Stress estimation device

Abstract

To improve estimation accuracy of stress generated in a specified component of a power transmission device.SOLUTION: A stress estimation device includes an execution device, and a storage device. The storage device stores a relation definition model that outputs an index value indicating stress generated in a specified component of a power transmission device of a vehicle when a plurality of types of input data is input. Here, the relation definition model is generated in advance by machine learning. The plurality of types of input data includes two or more selected from torque of an input shaft of the power transmission device, torque of an output shaft of the power transmission device, and a change gear ratio of the power transmission device, and road surface information which is information indicating force applied to the vehicle from a road surface of the road on which the vehicle is located. The execution device acquires a plurality of types of input data (S11-S17). The execution device outputs the index value by inputting the acquired plurality of types of input data to the relation definition model (S18).SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a stress estimation device. [Background technology]

[0002] The vehicle disclosed in Patent Document 1 includes an engine, a reduction gear, a continuously variable transmission, and a control device. The engine transmits power to the vehicle's drive wheels via the reduction gear and the continuously variable transmission. The control device estimates stress generated in the input shaft of the continuously variable transmission based on the torque input from the engine to the continuously variable transmission via the reduction gear and the gear ratio of the continuously variable transmission. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-008098 Summary of the Invention [Problem to be solved by the invention]

[0004] In a vehicle such as that described in Patent Document 1, as the vehicle travels, a force may be applied to the vehicle from the road surface on which the vehicle is located. The force applied to the vehicle from the road surface on which the vehicle is located also changes the stress generated in the input shaft of the continuously variable transmission mechanism. Therefore, the stress estimation configuration described in Patent Document 1 may not be able to accurately estimate the stress generated in the input shaft. While the input shaft of the continuously variable transmission mechanism has been described as an example here, the same problem occurs with components other than the input shaft of a power transmission device that transmits power from the vehicle's drive source to the drive wheels. [Means for solving the problem]

[0005] A stress estimation device for solving the above problem targets a predetermined specific part in a power transmission device that is mounted on a vehicle and transmits power from a drive source of the vehicle to drive wheels, and includes an execution device and a storage device. The storage device stores a relationship specification model that outputs an index value that indicates stress generated in the specific part when multiple types of input data are input. When the ratio between the rotational speed of an input shaft in the power transmission device and the rotational speed of an output shaft in the power transmission device is defined as a gear ratio, the multiple types of input data include two or more selected from the torque of the input shaft, the torque of the output shaft, and the gear ratio, and road surface information that is information that indicates a force applied to the vehicle from the surface of a road on which the vehicle is located. The execution device executes the following steps: acquires the multiple types of input data; and outputs the index value by inputting the acquired multiple types of input data into the relationship specification model. [Effects of the Invention]

[0006] According to the above configuration, by inputting multiple types of input data, including road surface information, into the relational specification model, an index value indicating the stress generated in a specific component of the power transmission device is output from the relational specification model. Therefore, the index value reflects the road surface information, i.e., the force applied to the vehicle from the road surface on which the vehicle is located. This improves the accuracy of estimating the stress generated in the specific component, compared to, for example, a case in which the force applied to the vehicle from the road surface on which the vehicle is located is not taken into account. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a schematic diagram of a vehicle. [Figure 2] FIG. 2 is a flowchart showing the estimation control. DETAILED DESCRIPTION OF THE INVENTION

[0008] <Vehicle Overview> An embodiment of the present invention will now be described with reference to Figures 1 and 2. First, the general configuration of a vehicle 100 will be described.

[0009] As shown in FIG. 1, a vehicle 100 includes an internal combustion engine 10, a torque converter 20, an automatic transmission 30, a differential 41, a plurality of drive wheels 42, and a hydraulic mechanism 50. The internal combustion engine 10 has four cylinders 11 and a crankshaft 12. The cylinders 11 are spaces for burning a mixture of fuel and intake air. The crankshaft 12 rotates due to the combustion of the mixture in the cylinders 11. In this embodiment, the cylinders 11 of the internal combustion engine 10 are an example of a drive source for the vehicle 100.

[0010] The torque converter 20 includes an input shaft 21 and an output shaft 22. The torque converter 20 transmits power from the input shaft 21 to the output shaft 22 via a fluid. At this time, the torque converter 20 reduces the rotation of the input shaft 21 and outputs it from the output shaft 22. A first end of the input shaft 21 is connected to the crankshaft 12. The torque converter 20 also includes a lock-up clutch (not shown). A second end of the input shaft 21 is connected to a first end of the output shaft 22 via the lock-up clutch. When the lock-up clutch is engaged, the input shaft 21 and the output shaft 22 rotate integrally.

[0011] The automatic transmission 30 includes an input shaft 31 and an output shaft 32. A first end of the input shaft 31 is connected to a second end of the output shaft 22 of the torque converter 20. A second end of the input shaft 31 is connected to a first end of the output shaft 32 via a clutch and a gear (not shown). A second end of the output shaft 32 is connected to left and right drive wheels 42 via a differential 41. The automatic transmission 30 is capable of changing a gear ratio, which is the ratio between the rotation speed of the input shaft 31 and the rotation speed of the output shaft 32. Here, the gear ratio of the automatic transmission 30 is a ratio indicating the number of times the input shaft 31 rotates for one rotation of the output shaft 32. Therefore, the larger the gear ratio, the higher the speed at which the input shaft 31 rotates relative to the output shaft 32. An example of the automatic transmission 30 is a stepped automatic transmission. Therefore, the automatic transmission 30 changes the gear ratio by changing the gear position.

[0012] The hydraulic mechanism 50 is attached to the automatic transmission 30. The hydraulic mechanism 50 supplies oil to the automatic transmission 30. The automatic transmission 30 is controlled by the oil supplied from the hydraulic mechanism 50.

[0013] 1, the vehicle 100 includes an accelerator operation amount sensor 71, a vehicle speed sensor 72, a GNSS receiver 73, an acceleration sensor 74, and an oil temperature sensor 75. The vehicle 100 also includes a crank angle sensor 76, an input rotation speed sensor 77, an output rotation speed sensor 78, and a display 79.

[0014] The accelerator operation amount sensor 71 detects an accelerator operation amount ACC, which is an operation amount of an accelerator pedal operated by a driver of the vehicle 100. The vehicle speed sensor 72 detects a vehicle speed SP, which is the speed of the vehicle 100.

[0015] The GNSS receiver 73 communicates with a GNSS satellite (not shown) to detect position coordinates PC, which are the coordinates of the location of the vehicle 100. Note that "GNSS" is an abbreviation for Global Navigation Satellite System.

[0016] The acceleration sensor 74 is a so-called three-axis sensor. That is, the acceleration sensor 74 can detect longitudinal acceleration GX, lateral acceleration GY, and vertical acceleration GZ. The longitudinal acceleration GX is acceleration along the longitudinal axis of the vehicle 100. The lateral acceleration GY is acceleration along the lateral axis of the vehicle 100. The vertical acceleration GZ is acceleration along the vertical axis of the vehicle 100. In other words, the longitudinal acceleration GX is acceleration in the longitudinal direction relative to the vehicle 100. Furthermore, the lateral acceleration GY is acceleration in the lateral direction relative to the vehicle 100. Furthermore, the vertical acceleration GZ is acceleration in the vertical direction relative to the vehicle 100.

[0017] The oil temperature sensor 75 detects the oil temperature TA, which is the temperature of the oil circulating inside the automatic transmission 30. The crank angle sensor 76 detects the crank angle SC, which is the angular position of the crankshaft 12. The input rotation speed sensor 77 detects the input rotation speed NIN, which is the rotation speed of the input shaft 31. The output rotation speed sensor 78 detects the output rotation speed NOUT, which is the rotation speed of the output shaft 32. The display 79 is located near the driver's seat of the vehicle 100. The display 79 is capable of displaying various types of information.

[0018] 1, the vehicle 100 is equipped with a control device 90. The control device 90 acquires various pieces of information from an accelerator operation amount sensor 71, a vehicle speed sensor 72, a GNSS receiver 73, an acceleration sensor 74, and an oil temperature sensor 75. The control device 90 acquires various pieces of information from a crank angle sensor 76, an input rotation speed sensor 77, and an output rotation speed sensor 78.

[0019] The control device 90 includes an execution device 91 and a storage device 92. An example of the execution device 91 is a CPU. The storage device 92 includes a read-only ROM, a readable / writable volatile RAM, and a readable / writable non-volatile storage. The storage device 92 stores various programs and data in advance. Specifically, the storage device 92 stores a control program 92A in advance as one of the various programs. The storage device 92 also stores a relationship definition model M in advance as one of the various data. The relationship definition model M describes, in a format recognizable by the execution device 91, the relationship between predetermined input data and an index value indicating the stress generated in the output shaft 32 of the automatic transmission 30. The relationship definition model M outputs an index value indicating the stress generated in the output shaft 32 of the automatic transmission 30 when multiple types of input data are input. In this embodiment, the relationship definition model M is generated in advance by machine learning. A detailed description of the relationship definition model M will be provided later. Furthermore, the storage device 92 pre-stores manufacturing history data DH as one of the various types of data. The manufacturing history data DH is data indicating the manufacturing history of the output shaft 32 of the automatic transmission 30. The manufacturing history data DH will be described in detail later. The execution device 91 executes a control program 92A stored in the storage device 92 to perform various processes described later. In this embodiment, the control device 90 is an example of a stress estimation device. The automatic transmission 30 is an example of a power transmission device that transmits power from a drive source of the vehicle 100 to the drive wheels 42. The output shaft 32 is a predetermined specific part of the power transmission device.

[0020] The execution device 91 of the control device 90 calculates a target driving force, which is a target value of the driving force of the vehicle 100, based on the accelerator operation amount ACC and the vehicle speed SP. Next, the execution device 91 calculates a target output, which is a target value of the output of the internal combustion engine 10, based on the target driving force. Then, the execution device 91 outputs a control signal corresponding to the target output to the internal combustion engine 10. As a result, the internal combustion engine 10 is controlled according to the target output. Furthermore, the execution device 91 calculates a target gear position, which is a target value of the gear position of the automatic transmission 30, based on the target driving force. Then, the execution device 91 outputs a control signal corresponding to the target gear position to the hydraulic mechanism 50. As a result, the hydraulic mechanism 50 is controlled, thereby controlling the automatic transmission 30.

[0021] An execution unit 91 of the control device 90 calculates the engine rotation speed NE, which is the rotation speed of the crankshaft 12, based on the crank angle SC. The execution unit 91 also outputs a control signal to the display 79, thereby displaying various information on the display 79.

[0022] <Estimation control> Next, the estimation control executed by the control device 90 will be described with reference to Fig. 2. This estimation control is control for estimating a specific stress ST of the output shaft 32 of the automatic transmission 30. The specific stress ST is a stress generated in the output shaft 32. In this embodiment, the execution device 91 of the control device 90 executes the estimation control at each predetermined control cycle, with the necessary condition being that the control device 90 is operating.

[0023] As shown in FIG. 2, when the execution unit 91 of the control device 90 starts estimation control, it executes the processing of step S11. In step S11, the execution unit 91 of the control device 90 acquires the input torque TIN, which is the torque of the input shaft 31 at the time of the processing of step S11. The execution unit 91 acquires the input torque TIN, for example, as follows. First, the execution unit 91 calculates the torque output from the crankshaft 12 based on the target output, which is a target value of the output of the internal combustion engine 10. Then, the execution unit 91 calculates the input torque TIN based on the torque output from the crankshaft 12, the engine rotation speed NE, and the input rotation speed NIN. After step S11, the execution unit 91 advances the processing to step S12.

[0024] In step S12, the execution unit 91 acquires the actual gear ratio RG, which is the actual gear ratio of the automatic transmission 30 at the time of processing step S12. For example, the execution unit 91 calculates the actual gear ratio RG based on the input rotation speed NIN and the output rotation speed NOUT. The actual gear ratio RG is expressed by the following equation (1).

[0025] Formula (1): Actual speed ratio RG = input rotation speed NIN / output rotation speed NOUT In this embodiment, the actual gear ratio RG corresponds to the gear ratio that is the ratio between the rotation speed of the input shaft 31 of the automatic transmission 30 and the rotation speed of the output shaft 32 of the automatic transmission 30. After step S12, the execution unit 91 advances the process to step S13.

[0026] In step S13, the execution unit 91 acquires the output torque TOUT, which is the torque of the output shaft 32 at the time of processing in step S13. For example, the execution unit 91 calculates the output torque TOUT based on the input torque TIN, the actual speed ratio RG, and the transmission efficiency. The output torque TOUT is expressed by the following equation (2).

[0027] Equation (2): Output torque TOUT = Input torque TIN x Actual speed ratio RG x Transmission efficiency Here, the transmission efficiency is the efficiency when torque is transmitted between the input shaft 31 and the output shaft 32. The transmission efficiency is a value determined in advance, for example, through experiments, simulations, etc. After step S13, the execution unit 91 advances the process to step S14.

[0028] In step S14, the execution unit 91 acquires the longitudinal acceleration GX, the lateral acceleration GY, and the vertical acceleration GZ at the time of processing step S14. After step S14, the execution unit 91 advances the process to step S15.

[0029] In step S15, the execution unit 91 acquires the oil temperature TA at the time of the processing of step S15. After step S15, the execution unit 91 advances the processing to step S16.

[0030] In step S16, the execution device 91 accesses the storage device 92 to acquire the manufacturing history data DH. As described above, the manufacturing history data DH is data indicating the manufacturing history of the output shaft 32 of the automatic transmission 30. For example, assume that a factory that manufactures the automatic transmission 30 has a first machine and a second machine as equipment for manufacturing the output shaft 32. Assume also that the output shaft 32 of the automatic transmission 30 of the vehicle 100 was manufactured by the first machine. In this case, the manufacturing history data DH includes a numerical value of "1" indicating the history that the output shaft 32 was manufactured by the first machine, i.e., the manufacturing history of the output shaft 32. In this embodiment, the numerical value indicating the manufacturing history of the output shaft 32 in the manufacturing history data DH is an example of manufacturing history information. Note that if the output shaft 32 of the automatic transmission 30 of the vehicle 100 was manufactured by the second machine, the manufacturing history data DH includes a numerical value of "2" indicating the manufacturing history of the output shaft 32. After step S16, the execution device 91 proceeds to step S17.

[0031] In step S17, the execution device 91 generates the input torque TIN, output torque TOUT, longitudinal acceleration GX, lateral acceleration GY, vertical acceleration GZ, oil temperature TA, and manufacturing history data DH as input variables of the relational specification model M. Specifically, the execution device 91 assigns the values ​​of the input torque TIN, output torque TOUT, longitudinal acceleration GX, lateral acceleration GY, vertical acceleration GZ, oil temperature TA, and manufacturing history data DH to the input variables x(1) to x(7) one by one in order. As described above, an example of the value of the manufacturing history data DH is "1." Below, the "7" for the input variables x(1) to x(7) will be written as "Z." In other words, "Z" is the number of input variables generated in step S17.

[0032] In this embodiment, the input torque TIN, output torque TOUT, longitudinal acceleration GX, lateral acceleration GY, vertical acceleration GZ, oil temperature TA, and manufacturing history data DH are each input data input to the relational specification model M. Furthermore, the vertical acceleration GZ is an example of information indicating the force applied to the vehicle 100 from the road surface on which the vehicle 100 is located, i.e., road surface information. After step S17, the execution device 91 proceeds to step S18.

[0033] In step S18, the execution device 91 inputs the input variables x(1) to x(Z) and the input variable x(0) as a bias parameter to the relational definition model M, and outputs the value of the output variable y(i) indicating the stress generated in the output shaft 32 of the automatic transmission 30. Here, the output variable y(i) is an index value indicating the stress generated in the output shaft 32 of the automatic transmission 30.

[0034] An example of the relationship definition model M is a function approximator, which is a fully connected forward propagation neural network with one intermediate layer. In this relationship definition model M, input variables x(1) to x(Z) and input variable x(0) as a bias parameter are transformed by a linear mapping defined by coefficients wFjk (j = 1 to m, k = 0 to Z), and each of the m values ​​is substituted into an activation function f. As a result, the values ​​of the intermediate layer nodes are determined. Furthermore, the values ​​of the intermediate layer nodes transformed by the linear mapping defined by coefficients wSij (i = 1) are substituted into an activation function g, thereby determining an output variable y(1). In this embodiment, an example of the activation function f is a ReLU function. An example of the activation function g is a sigmoid function. In other words, the output variable y(1) can vary within the range of 0 to 1. Note that the smaller the output variable y(1), the smaller the stress generated in the output shaft 32 of the automatic transmission 30.

[0035] The relationship specification model M is generated in advance, for example, as follows. First, an engineer or the like drives the vehicle 100 at various locations under various conditions. At this time, the input torque TIN, output torque TOUT, longitudinal acceleration GX, lateral acceleration GY, vertical acceleration GZ, oil temperature TA, and manufacturing history data DH are acquired in the same manner as above. Then, input variables x(1) to x(Z) are generated in the same manner as above. Furthermore, the actual stress generated in the output shaft 32 is determined by, for example, measuring the stress generated in the output shaft 32 with a measuring device attached to the output shaft 32 of the automatic transmission 30. Then, an output variable y(1) corresponding to the determined stress of the output shaft 32 is generated. The relationship specification model M is generated by machine learning using the data generated as described above. That is, the relationship specification model M is generated in advance by machine learning using a combination of the input torque TIN, output torque TOUT, longitudinal acceleration GX, lateral acceleration GY, vertical acceleration GZ, oil temperature TA, and manufacturing history data DH, and the stress of the output shaft 32, as training data. After step S18, the execution device 91 advances the process to step S19.

[0036] In step S19, the executing device 91 acquires the specific stress ST based on the output variable y(1). For example, the executing device 91 acquires the specific stress ST by converting the output variable y(1) by associating the output variable y(1) with a predetermined map. An example of the unit of the specific stress ST is "Pa." The executing device 91 also stores the acquired specific stress ST in the storage device 92. After step S19, the executing device 91 ends the current estimation control.

[0037] <Operation of this embodiment> When the vehicle 100 is traveling, for example, an uneven surface of the road on which the vehicle 100 is located may apply a vertical force to the vehicle 100. As a result, even if the power transmitted from the internal combustion engine 10 to the drive wheels 42 via the automatic transmission 30 is the same, the stress generated in the output shaft 32 of the automatic transmission 30, etc., may change due to the force applied to the vehicle 100 from the surface of the road on which the vehicle 100 is located.

[0038] 2, in estimation control, an execution unit 91 of the control device 90 acquires multiple types of input data including an input torque TIN, an output torque TOUT, a vertical acceleration GZ, etc. Then, the execution unit 91 inputs the multiple types of input data into a relational specification model M, thereby outputting an output variable y(1) that indicates the stress generated in the output shaft 32 of the automatic transmission 30.

[0039] <Effects of this embodiment> (1) According to this embodiment, by inputting multiple types of input data including the vertical acceleration GZ, i.e., road surface information, to the relationship specification model M, an index value indicating the stress occurring in the output shaft 32 of the automatic transmission 30 is output from the relationship specification model M. Therefore, the index value reflects the road surface information, i.e., the force applied to the vehicle 100 from the road surface on which the vehicle 100 is located. This makes it possible to improve the estimation accuracy of the stress occurring in the output shaft 32 of the automatic transmission 30, for example, compared to a case where the force applied to the vehicle 100 from the road surface on which the vehicle 100 is located is not taken into account.

[0040] If the execution device 91 can grasp the stress occurring on the output shaft 32 of the automatic transmission 30, it may be able to grasp fatigue and the like of the output shaft 32. Furthermore, if the execution device 91 can grasp the stress occurring on the output shaft 32 of the automatic transmission 30, it may be able to suppress the stress occurring on the output shaft 32 of the automatic transmission 30 by changing the control content of the vehicle 100.

[0041] (2) In this embodiment, the road surface information input to the relationship specification model M is the vertical acceleration GZ. According to this configuration, the index value output from the relationship specification model M reflects the vertical acceleration indicating the force actually applied to the vehicle 100 from the road surface on which the vehicle 100 is located. This makes it possible to obtain a more accurate index value than, for example, when a predicted value of the force applied to the vehicle 100 is reflected in the index value.

[0042] (3) Generally, when the vehicle 100 is traveling, not only the vertical acceleration GZ but also the longitudinal acceleration GX and the lateral acceleration GY depending on the operation of the driver of the vehicle 100 are applied to the vehicle 100.

[0043] In this regard, the multiple types of input data input to the relationship specification model M include the longitudinal acceleration GX and the lateral acceleration GY in addition to the vertical acceleration GZ. As a result, an index value indicating the stress generated in the output shaft 32 of the automatic transmission 30 is output from the relationship specification model M based on the vertical acceleration GZ, the longitudinal acceleration GX, and the lateral acceleration GY. As a result, an index value that more accurately reflects the force applied to the vehicle 100 can be obtained.

[0044] (4) In the automatic transmission 30, the higher the temperature of the oil circulating inside the automatic transmission 30, the higher the temperature of the output shaft 32 and the components around the output shaft 32 tends to be. When the temperature of the output shaft 32 and the components around the output shaft 32 increases in this way, the output shaft 32 and the components around the output shaft 32 expand. As a result, for example, the stress acting on the output shaft 32 may change due to a change in the size of the gap between the output shaft 32 and the components around the output shaft 32.

[0045] In this regard, the multiple types of input data input to the relational specification model M include the oil temperature TA, which is the temperature of the oil circulating inside the automatic transmission 30. As a result, by taking into account the oil temperature TA, in other words, by taking into account changes in stress occurring in the output shaft 32 in response to changes in the temperature of the output shaft 32, etc., a more accurate index value can be obtained.

[0046] (5) Even if the output shaft 32 has the same specifications, for example, if the output shaft 32 is manufactured by a first machine and if the output shaft 32 is manufactured by a second machine, the way in which stress occurs in the output shaft 32 may differ due to manufacturing errors of the output shaft 32. In other words, the way in which stress occurs in the output shaft 32 may differ depending on the manufacturing history of the output shaft 32.

[0047] In this regard, the multiple types of input data input to the relationship specification model M include manufacturing history information indicating the manufacturing history of the output shaft 32. As a specific example, the multiple types of input data input to the relationship specification model M include the history that the output shaft 32 was manufactured as the first unit, i.e., the numerical value "1" indicating the manufacturing history of the output shaft 32. This allows a more accurate index value to be obtained by taking into account the manufacturing history of the output shaft 32, i.e., by taking into account the way stress is generated according to the manufacturing history of the output shaft 32.

[0048] <Example of change> This embodiment can be modified as follows: This embodiment and the following modifications can be combined and implemented within the scope of technical compatibility.

[0049] In the above embodiment, the input data of the relationship definition model M may be changed. For example, the multiple types of input data input to the relationship specification model M do not have to include the input torque TIN and the output torque TOUT. As a specific example, the multiple types of input data of the relationship specification model M may include the actual gear ratio RG instead of the output torque TOUT. Also, as a specific example, the multiple types of input data of the relationship specification model M may include the actual gear ratio RG instead of the input torque TIN. In other words, the multiple types of input data of the relationship specification model M only need to include two or more selected from the input torque TIN, the output torque TOUT, and the actual gear ratio RG, and road surface information.

[0050] For example, the multiple types of input data input to the relationship specification model M do not have to include the longitudinal acceleration GX. As a specific example, if the relationship between the longitudinal acceleration GX and the force applied to a specific part is relatively weak, it is not a problem if the multiple types of input data to the relationship specification model M do not include the longitudinal acceleration GX.

[0051] For example, the multiple types of input data input to the relationship specification model M do not have to include the lateral acceleration GY. As a specific example, if the relationship between the lateral acceleration GY and the force applied to a specific part is relatively weak, it is not a problem if the multiple types of input data to the relationship specification model M do not include the lateral acceleration GY.

[0052] For example, the multiple types of input data input to the relationship specification model M do not have to include the vertical acceleration GZ. In other words, the road surface information in the input data of the relationship specification model M does not have to be the vertical acceleration GZ. As a specific example, the force applied to the vehicle 100 from the road surface on which the vehicle 100 is located changes depending on the position coordinate PC of the vehicle 100. Therefore, the multiple types of input data of the relationship specification model M may include the position coordinate PC as road surface information instead of the vertical acceleration GZ.

[0053] For example, the manufacturing history information in the multiple types of input data input to the relationship specification model M may be changed. As a specific example, assume that the output shaft 32 is manufactured by cutting using a cutting tool. In this case, the longer the cutting tool is used, the greater the amount of wear on the cutting tool. As the amount of wear on the cutting tool increases, the dimensions of the output shaft 32 may change depending on the amount of wear. As a result, the way in which stress is generated in the output shaft 32 may change due to manufacturing errors of the output shaft 32, etc. Therefore, the manufacturing history information in the multiple types of input data to the relationship specification model M may be a numerical value indicating the amount of time the cutting tool was used when cutting the output shaft 32.

[0054] For example, the multiple types of input data input to the relationship definition model M do not need to include manufacturing history information. As a specific example, if the change in stress of the output shaft 32 due to the manufacturing history of the output shaft 32 is small, the impact is small even if the multiple types of input data to the relationship definition model M do not include manufacturing history information.

[0055] For example, the multiple types of input data input to the relationship specification model M do not have to include the oil temperature TA. As a specific example, if the change in stress of the output shaft 32 in response to a change in the temperature of the output shaft 32 is small, the impact is small even if the multiple types of input data of the relationship specification model M do not include the oil temperature TA.

[0056] In the above embodiment, the relationship definition model M may be changed. For example, the activation function of the relationship definition model M is an example, and the activation function of the relationship definition model M can be changed.

[0057] For example, although a neural network with one hidden layer has been exemplified as the relational definition model M, the number of hidden layers may be two or more. For example, a fully connected forward propagation neural network has been exemplified as the neural network of the relationship definition model M, but this is not limiting. As a specific example, the neural network may be a recursive connection neural network. Also, for example, the function approximator as the relationship definition model M is not limited to a neural network. As a specific example, the relationship definition model M may be a regression formula without an intermediate layer.

[0058] For example, the relationship definition model M does not have to be generated by machine learning. As a specific example, the relationship definition model M may be a relational expression determined by experiments, simulations, or the like.

[0059] In the above embodiment, the stress estimation device may be changed. For example, the stress estimation device is not limited to the control device 90 of the vehicle 100, but may be a device separate from the control device 90 in the vehicle 100. In this case, the separate device may previously store the relationship specification model M and a stress estimation program for causing the device to function as the stress estimation device. Also, for example, the stress estimation device may be a device external to the vehicle 100. Here, an example of a device external to the vehicle 100 is a server capable of communicating with the vehicle 100. In this configuration, the server can perform estimation control by acquiring various types of information from the vehicle 100. In this case, the server may previously store the relationship specification model M and a stress estimation program for causing the device to function as the stress estimation device.

[0060] In the above embodiment, the specific parts may be changed. For example, the specific part may be the input shaft 31 of the automatic transmission 30. Also, for example, the specific part may be a clutch included in the automatic transmission 30. Furthermore, for example, the specific part may be a gear included in the automatic transmission 30. Also, for example, the specific part may be an engaging member for engaging multiple members included in the automatic transmission 30. Furthermore, for example, the specific part may be a case of the automatic transmission 30. Note that, because stress may be applied to the case of the automatic transmission 30 due to the power transmitted by the output shaft 32, etc., the case of the automatic transmission 30 may also be a specific part. In other words, any part in the power transmission device whose stress changes due to the transmission of power from the drive source of the vehicle 100 to the drive wheels 42 and whose stress changes due to a force applied from the road surface on which the vehicle 100 is traveling may be a specific part.

[0061] In the above embodiment, the power transmission device may be changed. For example, the power transmission device may be the torque converter 20. In other words, any device that transmits power from a drive source of the vehicle 100 to the drive wheels 42 can be a power transmission device.

[0062] In the above embodiment, the configuration of the vehicle 100 may be changed. For example, the vehicle 100 may be equipped with an electric motor instead of the internal combustion engine 10. In this case, the stator and rotor of the electric motor are the driving source of the vehicle 100. In this configuration, the rotating shaft of the electric motor connected to the rotor can be a specific part. [Explanation of symbols]

[0063] 10...Internal combustion engine 11...cylinder 12...Crankshaft 20...Torque converter 21...Input shaft 22...Output shaft 30...Automatic transmission 31...Input shaft 32...Output shaft 41...Differential 42...Drive wheel 50...Hydraulic mechanism 71...Accelerator operation amount sensor 72...Vehicle speed sensor 73...GNSS receiver 74...Acceleration sensor 75...Oil temperature sensor 76...Crank angle sensor 77...Input rotation speed sensor 78...Output rotation speed sensor 79...Display 90...Control device 91...Execution device 92...Storage device 92A...Control program DH...Manufacturing history data M...Related regulation model 100...Vehicle

Claims

1. The present invention is directed to a predetermined specific component in a power transmission device that is mounted on a vehicle and transmits power from a drive source of the vehicle to drive wheels, an execution device and a storage device; the storage device stores a relationship definition model that outputs an index value indicating a stress generated in the specific component when a plurality of types of input data are input, When the ratio between the rotation speed of the input shaft in the power transmission device and the rotation speed of the output shaft in the power transmission device is defined as a gear ratio, the plurality of types of input data include two or more selected from the torque of the input shaft, the torque of the output shaft, and the gear ratio, and road surface information which is information indicating a force applied to the vehicle from a road surface on which the vehicle is located, The execution device acquiring the plurality of types of input data; inputting the acquired plurality of types of input data into the relationship definition model to output the index value; Run Stress estimation device.

2. The road surface information is the vertical acceleration of the vehicle. The stress estimation device according to claim 1 .

3. The plurality of types of input data include, in addition to the vertical acceleration, a longitudinal acceleration relative to the vehicle and a lateral acceleration relative to the vehicle. The stress estimation device according to claim 2 .

4. The plurality of types of input data includes an oil temperature inside the power transmission device. The stress estimation device according to any one of claims 1 to 3.

5. The plurality of types of input data includes manufacturing history information indicating the manufacturing history of the specific part. The stress estimation device according to any one of claims 1 to 3.

Images