicle 1 includes basic components of the vehicle 1 other than those shown in FIG. 1, only the configuration related to the vehicle control system 100 and the control related to the configuration will be described here.
- the wheels 3 are used as a general term for the two front wheels 3F and the two rear wheels 3R.
- the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 is also referred to as stroke speed, and the portion of the vehicle 1 on the vehicle body 2 side with respect to the suspension system 4 is also referred to as sprung mass. The part of the vehicle 1 on the side is also called unsprung. Also, unless otherwise specified in the following description, the relative speed is the relative speed of the wheels 3 with respect to the vehicle body 2 in the vertical direction of the vehicle 1 .
- the control device 10 receives signals, data, etc. from each part of the vehicle control system 100, and also controls each part of the vehicle control system 100 and executes various calculations.
- the control device 10 is an example of a vehicle state quantity estimation device.
- the control device 10 is configured as a computer, and includes an arithmetic processing unit (microcomputer, ECU (Electronic Control Unit), etc., not shown) and a storage unit 10d (eg, ROM (Read Only Memory), RAM (Random Access Memory), flash memory), etc., see Fig. 3), etc.
- the arithmetic processing unit reads out a program stored (installed) in a non-volatile storage unit 10d (eg, ROM, flash memory, etc.), executes arithmetic processing according to the program, and executes each unit shown in FIG. can function (operate) as
- the storage unit 10d can also store data (tables (data groups), functions, etc.) used in various calculations related to control, calculation results (including values in the middle of calculation), and the like.
- a vehicle state estimation network 121 is stored in the storage unit 10d. Details of the vehicle state estimation network 121 will be described later.
- the steering device 11 includes, for example, a steering wheel, and steers (steers) the two front wheels 3F.
- the steering angle sensor 12 detects the steering angle (steering angle, turning angle, turning angle) of the front wheels 3F and outputs steering angle data indicating the detected steering angle.
- the yaw rate sensor 13 detects the yaw rate of the vehicle 1 (body 2) and outputs yaw rate information indicating the detected yaw rate.
- FIG. 2 is a schematic diagram showing a schematic configuration of one example of the suspension system 4 in the vehicle according to the first embodiment.
- the suspension device 4 is interposed between the wheels 3 and the vehicle body 2 to suppress transmission of vibrations and impacts from the road surface to the vehicle body.
- the suspension device 4 has a coil spring 4a and a shock absorber 4b.
- the shock absorber 4b can electrically control (adjust) the damping force (damping characteristic).
- the shock absorber 4b has an actuator 4bb that operates based on the input current.
- the actuator 4bb can change the degree of opening of an orifice provided in the piston of the shock absorber 4b, or change the degree of opening between the valve body and the valve seat.
- the damping force of the shock absorber 4b is adjusted by controlling the amount of lubricating oil flowing between the two oil chambers partitioned by the piston in the shock absorber 4b.
- the suspension device 4 is provided for each of the four wheels 3 (two front wheels 3F and two rear wheels 3R), and the control device 10 can control the damping force of each of the four wheels 3.
- the control device 10 can control the four wheels 3 to have different damping forces.
- the shock absorber 4b is also called a damper.
- the rotation sensor 5 can output a signal corresponding to the rotation speed (angular velocity, rotation speed, rotation state) of each of the four wheels 3 .
- the control device 10 can calculate the speed of the vehicle 1 from the detection result of the rotation sensor 5 .
- a rotation sensor (not shown) for detecting rotation of a crankshaft, an axle, or the like may be provided. A velocity of 1 may be obtained.
- vehicle control system 100 described above is merely an example, and can be implemented with various modifications.
- Well-known devices can be used as individual devices that configure vehicle control system 100 .
- each configuration of the vehicle control system 100 can be shared with other configurations.
- control device 10 includes a data acquisition unit 10a, a vehicle state estimation unit 10b, an attenuation It can function (operate) as the control unit 10c or the like.
- the program can include, for example, a module corresponding to each block except for the storage unit 10d shown in FIG.
- the data acquisition unit 10 a acquires wheel speed data indicating the rotational speed of the wheels 3 from each rotation sensor 5 .
- the data acquisition unit 10 a also acquires yaw rate data indicating the yaw rate of the vehicle 1 from the yaw rate sensor 13 .
- the data acquisition unit 10a also acquires current value data indicating the value of the current input to the shock absorber 4b from the attenuation control unit 10c.
- the data acquisition unit 10 a also acquires steering angle data indicating the steering angle of the vehicle 1 from the steering angle sensor 12 .
- the vehicle state estimation unit 10b receives predetermined data (hereinafter also referred to as input data) acquired by the data acquisition unit 10a.
- the vehicle state estimation unit 10b uses the vehicle state estimation network 121 to estimate the relative speed according to the input data.
- the input data includes at least wheel speed data.
- the input data may include at least one of yaw rate data, current value data, and steering angle data.
- Input data is not limited to the above.
- Wheel speed data is an example of the first data.
- the vehicle state estimation network 121 calculates the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 in the vertical direction of the vehicle 1 and the vehicle body speed, which is the speed of the vehicle body 2 in the vertical direction of the vehicle 1, according to the input of the input data. and at least one (as an example, both) is configured as a recurrent neural network (RNN) trained in advance.
- RNN recurrent neural network
- the input data is the above-described input data acquired by the data acquisition unit 10a, and the output data as teacher data is measured by, for example, a relative speed sensor (not shown).
- the vehicle state estimation network 121 may be configured as a recurrent neural network (RNN) trained in advance so as to estimate either the relative velocity or the vehicle body velocity.
- RNN recurrent neural network
- FIG. 4 is an exemplary and schematic block diagram showing the configuration of the vehicle state estimation network 121 according to the first embodiment.
- FIG. 5 is an exemplary and schematic block diagram showing an example of the configuration of the encoder section 121a of the vehicle state estimation network 121 according to the first embodiment.
- FIG. 6 is an exemplary and schematic block diagram showing an example of the configuration of the decoder section 121b of the vehicle state estimation network 121 according to the first embodiment.
- FIG. 7 is an exemplary and schematic block diagram showing an example of the configuration of the LSTM block of the vehicle state estimation network 121 according to the first embodiment.
- the vehicle state estimation network 121 is configured as a Seq2Seq (Sequence to Sequence) model. More specifically, the vehicle state estimation network 121 includes an encoder unit 121a that receives an input of input data and performs encoding processing, and performs decoding processing based on the result of the encoding performed by the encoder unit 121a. (hereinafter also referred to as output data).
- Seq2Seq Sequence to Sequence
- the vehicle state estimation network 121 receives input of time-series data such as the above - described input data x 1 , x 2 , x 3 , x 4 , x 5 , . It is pre-trained by machine learning so as to output time-series data indicating output for each time such as y 2 , y 3 , y 4 , y 5 , .
- the encoder unit 121a is configured based on LSTM (Long short-term memory). That is, the encoder section 121a is configured using a plurality (for example, N) of LSTM blocks B 11 , B 12 , . . . B 1N . LSTM blocks B 11 , B 12 , . . . B 1N may be collectively referred to as LSTM block B 1 hereinafter.
- the structure of each LSTM block B 11 , B 12 , . . . B 1N is a general structure with an input gate, an output gate and a forget gate. As an example, as shown in FIG.
- the LSTM block B 1 includes matrix multiplication units 201a and 201b, addition units 201c, 201d and 201k, multiplication units 201j and 201p, a slice unit 201e, a sigmoid function unit 201f, 201h, 201i and tanh portion 201g. Calculations are performed by these units.
- the addition units 201c, 201d, 201k and the multiplication units 201j, 201p are computations (Hadamard computations) for each matrix element. Note that Wh in FIG. 7 is the weight given to the hidden layer, and Wx is the weight given to the input value.
- the LSTM block B 11 receives the input data x 1 and passes the data h 1 indicating the output corresponding to the input and the data c 1 indicating the memory cell to the next LSTM block B 12 .
- the blocks after the LSTM block B12 operate in the same manner, and the N -th LSTM block B1N receives the input of the data xN, and receives the data hN indicating the output according to the input and the data c indicating the memory cell. N and are transferred to the outside of the encoder section 121a (that is, the decoder section 121b).
- the decoder section 121b is also configured based on the LSTM, like the encoder section 121a described above. That is, the decoder section 121b is also configured using a plurality (for example, N) of LSTM blocks B 21 , B 22 , . . . B 2N . The configuration of each of the LSTM blocks B 21 , B 22 , . be.
- the decoder unit 121b includes a plurality of ( eg, N ) transform layers L1, L2, . . . LN corresponding to the LSTM blocks B21 , B22, . there is These transform layers L 1 , L 2 , . . . , L N convert data H 1 , H 2 . Convert to output data y 1 , y 2 , . . . y N .
- output data y (data H).times.(weight W)+(bias b). Weight W and bias b are obtained by machine learning.
- the LSTM block B 21 receives the input of the data hN and cN from the encoder unit 121a, transfers the data H 1 indicating the output corresponding to the input to the conversion layer L 1 , and stores the data H 1 and Data C 1 indicating the cell and , are passed to the next LSTM block B 22 .
- the blocks after LSTM block B 22 operate similarly, and the N -th LSTM block B 2N passes data HN indicating an output according to the input to the transformation layer LN .
- the vehicle state estimation network 121 is configured based on a recurrent neural network configured by a Seq2Seq model based on LSTM. More specifically, in the embodiment, LSTM blocks B 11 , B 12 , . 21 , B 22 , . . . B 2N and transformation layers L 1 , L 2 , . . Vehicle state estimation network 121 is not limited to the above.
- the vehicle state estimation network 121 may perform Attention, RNN, bidirectional LSTM, skip connection, Transformer, etc. in addition to the above.
- the damping control section 10c controls the damping force of the shock absorber 4b based on at least one of the relative speed and the vehicle body speed (both as an example) estimated by the vehicle state estimating section 10b. Specifically, attenuation control unit 10c determines a current value to be input to shock absorber 4b, and inputs the current value to shock absorber 4b.
- FIG. 8 is a flowchart showing an example of a vehicle state estimation method executed by the control device 10 according to the first embodiment.
- FIG. 8 shows an example in which wheel speed data is applied as input data, input data is not limited to this.
- the data acquisition unit 10a acquires wheel speed data (S1).
- the vehicle state estimating unit 10b determines at least one of the relative speed (stroke speed and vehicle body speed) based on the wheel speed data acquired by the data acquiring unit 10a and the vehicle state estimation network 121 (as an example, both ) is estimated (S2).
- FIG. 9 is an exemplary and schematic diagram showing an example of stroke speed estimation results by the technique according to the first embodiment.
- FIG. 9 shows the stroke speed (estimated value) estimated by the technique of the present embodiment and the actually measured stroke speed (true value).
- it is possible to estimate the stroke speed of a waveform of 10 Hz or more, which is effective for controlling the damping force of the shock absorber 4b.
- control device 10 controls the shock absorber 4b as follows. That is, the control device 10 controls the damping force of the shock absorber 4b based on the relative speed and vehicle speed (sprung speed) estimated using the vehicle state estimation network 121. FIG. More specifically, the control device 10 performs known ride comfort control such as skyhook control based on the vehicle body speed to obtain the target damping force. Then, the control device 10 calculates the target damping coefficient of the shock absorber 4b based on the relative speed estimated using the vehicle state estimation network 121 and the target damping force. Next, the controller 10 inputs a current corresponding to the target damping coefficient to the shock absorber 4b.
- the control device 10 (vehicle state quantity estimating device) includes the data acquisition unit 10a and the vehicle state estimating unit 10b (vehicle state estimating unit).
- the data acquisition unit 10 a acquires wheel speed data indicating the rotation speed of the wheels 3 of the vehicle 1 .
- the vehicle state estimating unit 10b calculates the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 in the vertical direction of the vehicle 1 and the speed of the vehicle body 2 in the vertical direction of the vehicle 1 according to the input of the wheel speed data.
- vehicle state estimation network 121 neural network that has been trained to estimate at least one of the vehicle speed and the relative speed (stroke speed) according to the wheel speed data acquired by the data acquisition unit 10a and the vehicle body Estimate at least one of speed and speed.
- the vehicle state estimation unit 10b calculates the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 in the vertical direction of the vehicle 1 and the speed of the vehicle body 2 according to the input of the wheel speed data.
- Relative speed (stroke speed) according to the wheel speed data acquired by the data acquisition unit 10a using a vehicle state estimation network 121 (neural network) that has been trained to estimate at least one of the vehicle body speed and the vehicle body speed, it is possible to improve the accuracy of estimating the vehicle state (at least one of the relative speed and the vehicle body speed).
- the vehicle state estimation network 121 learns by considering an input data input delay (time lag) due to a communication delay as a feature during learning.
- the vehicle state estimation network 121 for example, it is not necessary to delete part of the input data using a filter or the like in order to suppress the influence of communication delay in estimating the vehicle state. Therefore, the vehicle state estimation network 121 can estimate the vehicle state even at time intervals corresponding to the unsprung resonance frequency.
- the vehicle state estimation network 121 is an LSTM.
- the data acquisition unit 10a acquires yaw rate data indicating the yaw rate of the vehicle 1.
- the vehicle state estimation network 121 performs learning so as to estimate at least one of the relative speed and the vehicle body speed according to the input of the wheel speed data and the yaw rate data.
- the vehicle state estimation unit 10b uses the vehicle state estimation network 121 to estimate at least one of the relative speed and the vehicle body speed according to the wheel speed data and the yaw rate data acquired by the data acquisition unit 10a.
- the vehicle 1 is provided with a shock absorber 4b interposed between the vehicle body 2 and the wheels 3 and capable of changing the damping force according to the input current.
- the data acquisition unit 10a acquires current value data indicating a value of current.
- the vehicle state estimation network 121 performs learning so as to estimate at least one of the relative speed and the vehicle body speed according to the input of the wheel speed data and the current value data.
- the vehicle state estimation unit 10b uses the vehicle state estimation network 121 to estimate at least one of the relative speed and the vehicle body speed according to the wheel speed data and the current value data acquired by the data acquisition unit 10a.
- the data acquisition unit 10a acquires steering angle data indicating the steering angle of the vehicle 1.
- the vehicle state estimation network 121 performs learning so as to estimate at least one of the relative speed and the vehicle body speed according to the input of the wheel speed data and the steering angle data.
- the vehicle state estimation unit 10b uses the vehicle state estimation network 121 to estimate at least one of the relative speed and the vehicle body speed according to the wheel speed data and the steering angle data acquired by the data acquisition unit 10a.
- FIG. 10 is a schematic diagram showing a schematic configuration of an example of the vehicle 1 according to the second embodiment. This embodiment differs from the first embodiment in that an acceleration sensor 6 is provided and in the processing executed by the control device 10 .
- the vehicle control system 100 of the vehicle 1 includes a control device 10, a steering device 11, a steering angle sensor 12, a yaw rate sensor 13, a braking system 61, and the like. Further, the vehicle control system 100 includes a suspension device 4, a rotation sensor 5, an acceleration sensor 6, etc. corresponding to each of the two front wheels 3F, and a suspension device corresponding to each of the two rear wheels 3R. 4, a rotation sensor 5, an acceleration sensor 6, and the like.
- Acceleration sensors 6 are provided corresponding to each of the two front wheels 3F and the two rear wheels 3R. That is, the acceleration sensors 6 are provided on the vehicle body 2 so as to correspond to the four wheels 3 and the suspension system 4, respectively.
- the acceleration sensor 6 detects acceleration of the vehicle body 2 of the vehicle 1 . More specifically, each acceleration sensor 6 is provided at an acceleration detection target location located directly above each wheel 3 in the vehicle body 2 (a position directly above the wheel). That is, in this embodiment, there are four acceleration sensing target locations.
- the acceleration sensor 6 detects acceleration in the vertical direction of the vehicle 1, acceleration in the front-rear direction (longitudinal direction) of the vehicle 1, direction) can be obtained.
- control device 10 includes a data acquisition unit 10a, a stroke speed estimation unit 10bA, an attenuation It can function (operate) as the control unit 10c or the like.
- the program can include, for example, a module corresponding to each block except for the storage unit 10d shown in FIG.
- the data acquisition unit 10 a acquires acceleration data indicating the acceleration of the vehicle 1 from each acceleration sensor 6 .
- the acceleration of the vehicle 1 may be acceleration in any direction.
- the acceleration of the vehicle 1 may be acceleration in a plurality of directions. That is, the acceleration of the vehicle 1 may be one or more of acceleration in the longitudinal direction of the vehicle 1 , acceleration in the lateral direction of the vehicle 1 , and acceleration in the vertical direction of the vehicle 1 .
- the data acquisition unit 10 a also acquires yaw rate data indicating the yaw rate of the vehicle 1 from the yaw rate sensor 13 .
- the data acquisition unit 10a also acquires current value data indicating the value of the current input to the shock absorber 4b from the attenuation control unit 10c.
- the data acquisition unit 10 a also acquires steering angle data indicating the steering angle of the vehicle 1 from the steering angle sensor 12 .
- the data acquisition unit 10 a also acquires wheel speed data indicating the rotational speed of the wheels 3 from the rotation sensor 5 .
- Acceleration data is an example of first data that is data relating to the speed of the vehicle 1 .
- the stroke speed estimating unit 10bA receives predetermined data (hereinafter also referred to as input data) acquired by the data acquiring unit 10a.
- Stroke speed estimator 10bA estimates relative speed according to input data using stroke speed estimation network 121A.
- the input data includes at least acceleration data.
- the input data may include at least one of yaw rate data, current value data, steering angle data, and wheel speed data. Input data is not limited to the above.
- the stroke speed estimation network 121A is a recurrent neural network (RNN) trained in advance so as to estimate the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 in the vertical direction of the vehicle 1 according to the input of input data. configured as During learning of the stroke speed estimation network 121A, the input data is the above-described input data acquired by the data acquisition unit 10a, and the output data as teacher data is measured by, for example, a relative speed sensor (not shown). It is a measured value (true value) of the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 .
- Stroke speed estimation network 121A is an example of a first neural network.
- FIG. 12 is an exemplary and schematic block diagram showing the configuration of a stroke speed estimation network 121A according to the second embodiment.
- the stroke speed estimation network 121A is configured as a Seq2Seq (Sequence to Sequence) model. More specifically, the stroke speed estimation network 121A has the same configuration as the vehicle state estimation network 121 of the first embodiment, ie, an encoder section 121a and a decoder section 121b.
- the damping control section 10c controls the damping force of the shock absorber 4b based on the relative speed estimated by the stroke speed estimating section 10bA. Specifically, attenuation control unit 10c determines a current value to be input to shock absorber 4b, and inputs the current value to shock absorber 4b.
- FIG. 13 is a flowchart showing an example of the relative speed estimation method executed by the control device 10 according to the second embodiment.
- FIG. 13 shows an example in which acceleration data is applied as input data, input data is not limited to this.
- the data acquisition unit 10a acquires acceleration data (S11).
- the stroke speed estimation unit 10bA estimates the stroke speed, which is the relative speed, based on the acceleration data acquired by the data acquisition unit 10a and the stroke speed estimation network 121A (S12).
- FIG. 14 is an exemplary and schematic diagram showing an example of stroke speed estimation results by the technique according to the second embodiment.
- FIG. 14 shows the stroke speed (estimated value) estimated by the technique of the present embodiment and the actually measured stroke speed (true value).
- FIG. 15 is an exemplary and schematic diagram showing an example of stroke speed estimation results by the technique according to the comparative example.
- FIG. 15 shows the stroke speed (estimated value) estimated by the technique of the comparative example and the actually measured stroke speed (true value).
- the technique of the comparative example estimates stroke speed based on the created equation of motion. As can be seen from FIGS. 14 and 15, the technique of the present embodiment has a smaller error between the estimated stroke speed and the actually measured stroke speed than the technique of the comparative example.
- FIG. 16 is an exemplary and schematic diagram showing an example of the stroke speed estimation error by the technique according to the second embodiment.
- the horizontal axis in FIG. 16 indicates the number of times of learning, and the vertical axis in FIG. 16 indicates the estimation error from the true value of the relative velocity.
- a line Q1 in FIG. 16 indicates an estimation error when a vertical acceleration corresponding to one wheel 3 is input.
- a line Q2 in FIG. 16 indicates an estimation error when vertical accelerations corresponding to the four wheels 3 are input.
- a line Q4 in FIG. 16 indicates an estimation error when vertical accelerations corresponding to four wheels 3 and longitudinal and lateral accelerations corresponding to one wheel 3 are input. Note that the acceleration in the example of FIG. 16 is an example, and the input acceleration is not limited to this.
- FIG. 17 is an exemplary and schematic diagram showing an example of the stroke speed estimation error by the technique according to the second embodiment.
- FIG. 17 shows the estimation error of the stroke speed corresponding to one wheel (the front wheel as an example).
- the horizontal axis of FIG. 17 indicates the number of times of learning, and the vertical axis of FIG. 17 indicates the estimation error from the true value of the relative velocity.
- a line Q5 in FIG. 17 indicates an estimation error when a vertical acceleration corresponding to one wheel 3 is input.
- a line Q6 in FIG. 17 indicates an estimation error when the vertical acceleration corresponding to one wheel 3 and the current value input to the shock absorber 4b of one wheel 3 are input.
- a line Q7 in FIG. 17 indicates an estimation error when the vertical accelerations corresponding to the four wheels 3 and the current values input to the shock absorbers 4b of the four wheels 3 are input.
- the acceleration in the example of FIG. 17 is an example, and the input acceleration is not limited to this.
- the control device 10 controls the shock absorber 4b as follows. That is, the control device 10 controls the damping force of the shock absorber 4b based on the relative speed estimated using the stroke speed estimation network 121A. More specifically, the control device 10 integrates the acceleration data from the acceleration sensor 6 to calculate the speed of the vehicle body 2 (hereinafter also referred to as sprung speed). Next, based on the speed of the vehicle body 2, known ride comfort control such as skyhook control is performed to obtain the target damping force. Then, the control device 10 calculates the target damping coefficient of the shock absorber 4b based on the relative speed estimated using the stroke speed estimation network 121A and the target damping force. Next, the controller 10 inputs a current corresponding to the target damping coefficient to the shock absorber 4b.
- the control device 10 vehicle state quantity estimating device
- the control device 10 includes the data acquisition unit 10a and the stroke speed estimating unit 10bA (relative speed estimating unit, vehicle state estimating unit).
- the data acquisition unit 10 a acquires acceleration data indicating the acceleration of the vehicle 1 .
- the stroke speed estimation unit 10bA uses a stroke speed estimation network 121A (first 1 neural network) is used to estimate the relative velocity (stroke velocity) according to the acceleration data acquired by the data acquisition unit 10a.
- the stroke speed estimator 10bA performs learning so as to estimate the relative speed of the wheels 3 of the vehicle 1 with respect to the vehicle body 2 of the vehicle 1 in the vertical direction of the vehicle 1 according to the input of the acceleration data. Since the stroke speed estimation network 121A is used to estimate the relative speed according to the acceleration data acquired by the data acquisition unit 10a, the accuracy of estimating the relative speed of the wheels 3 with respect to the vehicle body 2 can be improved.
- the stroke speed estimation network 121A is an LSTM.
- the data acquisition unit 10a acquires yaw rate data indicating the yaw rate of the vehicle 1.
- the stroke speed estimation network 121A performs learning so as to estimate the relative speed according to the input of acceleration data and yaw rate data.
- the stroke speed estimation unit 10bA uses the stroke speed estimation network 121A to estimate the relative speed according to the acceleration data and the yaw rate data acquired by the data acquisition unit 10a.
- the vehicle 1 is provided with a shock absorber 4b interposed between the vehicle body 2 and the wheels 3 and capable of changing the damping force according to the input current.
- the data acquisition unit 10a acquires current value data indicating a value of current.
- the stroke speed estimation network 121A performs learning so as to estimate the relative speed according to the input of acceleration data and current value data.
- the stroke speed estimation unit 10bA uses the stroke speed estimation network 121A to estimate the relative speed according to the acceleration data and current value data acquired by the data acquisition unit 10a.
- the data acquisition unit 10a acquires steering angle data indicating the steering angle of the vehicle 1.
- the stroke speed estimation network 121A performs learning so as to estimate the relative speed according to the inputs of acceleration data and steering angle data.
- the stroke speed estimation unit 10bA uses the stroke speed estimation network 121A to estimate the relative speed according to the acceleration data and the steering angle data acquired by the data acquisition unit 10a.
- the data acquisition unit 10a acquires wheel speed data indicating the rotation speed of the wheels 3.
- the stroke speed estimation network 121A performs learning so as to estimate the relative speed according to the inputs of acceleration data and wheel speed data.
- the stroke speed estimation unit 10bA uses the stroke speed estimation network 121A to estimate the relative speed according to the acceleration data and wheel speed data acquired by the data acquisition unit 10a.
- the acceleration sensors 6 may be mounted on only three wheels other than a predetermined one wheel (for example, the left rear wheel 3R) among the four wheels 3.
- the acceleration of one wheel not provided with the acceleration sensor 6 is geometrically calculated from the output value of the acceleration sensor 6 provided for the three wheels. can be estimated.
- the acceleration sensor 6 is preferably mounted directly above the wheel 3 (a position directly above the wheel). , the acceleration just above the wheel 3 may be estimated from the output value of the acceleration sensor 6 .
- FIG. 18 is a schematic diagram showing a schematic configuration of an example of the vehicle 1 according to the third embodiment. This embodiment differs from the second embodiment in the number of acceleration sensors 6 and the processing executed by the control device 10 .
- the acceleration sensors 6 are provided only for three of the four wheels 3.
- the acceleration sensors 6 are provided for the two left and right front wheels 3F and the left rear wheel 3L. That is, the acceleration sensor 6 is not provided for the right rear wheel 3R. That is, in the present embodiment, the acceleration sensors 6 are provided only at three of the four acceleration detection target locations located directly above each wheel 3 (right above the wheel) in the vehicle body 2. .
- the acceleration sensor 6 detects actual acceleration, which is the actual acceleration of the acceleration detection target location. Note that the acceleration of the vehicle body is also called sprung acceleration. That is, the acceleration sensor 6 detects sprung acceleration.
- FIG. 19 is a functional block diagram of an example control device 10 of the vehicle 1 according to the third embodiment.
- the data acquisition unit 10a has an acquisition unit 10aa and an estimation unit 10ab.
- the acquisition unit 10aa acquires from the acceleration sensor 6 actual acceleration data indicating the actual acceleration of the acceleration detection target location.
- the estimation unit 10ab receives the actual acceleration data of the three acceleration detection target locations of the acceleration sensor 6 acquired by the acquisition unit 10aa.
- the estimating unit 10ab uses the sprung acceleration estimation network 122 (second neural network) to determine all (for example, four) acceleration detection target locations according to the input actual acceleration data of the three acceleration detection target locations. Estimate the real acceleration of
- the storage unit 10d stores a sprung acceleration estimation network 122 in addition to the stroke speed estimation network 121A.
- FIG. 20 is an exemplary and schematic block diagram showing configurations of a stroke speed estimation network 121A and a sprung acceleration estimation network 122 according to the third embodiment.
- the sprung acceleration estimating network 122 selects all (for example, four) acceleration detection target locations in response to input of actual acceleration data (input data) of some of the acceleration detection target locations (three as an example). It is configured as a recurrent neural network (RNN) that has been trained in advance so as to estimate the actual acceleration data (output) of the acceleration detection target location.
- RNN recurrent neural network
- the input data is the actual acceleration data of some (for example, three) acceleration detection target positions among the plurality of acceleration detection target positions.
- the output data as teacher data is the actual acceleration detected by each acceleration sensor 6 when the acceleration sensors 6 are provided for all of the plurality of acceleration detection target locations. is.
- the vehicle 1 (a test vehicle for learning as an example) when the stroke speed estimation network 121A learns and the vehicle 1 (a production vehicle as an example) in which the sprung acceleration estimation network 122 is actually used are
- the mounting of each acceleration sensor 6 may be different.
- each acceleration sensor 6 may be more firmly attached to the vehicle body 2 than in the vehicle 1 in which the sprung acceleration estimation network 122 is actually used. This can be achieved, for example, by making the bracket or the like for attaching the acceleration sensor 6 to the vehicle body 2 relatively high in rigidity. As a result, vibration of the acceleration sensor 6 is suppressed during learning, and the accuracy of acceleration detection can be further improved.
- the sprung acceleration estimation network 122 is an example of a neural network and a second neural network.
- the sprung acceleration estimation network 122 is configured as a Seq2Seq model, similar to the stroke speed estimation network 121A. More specifically, similar to the stroke speed estimation network 121A, the sprung acceleration estimation network 122 receives input data and performs encoding processing on the encoder unit 121a, and decodes based on the encoder result of the encoder unit 121a. and a decoder unit 121b that executes the processing and outputs the data that has undergone the decoding processing.
- the acceleration data estimated by the data acquisition unit 10a is input to the stroke speed estimation unit 10bA.
- the stroke speed estimation unit 10bA uses the acceleration data estimated by the data acquisition unit 10a as input data, and estimates a stroke speed, which is a relative speed, by the stroke speed estimation network 121A.
- FIG. 21 is an exemplary and schematic diagram showing an example of sprung acceleration estimation results by the technology according to the third embodiment.
- FIG. 21 shows the sprung acceleration (estimated value) estimated by the technique of the third embodiment and the actually measured sprung acceleration (true value).
- FIG. 22 is an exemplary and schematic diagram showing an example of the result of estimating the sprung mass acceleration according to the technique according to the comparative example.
- FIG. 22 shows the sprung acceleration (estimated value) estimated by the technique of the comparative example and the actually measured sprung acceleration (true value).
- the technology of the comparative example is an example of geometrically obtaining the acceleration of the acceleration detection target location where the acceleration sensor 6 is not provided from the acceleration of the acceleration detection target location where the acceleration sensor 6 is provided.
- the technique of the present embodiment has a smaller error between the estimated spring acceleration and the actually measured sprung acceleration than the technique of the comparative example.
- the data acquisition unit 10a has the acquisition unit 10aa and the estimation unit 10ab.
- the acquisition unit 10aa obtains the actual acceleration, which is the actual acceleration of the acceleration detection target location, from the acceleration sensors 6 provided only for some of the plurality of acceleration detection target locations at different positions in the vehicle 1. Get data.
- the estimating unit 10ab estimates the actual acceleration of the acceleration detection target location detected by each acceleration sensor when acceleration sensors are provided for all of the plurality of acceleration detection target locations in response to the input of the actual acceleration data.
- the sprung acceleration estimating network 122 second neural network
- the estimation unit 10ab uses the sprung acceleration estimation network 122 to estimate the actual acceleration of all of the multiple acceleration detection target locations including locations where the acceleration sensor 6 is not provided. Data accuracy can be improved. Therefore, it is possible to further improve the accuracy of estimating the relative speed of the wheels with respect to the vehicle body.
- the estimation unit 10ab may use the sprung acceleration estimation network 122 to estimate only the actual acceleration of the acceleration detection target location where the acceleration sensor 6 is not provided among the plurality of acceleration detection target locations. Moreover, the estimation unit 10ab may use the sprung acceleration estimation network 122 to estimate the actual acceleration of at least the acceleration detection target location where the acceleration sensor 6 is not provided among the plurality of acceleration detection target locations. In these cases, the actual acceleration of the acceleration detection target location where the actual acceleration is not estimated by the estimating unit 10ab may be obtained by the obtaining unit 10aa from the acceleration sensor 6 and input to the stroke speed estimating unit 10bA.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mechanical Engineering (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Vehicle Body Suspensions (AREA)
Abstract
Description
図1は、第1の実施形態にかかる車両1の一例の概略構成が示された模式図である。本実施形態では、車両1は、例えば、内燃機関(エンジン、図示されず)を駆動源とする自動車(内燃機関自動車)であってもよいし、電動機(モータ、図示されず)を駆動源とする自動車(電気自動車、燃料電池自動車等)であってもよいし、それらの双方を駆動源とする自動車(ハイブリッド自動車)であってもよい。また、車両1は、種々の変速装置を搭載することができるし、内燃機関や電動機を駆動するのに必要な種々の装置(システム、部品等)を搭載することができる。また、車両1における車輪3の駆動に関わる装置の方式や、数、レイアウト等は、種々に設定することができる。また、本実施形態では、一例として、車両1は、四輪車(四輪自動車)であり、左右二つの前輪3Fと、左右二つの後輪3Rとを有する。なお、図1では、車両前後方向の前方(方向Fr)は、左側である。
図10は、第2の実施形態にかかる車両1の一例の概略構成が示された模式図である。本実施形態は、加速度センサ6が設けられている点と制御装置10が実行する処理とが第1の実施形態に対して異なる。
図18は、第3の実施形態にかかる車両1の一例の概略構成が示された模式図である。本実施形態は、加速度センサ6の数と制御装置10が実行する処理とが第2の実施形態に対して異なる。
2…車体
3…車輪
4b…ショックアブソーバ
10…制御装置(車両状態量推定装置)
10a…データ取得部
10aa…取得部
10ab…推定部
10b…車両状態推定部
10bA…ストローク速度推定部(相対速度推定部)
121…車両状態推定ネットワーク(第1のニューラルネットワーク)
121A…ストローク速度推定ネットワーク(第1のニューラルネットワーク)
122…ばね上加速度推定ネットワーク(ニューラルネットワーク、第2のニューラルネットワーク)
Claims (13)
- 車両の速度に関するデータである第1のデータを取得するデータ取得部と、
前記第1のデータの入力に応じて、前記車両の上下方向における前記車両の車体に対する前記車両の車輪の相対速度と、前記上下方向における前記車体の速度である車体速度との少なくとも一方を推定するように学習を行った第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記第1のデータに応じた前記相対速度と前記車体速度との少なくとも一方を推定する車両状態推定部と、
を備えた車両状態量推定装置。 - 前記第1のデータは、前記車輪の回転速度を示す車輪速度データである、請求項1に記載の車両状態量推定装置。
- 前記データ取得部は、前記車両のヨーレートを示すヨーレートデータを取得し、
前記第1のニューラルネットワークは、前記車輪速度データおよび前記ヨーレートの入力に応じて前記相対速度と前記車体速度との少なくとも一方を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記車輪速度データおよび前記ヨーレートデータに応じた前記相対速度と前記車体速度との少なくとも一方を推定する、請求項2に記載の車両状態量推定装置。 - 前記車両は、前記車体と前記車輪との間に介在し、入力される電流に応じて減衰力を変更可能なショックアブソーバを備え、
前記データ取得部は、前記電流の値を示す電流値データを取得し、
前記第1のニューラルネットワークは、前記車輪速度データおよび前記電流値データの入力に応じて前記相対速度と前記車体速度との少なくとも一方を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記車輪速度データおよび前記電流値データに応じた前記相対速度と前記車体速度との少なくとも一方を推定する、請求項2に記載の車両状態量推定装置。 - 前記データ取得部は、前記車両の操舵角度を示す操舵角度データを取得し、
前記第1のニューラルネットワークは、前記車輪速度データおよび前記操舵角度データの入力に応じて前記相対速度と前記車体速度との少なくとも一方を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記車輪速度データおよび前記操舵角度データに応じた前記相対速度と前記車体速度との少なくとも一方を推定する、請求項2に記載の車両状態量推定装置。 - 前記第1のデータは、前記車両の加速度を示す加速度データであり、
前記第1のニューラルネットワークは、前記相対速度を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記加速度データに応じた前記相対速度を推定する、請求項1に記載の車両状態量推定装置。 - 前記データ取得部は、前記車両のヨーレートを示すヨーレートデータを取得し、
前記第1のニューラルネットワークは、前記加速度データおよび前記ヨーレートデータの入力に応じて前記相対速度を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記加速度データおよび前記ヨーレートデータに応じた前記相対速度を推定する、請求項6に記載の車両状態量推定装置。 - 前記車両は、前記車体と前記車輪との間に介在し、入力される電流に応じて減衰力を変更可能なショックアブソーバを備え、
前記データ取得部は、前記電流の値を示す電流値データを取得し、
前記第1のニューラルネットワークは、前記加速度データおよび前記電流値データの入力に応じて前記相対速度を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記加速度データおよび前記電流値データに応じた前記相対速度を推定する、請求項6に記載の車両状態量推定装置。 - 前記データ取得部は、前記車両の操舵角度を示す操舵角度データを取得し、
前記第1のニューラルネットワークは、前記加速度データおよび前記操舵角度データの入力に応じて前記相対速度を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記加速度データおよび前記操舵角度データに応じた前記相対速度を推定する、請求項6に記載の車両状態量推定装置。 - 前記データ取得部は、前記車輪の回転速度を示す車輪速度データを取得し、
前記第1のニューラルネットワークは、前記加速度データおよび前記車輪速度データの入力に応じて前記相対速度を推定するように学習を行っており、
前記車両状態推定部は、前記第1のニューラルネットワークを用いて、前記データ取得部によって取得された前記加速度データおよび前記車輪速度データに応じた前記相対速度を推定する、請求項6に記載の車両状態量推定装置。 - 前記データ取得部は、
車両における互いに位置が異なる複数の加速度検知対象箇所のうち一部に対してのみ設けられた加速度センサから、前記加速度検知対象箇所の実際の加速度である実加速度を示す実加速度データを取得する取得部と、
前記実加速度データの入力に応じて、前記複数の加速度検知対象箇所の全てに対して前記加速度センサが設けられた場合の各前記加速度センサが検知する前記加速度検知対象箇所の前記実加速度を推定するように学習を行った第2のニューラルネットワークを用いて、前記実加速度データの入力に応じた前記複数の加速度検知対象箇所の全ての前記実加速度を推定する推定部と、
を有する、請求項6~10のうちいずれか一つに記載の車両状態量推定装置。 - 前記第1のニューラルネットワークは、LSTM(Long Short Term Memory)である、請求項1~11のうちいずれか一つに記載の車両状態量推定装置。
- 車両における互いに位置が異なる複数の加速度検知対象箇所のうち一部に対してのみ設けられた加速度センサから、前記加速度検知対象箇所の実際の加速度である実加速度を示す実加速度データを取得する取得部と、
前記実加速度データの入力に応じて、前記複数の加速度検知対象箇所の全てに対して前記加速度センサが設けられた場合の各前記加速度センサが検知する前記加速度検知対象箇所の前記実加速度を推定するように学習を行ったニューラルネットワークを用いて、前記実加速度データの入力に応じた前記複数の加速度検知対象箇所の全ての前記実加速度を推定する推定部と、
を備えた車両状態量推定装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022579471A JPWO2022168683A1 (ja) | 2021-02-03 | 2022-01-25 | |
CN202280012225.1A CN116867657A (zh) | 2021-02-03 | 2022-01-25 | 车辆状态量推定装置 |
EP22749557.9A EP4289642A1 (en) | 2021-02-03 | 2022-01-25 | Vehicle state quantity estimation device |
US18/036,300 US20240001936A1 (en) | 2021-02-03 | 2022-01-25 | Vehicle state quantity estimation device |
Applications Claiming Priority (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021015857 | 2021-02-03 | ||
JP2021-015711 | 2021-02-03 | ||
JP2021015711 | 2021-02-03 | ||
JP2021-015857 | 2021-02-03 | ||
JP2021094603 | 2021-06-04 | ||
JP2021-094603 | 2021-06-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022168683A1 true WO2022168683A1 (ja) | 2022-08-11 |
Family
ID=82741317
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/002726 WO2022168683A1 (ja) | 2021-02-03 | 2022-01-25 | 車両状態量推定装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240001936A1 (ja) |
EP (1) | EP4289642A1 (ja) |
JP (1) | JPWO2022168683A1 (ja) |
WO (1) | WO2022168683A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024042831A1 (ja) * | 2022-08-26 | 2024-02-29 | 株式会社アイシン | 制御装置 |
WO2024070111A1 (ja) * | 2022-09-26 | 2024-04-04 | 日立Astemo株式会社 | サスペンションシステム |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10913A (ja) | 1996-06-13 | 1998-01-06 | Toyota Motor Corp | 車両用サスペンション装置の減衰力制御装置 |
JP2007223494A (ja) * | 2006-02-24 | 2007-09-06 | Fuji Heavy Ind Ltd | 車両挙動推定予測装置および車両安定化制御システム |
WO2013133059A1 (ja) * | 2012-03-09 | 2013-09-12 | 日産自動車株式会社 | 車両の制御装置及び車両の制御方法 |
WO2015098217A1 (ja) * | 2013-12-24 | 2015-07-02 | 日産自動車株式会社 | 車両の制御装置 |
JP2016117326A (ja) | 2014-12-18 | 2016-06-30 | アイシン精機株式会社 | サスペンションの減衰力制御装置 |
-
2022
- 2022-01-25 US US18/036,300 patent/US20240001936A1/en active Pending
- 2022-01-25 WO PCT/JP2022/002726 patent/WO2022168683A1/ja active Application Filing
- 2022-01-25 EP EP22749557.9A patent/EP4289642A1/en active Pending
- 2022-01-25 JP JP2022579471A patent/JPWO2022168683A1/ja active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10913A (ja) | 1996-06-13 | 1998-01-06 | Toyota Motor Corp | 車両用サスペンション装置の減衰力制御装置 |
JP2007223494A (ja) * | 2006-02-24 | 2007-09-06 | Fuji Heavy Ind Ltd | 車両挙動推定予測装置および車両安定化制御システム |
WO2013133059A1 (ja) * | 2012-03-09 | 2013-09-12 | 日産自動車株式会社 | 車両の制御装置及び車両の制御方法 |
WO2015098217A1 (ja) * | 2013-12-24 | 2015-07-02 | 日産自動車株式会社 | 車両の制御装置 |
JP2016117326A (ja) | 2014-12-18 | 2016-06-30 | アイシン精機株式会社 | サスペンションの減衰力制御装置 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024042831A1 (ja) * | 2022-08-26 | 2024-02-29 | 株式会社アイシン | 制御装置 |
WO2024070111A1 (ja) * | 2022-09-26 | 2024-04-04 | 日立Astemo株式会社 | サスペンションシステム |
Also Published As
Publication number | Publication date |
---|---|
US20240001936A1 (en) | 2024-01-04 |
JPWO2022168683A1 (ja) | 2022-08-11 |
EP4289642A1 (en) | 2023-12-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022168683A1 (ja) | 車両状態量推定装置 | |
CN104039569B (zh) | 车辆 | |
JP5321603B2 (ja) | 車両のスタビライザ制御装置 | |
CN103608229B (zh) | 用于调节车辆行驶动态的装置和方法及带这种装置的车辆 | |
CN113365855A (zh) | 车辆行为装置 | |
US11897301B2 (en) | Vehicle travel state control device and vehicle travel state control method | |
US11919353B2 (en) | Damping control device and damping control method for vehicle | |
CN113752772A (zh) | 减振控制装置以及减振控制方法 | |
GB2281722A (en) | Controlling damping characteristic of vehicular shock absorber | |
WO2022024919A1 (ja) | サスペンション制御装置およびサスペンション装置の制御方法 | |
JP2021049953A (ja) | 状態量算出装置、制御装置および車両 | |
JP6638707B2 (ja) | サスペンション制御システム | |
JP2020117196A (ja) | 車両運動状態推定装置 | |
CN115298045A (zh) | 车辆控制装置、车辆控制方法以及车辆控制系统 | |
JPH05262118A (ja) | ショックアブソーバの減衰力制御装置 | |
CN109203904B (zh) | 用于车辆的行驶控制系统 | |
CN116867657A (zh) | 车辆状态量推定装置 | |
CN113071282B (zh) | 一种车辆调节方法及装置 | |
CN113752770B (zh) | 半主动悬架控制系统及方法、计算机存储介质、车辆 | |
WO2024042831A1 (ja) | 制御装置 | |
CN109878348B (zh) | 一种用于前后轴分布式驱动电动车的运动控制系统及方法 | |
JP7312707B2 (ja) | サスペンション制御装置 | |
KR100895703B1 (ko) | 센서 고장을 검출하는 차량용 현가장치 | |
JP7458525B2 (ja) | 車両のサスペンションシステム | |
WO2022009869A1 (ja) | 車両制御装置およびサスペンションシステム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22749557 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18036300 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2022579471 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280012225.1 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022749557 Country of ref document: EP Effective date: 20230904 |