Seal performance estimation device and seal performance estimation program

Abstract

To obtain an index value on which seal performance of a liquid gasket is more accurately reflected.SOLUTION: A seal performance estimation device targets a power transmission device of a vehicle which comprises a first case, a second case, and a liquid gasket interposed between the first case and second case. A seal performance estimation device comprises an execution device and a storage device. The storage device stores a relation regulation model which outputs an index value indicative of the seal performance of the liquid gasket by inputting a plurality of kinds of input data. Here, the relation regulation model is previously generated through machine learning. One of the plurality of kinds of input data is time-series data on the torque of an output shaft of the power transmission device. The execution device acquires the plurality of kinds of input data. The execution device inputs the plurality of kinds of acquired input data to the relation regulation model to output the index value.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a seal performance estimation device and a seal performance estimation program.

Background Art

[0002] The vehicle of Patent Document 1 includes an engine, a power transmission device, and a plurality of drive wheels. The power transmission device transmits driving force from the engine to the plurality of drive wheels. Further, the power transmission device stores oil in the internal space thereof. Specifically, the power transmission device includes a first case, a second case, and a liquid gasket. The first case and the second case partition the internal space of the power transmission device. The liquid gasket is interposed between the first case and the second case at the contact portion therebetween. The liquid gasket prevents oil from leaking from the internal space of the power transmission device through between the first case and the second case.

[0003] Moreover, the vehicle of Patent Document 1 includes a diagnostic device. The diagnostic device acquires the input torque input to the input shaft of the power transmission device. Further, the diagnostic device acquires, as the cumulative load, the number of times an input torque equal to or greater than a predetermined value has been input. Then, when the cumulative load exceeds 80% of a predetermined threshold value, the diagnostic device warns that there may be an oil leak.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In a power transmission device such as Patent Document 1, the relationship between the number of times an input torque equal to or greater than a predetermined value is input and the degree of deterioration of the liquid gasket does not always show a simple proportional relationship. Therefore, for example, even if the number of times an input torque equal to or greater than a predetermined value is input is the same, the sealing performance that the liquid gasket can exhibit can vary. Therefore, there is a need for a technique capable of calculating an index value that more accurately reflects the sealing performance of the liquid gasket, in other words, an index value that more directly reflects the risk of oil leakage.

Means for Solving the Problems

[0006] A sealing performance estimation device for solving the above problems targets a power transmission device of a vehicle including a first case, a second case, and a liquid gasket interposed between the first case and the second case, and includes an execution device and a storage device. The storage device stores a relationship defining model that outputs an index value indicating the sealing performance of the liquid gasket when a plurality of types of input data are input. One of the plurality of types of input data is time-series data of the torque of the output shaft in the power transmission device. The execution device executes acquiring the plurality of types of input data and outputting the index value by inputting the acquired plurality of types of input data into the relationship defining model.

[0007] A sealing performance estimation program for solving the above problems targets a power transmission device of a vehicle including a first case, a second case, and a liquid gasket interposed between the first case and the second case, and includes an execution device and a storage device. It is applied to a sealing performance estimation device for estimating the sealing performance of the liquid gasket. The storage device stores a relationship defining model that outputs an index value indicating the sealing performance of the liquid gasket when a plurality of types of input data are input. One of the plurality of types of input data is time-series data of the torque of the output shaft in the power transmission device. The execution device is caused to execute acquiring the plurality of types of input data and outputting the index value by inputting the acquired plurality of types of input data into the relationship defining model.

Advantages of the Invention

[0008] According to the above configuration, by inputting the time-series data of the torque of the output shaft in the power transmission device into the relationship regulation model as input data, an index value indicating the sealing performance of the liquid gasket is output. In this way, by using the time-series data of the torque of the output shaft as input data, information such as for what period the torque of the output shaft acts on the liquid gasket and at what intervals the torque of the output shaft acts on the liquid gasket is also reflected in the index value. That is, the index value reflects not only the magnitude of the torque but also the temporal parameters of the torque. Therefore, for example, an index value that more accurately reflects the sealing performance of the liquid gasket can be obtained compared to an index value obtained based only on the magnitude of the torque.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Embodiments for Carrying Out the Invention

[0010] <Schematic Configuration of the Estimation System> Hereinafter, an embodiment of the present invention will be described with reference to FIGS. 1 to 3. First, the schematic configuration of the estimation system SE will be described.

[0011] As shown in FIG. 1, the estimation system SE includes a plurality of vehicles 100. The vehicle 100 is, for example, an automobile owned by a user. Note that in FIG. 1, only one vehicle 100 is illustrated as a representative.

[0012] The 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 includes four cylinders 11 and a crankshaft 12. The cylinder 11 is a space for burning a mixture of fuel and intake air. The crankshaft 12 rotates due to the combustion of the mixture in the cylinder 11.

[0013] The torque converter 20 includes an input shaft 21 and an output shaft 22. The torque converter 20 transmits the driving force of the input shaft 21 to the output shaft 22 via a fluid. At this time, the torque converter 20 decelerates the rotation of the input shaft 21 and outputs it from the output shaft 22. The first end of the input shaft 21 is connected to the crankshaft 12. Further, the torque converter 20 includes a lock-up clutch (not shown). The second end of the input shaft 21 is connected to the first end of the output shaft 22 via the lock-up clutch. In a state where the lock-up clutch is engaged, the input shaft 21 and the output shaft 22 rotate integrally.

[0014] The automatic transmission 30 includes an input shaft 31, an output shaft 32, and a case 35. The first end of the input shaft 31 is connected to the second end of the output shaft 22 in the torque converter 20. The second end of the input shaft 31 is connected to the first end of the output shaft 32 via a clutch and gears (not shown). The second end of the output shaft 32 is connected to the left and right drive wheels 42 via a differential 41. The automatic transmission 30 can change the gear ratio, which is the ratio of the rotational speed of the input shaft 31 to the rotational speed of the output shaft 32. In the present embodiment, the gear ratio of the automatic transmission 30 is a ratio indicating the number of rotations of the input shaft 31 when the output shaft 32 makes one rotation. Therefore, the larger the gear ratio, the higher the rotational speed of the input shaft 31 with respect 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 stage.

[0015] Case 35 houses the input shaft 31 and the output shaft 32. Specifically, case 35 includes a first case, a second case, and a liquid gasket. The first case and the second case partition the internal space of case 35. The liquid gasket is interposed between the first case and the second case at their contact portion. The liquid gasket prevents oil from leaking from the internal space of case 35 through the gap between the first case and the second case. In this embodiment, the automatic transmission 30 is an example of a power transmission device.

[0016] The hydraulic mechanism 50 is attached to the case 35 of the automatic transmission 30. The hydraulic mechanism 50 supplies oil to the automatic transmission 30. And the automatic transmission 30 is controlled by the oil supplied from the hydraulic mechanism 50.

[0017] As shown in FIG. 1, the vehicle 100 includes an accelerator operation amount sensor 71, a vehicle speed sensor 72, and an oil temperature sensor 74. The vehicle 100 also includes a crank angle sensor 75, an input rotation speed sensor 76, an output rotation speed sensor 77, an acceleration sensor 78, and a display 79.

[0018] The accelerator operation amount sensor 71 detects the accelerator operation amount ACC, which is the operation amount of the accelerator pedal operated by the driver of the vehicle 100. The vehicle speed sensor 72 detects the vehicle speed SP, which is the speed of the vehicle 100.

[0019] The oil temperature sensor 74 detects the oil temperature TA, which is the temperature of the oil in the case 35. The crank angle sensor 75 detects the crank angle SC, which is the angular position of the crankshaft 12. The input rotation speed sensor 76 detects the input rotation speed NIN, which is the rotation speed of the input shaft 31. The output rotation speed sensor 77 detects the output rotation speed NOUT, which is the rotation speed of the output shaft 32.

[0020] The acceleration sensor 78 is a so-called three-axis sensor. That is, the acceleration sensor 78 can detect the longitudinal acceleration GX, the lateral acceleration GY, and the vertical acceleration GZ. The longitudinal acceleration GX is the acceleration along the longitudinal axis of the vehicle 100. The lateral acceleration GY is the acceleration along the lateral axis of the vehicle 100. The vertical acceleration GZ is the acceleration along the vertical axis of the vehicle 100. The display 79 is located near the driver's seat of the vehicle 100. The display 79 can display various kinds of information.

[0021] As shown in FIG. 1, the vehicle 100 includes a control device 90. The control device 90 acquires various kinds of information from the accelerator operation amount sensor 71, the vehicle speed sensor 72, and the oil temperature sensor 74. Further, the control device 90 acquires various kinds of information from the crank angle sensor 75, the input rotational speed sensor 76, the output rotational speed sensor 77, and the acceleration sensor 78. The control device 90 calculates the engine rotational speed NE, which is the rotational speed of the crankshaft 12, based on the crank angle SC.

[0022] The control device 90 includes an execution device 91, a storage device 92, and a communication device 93. An example of the execution device 91 is a CPU. The storage device 92 includes a read-only ROM, a volatile RAM that can be read and written, and a non-volatile storage that can be read and written. The storage device 92 stores various programs and various data in advance. The execution device 91 executes various processes described later by executing the programs stored in the storage device 92. Further, the execution device 91 can perform wireless communication with external devices of the vehicle 100 via the communication device 93 and the communication network NW.

[0023] 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. Subsequently, 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. Further, the execution device 91 calculates a target gear stage, which is a target value of the gear stage 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 stage to the hydraulic mechanism 50. As a result, the automatic transmission 30 is controlled by controlling the hydraulic mechanism 50.

[0024] As shown in FIG. 1, the estimation system SE includes a server 200. The server 200 includes an execution device 210, a storage device 220, and a communication device 230. An example of the execution device 210 is a CPU. The storage device 220 includes a ROM, a RAM, and a storage. The storage device 220 stores various programs and various data in advance. The storage device 220 stores a control program 220A in advance as one of the various programs. Further, the storage device 220 stores a relationship definition model M in advance as one of the various data. The relationship definition model M describes the relationship between predetermined input data and an index value indicating the sealing performance of the liquid gasket in a format recognizable by the execution device 210. In the present embodiment, the relationship definition model M is generated in advance by machine learning. A specific description of the relationship definition model M will be described later. The execution device 210 realizes various processes described later by executing the control program 220A stored in the storage device 220. The execution device 210 can communicate with devices external to the server 200 via the communication device 230 and the communication network NW. In the present embodiment, the server 200 is an example of a sealing performance estimation device. Further, the control program 220A is an example of a sealing performance estimation program.

[0025] <Acquisition Control> Next, with reference to FIG. 2, acquisition control executed by the control device 90 and the server 200 of the vehicle 100 will be described. This acquisition control is control for the server 200 to acquire the running data DD from the vehicle 100. Specific descriptions of the running data DD will be given later. In the present embodiment, the execution device 91 of the control device 90 starts the acquisition control at every predetermined control cycle on the condition that the control device 90 is operating.

[0026] As shown in FIG. 2, when the execution device 91 of the control device 90 starts the acquisition control, it executes the process of step S11. In step S11, the execution device 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 process in step S11. The execution device 91 acquires the input torque TIN, for example, as follows. First, the execution device 91 calculates the torque output from the crankshaft 12 based on the target output, which is the target value of the output of the internal combustion engine 10. Then, the execution device 91 calculates the input torque TIN based on the torque output from the crankshaft 12, the engine rotational speed NE, and the input rotational speed NIN. After step S11, the execution device 91 advances the process to step S12.

[0027] In step S12, the execution device 91 acquires the actual gear ratio RG, which is the actual gear ratio of the automatic transmission 30 at the time of the process in step S12. For example, the execution device 91 calculates the actual gear ratio RG based on the input rotational speed NIN and the output rotational speed NOUT. The actual gear ratio RG is represented by the following formula (1).

[0028] Formula (1): Actual gear ratio RG = Input rotational speed NIN / Output rotational speed NOUT After step S12, the execution device 91 advances the process to step S13. In step S13, the execution device 91 acquires the output torque TOUT, which is the torque of the output shaft 32 at the time of the process in step S13. For example, the execution device 91 calculates the output torque TOUT based on the input torque TIN, the actual gear ratio RG, and the transmission efficiency. The output torque TOUT is represented by the following formula (2).

[0029] Equation (2): Output torque TOUT = Input torque TIN × Actual gear ratio RG × Transmission efficiency Here, the transmission efficiency is the efficiency when torque is transmitted between the input shaft 31 and the output shaft 32. Note that the transmission efficiency is a value determined in advance by, for example, experiments and simulations. After step S13, the execution device 91 proceeds with the process to step S14.

[0030] In step S14, the execution device 91 acquires the vertical acceleration GZ at the time of the process in step S14. After step S14, the execution device 91 proceeds with the process to step S15.

[0031] In step S15, the execution device 91 acquires the oil temperature TA at the time of the process in step S15. After step S15, the execution device 91 proceeds with the process to step S16.

[0032] In step S16, the execution device 91 generates the input torque TIN, the actual gear ratio RG, the output torque TOUT, the vertical acceleration GZ, and the oil temperature TA as running data DD. After step S16, the execution device 91 proceeds with the process to step S21.

[0033] In step S21, the execution device 91 transmits the running data DD to the server 200. And when the server 200 acquires the running data DD, the execution device 210 of the server 200 proceeds with the process to step S31.

[0034] In step S31, the execution device 210 of the server 200 stores the running data DD acquired in step S21 in the storage device 220. After step S31, the execution device 210 of the server 200 ends the current acquisition control.

[0035] <Estimation control> Next, with reference to FIG. 3, the estimation control executed by the control device 90 and the server 200 of the vehicle 100 will be described. This estimation control is for estimating the sealing performance of the liquid gasket. In the present embodiment, the execution device 210 of the server 200 starts the estimation control at a predetermined control cycle on the condition that the running data DD of a predetermined number or more is stored in the storage device 220. Here, the predetermined number is, for example, an integer of 2 or more. Therefore, the execution device 210 of the server 200 starts the estimation control at a predetermined control cycle on the condition that the time-series data of the running data DD is stored in the storage device 220.

[0036] As shown in FIG. 3, when the execution device 210 of the server 200 starts the estimation control, it executes the process of step S61. In step S61, the execution device 210 acquires, from the storage device 220, a plurality of pieces of running data DD in the vehicle 100 that is the target of the estimation control, that is, the time-series data of the running data DD. At this time, the execution device 210 acquires all the running data DD stored in the storage device 220 at the time of the process of step S61. Note that the execution device 210 resets the running data DD each time a new liquid gasket is started to be used in the automatic transmission 30. Therefore, all the running data DD stored in the storage device 220 at the time of the process of step S61 is the time-series data of the running data DD stored in the storage device 220 from when the liquid gasket is started to be used in the automatic transmission 30 until the time of the process of step S61. After step S61, the execution device 210 advances the process to step S62.

[0037] In step S62, the execution device 210 generates the input torque TIN, the output torque TOUT, the vertical acceleration GZ, and the oil temperature TA among the driving data DD acquired in step S61 as input variables of the relationship defining model M. Here, let the number of the driving data DD acquired in step S61 be N. Also, among the N driving data DD, in order from the oldest, let them be the first time point, the second time point, ···, the Nth time point. Note that "N" is an integer of 2 or more. Further, it is assumed that the relationship defining model M can input the input variables from the first time point to the Xth time point. And "X" is an integer that is appropriately larger than the assumed "N". In step S62, when the execution device 210 generates the input variables for the driving data DD at the first time point, the values of the input torque TIN, the output torque TOUT, the vertical acceleration GZ, and the oil temperature TA in the driving data DD at the first time point are sequentially substituted into the input variables x(1) to x(4) one by one. Similarly to the above, the execution device 210 substitutes values into the input variables x(5) to x(4×N) for the driving data DD at the second time point to the Nth time point. Then, the execution device 210 sequentially substitutes "0" into the input variables x(4×N + 1) to x(4×X) for the driving data DD at the (N + 1)th time point to the Xth time point. In other words, the execution device 210 sets the values of the input variables when the driving data DD is not acquired to "0". Note that hereinafter, "4×X" is described as "Z". In other words, "Z" is the number of the input variables generated in step S62.

[0038] As described above, the input variables generated in step S62 include the values of the time-series data of the input torque TIN, the time-series data of the output torque TOUT, the time-series data of the vertical acceleration GZ, and the time-series data of the oil temperature TA. Here, each of the time-series data of the input torque TIN, the time-series data of the output torque TOUT, the time-series data of the vertical acceleration GZ, and the time-series data of the oil temperature TA is the input data input to the relationship defining model M. After step S62, the execution device 210 proceeds with the process to step S63.

[0039] In step S63, the execution device 210 inputs the input variables x(1) to x(Z) and the input variable x(0) as a bias parameter into the relationship specification model M, and outputs the value of the output variable y(i) indicating the sealing performance of the liquid gasket. Here, the output variable y(1) is an index value indicating the sealing performance of the liquid gasket.

[0040] An example of the relationship specification model M is a function approximator, which is a fully connected forward propagation neural network with one hidden layer. Specifically, in the relationship specification model M, each of the "m" values obtained by converting the input variables x(1) to x(Z) and the input variable x(0) as a bias parameter through a linear mapping defined by the coefficients wFjk (j = 1 to m, k = 0 to Z) is substituted into the activation function f. As a result, the values of the nodes in the hidden layer are determined. Also, each of the values obtained by converting the values of the nodes in the hidden layer through a linear mapping defined by the coefficient wSij (i = 1) is substituted into the activation function g, thereby determining the output variable y(1). In the present embodiment, an example of the activation function f is the ReLU function. Also, an example of the activation function g is the sigmoid function. That is, the output variable y(1) can vary in the range of "0" to "1". Note that the smaller the output variable y(1), the lower the sealing performance of the liquid gasket.

[0041] The relationship regulation model M is generated in advance as follows, for example. Engineers, etc. first drive the vehicle 100 under various conditions. At this time, in the same manner as above, for each time point, the input torque TIN, output torque TOUT, vertical acceleration GZ, and oil temperature TA are acquired. Then, in the same manner as above, the input variables x(1) to x(Z) for each time point are generated. Also, by disassembling the automatic transmission 30 of the vehicle 100 described above, etc., the sealing performance of the liquid gasket at each time point is grasped. And based on the grasped sealing performance of the liquid gasket, the output variable y(1) is generated. By performing machine learning using the data generated as described above, the relationship regulation model M is generated. That is, the relationship regulation model M is generated in advance by machine learning using, as teacher data, the combination of the time-series data of the input torque TIN, output torque TOUT, vertical acceleration GZ, and oil temperature TA and the sealing performance of the liquid gasket. After step S63, the execution device 210 proceeds with the process to step S71.

[0042] In step S71, the execution device 210 transmits the output variable y(1) output in step S63 to the vehicle 100. In other words, the execution device 210 transmits the output variable y(1) indicating the sealing performance of the liquid gasket to the vehicle 100. And when the control device 90 of the vehicle 100 acquires the output variable y(1), the execution device 91 of the control device 90 proceeds with the process to step S81.

[0043] In step S81, the execution device 91 of the control device 90 determines whether the output variable y(1) is less than or equal to a predetermined specified value. Here, the specified value is a threshold value for determining whether the sealing performance of the liquid gasket is unacceptably low. When the execution device 91 determines that the output variable y(1) is higher than the specified value, the execution device 91 ends the current estimation control. On the other hand, when the execution device 91 determines that the output variable y(1) is less than or equal to the specified value, the execution device 91 notifies the driver of the vehicle 100 or the like that the sealing performance of the liquid gasket is low. As a specific example, the execution device 91 outputs a control signal to the display 79, and the display 79 displays that the sealing performance of the liquid gasket is low. Then, the execution device 91 ends the current estimation control.

[0044] <Operations of this Embodiment> In the automatic transmission 30 of the vehicle 100, the torque input to the input shaft 31 is transmitted to the output shaft 32 via a clutch and gears. Then, the output torque TOUT output from the output shaft 32 is transmitted to the left and right drive wheels 42 via the differential 41. Here, when the output torque TOUT fluctuates or the like, a force acts on the case 35. Then, a force acts on the liquid gasket interposed between the first case and the second case in the case 35. And as the force acts on the liquid gasket and aging deterioration progresses, the sealing performance of the liquid gasket decreases.

[0045] In this embodiment, the execution device 210 of the server 200 acquires the time-series data of the running data DD by executing repeated acquisition control. Then, in the estimation control, the execution device 210 inputs the time-series data of the output torque TOUT included in the time-series data of the running data DD into the relationship specification model M as input data, and outputs an output variable y(i) indicating an index value of the sealing performance of the liquid gasket.

[0046] <Effects of this Embodiment> (1) According to this embodiment, the time-series data of the output torque TOUT is input to the relationship defining model M as input data. Therefore, for example, information such as the period over which the output torque TOUT acts on the liquid gasket and the interval at which the output torque TOUT acts is also reflected in the index value of the sealing performance. That is, the index value of the sealing performance reflects not only the magnitude of the output torque TOUT but also the temporal parameters of the output torque TOUT. Therefore, compared with the case where the index value is obtained based only on the magnitude of the output torque TOUT, for example, an index value that more accurately reflects the sealing performance of the liquid gasket can be obtained.

[0047] (2) In the automatic transmission 30, as the gear ratio changes, the magnitude of the input torque TIN with respect to the output torque TOUT changes. Therefore, for example, even if the manner of variation of the output torque TOUT is the same, the manner of variation of the input torque TIN changes according to the change in the gear ratio. As a result, the force acting on the liquid gasket may change.

[0048] In this regard, the plurality of types of input data input to the relationship defining model M includes the time-series data of the input torque TIN in addition to the time-series data of the output torque TOUT. Therefore, the gear ratio of the automatic transmission 30 derived from the output torque TOUT and the input torque TIN is reflected in the index value of the sealing performance. Thereby, compared with a configuration that does not take into account the gear ratio of the automatic transmission 30, an index value that more accurately reflects the sealing performance of the liquid gasket can be obtained.

[0049] (3) When the vehicle 100 travels or the like, the vehicle 100 may vibrate in the vertical direction. When the vehicle 100 vibrates in the vertical direction in this way, the vibration acts on the automatic transmission 30 and thus on the liquid gasket. Therefore, the sealing performance of the liquid gasket can change due to the vertical vibration of the vehicle 100.

[0050] In this regard, the plurality of types of input data input into the relationship specification model M includes time series data of the vertical acceleration GZ, which is the vertical acceleration of the vehicle 100. Therefore, the vertical acceleration GZ, that is, the vertical vibration of the vehicle 100, is taken into account in the index value of the sealing performance. As a result, an index value that more accurately reflects the sealing performance of the liquid gasket can be obtained as compared with a configuration that does not take into account the vertical vibration of the vehicle 100.

[0051] (4) In the automatic transmission 30, the temperatures of the first case and the second case may change according to the oil temperature TA, which is the temperature of the oil in the case 35. When the temperatures of the first case and the second case change in this way, the first case and the second case expand or contract. As a result, for example, even if the deterioration state of the liquid gasket is the same, the sealing performance of the liquid gasket changes due to a change in the size of the gap between the first case and the second case in which the liquid gasket is interposed.

[0052] In this regard, the plurality of types of input data input into the relationship specification model M includes time series data of the oil temperature TA, which is the temperature of the oil in the case 35. Therefore, the oil temperature TA is taken into account in the index value of the sealing performance. As a result, even if the sealing performance of the liquid gasket changes according to the oil temperature TA, an index value that more accurately reflects the sealing performance can be obtained.

[0053] <Modification example> This embodiment can be implemented with the following modifications. This embodiment and the following modification examples can be implemented in combination with each other as long as they do not technically conflict with each other.

[0054] · In the above embodiment, the input data of the relationship specification model M may be changed. For example, the plurality of types of input data input into the relationship specification model M may not include the time series data of the oil temperature TA. As a specific example, when the change in the sealing performance of the liquid gasket according to the oil temperature TA is small in the target vehicle 100, the influence is small even if the input data of the relationship specification model M does not include the time series data of the oil temperature TA.

[0055] ·For example, the plurality of types of input data input to the relationship definition model M may include time series data of the longitudinal acceleration GX and the lateral acceleration GY instead of or in addition to the time series data of the vertical acceleration GZ. Note that even if the input data of the relationship definition model M does not include the time series data of the vertical acceleration GZ, it is acceptable as long as the change in the sealing performance of the liquid gasket according to the vertical vibration in the target vehicle 100 is small.

[0056] ·For example, the plurality of types of input data input to the relationship definition model M may include time series data of the actual gear ratio RG instead of or in addition to the time series data of the input torque TIN. Note that if the input data of the relationship definition model M includes the actual gear ratio RG, the gear ratio of the automatic transmission 30 is reflected in the index value of the sealing performance.

[0057] ·For example, the plurality of types of input data input to the relationship definition model M may not include the time series data of the input torque TIN and the time series data of the actual gear ratio RG. As a specific example, when the change in the force acting on the liquid gasket according to the change in the gear ratio is small, the influence is small even if the input data of the relationship definition model M does not include the time series data of the input torque TIN and the time series data of the actual gear ratio RG.

[0058] Note that generally, the output torque TOUT has more opportunities to be larger than the input torque TIN. Therefore, the output torque TOUT is more likely to affect the sealing performance of the liquid gasket than the input torque TIN. Therefore, if the input data of the relationship definition model M includes the time series data of the output torque TOUT, the probability of obtaining a more accurate index value is higher than when only the time series data of the input torque TIN is included.

[0059] ·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.

[0060] ·For example, as the relationship defining model M, a neural network with one hidden layer was exemplified, but the number of hidden layers may be two or more. ·For example, as the neural network of the relationship defining model M, a fully connected feedforward neural network was exemplified, but it is not limited to this. As a specific example, the neural network may be a recurrent connection type neural network. Further, for example, the function approximator as the relationship defining model M is not limited to a neural network. As a specific example, the relationship defining model M may be a regression equation without a hidden layer.

[0061] ·For example, the relationship defining model M may not be generated by machine learning. As a specific example, the relationship defining model M may be a relational expression determined by experiments and simulations, etc.

[0062] ·In the above embodiment, the seal performance estimation device may be changed. For example, instead of the server 200, the control device 90 of the vehicle 100 may function as the seal performance estimation device. In this case, it is only necessary that the storage device 92 of the control device 90 stores the relationship defining model M and the seal performance estimation program in advance.

Explanation of Signs

[0063] M...Relationship defining model SE...Estimation system 10...Internal combustion engine 20...Torque converter 30...Automatic transmission 31...Input shaft 32...Output shaft 35...Case 41...Differential 42...Drive wheel 50...Hydraulic mechanism 71...Accelerator operation amount sensor 72...Vehicle speed sensor 74...Oil temperature sensor 75...Crank angle sensor 76...Input rotation speed sensor 77...Output rotation speed sensor 78...Acceleration sensor 79...Display 90...Control device 91...Execution device 92...Storage device 93...Communication device 100...Vehicle 200...Server 210...Execution device 220...Storage device 220A...Control program 230...Communication device

Claims

1. A vehicle power transmission device including a first case, a second case, and a liquid gasket interposed between the first case and the second case is targeted, An execution device and a storage device are provided, The storage device stores a relationship defining model that outputs an index value indicating the sealing performance of the liquid gasket when a plurality of types of input data are input, One of the plurality of types of input data is time-series data of the torque of the output shaft in the power transmission device, The execution device Acquires the plurality of types of input data, Outputs the index value by inputting the acquired plurality of types of input data into the relationship defining model, And executes A sealing performance estimation device.

2. The power transmission device has a transmission that can change a gear ratio that is the ratio of the rotational speed of the input shaft and the rotational speed of the output shaft in the power transmission device, The plurality of types of input data includes one or more selected from the time-series data of the torque of the input shaft and the time-series data of the gear ratio, The sealing performance estimation device according to claim 1.

3. One of the plurality of types of input data is time-series data of the acceleration in the vertical direction of the vehicle, The sealing performance estimation device according to claim 1 or claim 2.

4. One of the plurality of types of input data is time-series data of the temperature of the oil in the power transmission device, The sealing performance estimation device according to claim 1 or claim 2.

5. A vehicle power transmission device including a first case, a second case, and a liquid gasket interposed between the first case and the second case is targeted, An execution device and a storage device, which are applied to a seal performance estimation device for estimating the seal performance of the liquid gasket. The storage device stores a relationship defining model that outputs an index value indicating the seal performance of the liquid gasket when a plurality of types of input data are input. One of the plurality of types of input data is time-series data of the torque of the output shaft in the power transmission device. In the execution device, acquire the plurality of types of input data; input the acquired plurality of types of input data into the relationship defining model to output the index value; and execute a seal performance estimation program.

Images