Tire remaining durability prediction device, tire remaining durability prediction method, and program

Abstract

A tire remaining durability prediction apparatus according to the present disclosure includes: a data acquisition unit configured to acquire traveling data of a vehicle on which a tire is mounted or external force data of an external force acting on the tire; a deterioration history data calculation section configured to calculate deterioration history data for at least a part of a base tire portion of the tire based on the traveling data or the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; and a durability prediction section configured to output a remaining durability of the tire based on deterioration history data for at least a part of the base tire portion.

Description

Technical Field

[0001] The present disclosure relates to a tire remaining durability prediction device, a tire remaining durability prediction method, and a program. Background Art

[0002] Conventionally, techniques for predicting the remaining durability of tires have been known. For example, Patent Document 1 discloses a tire carcass life prediction system for predicting the remaining life of a tire carcass using tire state or vehicle driving state.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2014-046879 Summary of the Invention

[0006] Problems to be Solved by the Invention

[0007] In recent years, there has been a need to further improve the prediction accuracy of the remaining durability of tires.

[0008] Therefore, it may be helpful to provide a tire remaining durability prediction device, a tire remaining durability prediction method, and a program that can improve the prediction accuracy of the remaining durability of tires.

[0009] Solutions to the Problems

[0010] [1] A tire remaining durability prediction device according to an embodiment of the present disclosure includes: a data acquisition unit configured to acquire driving data of a vehicle on which a tire is mounted; an external force calculation unit configured to calculate external force data of an external force acting on the tire based on the driving data; a deterioration history data calculation unit configured to calculate deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data for at least a part of a base tire portion of the tire based on the external force data; and a durability prediction unit configured to output the remaining durability of the tire based on the deterioration history data for at least a part of the base tire portion.

[0011] [2] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to [1], wherein the external force calculation unit is configured to calculate the external force data based on the driving data and information related to the tire.

[0012] [3] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to [1] or [2], wherein the deterioration history data calculation unit includes a calculation model constructed by machine learning, and the calculation model is configured to acquire the external force data and output the deterioration history data.

[0013] [4] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to [3], wherein the deterioration history data at least includes the temperature history data, and the calculation model configured to output the temperature history data is a recursive calculation model that uses past outputs as inputs.

[0014] [5] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to any one of [1] to [4], wherein the durability prediction unit is configured to output the remaining durability of the tire based on the remaining durability of the tire at a specific time point and the deterioration history data from the specific time point.

[0015] [6] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to any one of [1] to [5], wherein the deterioration history data at least includes the temperature history data, the data acquisition unit is configured to further acquire outdoor temperature data, and the deterioration history data calculation unit is configured to calculate the temperature history data based on the external force data and the outdoor temperature data.

[0016] [7] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to [6], wherein the deterioration history data calculation unit is configured to calculate the temperature history data based on the outdoor temperature data without using the external force data when the driving data meets a predetermined condition.

[0017] [8] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to [3], wherein the deterioration history data at least includes the strain history data, and the calculation model configured to calculate the strain history data is configured to acquire the external force data and output data related to the principal strain of the tire as the strain history data.

[0018] [9] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to any one of [1] to [8], wherein the data acquisition unit is configured to further acquire the wear state of the tire, and the deterioration history data calculation unit is configured to calculate the deterioration history data based on the external force data and the wear state of the tire.

[0019]

[10] The tire remaining durability prediction device according to an embodiment of the present disclosure is preferably the tire remaining durability prediction device according to any one of [1] to [8], and further includes: a wear state prediction unit configured to calculate the wear state of the tire based on the external force data, wherein the deterioration history data calculation unit is configured to calculate the deterioration history data based on the external force data and the wear state of the tire.

[0020]

[11] The tire remaining durability prediction method according to an embodiment of the present disclosure is a tire remaining durability prediction method executed by one or more computers, and the tire remaining durability prediction method includes: acquiring driving data of a vehicle equipped with a tire; calculating external force data of an external force acting on the tire based on the driving data; calculating deterioration history data for at least a part of a base tire portion of the tire based on the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; and outputting the remaining durability of the tire based on the deterioration history data for at least a part of the base tire portion.

[0021]

[12] A program according to an embodiment of the present disclosure is a program for causing one or more computers to perform operations, the operations including: acquiring driving data of a vehicle equipped with a tire; calculating external force data of an external force acting on the tire based on the driving data; calculating deterioration history data for at least a part of a base tire portion of the tire based on the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; and outputting the remaining durability of the tire based on the deterioration history data for at least a part of the base tire portion.

[0022] Effects of the Invention

[0023] Therefore, it is possible to provide a tire remaining durability prediction device, a tire remaining durability prediction method, and a program that can improve the prediction accuracy of the remaining durability of a tire. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In the drawings:

[0025] Figure 1FIG. is a diagram schematically showing the structure of a tire remaining durability prediction system according to an embodiment of the present disclosure;

[0026] Figure 2 is an illustration of Figure 1 a block diagram showing the structure of the illustrated server;

[0027] Figure 3 is an illustration of Figure 1 a flowchart showing an example of the operation of the illustrated server;

[0028] Figure 4 is a schematic diagram showing external forces acting on a tire mounted on a vehicle;

[0029] Figure 5 is a partial cross-sectional view of a typical tire in the tire width direction; and

[0030] Figure 6 is an illustration of Figure 1 a flowchart showing another example of the operation of the illustrated server. DETAILED DESCRIPTION

[0031] A tire remaining durability prediction device according to an embodiment of the present disclosure will be described below with reference to the accompanying drawings. In the drawings, the same or corresponding parts are given the same reference numerals. In the description of the present embodiment, the description of these same or corresponding parts will be appropriately omitted or simplified.

[0032] (Structure of Tire Remaining Durability Prediction System)

[0033] First, an overview of a tire remaining durability prediction system 1 according to the present embodiment will be given with reference to Figure 1 . Figure 1 FIG. is a diagram schematically showing the structure of a tire remaining durability prediction system 1. As Figure 1 illustrated, the tire remaining durability prediction system 1 includes a server 10, a measurement device 20, and a terminal device 30. Although one server 10, one measurement device 20, and one terminal device 30 are illustrated in Figure 1 , the tire remaining durability prediction system 1 may include any number of servers 10, any number of measurement devices 20, and any number of terminal devices 30.

[0034] The server 10 is composed of one or more computers. In the present embodiment, the server 10 is described as being composed of one computer. However, the server 10 may be composed of multiple computers such as a cloud computing system. In the present disclosure, the server 10 is also referred to as a tire remaining durability prediction device.

[0035] The measuring device 20 is constituted by one or more computers (such as a digital tachograph, a tire pressure monitoring system (TPMS), an electronic control unit (ECU), or a car navigation device, etc.). The measuring device 20 generates at least one of the driving data (travel data) of the vehicle 2 equipped with the tire 3 and the tire state data of the tire 3, and transmits the same as time series data to the server 10. For this purpose, the measuring device 20 can be mounted on the vehicle 2 or the tire 3.

[0036] The driving data of the vehicle 2 equipped with the tire 3 is, for example, time series data of the speed, acceleration, load, driving time, driving distance, or driving path of the vehicle 2 or the number of revolutions of the tire 3. For example, the driving data of the vehicle 2 can be generated by a digital tachograph. The driving data of the vehicle 2 is not limited to these examples, and can include any data for indicating the driving state of the vehicle 2 equipped with the tire 3.

[0037] The tire state data of the tire 3 is, for example, time series data of the internal pressure (air pressure) or temperature of the tire 3. For example, the tire state data of the tire 3 can be generated by a TPMS. The tire state data of the tire 3 is not limited to these examples, and can include any data for indicating the state of the tire 3.

[0038] The vehicle 2 is, for example, a truck. The vehicle 2 is not limited to a truck, and can be any vehicle on which the tire 3 can be mounted, such as a passenger car, an engineering vehicle, a work vehicle, a motorcycle, a bicycle, or an airplane, etc.

[0039] The terminal device 30 is, for example, a computer such as a smart phone, a tablet terminal, or a personal computer, etc.

[0040] The network 40 is any communication network that enables the server 10, the measuring device 20, and the terminal device 30 to communicate with each other. The network 40 in this embodiment can be, for example, the Internet, a mobile communication network, a local area network (LAN), or a combination of these.

[0041] The tire remaining durability prediction system 1 is used to predict the remaining durability of one or more tires 3. In the tire remaining durability prediction system 1, for example, the server 10 acquires the driving data of the vehicle 2 equipped with the tire 3 from the measuring device 20, and calculates the external force data of the external force acting on the tire 3 (hereinafter referred to as "the external force data acting on the tire 3") based on the driving data. The external force data acting on the tire 3 is time series data indicating the magnitude and direction of each force applied to the tire 3. The server 10 calculates the deterioration history data for at least a part of the base tire portion of the tire 3 based on the external force data. The deterioration history data includes at least one of temperature history data, strain history data, and oxygen concentration history data. Then, the server 10 outputs the remaining durability of the tire 3 based on the deterioration history data for at least a part of the base tire portion of the tire 3. For example, the remaining durability of the tire 3 can be sent from the server 10 to the terminal device 30 and displayed by the terminal device 30. Thus, instead of directly predicting the remaining durability of the tire 3 based on the data acquired from the measuring device 20, the remaining durability of the tire 3 is gradually predicted by calculating the external force data acting on the tire 3 as intermediate data. This can improve the prediction accuracy of the remaining durability of the tire 3.

[0042] The durability of the tire 3 is an index representing the state of the tire 3 that changes as the tire 3 is used. In the present disclosure, the durability of the tire 3 is represented by an index that decreases as the tire 3 is used. An example of an index that decreases as the tire 3 is used is the remaining durability of the tire 3. The remaining durability of the tire 3 is an index representing the remaining time period until the in-use tire 3 reaches a predetermined limit state. The remaining durability is also referred to as the remaining life. For example, the remaining durability of the tire 3 can be represented as a value from 0 to 100, where the value in the initial state of the tire 3 is 100 and the value in the limit state of the tire 3 is 0. Alternatively, the durability of the tire 3 can be represented by an index that increases as the tire 3 is used. An example of an index that increases as the tire 3 is used is the fatigue degree of the tire 3. The fatigue degree of the tire 3 is an index representing the accumulated fatigue degree in the in-use tire 3. For example, the fatigue degree of the tire 3 can be represented as a value from 0 to 100, where the value in the initial state of the tire 3 is 0 and the value in the limit state of the tire 3 is 100.

[0043] Next, reference will be made to Figure 2 to describe in detail the server 10 as a tire remaining durability prediction device. Figure 2 is a block diagram illustrating the structure of the server 10. As Figure 2As illustrated, the server 10 includes a communication unit 11, an output unit 12, an input unit 13, a storage unit 14, and a controller 15. In the server 10, the communication unit 11, the output unit 12, the input unit 13, the storage unit 14, and the controller 15 are connected in a manner that enables them to communicate with each other either wired or wirelessly.

[0044] The communication unit 11 includes a communication module for connecting to the network 40. The communication module is a communication module compatible with mobile communication standards such as 4G (4th generation) or 5G (5th generation). The communication module can be a communication module compatible with standards such as wired LAN or wireless LAN. The communication module can be a communication module compatible with short-range wireless communication standards (such as (Wi-Fi is a registered trademark in Japan, other countries, or both), (Bluetooth is a registered trademark in Japan, other countries, or both) or infrared communication, etc.). In this embodiment, the server 10 is connected to the network 40 via the communication unit 11. This enables the server 10 to communicate with the measurement device 20, the terminal device 30, other computers, etc.

[0045] The output unit 12 includes one or more output devices. Examples of the output devices included in the output unit 12 include a display, a speaker, and a light. This enables the output unit 12 to output images, sounds, light, etc.

[0046] The input unit 13 includes one or more input devices. Examples of the input devices included in the input unit 13 include a touch panel, a camera, and a microphone. The input unit 13 receives, for example, the input operations of the user of the server 10.

[0047] The storage unit 14 is, for example, a semiconductor memory, a magnetic memory, or an optical memory. The storage unit 14 is used, for example, as a main storage unit, an auxiliary storage unit, or a cache memory. The storage unit 14 stores any information used in the operation of the server 10. For example, the storage unit 14 stores system programs, application programs, embedded software, databases, etc. For example, the information stored in the storage unit 14 can be updated using the information obtained from the network 40 via the communication unit 11.

[0048] For example, the storage unit 14 can store the tire identification information of each of one or more tires 3 to be measured by the measurement device 20. The tire identification information of the tire 3 is information that can uniquely identify the tire 3. The tire identification information is, for example, an identifier (ID) of the tire 3 uniquely assigned by the server 10. The tire identification information is not limited to this, and can be, for example, the manufacturing number of the tire 3. The storage unit 14 can store the information related to the tire 3 in association with the tire identification information of the tire 3.

[0049] The controller 15 includes one or more processors. Examples of processors include general-purpose processors such as a central processing unit (CPU) and dedicated processors dedicated to specific processing. The controller 15 is not limited to one or more processors and may include one or more dedicated circuits. Examples of dedicated circuits include a field programmable gate array (FPGA) and an application specific integrated circuit (ASIC). The controller 15 controls each of the foregoing components such as the communication unit 11, the output unit 12, the input unit 13, and the storage unit 14 to implement the functions of the server 10 including the functions of these components. In the present disclosure, the controller 15 controls the foregoing components in the server 10 and thus can operate as a data acquisition unit 151, an external force calculation unit 152, a deterioration history data calculation unit 153, a wear state prediction unit 154, a durability prediction unit 155, and a model construction unit 156 (described in detail later).

[0050] (Operation of Tire Remaining Durability Prediction Device)

[0051] Reference will be made to Figure 3 、 Figure 4 、 Figure 5 and Figure 6 to describe the operation of the server 10 as a tire remaining durability prediction device. Figure 3 is a flowchart illustrating an example of the operation of the server 10. Figure 4 is a schematic diagram illustrating the external force acting on the tire 3 mounted on the vehicle 2. Figure 5 is a partial cross-sectional view of a typical tire 3 in the tire width direction. Figure 6 is a flowchart illustrating another example of the operation of the server 10. In Figure 3 and Figure 6 the operation of the server 10 is illustrated in the flowchart. The described operations correspond to the tire remaining durability prediction method executed by the server 10.

[0052] First, reference will be made to Figure 3 to describe the operation of predicting the remaining durability of the tire 3 using the server 10.

[0053] In the description of this operation, it is assumed that the storage unit 14 in the server 10 stores the tire identification information of the tire 3 and information related to the tire 3 associated with the tire identification information of the tire 3. The information related to the tire 3 includes, for example, at least one of the structural information of the tire 3, the structural information of the vehicle 2 on which the tire 3 is mounted, and the position information of the position of the tire 3 mounted on the vehicle 2. The structural information of the tire 3 is, for example, the type, model, material properties, belt angle, size, weight, etc. of the tire 3. The structural information of the tire 3 may also include manufacturing data unique to the tire 3, such as the length of the folded portion of the carcass (ply) or the belt width measured by an X-ray inspection machine when the tire 3 is shipped from the factory. Even for tires 3 of the same model, due to manufacturing deviations between the tires 3, the manufacturing data may be different. Considering this can further improve the prediction accuracy of the remaining durability of the tire 3. The structural information of the vehicle 2 on which the tire 3 is mounted includes the type, model, displacement, number of tires installed, number of axles, etc. of the vehicle 2.

[0054] In step S101, the controller 15 in the server 10, as the data acquisition unit 151, acquires the driving data of the vehicle 2 on which the tire 3 is mounted as time series data.

[0055] For example, the controller 15 in the server 10 acquires the driving data of the vehicle 2 on which the tire 3 is mounted from the measuring device 20 via the communication unit 11. The control unit 15 may store the acquired driving data in the storage unit 14 in association with the tire identification information of the tire 3.

[0056] In step S101, the controller 15 in the server 10, as the data acquisition unit 151, may acquire data other than the driving data of the vehicle 2.

[0057] As an example, the controller 15 in the server 10 may acquire the tire state data of the tire 3 from the measuring device 20 via the communication unit 11 as time series data. As another example, the controller 15 may acquire the outdoor temperature data from the measuring device 20 or the weather information service via the communication unit 11. The outdoor temperature data is, for example, the data of the air temperature, humidity, or precipitation at the location where the vehicle 2 on which the tire 3 is mounted is located. Alternatively, the controller 15 may acquire the wear state of the tire 3 from the terminal device 30 via the communication unit 11. The wear state of the tire 3 is an index indicating the degree of wear of the tire 3 due to the use of the tire 3. The wear state of the tire 3 is, for example, the remaining groove depth of the tread of the tire 3. The control unit 15 may store the acquired data in the storage unit 14 in association with the tire identification information of the tire 3.

[0058] In step S102, the controller 15 in the server 10, acting as an external force calculation unit 152, calculates external force data acting on the tire 3 based on the running data of the vehicle 2 equipped with the tire 3.

[0059] The external force data acting on the tire 3 is time-series data representing the force applied to the tire 3. The external force data may consist of one or more external force components. In this operation example, as Figure 4 illustrated, in the state where the tire 3 is mounted on the vehicle 2, the external force data is composed of an external force component Fx in the traveling direction of the vehicle 2, an external force component Fy in the rotational axis direction of the tire 3, and an external force component Fz in the vertical direction. Therefore, the external force data on the tire 3 can represent the magnitude and direction of each force applied to the tire 3. The number of components constituting the external force data on the tire 3 is not limited to three.

[0060] Any method can be used to calculate the external force data acting on the tire 3. The controller 15 in the server 10 can pre-store in the storage unit 14 the correlation algorithm between the running data of the vehicle 2 equipped with the tire 3 and the external force data acting on the tire 3. The controller 15 can use this correlation algorithm to calculate the external force data acting on the tire 3 based on the running data of the vehicle 2 equipped with the tire 3.

[0061] In this embodiment, a correlation algorithm for calculating the external force data acting on the tire 3 is constructed by statistical methods such as machine learning or deep learning. In this operation example, the correlation algorithm includes one or more calculation models constructed by machine learning (described in detail later). In the case where there are multiple calculation models, an appropriate calculation model can be used according to the target tire 3. The calculation model acquires the running data of the vehicle 2 equipped with the tire 3 and outputs the external force data acting on the tire 3. Therefore, the server 10 can further improve the calculation accuracy of the external force data acting on the tire 3 through machine learning. The correlation algorithm may include a predetermined relational expression not based on statistical methods. The controller 15 can store the calculated external force data acting on the tire 3 in the storage unit 14 in association with the tire identification information of the tire 3.

[0062] Refer again to Figure 3, when calculating the external force data acting on the tire 3 in step S102, the controller 15 in the server 10 can use other information in addition to the driving data of the vehicle 2 equipped with the tire 3. For example, the controller 15 in the server 10 can use the tire state data of the tire 3 in addition to the driving data of the vehicle 2 equipped with the tire 3 to calculate the external force data. For example, preferably, the controller 15 in the server 10 calculates the external force data based on the driving data of the vehicle 2 equipped with the tire 3 and the information related to the tire 3. As described above, the information related to the tire 3 includes at least one of the structural information of the tire 3, the structural information of the vehicle 2 equipped with the tire 3, and the position information of the position where the tire 3 is installed on the vehicle 2. Even in the case of the same driving data, the external force data acting on the tire 3 may be different depending on the structure of the tire 3, the structure of the vehicle 2 equipped with the tire 3, the position where the tire 3 is installed on the vehicle 2, etc. Therefore, using the information related to the tire 3 can further improve the calculation accuracy of the external force data.

[0063] As an example, the controller 15 in the server 10, as the external force calculation unit 152, can calculate the external force data acting on the tire 3 based on the driving data of the vehicle 2 equipped with the tire 3, the tire state data of the tire 3, and the outdoor temperature data. In this case, the aforementioned correlation algorithm for calculating the external force data can be configured to receive, in addition to the driving data of the vehicle 2 equipped with the tire 3, the tire state data of the tire 3 and the outdoor temperature data as inputs. As described above, the tire state data of the tire 3 can be, for example, the time series data of the internal pressure (air pressure) or temperature of the tire 3 generated by the TPMS.

[0064] Specifically, the controller 15 in the server 10 can use the time series data of the internal pressure and / or temperature of the tire 3, the outdoor temperature data, and the time series data of the speed of the vehicle 2 to calculate the external force component Fz of the external force data. The controller 15 can further use the calculated external force component Fz and the time series data of the speed and / or acceleration of the vehicle 2 to calculate the external force components Fx and Fy of the external force data. The controller 15 can store the calculated external force components Fx, Fy, and Fz in the storage unit 14 in association with the tire identification information of the tire 3 as the external force data acting on the tire 3.

[0065] In step S103, the controller 15 in the server 10, as the deterioration history data calculation unit 153, calculates the deterioration history data for at least a part of the base tire portion of the tire 3 based on the external force data acting on the tire 3.

[0066] The deterioration history data is time-series data of indices related to the deterioration of the tire 3. The deterioration history data may include at least one of temperature history data, strain history data, and oxygen concentration history data. The temperature history data is time-series data of the temperature in at least a part of the carcass portion 3A of the tire 3. The strain history data is time-series data of the strain occurring in at least a part of the carcass portion 3A of the tire 3. The oxygen concentration history data is time-series data of the concentration of oxygen contained in the rubber forming at least a part of the carcass portion 3A of the tire 3. The deterioration history data preferably includes at least two selected from the temperature history data, the strain history data, and the oxygen concentration history data, and more preferably includes all of the temperature history data, the strain history data, and the oxygen concentration history data.

[0067] As Figure 5 illustrated, the carcass portion 3A of the tire 3 may be a portion of the tire 3 other than the tread rubber 3B. The carcass portion 3A of the tire 3 includes a belt layer, a carcass, a bead core, a sidewall rubber, etc. The carcass portion 3A of the tire 3 is a portion that can be continuously used without being removed when retreading the tire 3. By calculating the deterioration history data for at least a part of the carcass portion 3A of the tire 3, even when the tire 3 is retreaded, the remaining durability of the tire calculated by this operation can be continued to be used as an evaluation index for the durability of the tire 3.

[0068] At least a part of the carcass portion 3A of the tire 3 includes an inter-belt portion (i.e., the portion between the belt layers) 3A-1, a belt-carcass portion (i.e., the portion between the belt layer and the carcass) 3A-2, and a carcass end portion 3A-3. In Figure 5 it, the schematic positions of the inter-belt portion 3A-1, the belt-carcass portion 3A-2, and the carcass end portion 3A-3 are specified by the dotted circles. However, the inter-belt portion 3A-1, the belt-carcass portion 3A-2, and the carcass end portion 3A-3 are not limited to Figure 5 the range of the dotted circles in

[0069] The inter-belt portion 3A-1 is the position between the belt layers or belt reinforcing layers forming the belt. The belt-carcass portion 3A-2 is the position between the belt layer and the carcass. The carcass end portion 3A-3 is the end of the folded portion of the carcass and its vicinity. Among these positions, when using the tire 3, cracks may occur along the cords between the rubber and the cords such as steel cords forming the belt layer or the carcass. Such cracks may cause a decrease in the durability of the tire 3. Calculating the deterioration history data for such parts that may cause a decrease in the durability of the tire 3 helps to evaluate the durability of the tire 3 in subsequent processing. At least a part of the carcass portion 3A of the tire 3 is not limited to these examples and may include any part of the tire 3.

[0070] Any method can be used to calculate the deterioration history data. The controller 15 in the server 10 can pre-store in the storage unit 14 an association algorithm between the external force data acting on the tire 3 and the deterioration history data for at least a part of the carcass portion 3A of the tire 3. The controller 15 can use this association algorithm to calculate the deterioration history data for at least a part of the carcass portion 3A of the tire 3 based on the external force data acting on the tire 3.

[0071] In the present embodiment, an association algorithm for calculating the deterioration history data is constructed by a statistical method such as machine learning or deep learning. In this operation example, the association algorithm includes one or more calculation models (described in detail later) constructed by machine learning. In the case where there are a plurality of calculation models, an appropriate calculation model can be used according to the target tire 3 and a part of the carcass portion 3A of the tire 3. The calculation model acquires the external force data acting on the tire 3 and outputs the deterioration history data. Thus, the server 10 can further improve the calculation accuracy of the deterioration history data of the tire 3 by machine learning. The association algorithm can include a predetermined relational expression not based on a statistical method. The control unit 15 can store the calculated deterioration history data of the tire 3 in association with the tire identification information of the tire 3 in the storage unit 14.

[0072] The calculation model can be composed of a plurality of calculation models each for outputting temperature history data, strain history data, or oxygen concentration history data. Different machine learning methods can be used to construct these plurality of calculation models according to the deterioration history data to be output. For example, the calculation model for outputting temperature history data is preferably a recursive calculation model, which uses the past output as an input in addition to using the external force data acting on the tire 3. The recursive calculation model is, for example, a recursive neural network or a long short-term memory (LSTM). Since the temperature history data is time-series data highly correlated with the previous data and the subsequent data, using the past output as an input can improve the calculation accuracy of the temperature history data. The calculation model for calculating the strain history data, for example, acquires the external force data acting on the tire 3 and outputs data related to the principal strain of the tire 3 as the strain history data. This can improve the calculation accuracy of the strain history data that periodically changes in intensity as the tire 3 rotates during the running of the vehicle 2. Alternatively, the same machine learning method can be used to construct each of the calculation models for outputting temperature history data, strain history data, and oxygen concentration history data.

[0073] Refer again to Figure 3 , when calculating the deterioration history data in step S103, the controller 15 in the server 10 can acquire other data as an input in addition to acquiring the external force data acting on the tire 3 calculated in step S102.

[0074] As an example, the controller 15 in the server 10, as the deterioration history data calculation unit 153, can calculate the deterioration history data based on the external force data acting on the tire 3 and the tire state data of the tire 3. As described above, the tire state data of the tire 3 is, for example, time-series data of the internal pressure (air pressure) or temperature of the tire 3. In this way, the internal pressure or temperature of the tire 3 can be taken into account, thereby improving the calculation accuracy of the deterioration history data.

[0075] As another example, the controller 15 in the server 10, as the deterioration history data calculation unit 153, can calculate the deterioration history data based on the external force data acting on the tire 3 and the outdoor temperature data. More preferably, the controller 15 can calculate the temperature history data based on the external force data acting on the tire 3 and the outdoor temperature data. By considering the influence of the outdoor temperature, the calculation accuracy of the temperature history data can be improved.

[0076] If the driving data of the vehicle 2 satisfies a predetermined condition, the controller 15 in the server 10 can calculate the temperature history data based on the outdoor temperature data without using the external force data acting on the tire 3. The predetermined condition is, for example, a condition for indicating that the vehicle 2 stops. It is known that the temperature of the tire 3 is equal to or close to the value of the outdoor temperature data during the stop of the vehicle 2. Therefore, the temperature history data can be calculated based on the outdoor temperature data without using the external force data. Therefore, during this period, the calculation of the external force data can be omitted without reducing the calculation accuracy of the temperature history data, so that an increase in the calculation amount in the server 10 can be suppressed.

[0077] As yet another example, the controller 15 in the server 10, as the deterioration history data calculation unit 153, can calculate the deterioration history data based on the external force data acting on the tire 3 and the wear state of the tire 3. As described above, the wear state of the tire 3 can be the remaining groove depth of the tread rubber 3B of the tire 3. Even for tires 3 of the same model, the external force acting on the tire 3 may vary depending on the wear state of the tread rubber 3B. By considering the wear state of the tread rubber 3B of the tire 3, the calculation accuracy of the deterioration history data for at least a part of the base tire portion 3A of the tire 3 can be improved.

[0078] The wear state of the tire 3 can be prepared by any method. The controller 15 in the server 10 can obtain the measured value of the remaining groove depth of the tread rubber 3B of the tire 3 as the wear state of the tire 3 via the communication unit 11 or the input unit 13. Alternatively, the wear state of the tire 3 can be calculated based on the external force data acting on the tire 3. In this case, in step S104, the controller 15 in the server 10, as the wear state prediction unit 154, can calculate the wear state of the tire 3 based on the external force data acting on the tire 3. Calculating the wear state of the tire 3 using the correlation between the external force data acting on the tire 3 and the wear state of the tire 3 eliminates the need to obtain the measured value of the wear state of the tire 3 from outside the server 10.

[0079] Any method can be used to calculate the wear state of the tire 3. Typically, the wear energy applied to the tread rubber 3B of the tire 3 can be calculated based on the external force acting on the tire 3. The wear energy is expressed as the product of the slip amount of the tread rubber 3B relative to the road surface and the shear force acting on the tread rubber 3B. It is known that the wear energy and the wear amount of the tread rubber 3B are related to each other. Therefore, the controller 15 in the server 10 can pre-store the association algorithm between the external force data acting on the tire 3 and the wear state of the tire 3 in the storage unit 14. The controller 15 can use this association algorithm to calculate the wear state of the tire 3 based on the external force data.

[0080] In this embodiment, the association algorithm for calculating the wear state of the tire 3 is constructed by statistical methods such as machine learning or deep learning. In this operation example, the association algorithm includes one or more calculation models constructed by machine learning. In the case of multiple calculation models, an appropriate calculation model can be used according to the target tire 3. The calculation model obtains the external force data acting on the tire 3 and outputs the wear state of the tire 3. Thus, the server 10 can further improve the calculation accuracy of the wear state of the tire 3 through machine learning. The association algorithm can include a predetermined relationship that is not based on statistical methods. The controller 15 can store the calculated wear state of the tire 3 in association with the tire identification information of the tire 3 in the storage unit 14.

[0081] As another example, in step S103, the controller 15 in the server 10, as the deterioration history data calculation unit 153, in addition to or instead of using information such as the external force data acting on the tire 3 described above, can also use the driving data of the vehicle 2 equipped with the tire 3 and / or the tire state data of the tire 3. In this case, the correlation algorithm for calculating the deterioration history data can be configured to receive, in addition to or instead of receiving information such as the external force data acting on the tire 3, the driving data of the vehicle 2 equipped with the tire 3 and / or the tire state data of the tire 3 as inputs. As described above, the tire state data of the tire 3 can be, for example, time series data of the internal pressure (air pressure) or temperature of the tire 3 generated by the TPMS.

[0082] Specifically, when calculating the temperature history data included in the deterioration history data, the controller 15 in the server 10 can use at least one of the time series data of the temperature of the tire 3, the time series data of the speed of the vehicle 2, and the position information of the tire 3 mounted on the vehicle 2. When calculating the strain history data included in the deterioration history data. The controller 15 can use at least one of the wear state of the tire 3 and the time series data of the internal pressure of the tire 3. When calculating the oxygen concentration history data included in the deterioration history data, the controller 15 can use the temperature history data included in the deterioration history data. The controller 15 can store the calculated temperature history data, strain history data, or oxygen concentration history data in the storage unit 14 in association with the tire identification information of the tire 3 as the deterioration history data.

[0083] In step S105, the controller 15 in the server 10, as the durability prediction unit 155, outputs the remaining durability of the tire 3 based on the deterioration history data of at least a part of the base tire portion 3A of the tire 3.

[0084] Any method can be used to calculate the remaining durability of the tire 3. The controller 15 in the server 10 can pre-store in the storage unit 14 an association algorithm between the deterioration history data of at least a part of the base tire portion 3A of the tire 3 and the remaining durability of the tire 3. The controller 15 can use this association algorithm to calculate the remaining durability of the tire 3 based on the deterioration history data of at least a part of the tire base 3A of the tire 3. Specifically, the control unit 15 can calculate the current remaining durability of the tire 3 (e.g., 0 to 100) by subtracting the amount of durability decrease caused by the use of the tire 3 calculated according to the deterioration history data of the tire 3 from the remaining durability of the tire 3 in the unused state when shipped from the factory (e.g., 100) as the initial value. When calculating the remaining durability of the tire 3, the controller 15 can, for example, use information related to the tire 3 (such as the unique manufacturing data of the tire 3, etc.) to correct the initial value of the remaining durability of the tire 3. As described above, the unique manufacturing data of the tire 3 includes the length of the folded portion of the carcass (ply), the belt width, etc. For the length of the folded portion of the carcass or the belt width, there are optimal values for the durability index, and deviation from the optimal value may result in a decrease in durability. For example, when the length of the folded portion of the carcass is longer, the remaining durability of the tire 3 can be calculated as higher. For example, when the belt width is narrower, the remaining durability of the tire 3 can be calculated as higher. By taking into account the manufacturing deviations between the tires 3 in this way, the calculation accuracy of the remaining durability of the tire 3 can be further improved.

[0085] In this embodiment, a statistical method such as machine learning or Bayesian estimation is used to construct an association algorithm for calculating the remaining durability of the tire 3. In this operation example, the association algorithm includes one or more calculation models constructed by machine learning. In the case where there are multiple calculation models, an appropriate calculation model can be used according to the target tire 3 and a part of the base tire portion 3A of the tire 3. The calculation model acquires the deterioration history data of at least a part of the base tire portion 3A of the tire 3 and outputs the remaining durability of the tire 3. Thus, the server 10 can further improve the calculation accuracy of the remaining durability of the tire 3 through machine learning. The association algorithm can include a predetermined relational expression not based on a statistical method. The controller 15 can store the calculated remaining durability of the tire 3 in association with the tire identification information of the tire 3 in the storage unit 14.

[0086] When calculating the remaining durability of the tire 3 in step S105, the controller 15 in the server 10 can, in addition to obtaining the deterioration history data calculated in step S103, also obtain the remaining durability of the tire 3 at a specific time point as an input. Specifically, the controller 15 can output the remaining durability of the tire 3 based on the remaining durability of the tire 3 at a specific time point and the deterioration history data from the specific time point. For example, if the controller 15 has previously calculated the remaining durability of the tire 3 at a specific time point, the controller 15 can calculate the current remaining durability of the tire 3 by subtracting the amount of decrease in the durability of the tire 3 calculated based on the deterioration history data of the tire 3 from the specific time point from the remaining durability of the tire 3 at the specific time point as the initial value. This can omit the calculation of the amount of decrease in the durability of the tire 3 from the time of shipment from the factory until the specific time point, and suppress an increase in the calculation amount of the server 10.

[0087] The controller 15 in the server 10 can output the remaining durability of the tire 3 calculated in step S105 by any method. For example, the controller 15 can display the remaining durability of the tire 3 via an output unit 12 such as a display. Alternatively, the controller 15 can send a request for displaying the remaining durability of the tire 3 to the terminal device 30 via the communication unit 11. In such a case, the terminal device 30 can display the remaining durability of the tire 3 via a display or the like based on the request received from the server 10. As a result, the user of the tire remaining durability prediction system 1 can view the visualized remaining durability of the tire 3. Thus, the tire remaining durability prediction system 1 can improve the usefulness of the technology for predicting the remaining durability of the tire 3. In addition to outputting the remaining durability, the controller 15 can also output intermediate data in the calculation of the remaining durability of the tire 3, such as external force data acting on the tire 3. Presenting to the user not only the remaining durability of the tire 3 but also the intermediate data in the calculation of the remaining durability can improve the reliability of the remaining durability calculated using machine learning or the like.

[0088] In step S106, if the remaining durability of the tire 3 is less than a predetermined threshold, the controller 15 in the server 10 can output an alarm. The predetermined threshold can be, for example, a threshold for indicating an acceptable range of the durability of the tire 3. Alternatively, the predetermined threshold can be associated with at least one of replacement, retreading, and rotation of the tire 3. For example, in the case where the predetermined threshold is associated with the replacement of the tire 3, if the remaining durability of the tire 3 is less than the predetermined threshold, an alarm can be output to prompt the replacement of the tire 3.

[0089] Any method can be used to output an alert. The controller 15 in the server 10 can display information via the output unit 12 or output sound or light. Alternatively, the controller 15 can send a request for outputting an alert to the terminal device 30 via the communication unit 11. In such a case, the terminal device 30 can output an alert via a display or the like based on the request received from the server 10. As a result, the user of the tire remaining durability prediction system 1 can be prompted to perform actions such as replacement, retreading, or rotation of the tire 3.

[0090] Next, the operation of constructing a calculation model using the server 10 will be described with reference to Figure 6 As described above, the external force calculation unit 152, the deterioration history data calculation unit 153, the wear state prediction unit 154, and the durability prediction unit 155 can use calculation models. These calculation models can be constructed by the model construction unit 156.

[0091] In step S201, the controller 15 in the server 10, as the model construction unit 156, generates training (teaching) data for constructing each calculation model.

[0092] Any method can be used to generate the training data. For example, the controller 15 in the server 10 can generate training data in which the past measured values corresponding to the input and output in the calculation model are the explanatory variables and the target variables. Thus, the accuracy of the output of the calculation model can be improved by accumulating measurement data. The controller 15 in the server 10 can generate training data in which, in addition to or instead of the past measured values, virtual time series data generated by simulation are the explanatory variables and the target variables. For example, it is preferable to generate virtual time series data that maintains summary statistics (mean, variance, etc.) based on actual vehicle driving data or the like by using a known stochastic process method or a modal decomposition method such as principal component analysis. In this way, even in the initial stage where the accumulated measurement data is small, a highly accurate calculation model can be efficiently constructed. A vehicle driving simulator, a three-dimensional tire rolling simulator, etc. can be used to generate virtual time series data by simulation. The three-dimensional tire rolling simulator uses, for example, the finite element method (FEM).

[0093] In step S202, the controller 15 in the server 10, as the model construction unit 156, performs machine learning based on the training data to construct a calculation model.

[0094] In addition to time series data such as the running data of the vehicle 2 equipped with the tire 3 and the tire state data of the tire 3, in steps S201 and S202, any information can also be used to construct a calculation model. For example, in addition to time series data such as the running data of the vehicle 2 equipped with the tire 3 and the tire state data of the tire 3, information related to the tire 3 can also be used, such as the structural information of the tire 3, the structural information of the vehicle 2 equipped with the tire 3, or the position information of the tire 3 installed on the vehicle 2. In addition, for example, outdoor temperature data, the wear state of the tire 3, or manufacturing data unique to the tire 3 can be used. This can improve the accuracy of the output of the calculation model constructed by machine learning.

[0095] As described above, in the present embodiment, the server 10 as the tire remaining durability prediction device includes: a data acquisition unit 151 configured to acquire the running data of the vehicle 2 equipped with the tire 3; an external force calculation unit 152 configured to calculate external force data of the external force acting on the tire 3 based on the running data; a deterioration history data calculation unit 153 configured to calculate deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data for at least a part of the carcass portion 3A of the tire 3 based on the external force data; and a durability prediction unit 155 configured to output the remaining durability of the tire 3 based on the deterioration history data for at least a part of the carcass portion 3A.

[0096] With this structure, instead of directly predicting the remaining durability of the tire 3 based on the running data of the vehicle 2 equipped with the tire 3, the server 10 gradually predicts the remaining durability of the tire 3 by calculating the external force data acting on the tire 3 as intermediate data. This can improve the prediction accuracy of the remaining durability of the tire 3.

[0097] Although the present disclosure has been illustrated above through embodiments and drawings, those of ordinary skill in the art can make various changes and modifications based on the present disclosure. Therefore, such changes and modifications are included in the scope of the present disclosure. For example, the structures, functions, etc. included in each embodiment can be rearranged without logical inconsistency. The structures, functions, etc. included in each embodiment can be combined with other embodiments, and multiple structures, functions, etc. can be combined into one structure, function, etc., one structure, function, etc. can be divided into multiple structures, functions, etc., or a part of these structures, functions, etc. can be omitted.

[0098] For example, in the above reference Figure 3In the operation of predicting the remaining durability of the tire 3, although the controller 15 in the server 10 calculates the external force data acting on the tire 3 in step S102, the present disclosure is not limited thereto. For example, a computer other than the server 10 may calculate the external force data. In such a case, the controller 15 in the server 10 can obtain the external force data acting on the tire 3 in step S101 as the data acquisition unit 151 in Figure 3 Step S101. Then, the controller 15 can use the external force data obtained in step S101 in the processing after step S101.

[0099] For example, although the above-described embodiment describes the case where the controller 15 in one server 10 operates as the data acquisition unit 151, the external force calculation unit 152, the deterioration history data calculation unit 153, the wear state prediction unit 154, the durability prediction unit 155, and the model construction unit 156, the present disclosure is not limited thereto. A plurality of controllers 15 and servers 10 dedicated to each operation may be provided.

[0100] For example, the following embodiment is also possible: A general-purpose computer is used as the server 10 according to the above-described embodiment. Specifically, a program for processing for implementing the functions of the server 10 according to the above-described embodiment is stored in the memory of the general-purpose computer, and is read and executed by the processor in the general-purpose computer. Thus, the present disclosure can also be implemented as a program executable by a processor or a non-transitory computer-readable medium storing the program. Examples of the non-transitory computer-readable medium include a magnetic recording device, an optical disc, a magneto-optical recording medium, and a semiconductor memory.

[0101] Industrial Applicability

[0102] Therefore, it is possible to provide a tire remaining durability prediction device, a tire remaining durability prediction method, and a program that can improve the prediction accuracy of the remaining durability of a tire.

[0103] [Contribution to the United Nations-led Sustainable Development Goals (SDGs)]

[0104] The SDGs have been proposed to create a sustainable society. The embodiments of the present disclosure are considered to be technologies that can contribute to "Goal 12: Responsible Consumption and Production" and "Goal 13: Climate Action", etc.

[0105] Explanation of Reference Numerals

[0106] 1: Tire remaining durability prediction system; 2: Vehicle; 3: Tire; 3A: Base tire; 3A-1: Portion between belt layers; 3A-2: Belt-carcass portion; 3A-3: Carcass end; 3B: Tread rubber; 10: Server (tire remaining durability prediction device); 11: Communication unit; 12: Output unit; 13: Input unit; 14: Storage unit; 15: Controller; 151: Data acquisition unit; 152: External force calculation section; 153: Deterioration history data calculation section; 154: Wear state prediction section; 155: Durability prediction section; 156: Model construction unit; 20: Measuring device; 30: Terminal device; 40: Network; Fx, Fy, Fz: External force components; CL: Tire equatorial plane

Claims

1. A tire remaining durability prediction device, comprising: A data acquisition unit configured to acquire driving data of a vehicle equipped with a tire or external force data of an external force acting on the tire; A deterioration history data calculation unit configured to calculate deterioration history data for at least a part of a base tire portion of the tire based on the driving data or the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; And A durability prediction unit configured to output the remaining durability of the tire based on the deterioration history data for at least a part of the base tire portion.

2. The tire remaining durability prediction device according to claim 1, further comprising: An external force calculation unit configured to calculate the external force data based on the driving data, wherein the external force calculation unit is configured to calculate the external force data based on the driving data and information related to the tire.

3. The tire remaining durability prediction device according to claim 1 or 2, wherein, The deterioration history data calculation unit includes a calculation model constructed by machine learning, and the calculation model is configured to acquire the external force data and output the deterioration history data.

4. The tire remaining durability prediction device according to claim 3, wherein, The deterioration history data at least includes the temperature history data, and the calculation model configured to output the temperature history data is a recursive calculation model that uses past outputs as inputs.

5. The tire remaining durability prediction device according to claim 1, wherein, The durability prediction unit is configured to output the remaining durability of the tire based on the remaining durability of the tire at a specific time point and the deterioration history data starting from the specific time point.

6. The tire remaining durability prediction device according to claim 1, wherein, The deterioration history data at least includes the temperature history data, the data acquisition unit is configured to further acquire outdoor temperature data, and the deterioration history data calculation unit is configured to calculate the temperature history data based on the external force data and the outdoor temperature data.

7. The tire remaining durability prediction device according to claim 6, wherein, The deterioration history data calculation unit is configured to calculate the temperature history data based on the outdoor temperature data without using the external force data when the driving data meets a predetermined condition.

8. The tire remaining durability prediction device according to claim 3, wherein The deterioration history data at least includes the strain history data, and the calculation model configured to calculate the strain history data is configured to acquire the external force data and output data related to the principal strain of the tire as the strain history data.

9. The tire remaining durability prediction device according to claim 1, wherein, The data acquisition unit is configured to further acquire the wear state of the tire, and the deterioration history data calculation unit is configured to calculate the deterioration history data based on the external force data and the wear state of the tire.

10. The tire remaining durability prediction device according to claim 1, further comprising: A wear state prediction unit configured to calculate the wear state of the tire based on the external force data, wherein the deterioration history data calculation unit is configured to calculate the deterioration history data based on the external force data and the wear state of the tire.

11. A tire remaining durability prediction method, which is executed by one or more computers, the tire remaining durability prediction method comprising: Acquiring driving data of a vehicle equipped with a tire or external force data of an external force acting on the tire; Calculating deterioration history data for at least a part of a base tread portion of the tire based on the driving data or the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; And Outputting remaining durability of the tire based on the deterioration history data for at least a part of the base tread portion.

12. A program for causing one or more computers to perform operations, the operations including: Obtaining driving data of a vehicle equipped with a tire or external force data of an external force acting on the tire; Calculating deterioration history data for at least a part of a base tread portion of the tire based on the driving data or the external force data, the deterioration history data including at least one of temperature history data, strain history data, and oxygen concentration history data; And Outputting remaining durability of the tire based on the deterioration history data for at least a part of the base tread portion.

Images