Information processing device

Abstract

The objective is to detect loosening in the fasteners of a vehicle's drivetrain based on data acquired from the vehicle itself, without the need for inspection equipment. [Solution] The information processing device acquires input data related to the loosening of fasteners in the drive system of a vehicle, and uses a machine learning model to acquire output regarding the loosening of fasteners in relation to the input data. The information processing device detects whether or not there is loosening of the fasteners according to the acquired output. Then, if loosening of the fasteners is detected, the information processing device outputs information indicating that loosening has been detected in the fasteners. The input data includes data on drive system vibration, drive system temperature, vehicle body vibration, and vehicle shaft torque.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus.

Background Art

[0002] Patent Document 1 discloses a rotation loosening prevention bolt for fastening a portion subject to large vibration and temperature changes with a bolt. In the rotation loosening prevention bolt, a recessed groove is formed by forging on the bolt bearing surface.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of Invention

Problems to be Solved by the Invention

[0004] An object of the present disclosure is to grasp that a fastener in a drive system of a vehicle is loosened in accordance with data acquired from the vehicle side without using inspection equipment.

Means for Solving the Problems

[0005] An information processing apparatus according to the present disclosure includes a control unit. The control unit is configured to execute: acquiring input data related to loosening of a fastener in a drive system of a vehicle; acquiring an output related to loosening of the fastener for the input data using a machine learning model; detecting presence or absence of loosening of the fastener in accordance with the acquired output; and outputting information indicating that loosening is detected in the fastener when the loosening of the fastener is detected. The input data includes data related to vibration of the drive system, data related to temperature of the drive system, data related to vibration of a vehicle body of the vehicle, and data related to shaft torque of the vehicle.

Effects of the Invention

[0006] This disclosure makes it possible to determine if there is looseness in the fasteners of the vehicle's drive system based on data acquired from the vehicle, without the need for inspection equipment. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 shows a schematic configuration of the loosening detection system. [Figure 2] Figure 2 shows an example of the table structure of sensor data held in the auxiliary storage unit. [Figure 3] Figure 3 is a flowchart of the processes performed by the processor. [Modes for carrying out the invention]

[0008] Loosening can occur in the fasteners of a vehicle's drivetrain. Therefore, inspection equipment is generally used to check whether or not the fasteners in the vehicle's drivetrain are loose. However, this requires inspection equipment, making it difficult to check for loosening at any given time.

[0009] In contrast, the information processing device according to this disclosure includes a control unit. The control unit is configured to acquire input data related to the loosening of fasteners in the drive system of a vehicle, to acquire output regarding the loosening of fasteners in relation to the input data using a machine learning model, to detect whether or not there is loosening of the fasteners according to the acquired output, and, if loosening of the fasteners is detected, to output information indicating that loosening has been detected in the fasteners.

[0010] Here, it is assumed that vibrations in the drivetrain may cause the drivetrain fasteners to loosen. Furthermore, expansion or contraction of the fasteners due to temperature changes in the drivetrain may also cause them to loosen. Additionally, since the vehicle body supports the drivetrain, vibrations of the vehicle body are expected to affect the drivetrain. Moreover, since shaft torque applies force to the drivetrain, shaft torque is expected to affect the drivetrain. Therefore, the input data includes data related to drivetrain vibration, drivetrain temperature, vehicle body vibration, and vehicle shaft torque.

[0011] As explained above, the information processing device relating to this disclosure outputs information indicating that a fastener is loose when it is determined that a fastener is loose using the input data. This makes it possible to determine if a fastener is loose based on data acquired from the vehicle, without the need for inspection equipment.

[0012] The following describes specific embodiments of this disclosure with reference to the drawings. Unless otherwise specified, the hardware configurations, module configurations, functional configurations, etc., described in each embodiment are not intended to limit the technical scope of the disclosure to those configurations alone.

[0013] <Embodiment> (System Overview) Figure 1 shows a schematic configuration of the loosening detection system 1. The loosening detection system 1 consists of an in-vehicle device 100 and a server 200. In the loosening detection system 1, the in-vehicle device 100 and the server 200 are interconnected by a network N1. The network N1 may be a wide area network (WAN), such as the internet, or a telephone communication network such as a mobile phone network.

[0014] (In-vehicle device) The in-vehicle device 100 is mounted on the vehicle 10. The in-vehicle device 100 transmits sensor data to the server 200 in real time via the network N1. Here, the sensor data is generated according to the values ​​detected by the sensor group 110. The sensor group 110 is a collection of multiple sensors for acquiring sensor data while the vehicle 10 is in motion. The sensors may be configured to acquire data such as physical quantities and images.

[0015] The sensor group 110 includes a sensor for measuring the vibration frequency of the vehicle 10's drive system, a sensor for measuring the temperature of the vehicle 10's drive system, a sensor for measuring the vibration frequency of the vehicle body 10, a sensor for measuring the shaft torque of the vehicle 10, and a sensor for measuring the position of the vehicle 10. The vehicle 10's drive system may include the vehicle 10's power source (engine, motor, etc.), power transmission device, shaft, couplings, etc.

[0016] Furthermore, for example, a knock sensor may be used as a sensor to measure the vibration frequency of the drive system of the vehicle 10. A temperature sensor attached to the drive system may be used as a sensor to measure the temperature of the drive system of the vehicle 10. An acceleration sensor provided on the vehicle body may be used as a sensor to measure the vibration frequency of the vehicle body. A torque sensor that measures the torque of the crankshaft may be used as a sensor to measure the shaft torque of the vehicle 10. A position sensor may be used as a sensor to measure the position of the vehicle 10. The position sensor may be, for example, a GPS (Global Positioning System). Positioning System (Positioning System) sensors, GNSS (Global Navigation Satellite System) sensors It may include things like "sa," etc.

[0017] Furthermore, the in-vehicle device 100 receives notification information from the server 200 via the network N1. Here, the notification information indicates that there is looseness in the fasteners of the drive system of the vehicle 10. This is information for that purpose. Upon receiving the notification information, the in-vehicle device 100 notifies the user of the vehicle 10 that the fastener in the drive system of the vehicle 10 is loose. Specifically, the in-vehicle device 100 displays on the display that the fastener in the drive system of the vehicle 10 is loose, or provides voice guidance indicating that the fastener in the drive system of the vehicle 10 is loose. Here, the fastener in the drive system is, for example, bolts, nuts, and the like used in the drive system.

[0018] (Server) The server 200 is a server device that detects looseness of the fastener in the drive system of the vehicle 10 according to sensor data. In general, inspection equipment is used to inspect whether a fastener in the drive system of a vehicle is loose. In this case, the inspection equipment is required, making it difficult to inspect whether the fastener in the drive system of the vehicle 10 is loose at any arbitrary timing. Accordingly, the server 200 detects looseness of the fastener in the drive system of the vehicle 10 according to the sensor data received from the in-vehicle device 100.

[0019] The server 200 is configured to include a computer having a processor 210, a main storage unit 220, an auxiliary storage unit 230, and a communication interface (communication I / F) 240. The processor 210 is, for example, a CPU (Central Processing Unit) or a DSP (Digital Signal Processor). The main storage unit 220 is, for example, a RAM (Random Access Memory) . The auxiliary storage unit 230 is, for example, a ROM (Read Only Memory). Further, the auxiliary storage unit 230 is, for example, an HDD (Hard Disk Drive), or a CD-ROM, a DVD disc , or a disk recording medium such as a Blu-ray Disc. Further, the auxiliary storage unit 230 may be a removable medium (portable storage medium). Here, examples of the removable medium include a USB memory or an SD card. The communication I / F 240 is, for example, a LAN (Local Area Network) interface board, or a wireless communication circuit for wireless communication.

[0020] In the server 200, the auxiliary storage unit 230 stores an operating system (OS), various programs, various information tables, and the like. Further, in the server 200, the processor 210 loads the programs stored in the auxiliary storage unit 230 into the main storage unit 220 and executes them, whereby various functions as will be described later can be realized. However, some or all of the functions in the server 200 may be realized by a hardware circuit such as an ASIC or an FPGA. Note that the server 200 does not necessarily need to be realized by a single physical configuration, and may be configured by a plurality of computers that cooperate with each other.

[0021] The processor 210 receives sensor data from the in-vehicle device 100 via the communication I / F 240. The processor 210 stores the received sensor data in the auxiliary storage unit 230. Figure 2 is a diagram illustrating an example of the table configuration of sensor data held in the auxiliary storage unit 230.

[0022] As shown in Figure 2, the sensor data held in the auxiliary storage unit 230 has a vehicle ID field, a date and time field, a drive system vibration field, a temperature field, a vehicle body vibration field, a shaft torque field, and a position field. The vehicle ID field stores an identifier (vehicle ID) for identifying the vehicle 10 on which the in-vehicle device 100 that transmitted the sensor data is mounted. The date and time field stores information indicating the date and time when the sensor data was transmitted.

[0023] The vehicle vibration field stores information indicating the vibration frequency of the drivetrain of the vehicle 10, acquired by the sensors in the sensor group 110 that measure the vibration frequency of the drivetrain. The temperature field stores information indicating the vibration frequency of the drivetrain. The following information is stored: The vehicle vibration frequency field stores information indicating the temperature of the vehicle 10's drivetrain, measured by a sensor in sensor group 110 that measures the temperature of the vehicle 10's drivetrain. The vehicle vibration frequency field stores information indicating the vibration frequency of the vehicle 10's body, measured by a sensor in sensor group 110 that measures the vibration frequency of the vehicle 10's body. The shaft torque field stores information indicating the shaft torque of the vehicle 10, measured by a sensor in sensor group 110 that measures the shaft torque of the vehicle 10. The position field stores information indicating the position of the vehicle 10, measured by a sensor in sensor group 110 that measures the position of the vehicle 10.

[0024] Here, it is assumed that vibrations in the drive system of vehicle 10 may cause the fasteners of the drive system to loosen. It is also assumed that temperature changes in the drive system of vehicle 10 may cause expansion or contraction of components, which may cause the fasteners of the drive system to loosen. Furthermore, since the body of vehicle 10 supports the drive system, vibrations in the body of vehicle 10 are expected to affect the drive system. In addition, the shaft torque of vehicle 10 applies force to the drive system, so it is assumed that the shaft torque affects the drive system. Therefore, it is assumed that the shaft torque of vehicle 10 affects the loosening of the fasteners of the drive system of vehicle 10.

[0025] Furthermore, for example, if the road has a gradient, a force is applied to the drive system of the vehicle 10 in a direction parallel to the road. Also, for example, if the road is curved, a force is applied to the drive system of the vehicle 10 in the direction outward from the curve. In this way, the force applied to the vehicle horizontally depending on the road shape may loosen the fasteners of the drive system of the vehicle 10. In addition, it is expected that the drive system may deteriorate more easily depending on the environment in which the vehicle 10 is located, such as in coastal areas or areas with a lot of sand and dust, which may affect the drive system. Therefore, the location of the vehicle 10 may affect the loosening of the fasteners of the drive system of the vehicle 10.

[0026] The processor 210 then uses the sensor data held in the auxiliary storage unit 230 as input data and, using a machine learning model, outputs an output value related to the loosening of the fasteners in the drive system of the vehicle 10. Here, the output value related to the loosening of the fasteners in the drive system of the vehicle 10 (hereinafter sometimes simply referred to as the "output value") is a numerical value indicating the degree of loosening of the fasteners. Alternatively, the output value may also include a numerical value indicating the probability that the fasteners are loose. Furthermore, the output value related to the loosening of the fasteners in the drive system of the vehicle 10 may also include information indicating whether or not loosening has occurred. The processor 210 then detects whether or not there is looseness in the fasteners in the drive system of the vehicle 10, according to the output value. At this time, the processor 210 detects whether or not there is looseness in the fasteners in the drive system of the vehicle 10. The processor 210 may also detect whether or not there are signs of loosening in the fasteners in the drive system of the vehicle 10.

[0027] The mechanical model is a supervised, pre-trained model that has been trained using data on drivetrain vibration, drivetrain temperature, vehicle body vibration, shaft torque, and vehicle position, as well as actual drivetrain fastener loosening data.

[0028] (flowchart) Figure 3 is a flowchart of the process performed by the processor 210. The process shown in Figure 3 is the process of detecting loosening of the fasteners in the drive system of the vehicle 10. The process shown in Figure 3 is performed periodically at predetermined intervals. The predetermined interval is set so that the process shown in Figure 3 is performed each time a period of time during which loosening of the drive system fasteners is expected to occur. In addition, the process shown in Figure 3 may be started, for example, in response to instructions from the user of the vehicle 10.

[0029] In step S101, the processor 210 inputs the sensor data held in the auxiliary storage unit 230 as input values ​​to the machine learning model. The sensor data used as input values ​​consists of time-series data of drivetrain vibration, drivetrain temperature, vehicle body vibration, shaft torque, and vehicle position. The sensor data used as input values ​​consists of the most recent time-series data of a predetermined length. Time-series data from the period may be used, or data for the entire period held in the auxiliary storage unit 230 may be used. Furthermore, the data used as input values ​​does not have to be time-series data. In this case, the latest sensor data may be used as the input value.

[0030] Next, in step S102, the processor 210 obtains an output value for the input value. In step S103, the processor 210 determines whether or not looseness is detected by referring to the obtained output value. The processor 210 may determine whether or not looseness is detected in the fastener by determining whether or not the output value exceeds a threshold.

[0031] If a negative result is obtained in step S103, no looseness has been detected in the fasteners. Therefore, the processor 210 terminates the process shown in Figure 3. On the other hand, if a positive result is obtained in step S103, there is a possibility that the fasteners in the vehicle 10's drive system are loose. Therefore, the processor 210 proceeds to the next step, S104. In step S104, the processor 210 outputs notification information. This prompts the user of the vehicle 10 to perform maintenance on the fasteners in the vehicle 10's drive system. Once the output of the notification information is complete, the processor 210 terminates the process shown in Figure 3.

[0032] As explained above, the looseness detection system 1 detects whether or not the fasteners of the vehicle 10's drive system are loose by inputting sensor data as input values ​​into a machine learning model. At this time, the machine learning model receives data on the drive system's vibration and temperature, as well as data on the vehicle body's vibration, shaft torque, and vehicle position. By further inputting data on the vehicle body's vibration, shaft torque, and vehicle position in addition to the drive system's vibration and temperature data, the system can further consider factors that affect the loosening of the drive system's fasteners and detect whether or not the fasteners are loose. Therefore, it is possible to detect whether or not the fasteners of the vehicle 10's drive system are loose more accurately. In this way, even without using inspection equipment, it is possible to more accurately determine whether or not the fasteners are loose based on the data acquired from the vehicle.

[0033] <Other Embodiments> The embodiments described above are merely examples, and this disclosure may be modified as appropriate without departing from its essence. Furthermore, the processes and means described in this disclosure may be freely combined and implemented as long as no technical inconsistencies arise.

[0034] Furthermore, a process described as being performed by a single device may be divided and executed by multiple devices. Conversely, a process described as being performed by different devices may be executed by a single device. In a computer system, the hardware configuration (server configuration) by which each function is implemented can be flexibly changed.

[0035] The present disclosure can also be realized by supplying a computer program implementing the functions described in the embodiments above to a computer, and having one or more processors in the computer read and execute the program. Such a computer program may be provided to the computer by a non-temporary computer-readable storage medium that can be connected to the computer's system bus, or it may be provided to the computer via a network. The non-temporary computer-readable storage medium includes any type of disk, such as magnetic disks (floppy disks or hard disk drives (HDDs), etc.), optical disks (CD-ROMs, DVDs, or Blu-ray discs, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, flash memory, or optical cards, and any other type of medium suitable for storing electronic instructions. [Explanation of symbols]

[0036] 1. Loosening detection system 10. Vehicles 100...In-vehicle equipment 110 Sensor Group 200 Servers 210 Processor 220 Main memory 230...Auxiliary storage section 240 ··Communication I / F

Claims

[Claim 1] To acquire input data related to the loosening of fasteners in the drive system of a vehicle, Using a machine learning model, obtain an output regarding the loosening of the fastener in relation to the input data, Based on the acquired output, the presence or absence of looseness in the fastener is detected, When loosening of the fastener is detected, information indicating that loosening has been detected in the fastener is output. A control unit configured to perform the following actions: The input data includes data relating to the vibration of the drive system, data relating to the temperature of the drive system, data relating to the vibration of the vehicle body, and data relating to the shaft torque of the vehicle. Information processing device.

Images