Deterioration determination device

Abstract

To determine deterioration of a rubber component with higher accuracy.SOLUTION: A learned model obtained by machine learning using, as input variables, first data that is time-series data of a temperature of the rubber damper or a temperature reflection parameter that reflects the temperature of the rubber damper, second data that is time-series data of a steering angle of the vehicle, position information of the vehicle, and a humidity or a humidity reflection parameter that reflects the humidity, and using, as an output variable, presence or absence of deterioration of the rubber damper; Is used to determine the presence or absence of deterioration of the rubber component.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a deterioration determination device. [Background technology]

[0002] Conventionally, as this type of deterioration determination device, a device for determining the deterioration of a non-pneumatic tire has been proposed (see, for example, Patent Document 1). This device determines the presence or absence of deterioration in a non-pneumatic tire based on the vibration value of the tire when the non-pneumatic tire is mounted on a vehicle and used, the acceleration applied to the tire, the number of tire rotations, the temperature of the tire tread, the amount of wear on the tire tread, the distance traveled by the vehicle, the time the vehicle is traveling, the vehicle traveling speed, the vehicle acceleration, the vehicle traveling route, the vehicle steering angle, the number of times the vehicle brakes, and the amount of brake operation by the vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-53568 Summary of the Invention [Problem to be solved by the invention]

[0004] It is desirable for the above-mentioned deterioration determination device to determine the deterioration of rubber parts with higher accuracy.

[0005] The deterioration determination device of the present disclosure has a primary objective of determining the deterioration of rubber parts with higher accuracy. [Means for solving the problem]

[0006] The deterioration determination device of the present disclosure employs the following measures to achieve the above-mentioned main object.

[0007] The deterioration determination device of the present disclosure includes: A deterioration determination device for determining deterioration of a rubber part used in a vehicle suspension, The presence or absence of deterioration of the rubber part is determined using a trained model obtained by machine learning that uses as input variables first data that is time-series data of the temperature of the rubber part or a temperature-reflecting parameter that reflects the temperature of the rubber part, second data that is time-series data of the steering angle of the vehicle, position information of the vehicle, and humidity or a humidity-reflecting parameter that reflects the humidity, and an output variable that indicates the presence or absence of deterioration of the rubber part, and the first and second data, the position information, and the humidity or the humidity-reflecting parameter. The gist of this is as follows.

[0008] The degradation device disclosed herein determines whether a rubber part has deteriorated using a trained model obtained by machine learning that uses first data, which is time-series data of the temperature of the rubber part or a temperature-reflecting parameter that reflects the temperature of the rubber part, second data, which is time-series data of the steering angle of the vehicle, vehicle position information, and humidity or a humidity-reflecting parameter that reflects the humidity as input variables and whether or not the rubber part has deteriorated as an output variable, as well as the first and second data, the position information, and the humidity or the humidity-reflecting parameter. The trained model that uses humidity as an input variable in addition to the first and second data and the position information determines whether or not the rubber part has deteriorated. As a result, the degradation of the rubber part can be determined with higher accuracy. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing an outline of the configuration of a vehicle 20 on which a deterioration determination device according to an embodiment is mounted. [Figure 2] 4 is a flowchart showing an example of a determination routine executed by the ECU 60. [Figure 3] FIG. 1 is an explanatory diagram illustrating a method for constructing a trained model. DETAILED DESCRIPTION OF THE INVENTION

[0010] 1 is a diagram showing an outline of the configuration of a vehicle 20 equipped with a deterioration determination device according to an embodiment. As shown in the figure, the vehicle 20 includes a power source 32, tires 30a-30d as rubber components, a vehicle body 38, suspension devices 40a-40d, a navigation system 50, and an electronic control unit (hereinafter referred to as "ECU") 60.

[0011] The power source 32 is configured to output power for running to a drive shaft 36, which is connected to tires 30a, 30b as drive wheels via a differential gear 35. The power source 32 is controlled by an ECU 60.

[0012] The tires 30a to 30d are configured as rubber parts having treads on the surface of which sulfur is added to crude rubber and molded while heating.

[0013] The suspension devices 40a to 40d are configured as well-known suspension devices that are attached between the tires 30a to 30d and the vehicle body 38 and absorb shocks transmitted from the road surface to the vehicle body 38. The suspension devices 40a to 40d include arms, springs, dampers, and rubber bushings 42a to 42d. The rubber bushings 42a to 42d are inserted into the parts that connect the springs and dampers to the vehicle body and absorb small vibrations.

[0014] The navigation system 50 displays the route to the destination, the vehicle position Pv, ​​which is the position information of the vehicle itself, and the like on a display device (not shown) based on map information.

[0015] Although not shown, the ECU 60 is configured as a microprocessor centered around a CPU, and in addition to the CPU, it is equipped with a ROM for storing processing programs, a RAM for temporarily storing data, a flash memory, input / output ports, and communication ports.

[0016] Signals from various sensors are input to the ECU 60. Examples of the signals input to the ECU 60 include a detection signal from a sensor for detecting the state of the power source 32, a wheel temperature Tw from a temperature sensor 31a that detects the temperature of the tire 30a, an acceleration αv from an acceleration sensor 70 that detects acceleration in the longitudinal direction, a steering angle θ from a steering angle sensor 72 that detects the steering angle of a steering wheel (not shown), and a humidity Hu from a humidity sensor 74 that detects relative humidity.

[0017] Various control signals are output from the ECU 60 via an output port. Examples of signals output from the ECU 60 include control signals for controlling the power source 32. The ECU 60 stores vehicle specifications such as the vehicle height H, vehicle weight, and the model of the power source 32 in a ROM.

[0018] In the vehicle 20 of this embodiment, the ECU 60 controls the power source 32 to travel based on the required load rate and the required power. During travel, the ECU 60 stores in a flash memory first data Dt, which is time-series data of the wheel temperature Tw from the temperature sensor 31a, and second data Dθ, which is time-series data of the steering angle θ from the steering angle sensor 72. The first data Dt and the second data Dθ are stored as time-series data in the flash memory of the vehicle 20 without being erased regardless of whether the ignition switch is on or off.

[0019] Next, the operation of the vehicle 20 of this embodiment configured as described above, particularly the operation when determining the deterioration of the tire 30a, will be described. Figure 2 is a flowchart showing an example of a determination routine executed by the ECU 60. This routine is executed at predetermined time intervals or each time the ignition switch is turned on to start up the system of the vehicle 20.

[0020] When this routine is executed, the CPU of the ECU 60 inputs the first data Dt, the second data Dθ, the vehicle position Pv from the navigation system 50, the acceleration αv from the acceleration sensor 70, the humidity Hu from the humidity sensor 74, and the vehicle height H stored in the ROM (S100).

[0021] Then, using the trained model created in advance and stored in ROM, and the first data Dt, second data Dθ, vehicle position Pv, ​​acceleration αv, humidity Hu, and vehicle height H input in S100, the presence or absence of deterioration of tire 30a is determined (S110), and this routine ends. Here, the trained model will be described.

[0022] FIG. 3 is an explanatory diagram illustrating a method for constructing a trained model. When constructing a trained model, a tester actually drives the vehicle 20 for a predetermined period of time. While the vehicle 20 is traveling, the ECU 60 acquires first data Dt, second data Dθ, vehicle position Pv, ​​acceleration αv, and humidity Hu, which are data to be input (input variables) into the neural network. The first data Dt is acquired based on the correlation between the deterioration of the tire 30a as a rubber component and its temperature history. The second data Dθ is acquired based on the correlation between the deterioration of the rubber component and the external force acting on the tire 30a when the vehicle 20 turns. The vehicle position Pv is acquired based on the correlation between the deterioration of the tire 30a, the deterioration of the rubber component, and the condition of the road surface during travel (such as whether the road is paved or not, or whether the road surface is wet for a long period of time in a rainy region). The acceleration αv is acquired based on the correlation between the deterioration of the tire 30a and the external force acting on the tire 30a. The humidity Hu is acquired based on the correlation between the deterioration of the tire 30a and humidity. The vehicle height H is acquired based on the correlation between the deterioration of the tire 30a and external forces acting on the tire 30a depending on the vehicle height H.

[0023] After acquiring the data that will serve as input variables in this manner, the tester stops the vehicle 20, visually checks whether the tire 30a has deteriorated, and inputs the presence or absence of deterioration of the tire 30a, which will serve as an output (output variable), into the ECU 60 using an electronic device such as a smartphone that can be connected to the ECU 60. At this time, the tester determines that the tire 30a has deteriorated if the tread of the tire 30a is not in the minimum condition required for the tire to function as a part of the vehicle 20, such as if hardening, cracks, or tears have occurred.

[0024] The ECU 60 repeatedly acquires the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, the humidity Hu, the vehicle height H, and the presence or absence of deterioration of the tire 30a. After acquiring the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, the humidity Hu, the vehicle height H, and the presence or absence of deterioration of the tire 30a in the number required to construct a highly accurate neural network, the ECU 60 constructs a trained model using a neural network that inputs the acquired first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, the humidity Hu, and the vehicle height H and outputs the presence or absence of deterioration of the tire 30a, and stores the trained model in advance in ROM. In S110, the presence or absence of deterioration of the tire 30a is determined from the trained model thus stored in ROM and the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, the humidity Hu, and the vehicle height H input in S100, thereby enabling more accurate determination of the deterioration of the tire 30a.

[0025] According to the vehicle 20 equipped with the deterioration determination device of the present embodiment described above, the deterioration of the tire 30a can be determined with higher accuracy by determining whether or not the tire 30a has deteriorated using a trained model that inputs the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, and the humidity Hu and outputs the presence or absence of deterioration of the tire 30a, and the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, and the humidity Hu.

[0026] In the above-described embodiment, the first data Dt is time series data of the wheel temperature Tw from the temperature sensor 31a, but it may also be time series data of a temperature-reflecting parameter, which is the temperature of another part located near the tire 30a and reflects the temperature of the tire 30a.

[0027] In the above-described embodiment, the humidity Hu is the humidity Hu from the humidity sensor 74, but it may be the humidity Hu or a humidity reflecting parameter that reflects the humidity Hu that can be indirectly measured.

[0028] In the above-described embodiment, the inputs used to construct the neural network are the first data Dt, the second data Dθ, the vehicle position Pv, ​​the acceleration αv, the humidity Hu, and the vehicle height H. However, it is sufficient if the inputs include at least the first data Dt, the second data Dθ, the vehicle position Pv, ​​and the humidity Hu, and the acceleration αv and the vehicle height H do not have to be included.

[0029] In the above-described embodiment, the presence or absence of deterioration of the tire 30a is determined. However, instead of the tire 30a, the presence or absence of deterioration of other rubber parts used in the suspension of the vehicle 20, such as the rubber bushings 42a-42d of the suspension units 40a-40d, drive shaft boots, tie rod end boots, and lower arm ball joint boots, may also be determined.

[0030] In the above-described embodiment, the tester visually checks whether the tire 30a has deteriorated, and inputs the whether or not the tire 30a has deteriorated, which serves as an output (output variable), to the ECU 60 using an electronic device such as a smartphone connectable to the ECU 60. However, an image of the appearance of the tire 30a may be captured by a camera and input to the ECU 60 as image data, and the ECU 60 may use the image data to determine whether or not the tire 30a has deteriorated.

[0031] In the above-described embodiment, the trained model is constructed using a neural network. However, the trained model may be constructed using a machine learning method other than a neural network.

[0032] The correspondence between the main elements of the embodiment and the main elements of the invention described in the section on means for solving the problem will be described below. In the embodiment, the tire 30a corresponds to the "rubber part," and the ECU 60 corresponds to the "deterioration determination device."

[0033] The correspondence between the main elements of the embodiments and the main elements of the invention described in the "Means for Solving the Problem" section does not limit the elements of the invention described in the "Means for Solving the Problem" section, since the embodiments are examples for specifically explaining the mode for implementing the invention described in the "Means for Solving the Problem" section. In other words, the interpretation of the invention described in the "Means for Solving the Problem" section should be based on the description in that section, and the embodiments are merely specific examples of the invention described in the "Means for Solving the Problem" section.

[0034] The above describes the forms for implementing the present disclosure using embodiments, but the present disclosure is not limited to these embodiments in any way, and it goes without saying that the present disclosure can be implemented in various forms within the scope that does not deviate from the gist of the present disclosure. [Industrial Applicability]

[0035] The present disclosure is applicable to industries such as the manufacturing industry of deterioration determination devices. [Explanation of symbols]

[0036] 20 vehicle, 30a to 30d tires, 31a temperature sensor, 32 power source, 35 differential gear, 36 drive shaft, 40a to 40d suspension device, 42a to 42d rubber bushing, 50 navigation system, 60 electronic control unit (ECU), 70 acceleration sensor, 72 steering angle sensor, 74 humidity sensor.

Claims

[Claim 1] A deterioration determination device for determining deterioration of a rubber part used in a vehicle suspension, The presence or absence of deterioration of the rubber part is determined using a trained model obtained by machine learning that uses first data, which is time-series data of the temperature of the rubber part or a temperature-reflecting parameter reflecting the temperature of the rubber part, second data, which is time-series data of the steering angle of the vehicle, position information of the vehicle, and humidity or a humidity-reflecting parameter reflecting the humidity as input variables and the presence or absence of deterioration of the rubber part as an output variable, and the first and second data, the position information, and the humidity or the humidity-reflecting parameter. Deterioration determination device.

Images