Suspension system

Abstract

The invention relates to a suspension system. A suspension system according to an embodiment is provided with: an estimation unit that estimates at least one of a stroke displacement amount indicating a displacement amount of a damper and a stroke speed indicating a displacement speed of the damper, using a learned model, from input information including a measured value of an acceleration on a spring; a calculation unit that calculates an estimated value of the on-spring acceleration on the basis of the estimation result of the estimation unit; and an abnormality determination unit that determines the presence or absence of an abnormality on the basis of the error between the measured value of the on-spring acceleration and the estimated value of the on-spring acceleration.

Description

Technical Field

[0001] The present invention relates to suspension systems. Background Art

[0002] In a suspension system that adjusts the damping force to converge the vibration (expansion and contraction) of a spring that mitigates impact from the road surface on the vehicle body according to the situation, a learned model (artificial intelligence) may be used to control the damping force.

[0003] Patent Document 1: International Publication No. 2022 / 024919

[0004] Patent Document 2: International Publication No. 2019 / 064833

[0005] In the above-described system, a function of detecting the occurrence of anomalies is required, taking into account the possibility that the processing performed by the learned model may lose its applicability. Summary of the Invention

[0006] One of the problems to be solved by the embodiments of the present invention is to be able to detect abnormalities in a suspension system that adjusts the damping force using a learned model.

[0007] One embodiment of the present invention is a suspension system having a shock absorber that generates a damping force for converging the vibration of a spring interposed between a wheel and a vehicle body, and capable of adjusting the damping force, the suspension system comprising: an inference unit that uses a learned model to estimate at least one of a stroke displacement amount representing the displacement amount of the shock absorber and a stroke velocity representing the displacement velocity of the shock absorber based on input information including a measured value of the spring acceleration; a calculation unit that calculates an estimated value of the spring acceleration based on the inference result of the inference unit; and an abnormality determination unit that determines the presence or absence of an abnormality based on an error between the measured value of the spring acceleration and the estimated value of the spring acceleration.

[0008] According to an embodiment of the present invention, a control device calculates an estimated value of sprung acceleration based on, for example, at least one of a stroke displacement and a stroke velocity estimated by a learned model based on input information including an actual measured value of sprung acceleration, and determines an abnormality based on the error between the actual measured value and the estimated value of sprung acceleration. This makes it possible to accurately detect abnormalities in a system controlled using a learned model, thereby improving system reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a diagram showing an example of the structure of a suspension system mounted on the vehicle according to the first embodiment.

[0010] Figure 2 It is a diagram showing an example of the structure of the suspension device according to the first embodiment.

[0011] Figure 3 This is a diagram showing an example of the functional configuration of the ECU according to the first embodiment.

[0012] Figure 4 This is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the first embodiment.

[0013] Figure 5 This is a diagram showing an example of the relationship among the sprung acceleration, the error, and the abnormality determination flag when an abnormality occurs in the first embodiment.

[0014] Figure 6 This is a flowchart showing an example of processing performed by the ECU according to the first embodiment.

[0015] Figure 7 This is a diagram showing an example of the functional configuration of the ECU according to the second embodiment.

[0016] Figure 8 This is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the second embodiment.

[0017] Figure 9 This is a flowchart showing an example of processing performed by the ECU according to the second embodiment.

[0018] Figure 10 This is a diagram showing an example of the functional configuration of the ECU according to the third embodiment.

[0019] Figure 11 This is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the third embodiment.

[0020] Figure 12 This is a flowchart showing an example of processing performed by the ECU according to the third embodiment. DETAILED DESCRIPTION

[0021] The following discloses exemplary embodiments of the present invention. The structures of the embodiments described below and the functions, results, and effects resulting from these structures are merely examples. The present invention can also be implemented with structures other than those disclosed in the following embodiments, and can provide at least one of the various effects and derivative effects based on the basic structure.

[0022] (First embodiment)

[0023] Figure 1 1 is a diagram showing an example of the structure of a suspension system S of a vehicle 1 according to the first embodiment. The vehicle 1 illustrated here is a four-wheeled vehicle capable of traveling on a road, and includes a vehicle body 2 and four wheels 3 .

[0024] The suspension system S includes a suspension device 11 , an acceleration sensor 12 , and an ECU (Electronic Control Unit) 13 .

[0025] The suspension device 11 is provided between each of the four wheels 3 and the vehicle body 2 , and serves to mitigate impacts on the vehicle body 2 from the road surface.

[0026] Acceleration sensors 12 are installed above each of the four suspension systems 11 and detect the sprung acceleration corresponding to each installation location. Sprung acceleration is the acceleration of the vertical displacement of the upper portion of the suspension system 11 (main vehicle body 2). The number and installation locations of acceleration sensors 12 are not limited to these.

[0027] The ECU 13 is an information processing device that performs information processing for controlling each suspension device 11. It is communicatively connected to the suspension device 11 and other on-board equipment via a network such as a CAN (Controller Area Network). Furthermore, the ECU 13 receives the signal (analog signal) output from the acceleration sensor 12 via appropriate circuitry. The ECU 13 can be configured using, for example, a CPU (Central Processing Unit), memory, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), and the like. In addition to the suspension device 11 and the acceleration sensor 12, the on-board equipment connected to the ECU 13 can also include, for example, a wheel speed sensor that detects the rotational speed (wheel speed) of the wheel 3, a three-axis acceleration sensor that detects the tilt of the vehicle body 2, a steering angle sensor that detects the steering angle, and other ECUs that perform specified control.

[0028] Figure 2 1 is a diagram showing an example of the structure of the suspension device 11 according to the first embodiment. Figure 2 , the structure of one suspension device 11 interposed between one wheel 3 and the vehicle body 2 is schematically shown. The suspension device 11 includes a spring 21 and a shock absorber 22. In addition, all four suspension devices 11 have the same structure.

[0029] The spring 21 is a component interposed between the wheel 3 and the vehicle body 2 that expands and contracts to absorb impacts from the road surface R on the vehicle body 2. The spring 21 generates a reaction force (restoring force) depending on its expansion and contraction state. Hereinafter, the reaction force corresponding to the expansion and contraction state of the spring 21 is referred to as the spring force.

[0030] The shock absorber 22 generates a damping force to reduce the vibration (contraction and extension) of the spring 21. The damping force of the shock absorber 22 can be varied based on a control signal (control current) from the ECU 13. While the specific structure of the shock absorber 22 is not particularly limited, it can employ, for example, a hydraulic shock absorber whose damping force varies based on fluid pressure, or an actuator that operates by varying the fluid pressure of the hydraulic shock absorber based on a control current from the ECU 13.

[0031] The ECU 13 of this embodiment executes processing to optimize the damping force of the shock absorber 22 based on various information related to the vehicle 1 obtained from the acceleration sensor 12, the CAN, and other means. This information can include sprung acceleration obtained from the acceleration sensor 12, wheel speeds obtained from wheel speed sensors, and longitudinal acceleration, lateral acceleration, and yaw rate obtained from a triaxial acceleration sensor mounted on the vehicle body 2. While the specific method for controlling the damping force by the ECU 13 is not particularly limited, for example, control based on the skyhook theory can be utilized.

[0032] Figure 3 This diagram shows an example of the functional configuration of the ECU 13 of the first embodiment. The ECU 13 of this embodiment includes an estimation unit 101, a drive control unit 102, a calculation unit 103, and an abnormality determination unit 104. These functional units 101-104 can be configured by a combination of hardware components and software components (such as programs) that constitute the ECU 13. Furthermore, at least one of these functional units 101-104 can be configured by dedicated hardware (such as circuits).

[0033] The inference unit 101 uses the learned model and predetermined input information to estimate the stroke displacement and stroke velocity of the shock absorber 22. The stroke displacement refers to the vertical displacement of the shock absorber 22. The stroke velocity refers to the vertical displacement velocity of the shock absorber 22. The input information includes at least the measured value of the acceleration applied to the spring, detected by the acceleration sensor 12, or the measured sprung acceleration. The input information may also include wheel speed, longitudinal acceleration, lateral acceleration, yaw rate, and other information.

[0034] The learned model can be a model generated by using prescribed teacher data for a neural network and performing machine learning (deep learning) in advance, and can be a prescribed algorithm that applies parameters (weights) determined by machine learning. The parameters of the learned model can also include parameters that are updated according to use (driving of the vehicle 1). The learned model of this embodiment outputs an estimated value of the stroke displacement, i.e., the estimated stroke displacement, and an estimated value of the stroke speed, i.e., the estimated stroke speed, with respect to input information including the measured acceleration on the spring. The specific implementation of the learned model should not be particularly limited, but for example, a model having an RNN (Recurrent Neural Network) structure, an LSTM (Long Short Term Memory) structure, etc. can be used.

[0035] The drive control unit 102 determines a target value for the damping force of the shock absorber 22 based on information obtained from the acceleration sensor 12 and the CAN, the estimation results of the estimation unit 101, and the like, and outputs a control signal (control current) to the shock absorber 22 so that the damping force of the shock absorber 22 reaches the target value. The method for determining the target value for the damping force is not particularly limited, but, for example, a method based on the skyhook theory can be employed.

[0036] The calculation unit 103 calculates the estimated value of the sprung acceleration, or the estimated sprung acceleration, based on the estimation results of the estimation unit 101, namely, the estimated stroke displacement and estimated stroke velocity output from the learned model. The method for calculating the estimated sprung acceleration from the estimated stroke displacement and estimated stroke velocity can be implemented using any known calculation method as appropriate. For example, the estimated spring force, or the estimated value of the spring force of the spring 21, can be calculated from the estimated stroke displacement; the estimated damping force, or the estimated value of the damping force of the shock absorber 22, can be calculated from the estimated stroke velocity; and the estimated sprung acceleration can be calculated from the estimated spring force and the estimated damping force based on an equation of motion, for example.

[0037] The abnormality determination unit 104 determines the presence of an abnormality based on the error between the measured sprung acceleration obtained from the acceleration sensor 12 and the estimated sprung acceleration calculated by the calculation unit 103. The abnormality determination unit 104 determines that an abnormality exists when the error is equal to or greater than a threshold value.

[0038] In addition, when the abnormality determination unit 104 determines that an abnormality exists, it can also perform a prescribed abnormality corresponding process. The abnormality corresponding process can be, for example, resetting the parameters in the learned model. The parameters that become the object of reset are, for example, parameters that are updated by use (driving of the vehicle 1), such as storage values in RNN, LSTM, etc. Thus, there is a possibility of normalizing the effect of the learned model. In addition, the abnormality corresponding process can also be, for example, a process of prohibiting the use of the inference result of the inference unit 101 in the control of the damping force of the shock absorber 22. Thus, the control of the damping force based on inappropriate inference results can be avoided.

[0039] Figure 4 1 is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the first embodiment. Figure 4 As shown, the learned model of this embodiment outputs an estimated stroke displacement and an estimated stroke velocity when input information of the measured sprung acceleration obtained from the acceleration sensor 12 is input. In addition to the measured sprung acceleration, the input information may also include wheel speed, longitudinal acceleration, lateral acceleration, yaw rate, feedback value of the estimated spring force, feedback value of the estimated damping force, and the like. By including information other than the measured sprung acceleration in the input information, the estimation accuracy of the learned model can be improved.

[0040] The estimated spring force is calculated by multiplying the estimated stroke displacement output from the learned model by the spring constant of spring 21. Furthermore, the estimated damping force, the damping force corresponding to the estimated stroke velocity output from the learned model, is calculated using the Forth-Velocity (FV) equation, which represents the correspondence between stroke velocity and damping force. The FV equation can be generated based on, for example, pre-conducted experiments or simulations, or based on information acquired during driving. The estimated spring force and estimated damping force thus calculated can also be fed back as input to the learned model.

[0041] The estimated sprung acceleration is calculated by adding the estimated spring force and the estimated damping force calculated as described above and dividing the result by the sprung weight (e.g., the weight of the vehicle body 2). The presence of an abnormality is then determined based on the error between the measured sprung acceleration and the estimated sprung acceleration.

[0042] The above-mentioned calculation method is merely an example, and the calculation method of the estimated sprung acceleration in this embodiment is not limited thereto.

[0043] Figure 5 : is a diagram showing an example of the relationship between the sprung acceleration, error, and abnormality determination flag when an abnormality occurs in the first embodiment. Figure 5, the correspondence between the spring acceleration change information 201, the error change information 202, and the flag change information 203 is illustrated.

[0044] The sprung acceleration change information 201 illustrates the time-series changes in the measured value (measured sprung acceleration) and the estimated value (estimated sprung acceleration) of the sprung acceleration. The error change information 202 illustrates the time-series changes in the error (estimated value - measured value) between the measured and estimated values of the sprung acceleration. Th1 represents the positive threshold, and Th2 represents the negative threshold. The flag change information 203 illustrates the time-series changes in the value (true / false value) of the flag indicating the presence or absence of an abnormality. Here, the flag value is "0" in normal conditions and "1" when an abnormality occurs. The time axes (horizontal axes) of the sprung acceleration change information 201, error change information 202, and flag change information 203 coincide.

[0045] exist Figure 5 In the example, the measured value and the estimated value of the sprung acceleration gradually deviate over time, and the error reaches the threshold value Th1 at time t1. In this case, the value of the flag becomes 1 at time t1, and the abnormality processing is executed. Figure 5 As shown, after time t1, the deviation (error) between the measured value and the estimated value of the sprung acceleration almost disappears, and the value of the flag becomes zero.

[0046] Figure 6 This is a flowchart illustrating an example of processing performed by the ECU 13 of the first embodiment. The estimation unit 101 inputs input information to the learned model and obtains an estimated stroke displacement and an estimated stroke velocity (S101). The calculation unit 103 calculates an estimated spring force based on the estimated stroke displacement (S102), an estimated damping force based on the estimated stroke velocity (S103), and an estimated sprung acceleration based on the estimated spring force and the estimated damping force (S104).

[0047] The abnormality determination unit 104 calculates the error between the measured sprung acceleration and the estimated sprung acceleration (S105) and determines whether the error is greater than a threshold value (S106). If the error is not greater than the threshold value (S106: No), the process from step S101 onward is repeated. If the error is greater than the threshold value (S106: Yes), the abnormality determination unit 104 performs abnormality processing such as resetting the parameters of the learned model (S107).

[0048] As described above, according to this embodiment, an estimated value of sprung acceleration is calculated based on the stroke displacement and stroke velocity estimated by a learned model based on input information including the measured value of sprung acceleration, and an abnormality is determined based on the error between the measured and estimated values of sprung acceleration. This makes it possible to accurately detect abnormalities in a suspension system S controlled using the learned model, thereby improving the reliability of the system.

[0049] Hereinafter, although other embodiments will be described, description of locations that achieve the same or similar functions and effects as those of the first embodiment will be appropriately omitted.

[0050] (Second embodiment)

[0051] The learned model of the first embodiment outputs the estimated stroke displacement and the estimated stroke speed in response to input information, but the learned model of the second embodiment outputs the estimated stroke displacement but does not output the estimated stroke speed in response to input information.

[0052] Figure 7 This diagram illustrates an example of the functional configuration of the ECU 13 according to the second embodiment. The estimation unit 101 of this embodiment utilizes the learned model described above and estimates an estimated value of the stroke displacement (estimated stroke displacement) based on input information including the measured sprung acceleration. The calculation unit 103 of this embodiment calculates an estimated value of the sprung acceleration (estimated sprung acceleration) based on the estimated stroke displacement estimated by the estimation unit 101.

[0053] Figure 8 : is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the second embodiment. Figure 8 As shown, the learned model of this embodiment outputs an estimated stroke displacement when input information including the measured spring acceleration obtained from the acceleration sensor 12 is input. Furthermore, in this embodiment, the estimated stroke displacement output from the learned model is differentiated to calculate the estimated stroke velocity.

[0054] Subsequent processing, namely the calculation of the estimated spring force, estimated damping force, and estimated sprung acceleration, is performed in the same manner as in the first embodiment. Specifically, the estimated spring force is calculated by multiplying the estimated stroke displacement output from the learned model by the spring constant of spring 21. The estimated damping force corresponding to the estimated stroke velocity is calculated using a predetermined FV relationship. The estimated sprung acceleration is then calculated based on the estimated spring force and the estimated damping force.

[0055] The above-mentioned calculation method is merely an example, and the calculation method of the estimated sprung acceleration in this embodiment is not limited thereto.

[0056] Figure 9 This is a flowchart illustrating an example of processing performed by the ECU 13 of the second embodiment. The estimation unit 101 inputs input information to the learned model and obtains an estimated stroke displacement (S201). The calculation unit 103 calculates an estimated spring force and an estimated stroke velocity based on the estimated stroke displacement (S202), calculates an estimated damping force based on the estimated stroke velocity (S203), and calculates an estimated sprung acceleration based on the estimated spring force and the estimated damping force (S204).

[0057] The abnormality determination unit 104 calculates the error between the measured sprung acceleration and the estimated sprung acceleration (S205) and determines whether the error is greater than a threshold value (S206). If the error is not greater than the threshold value (S206: No), the process from step S201 onward is repeated. If the error is greater than the threshold value (S206: Yes), the abnormality determination unit 104 performs abnormality processing such as resetting the parameters of the learned model (S207).

[0058] As described above, according to this embodiment, even when a model is learned by outputting an estimated stroke displacement amount (without outputting an estimated stroke velocity) in response to input information including the measured value of the sprung acceleration, it is possible to detect system abnormalities and improve system reliability, as in the first embodiment.

[0059] (Third embodiment)

[0060] The learned model of the first embodiment outputs an estimated stroke displacement and an estimated stroke speed in response to input information, but the learned model of the third embodiment outputs an estimated stroke speed but does not output an estimated stroke displacement in response to input information.

[0061] Figure 10 This diagram illustrates an example of the functional configuration of the ECU 13 according to the third embodiment. The estimation unit 101 of this embodiment utilizes the learned model described above and estimates an estimated value of the stroke velocity (estimated stroke velocity) based on input information including the measured sprung acceleration. The calculation unit 103 of this embodiment calculates an estimated value of the sprung acceleration (estimated sprung acceleration) based on the estimated stroke velocity estimated by the estimation unit 101.

[0062] Figure 11 : is a diagram for explaining an example of a method for calculating the estimated sprung acceleration in the third embodiment. Figure 11As shown, the learned model of this embodiment outputs an estimated stroke velocity when input information including the measured spring acceleration obtained from the acceleration sensor 12 is input. Furthermore, in this embodiment, the estimated stroke displacement is calculated by integrating the estimated stroke velocity output from the learned model.

[0063] Subsequent processing, namely the calculation of the estimated spring force, estimated damping force, and estimated sprung acceleration, is performed in the same manner as in the first embodiment. Specifically, the estimated spring force is calculated by multiplying the estimated stroke displacement calculated as described above by the spring constant of spring 21. The estimated damping force corresponding to the estimated stroke velocity is then calculated using a predetermined FV relationship. The estimated sprung acceleration is then calculated based on the estimated spring force and estimated damping force.

[0064] The above-mentioned calculation method is merely an example, and the calculation method of the estimated sprung acceleration in this embodiment is not limited thereto.

[0065] Figure 12 This is a flowchart illustrating an example of processing performed by the ECU 13 of the third embodiment. The estimation unit 101 inputs input information to the learned model and obtains an estimated stroke velocity (S301). The calculation unit 103 calculates an estimated stroke displacement and an estimated damping force based on the estimated stroke velocity (S302), calculates an estimated spring force based on the estimated stroke displacement (S303), and calculates an estimated sprung acceleration based on the estimated spring force and the estimated damping force (S304).

[0066] The abnormality determination unit 104 calculates the error between the measured sprung acceleration and the estimated sprung acceleration (S305) and determines whether the error is greater than a threshold value (S306). If the error is not greater than the threshold value (S306: No), the process from step S301 onward is repeated. If the error is greater than the threshold value (S306: Yes), the abnormality determination unit 104 performs abnormality processing such as resetting the parameters of the learned model (S307).

[0067] As described above, according to this embodiment, even when using a learned model that outputs an estimated stroke velocity (without outputting an estimated stroke displacement) in response to input information including the actual measured value of the sprung acceleration, it is possible to detect system abnormalities and improve system reliability, as in the first embodiment.

[0068] The program for enabling a computer (e.g., ECU 14, etc.) to implement the functions of the suspension system S of the above-described embodiment may also be provided as a file in an installable or executable form stored on a computer-readable recording medium such as a CD-ROM, a floppy disk (FD), a CD-R, or a DVD (Digital Versatile Disk).

[0069] Alternatively, the program may be stored on a computer connected to a network such as the Internet and provided by downloading the program via the network. Alternatively, the program may be provided or distributed via a network such as the Internet.

[0070] While several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These new embodiments can be implemented in various other forms and can be omitted, replaced, or modified in various ways without departing from the spirit of the invention. These embodiments and their variations are included within the scope and spirit of the invention and are included within the scope of the invention described in the technical solution.

[0071] [Summary of this embodiment]

[0072] The suspension system (S) of this embodiment has at least the following configuration.

[0073] That is, a suspension system (S) is a suspension system (S) that is provided with a shock absorber (22) that generates a damping force for converging the vibration of a spring (21) interposed between a wheel (3) and a vehicle body (2), and is capable of adjusting the damping force, and comprises: an inference unit (101) that uses a learned model and, based on input information including a measured value of the spring acceleration, infers at least one of a stroke displacement amount representing the displacement amount of the shock absorber (22) and a stroke velocity representing the displacement velocity of the shock absorber (22); a calculation unit (103) that calculates an estimated value of the spring acceleration based on the inference result of the inference unit (101); and an abnormality determination unit (104) that determines the presence or absence of an abnormality based on an error between the measured value of the spring acceleration and the estimated value of the spring acceleration.

[0074] With this configuration, an estimated value of the sprung acceleration is calculated based on at least one of the stroke displacement and the stroke velocity estimated by the learned model based on input information including the measured value of the sprung acceleration. An abnormality is determined based on the error between the measured and estimated values of the sprung acceleration. This allows for highly accurate detection of abnormalities in a system controlled using the learned model, thereby improving system reliability.

[0075] In addition, in the suspension system (S), when the inference unit (101) infers the stroke displacement and the stroke speed, the calculation unit (103) preferably calculates the reaction force generated by the spring (21), that is, the estimated value of the spring force, based on the estimated value of the stroke displacement estimated by the inference unit (101), calculates the estimated value of the damping force based on the estimated value of the stroke speed estimated by the inference unit (101), and calculates the estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

[0076] According to this configuration, the estimated value of the sprung acceleration can be efficiently calculated based on the stroke displacement and stroke velocity estimated by the learned model.

[0077] In addition, in the suspension system (S), when the inference unit (101) infers the stroke displacement, the calculation unit (103) preferably calculates the reaction force generated by the spring (21), that is, the estimated value of the spring force, and the estimated value of the stroke speed representing the displacement speed of the shock absorber (22) based on the estimated value of the stroke displacement estimated by the inference unit (101), and calculates the estimated value of the damping force based on the estimated value of the stroke speed, and calculates the estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

[0078] According to this configuration, the estimated value of the sprung acceleration can be efficiently calculated based on the stroke displacement estimated by the learned model.

[0079] In addition, in the suspension system (S), when the inference unit (101) infers the stroke speed, the calculation unit (103) preferably calculates an estimated value of the stroke displacement and an estimated value of the damping force based on the estimated value of the stroke speed inferred by the inference unit (101), calculates an estimated value of the reaction force generated by the spring (21), that is, the spring force, based on the estimated value of the stroke displacement, and calculates an estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

[0080] According to this configuration, the estimated value of the sprung acceleration can be efficiently calculated based on the stroke velocity estimated by the learned model.

[0081] Furthermore, in the suspension system (S), the abnormality determination unit (104) preferably resets the parameters of the learned model when determining that an abnormality exists.

[0082] According to this configuration, the function of the learned model can be normalized.

[0083] Furthermore, in the above configuration, preferably, when the abnormality determination unit (104) determines that an abnormality exists, it prohibits the use of the estimation result of the estimation unit (101) in the control of the damping force.

[0084] According to this configuration, execution of control based on inappropriate estimation results can be avoided.

[0085] Description of Reference Signs

[0086] 1…Vehicle, 2…Vehicle body, 3…Wheel, 11…Suspension device, 12…Acceleration sensor, 13…ECU, 21…Spring, 22…Shock absorber, 101…Inference unit, 102…Drive control unit, 103…Calculation unit, 104…Abnormality determination unit, 201…Spring acceleration change information, 202…Error change information, 203…Sign change information, R…Road surface, S…Suspension system

Claims

1. A suspension system comprising a shock absorber that generates a damping force for converging vibrations of a spring interposed between a wheel and a vehicle body, and capable of adjusting the damping force, comprising: an estimating unit that estimates at least one of a stroke displacement amount representing a displacement amount of the shock absorber and a stroke velocity representing a displacement velocity of the shock absorber based on input information including a measured value of a spring acceleration using the learned model; a calculation unit that calculates an estimated value of the sprung acceleration based on the estimation result of the estimation unit; and The abnormality determination unit determines the presence or absence of an abnormality based on an error between the actual measurement value of the sprung acceleration and the estimated value of the sprung acceleration.

2. The suspension system according to claim 1, wherein: When the inference unit infers the stroke displacement and the stroke velocity, the calculation unit calculates the estimated value of the reaction force generated by the spring, that is, the spring force, based on the estimated value of the stroke displacement estimated by the inference unit, calculates the estimated value of the damping force based on the estimated value of the stroke velocity estimated by the inference unit, and calculates the estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

3. The suspension system according to claim 1, wherein: When the estimating unit estimates the stroke displacement, the calculating unit calculates an estimated value of the spring force, which is a reaction force generated by the spring, and an estimated value of the stroke velocity, which represents the displacement velocity of the shock absorber, based on the estimated value of the stroke displacement estimated by the estimating unit, and calculates an estimated value of the damping force based on the estimated value of the stroke velocity, and calculates an estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

4. The suspension system according to claim 1, wherein: When the inference unit estimates the stroke velocity, the calculation unit calculates an estimated value of the stroke displacement and an estimated value of the damping force based on the estimated value of the stroke velocity estimated by the inference unit, calculates an estimated value of the reaction force generated by the spring, that is, the spring force, based on the estimated value of the stroke displacement, and calculates an estimated value of the acceleration on the spring based on the estimated value of the spring force and the estimated value of the damping force.

5. The suspension system according to any one of claims 1 to 4, wherein: The abnormality determination unit resets the parameters of the learned model when determining that an abnormality exists.

6. The suspension system according to any one of claims 1 to 4, wherein: The abnormality determination unit prohibits use of the estimation result of the estimation unit in the control of the damping force when determining that an abnormality exists.

Images