Seal temperature estimation device and seal temperature estimation program

Abstract

To estimate a temperature of an oil seal highly accurately.SOLUTION: A target of a seal temperature estimation device is a rotating body device including a case, a rotating body rotatably supported relative to the case and an oil seal interposed between the case and the rotating body. The seal temperature estimation device includes an execution device and a storage device. The storage device stores a relation definition model to which a plurality of types of input data are input to output an index value indicating a temperature of the oil seal. The relation definition model is generated beforehand through mechanical learning. The plurality of types of input data include time series data on rotating speed of the rotating body and time series data on a temperature of oil within the case. The execution device acquires the plurality of types of input data (S61). The execution device outputs the index value by inputting the acquired plurality of types of input data to the relation definition model (S63).SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a seal temperature estimation device and a seal temperature estimation program. [Background technology]

[0002] The motor device of Patent Document 1 includes a case, a rotor, a stator, an oil seal, and a temperature sensor. The case houses the stator and the temperature sensor. The case also supports the rotor. The rotor is rotatable relative to the case and the stator. The oil seal is interposed between the outer circumferential surface of the rotor's rotating shaft and the inner circumferential surface of the case. The temperature sensor is located near the oil seal. The temperature sensor detects the temperature of the oil seal. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-002522 Summary of the Invention [Problem to be solved by the invention]

[0004] In a motor device such as that described in Patent Document 1, for example, depending on the structure and dimensions of the motor device, it may not be possible to install a temperature sensor near the oil seal. In such cases, the temperature of the oil seal must be estimated based on other parameters. However, no method has been established for accurately estimating the temperature of the oil seal. Note that while a motor device has been used as an example here, similar issues arise in other devices as long as the oil seal is located between the case and the rotating body. [Means for solving the problem]

[0005] A seal temperature estimation device for solving the above problem targets a rotating body device having a case, a rotating body rotatably supported on the case, and an oil seal interposed between the case and the rotating body, and comprises an execution device and a memory device, wherein the memory device stores a relationship specification model that outputs an index value indicating the temperature of the oil seal when multiple types of input data are input, the multiple types of input data including time series data of the rotational speed of the rotating body and time series data of the temperature of the oil inside the case, and the execution device 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.

[0006] A seal temperature estimation program for solving the above problem targets a rotating body device having a case, a rotating body rotatably supported relative to the case, and an oil seal interposed between the case and the rotating body, and is applied to a seal temperature estimation device having an execution device and a memory device, wherein the memory device stores a relationship specification model that outputs an index value indicating the temperature of the oil seal when multiple types of input data are input, the multiple types of input data including time series data of the rotational speed of the rotating body and time series data of the temperature of the oil inside the case, and causes the execution device to acquire the multiple types of input data and output the index value by inputting the acquired multiple types of input data into the relationship specification model. [Effects of the Invention]

[0007] In the rotating body device described above, the temperature of the oil seal changes depending on the rotational speed of the rotating body and the temperature of the oil. According to the above configuration, time-series data on the rotational speed of the rotating body and time-series data on the oil temperature are input into a relationship specification model, and an index value indicating the temperature of the oil seal is output. This allows the temperature of the oil seal to be determined, even in cases where it is not possible to install a temperature sensor to detect the temperature of the oil seal. Furthermore, by estimating the temperature of the oil seal using time-series data rather than instantaneous values of the rotational speed of the rotating body and the oil temperature, more accurate estimation is possible. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram of a vehicle. [Figure 2] FIG. 2 is a flowchart showing the data collection control. [Figure 3] FIG. 3 is a flowchart showing the estimation control. DETAILED DESCRIPTION OF THE INVENTION

[0009] <Vehicle Overview> An embodiment of the present invention will be described below with reference to Figures 1 to 3. First, a general configuration of a vehicle 100 will be described. Note that the following description will be based on the up / down, front / rear, left / right directions of the vehicle 100. Here, the up / down, front / rear, left / right directions of the vehicle 100 are directions when viewed from the driver sitting in the driver's seat of the vehicle 100.

[0010] 1, vehicle 100 includes a spark-ignition internal combustion engine 10. Vehicle 100 also includes, as components of a transaxle 30 (described later), a first motor generator 71 and a second motor generator 72 that function as both an electric motor and a generator. Therefore, vehicle 100 is a so-called hybrid vehicle.

[0011] The internal combustion engine 10 includes a crankshaft 15. The crankshaft 15 rotates due to combustion of a mixture of fuel and intake air in cylinders (not shown). The vehicle 100 includes a damper 20, a transaxle 30, two drive shafts 26, and two drive wheels 27. In the following description, when the two drive shafts 26 are not to be distinguished from one another, they will simply be referred to as drive shafts 26. When the two drive shafts 26 are to be distinguished from one another, one of the two drive shafts 26 will be referred to as a first drive shaft 26A, and the other of the two drive shafts 26 will be referred to as a second drive shaft 26B.

[0012] The crankshaft 15 of the internal combustion engine 10 is connected to the transaxle 30 via a damper 20. The damper 20 attenuates fluctuations in torque transmitted from the crankshaft 15 of the internal combustion engine 10 and transmits the torque to the transaxle 30.

[0013] The transaxle 30 includes a case 35, a planetary gear mechanism 40, a reduction gear mechanism 50, and a differential 60. The transaxle 30 also includes a first motor generator 71, a second motor generator 72, an oil supply device 80, a first oil seal 85A, and a second oil seal 85B.

[0014] The case 35 houses the planetary gear mechanism 40, the reduction mechanism 50, the differential 60, the first motor generator 71, the second motor generator 72, and the oil supply device 80. The case 35 also stores oil for lubricating and cooling the components housed within the case 35, such as the planetary gear mechanism 40.

[0015] The planetary gear mechanism 40 includes a sun gear 41, a ring gear 42, multiple pinion gears 43, and a carrier 44. The sun gear 41 is generally disk-shaped. The sun gear 41 has external teeth. The sun gear 41 is connected to the rotating shaft 71A of the first motor generator 71. The ring gear 42 is generally annular. The ring gear 42 has internal and external teeth. The ring gear 42 is positioned coaxially with the sun gear 41. The external teeth of the ring gear 42 are connected to the reduction mechanism 50. Each pinion gear 43 is positioned between the external teeth of the sun gear 41 and the internal teeth of the ring gear 42. Each pinion gear 43 meshes with both the external teeth of the sun gear 41 and the internal teeth of the ring gear 42. The carrier 44 supports the pinion gear 43. The pinion gear 43 is rotatable on its own axis and revolves by rotating together with the carrier 44. The carrier 44 is connected to the crankshaft 15 via the damper 20 .

[0016] When power from the internal combustion engine 10 is input to the carrier 44, the power from the internal combustion engine 10 is distributed to the sun gear 41 and the ring gear 42. Then, when the power from the internal combustion engine 10 transmitted via the sun gear 41 is input to the rotating shaft 71A of the first motor generator 71, the first motor generator 71 functions as a generator.

[0017] On the other hand, when the first motor generator 71 is made to function as an electric motor, the power from the first motor generator 71 is input to the sun gear 41. Then, the power from the first motor generator 71 input to the sun gear 41 is distributed to the carrier 44 and the ring gear 42. Then, when the power from the first motor generator 71 transmitted via the carrier 44 is input to the crankshaft 15 of the internal combustion engine 10, the crankshaft 15 of the internal combustion engine 10 rotates.

[0018] The reduction mechanism 50 includes a first gear 51 and a second gear 52. The first gear 51 is generally disk-shaped. The first gear 51 has external teeth. The first gear 51 of the reduction mechanism 50 meshes with the external teeth of the ring gear 42 of the planetary gear mechanism 40. The second gear 52 is generally disk-shaped. The second gear 52 has external teeth. The second gear 52 is positioned coaxially with the first gear 51. The second gear 52 is connected to the first gear 51 and rotates integrally with the first gear 51. The number of external teeth of the second gear 52 is smaller than the number of external teeth of the first gear 51. Therefore, the reduction mechanism 50 can output a rotational speed that is slower than the rotational speed input to the reduction mechanism 50.

[0019] The differential 60 includes a ring gear 61 and a differential case 62. The ring gear 61 is generally disk-shaped. The ring gear 61 has external teeth. The ring gear 61 of the differential 60 meshes with the second gear 52 of the reduction mechanism 50. The differential case 62 is connected to the ring gear 61 and rotates integrally therewith. The differential case 62 houses multiple gears (not shown). The multiple gears are connected to the drive wheels 27 via the drive shaft 26. As a result, the differential 60 transmits power input to the ring gear 61 to the left and right drive wheels 27 while allowing a difference in rotational speed to occur between the left and right drive wheels 27. Note that a portion of the drive shaft 26 is inserted into a through-hole (not shown) in the case 35 and is therefore located inside the case 35.

[0020] The first oil seal 85A is interposed between the outer peripheral surface of the first drive shaft 26A and the inner peripheral surface of a through hole (not shown) in the case 35. The first oil seal 85A is generally annular in shape. The first oil seal 85A prevents oil inside the case 35 from leaking out of the case 35 between the outer peripheral surface of the first drive shaft 26A and the inner peripheral surface of the through hole in the case 35. The second oil seal 85B is interposed between the outer peripheral surface of the second drive shaft 26B and the inner peripheral surface of the through hole in the case 35. The second oil seal 85B is generally annular in shape. The second oil seal 85B prevents oil inside the case 35 from leaking out of the case 35 between the outer peripheral surface of the second drive shaft 26B and the inner peripheral surface of the through hole in the case 35.

[0021] In this embodiment, each of the two drive shafts 26 is rotatably supported relative to the case 35. Therefore, each of the two drive shafts 26 is an example of a rotating body. Furthermore, each of the first oil seal 85A and the second oil seal 85B is an example of an oil seal. Furthermore, the case 35, the first drive shaft 26A, and the first oil seal 85A constitute a rotating body device. Furthermore, the case 35, the second drive shaft 26B, and the second oil seal 85B constitute a rotating body device. Furthermore, the rotating body device is mounted on the vehicle 100.

[0022] The second motor generator 72 includes a rotating shaft 72A and a connecting gear 72B. The rotating shaft 72A is connected to the rotor of the second motor generator 72 and rotates integrally with the rotor. The connecting gear 72B is connected to the rotating shaft 72A and rotates integrally with the rotating shaft 72A. The connecting gear 72B meshes with the first gear 51 of the reduction gear mechanism 50.

[0023] When the second motor generator 72 is made to function as an electric motor, the power of the second motor generator 72 is transmitted to the drive wheels 27 via the reduction gear mechanism 50, the differential 60, and the drive shaft 26. As a result, the drive wheels 27 are rotated by the power from the second motor generator 72. Therefore, the second motor generator 72 is a drive source for the vehicle 100. On the other hand, when the second motor generator 72 is made to function as a generator, a regenerative braking force corresponding to the amount of power generated by the second motor generator 72 can be generated in the vehicle 100.

[0024] 1, the oil supply device 80 includes an oil pump 81 and oil piping 82. The oil pump 81 is connected to the ring gear 61 of the differential 60, and is driven by power transmitted from the differential 60. In other words, the oil pump 81 is a so-called mechanical oil pump. The oil pump 81 supplies oil via the oil piping 82 to each component housed in the case 35, such as the planetary gear mechanism 40.

[0025] As shown in FIG. 1 , the vehicle 100 includes a first inverter 86, a second inverter 87, and a battery 88. The battery 88 is a secondary battery. The first inverter 86 converts AC power to DC power between the first motor generator 71 and the battery 88. The first inverter 86 also adjusts the amount of power exchanged between the first motor generator 71 and the battery 88. The second inverter 87 converts AC power to DC power between the second motor generator 72 and the battery 88. The second inverter 87 also adjusts the amount of power exchanged between the second motor generator 72 and the battery 88.

[0026] As shown in FIG. 1, a vehicle 100 includes an accelerator operation amount sensor 101 , a plurality of wheel speed sensors 102 , an acceleration sensor 103 , an oil temperature sensor 104 , and an outside air temperature sensor 105 .

[0027] The accelerator operation amount sensor 101 detects an accelerator operation amount ACC, which is the amount of operation of the accelerator pedal operated by the driver of the vehicle 100. The wheel speed sensor 102 detects a wheel speed WS, which is the rotational speed of the wheels of the vehicle 100. The wheel speed sensors 102 are located near each wheel of the vehicle 100. In this embodiment, the vehicle 100 is equipped with four wheel speed sensors 102 corresponding to the four wheels equipped on the vehicle 100. Note that two of the four wheels equipped on the vehicle 100 are the two drive wheels 27 described above. Also, only one wheel speed sensor 102 is shown representatively in FIG. 1 .

[0028] The acceleration sensor 103 is a so-called three-axis sensor. That is, the acceleration sensor 103 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.

[0029] The oil temperature sensor 104 detects the oil temperature TA, which is the temperature of the oil inside the case 35. The outside air temperature sensor 105 detects the outside air temperature TB, which is the temperature of the air outside the vehicle 100. In other words, the outside air temperature TB corresponds to the temperature of the air outside the case 35.

[0030] 1, a vehicle 100 is equipped with a control device 90. The control device 90 acquires various types of information from an accelerator operation amount sensor 101, a plurality of wheel speed sensors 102, an acceleration sensor 103, an oil temperature sensor 104, and an outside air temperature sensor 105.

[0031] 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 temperature of the first oil seal 85A. The relationship definition model M outputs an index value indicating the temperature of the first oil seal 85A when multiple types of input data are input. In this embodiment, the relationship definition model M is generated in advance by machine learning. The relationship definition model M will be described in detail later. The execution device 91 executes the control program 92A stored in the storage device 92 to perform various processes, which will be described later. In this embodiment, the control device 90 is an example of a seal temperature estimation device. The control program 92A is an example of a seal temperature estimation program. In the following, a configuration for estimating the first seal temperature TSA, which is the temperature of the first oil seal 85A, of the first oil seal 85A and the second oil seal 85B, will be described.

[0032] The execution unit 91 of the control device 90 calculates the vehicle speed SP, which is the speed of the vehicle 100, for each predetermined control cycle. For example, the execution unit 91 calculates the vehicle speed SP by multiplying the average value of the four wheel speeds WS by a predetermined coefficient. In other words, the execution unit 91 can obtain the vehicle speed SP.

[0033] The execution unit 91 of the control device 90 calculates the inclination angle AR of the vehicle 100 according to the gradient of the road surface at the point where the vehicle 100 is located, based on the longitudinal acceleration GX, the lateral acceleration GY, and the vertical acceleration GZ, at each predetermined control cycle. In this embodiment, the inclination angle AR indicates the degree of inclination of the vehicle 100 according to the gradient of the road surface when the vehicle 100 moves forward. In other words, the inclination angle AR is a value indicating the inclination between the horizontal plane and the longitudinal axis of the vehicle 100. Specifically, when the vehicle 100 is located on a level road surface, the inclination angle AR is zero. Furthermore, when the vehicle 100 is located on an uphill slope, the inclination angle AR is a positive value. Furthermore, when the vehicle 100 is located on a downhill slope, the inclination angle AR is a negative value.

[0034] The execution unit 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 unit 91 determines the torque distribution among the internal combustion engine 10, the first motor generator 71, and the second motor generator 72 based on the target driving force. The execution unit 91 controls the output of the internal combustion engine 10 and the power running and regeneration of the first motor generator 71 and the second motor generator 72 based on the torque distribution among the internal combustion engine 10, the first motor generator 71, and the second motor generator 72. Specifically, the execution unit 91 controls the internal combustion engine 10 by outputting a control signal to the internal combustion engine 10. Furthermore, the execution unit 91 controls the first motor generator 71 via the first inverter 86 by outputting a control signal to the first inverter 86. Furthermore, the execution unit 91 controls the second motor generator 72 via the second inverter 87 by outputting a control signal to the second inverter 87.

[0035] <Data collection control> Next, the data collection control executed by the control device 90 will be described with reference to Fig. 2. This data collection control is control for collecting various types of data. In this embodiment, the execution device 91 of the control device 90 starts the data collection control at each predetermined control cycle, with the necessary condition being that the control device 90 is operating.

[0036] As shown in FIG. 2, when the execution unit 91 of the control device 90 starts data collection control, it executes the process of step S11. In step S11, the execution unit 91 acquires, from among the multiple wheel speeds WS at the time of the process of step S11, the wheel speed WS corresponding to the first oil seal 85A as the specific rotational speed WSA. Here, the wheel speed WS corresponding to the first oil seal 85A is the wheel speed WS of the drive wheel 27 connected to the first drive shaft 26A. In this embodiment, the specific rotational speed WSA corresponds to the rotational speed of the rotating body. After step S11, the execution unit 91 advances the process to step S12.

[0037] In step S12, the execution unit 91 acquires the oil temperature TA at the time of the processing of step S12. After step S12, the execution unit 91 advances the processing to step S13.

[0038] In step S13, the execution unit 91 obtains the tilt angle AR at the time of the processing of step S 13. After step S13, the execution unit 91 advances the processing to step S14.

[0039] In step S14, the execution unit 91 acquires the outside air temperature TB at the time of the processing of step S14. After step S14, the execution unit 91 advances the processing to step S15.

[0040] In step S15, the execution unit 91 acquires the vehicle speed SP at the time of the processing of step S15. After step S15, the execution unit 91 advances the processing to step S16. In step S16, the execution unit 91 stores the data acquired in steps S11 to S15 in the storage device 92. That is, the execution unit 91 stores the specific rotation speed WSA, the oil temperature TA, the tilt angle AR, the outside air temperature TB, and the vehicle speed SP in the storage device 92. After step S16, the execution unit 91 ends the current data collection control.

[0041] <Estimation control> Next, the estimation control executed by the control device 90 will be described with reference to Fig. 3. This estimation control is control for estimating the first seal temperature TSA, which is the temperature of the first oil seal 85A. In this embodiment, the execution device 91 of the control device 90 starts the estimation control at each predetermined control cycle, provided that the control device 90 is operating and the above-described data collection control has been executed two or more times during the current operation of the control device 90.

[0042] As shown in FIG. 3, when the execution unit 91 of the control device 90 starts estimation control, it executes the process of step S61. In step S61, the execution unit 91 acquires time-series data of the specific rotation speed WSA, the oil temperature TA, the tilt angle AR, the outside air temperature TB, and the vehicle speed SP from the storage device 92. Here, the time-series data is data acquired by the data collection control during the current operation of the control device 90. In other words, the time-series data is data acquired by the data collection control from the time the system of the vehicle 100 is started until the time of the process of step S61. The number of times that the data collection control has been executed during the current operation of the control device 90 is defined as "N." The times at which the data collection control has been executed are defined as the first time point, the second time point, ..., the Nth time point, in order from the oldest to the newest. Therefore, the execution unit 91 acquires N values from the first time point to the Nth time point for each of the time-series data. Here, "N" is an integer equal to or greater than 2. After step S61, the execution unit 91 proceeds to step S62.

[0043] In step S62, the execution device 91 generates the various values acquired in step S61 as input variables of the relationship definition model M. Here, it is assumed that input variables from the first time point to the Xth time point can be input to the relationship definition model M. Here, "X" is an integer that is appropriately larger than the assumed "N" above.

[0044] First, the generation of input variables for the time series data will be described. Here, the time series data is a total of five types of time series data: specific rotation speed WSA, oil temperature TA, lean angle AR, outside air temperature TB, and vehicle speed SP. When generating input variables for a first time point for the time series data, the execution device 91 sequentially assigns the values of the five types of time series data at the first time point to input variables x(1) through x(5). Similarly, when generating input variables for a second time point for the time series data, the execution device 91 sequentially assigns the values of the five types of time series data at the second time point to input variables x(6) through x(10). In the same manner as above, when generating input variables for a third time point through an Nth time point for the time series data, the execution device 91 assigns each value to input variables x(11) through x(5×N). Then, when generating input variables for time point N+1 to time point X of the time series data, the execution device 91 sequentially assigns "0" to the input variables x(5×N+1) to x(5×X) one by one. In other words, the execution device 91 sets the value of the input variable when no data is acquired to "0." Note that hereinafter, "5×X" will be written as "Z." In other words, "Z" is the number of input variables generated in step S62.

[0045] In this embodiment, the time series data of the specific rotation speed WSA, the time series data of the oil temperature TA, the time series data of the tilt angle AR, the time series data of the outside air temperature TB, and the time series data of the vehicle speed SP are each input data to the relationship definition model M. After step S62, the execution unit 91 proceeds to step S63.

[0046] In step S63, the execution device 91 outputs the value of the output variable y(i) indicating the temperature of the first oil seal 85A by inputting the input variables x(1) to x(Z) and the input variable x(0) as a bias parameter to the relationship definition model M. Here, the output variable y(i) is an index value indicating the temperature of the first oil seal 85A.

[0047] An example of the relationship definition model M is a function approximator, which is a fully connected forward propagation type 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 a smaller output variable y(1) indicates a lower temperature of the first oil seal 85A.

[0048] The relationship definition model M is generated in advance, for example, as follows. First, an engineer or the like drives the vehicle 100 under various conditions. At this time, various data including the specific rotational speed WSA and the like are acquired in the same manner as above. Then, input variables x(1) to x(Z) are generated in the same manner as above. The temperature of the first oil seal 85A is determined through experiments, simulations, and the like. Furthermore, an output variable y(1) corresponding to the determined temperature of the first oil seal 85A is generated. Then, the relationship definition model M is generated by machine learning using the data generated as described above. In other words, the relationship definition model M is generated in advance by machine learning using a combination of the above five types of time-series data and the temperature of the first oil seal 85A as training data. After step S63, the execution device 91 proceeds to step S64.

[0049] In step S64, the executing unit 91 acquires the first sealing temperature TSA based on the output variable y(1). For example, the executing unit 91 acquires the first sealing temperature TSA 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 first sealing temperature TSA is "°C". After step S64, the executing unit 91 ends the current estimation control.

[0050] <Operation of this embodiment> In vehicle 100, because first drive shaft 26A and first oil seal 85A slide on each other, the temperature of first oil seal 85A tends to rise as the rotational speed of first drive shaft 26A increases. Also, because heat is exchanged between the oil inside case 35 and first oil seal 85A, the temperature of first oil seal 85A tends to rise as the temperature of the oil inside case 35 increases.

[0051] 3, in estimation control, an execution unit 91 of a control device 90 acquires time-series data of a specific rotation speed WSA and time-series data of an oil temperature TA as multiple types of input data. Then, the execution unit 91 inputs the multiple types of input data into a relational definition model M, thereby outputting an output variable y(1) that is an index value of the temperature of the first oil seal 85A.

[0052] <Effects of this embodiment> (1) According to this embodiment, an index value for the temperature of the first oil seal 85A is estimated based on time-series data of the specific rotational speed WSA and the oil temperature TA. This makes it possible to determine the temperature of the first oil seal 85A even when, for example, a temperature sensor for detecting the temperature of the first oil seal 85A cannot be installed. Furthermore, by estimating the temperature of the first oil seal 85A using time-series data of the specific rotational speed WSA and the oil temperature TA rather than instantaneous values of these, more accurate estimation is possible. Furthermore, if the temperature of the first oil seal 85A can be determined, it becomes easier to estimate, for example, the degree of deterioration of the first oil seal 85A.

[0053] (2) In the vehicle 100, the oil inside the case 35 moves in accordance with the inclination angle AR of the vehicle 100. Therefore, the ease of heat exchange between the oil inside the case 35 and the first oil seal 85A changes in accordance with the inclination angle AR of the vehicle 100.

[0054] In this regard, according to the present embodiment, time-series data of the inclination angle AR is included as input data to the relationship specification model M. This makes it possible to estimate the temperature of the first oil seal 85A by taking into account the inclination angle AR of the vehicle 100, that is, by taking into account the ease of heat exchange between the oil inside the case 35 and the first oil seal 85A according to the inclination angle AR of the vehicle 100.

[0055] (3) In the vehicle 100, the amount of air circulating outside the case 35 and the manner in which the air circulates outside the case 35 change depending on the vehicle speed SP. As a result, the ease of heat exchange between the air outside the case 35 and the first oil seal 85A changes.

[0056] In this regard, according to the present embodiment, time-series data of the vehicle speed SP is included as input data to the relationship specification model M. This makes it possible to estimate the temperature of the first oil seal 85A by taking into account the vehicle speed SP, that is, by taking into account the ease of heat exchange between the air outside the case 35 and the first oil seal 85A according to the vehicle speed SP.

[0057] (4) In the vehicle 100, the higher the outside air temperature TB, the higher the temperature of the first oil seal 85A tends to be. In contrast, in this embodiment, time-series data of the outside air temperature TB is included as input data input to the relationship specification model M. This makes it possible to estimate the temperature of the first oil seal 85A by taking into account the outside air temperature TB, that is, by taking into account changes in the temperature of the first oil seal 85A according to the outside air temperature TB.

[0058] <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.

[0059] 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 may include only the outside air temperature TB at a certain point in time, instead of time-series data of the outside air temperature TB. As a specific example, if the change in temperature of the first oil seal 85A according to the outside air temperature TB is small, the multiple types of input data input to the relationship specification model M may include only the latest outside air temperature TB.

[0060] For example, the multiple types of input data input to the relationship specification model M do not have to include the outside air temperature TB. As a specific example, if the change in temperature of the first oil seal 85A in response to the outside air temperature TB is small, the impact will be small even if the multiple types of input data input to the relationship specification model M do not include the outside air temperature TB.

[0061] For example, the multiple types of input data input to the relationship specification model M may include only the vehicle speed SP at a certain point in time, instead of time-series data of the vehicle speed SP. As a specific example, if the change in the ease of heat exchange between the air outside the case 35 and the first oil seal 85A according to the vehicle speed SP is small, the multiple types of input data input to the relationship specification model M may include only the latest vehicle speed SP.

[0062] For example, the multiple types of input data input to the relationship specification model M do not have to include the vehicle speed SP. As a specific example, if the change in the ease of heat exchange between the air outside the case 35 and the first oil seal 85A depending on the vehicle speed SP is small, the impact will be small even if the multiple types of input data input to the relationship specification model M do not include the vehicle speed SP.

[0063] For example, the multiple types of input data input to the relationship specification model M may include only the inclination angle AR at a certain point in time, instead of time-series data of the inclination angle AR. As a specific example, if the change in the ease of heat exchange between the oil inside the case 35 and the first oil seal 85A according to the inclination angle AR of the vehicle 100 is small, the multiple types of input data input to the relationship specification model M may include only the latest inclination angle AR.

[0064] For example, the multiple types of input data input to the relationship specification model M do not have to include the inclination angle AR. As a specific example, if the change in the ease of heat exchange between the oil inside the case 35 and the first oil seal 85A depending on the inclination angle AR of the vehicle 100 is small, the impact will be small even if the multiple types of input data input to the relationship specification model M do not include the inclination angle AR.

[0065] For example, the multiple types of input data input to the relationship specification model M may include time series data of other inclination angles instead of or in addition to the time series data of the inclination angle AR. An example of the other inclination angle is a value indicating the degree of inclination of the vehicle 100 relative to the left and right of the vehicle 100. In other words, an example of the other inclination angle is a value indicating the inclination between a horizontal plane and the left-right axis of the vehicle 100.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] In the above embodiment, the seal temperature estimation device may be modified. For example, the seal temperature estimation device is not limited to the control device 90, but may be a device separate from the control device 90 in the vehicle 100. In this case, the separate device may store the relationship specification model M and the seal temperature estimation program in advance. Also, for example, the seal temperature 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 information from the vehicle 100. In this case, the server may store the relationship specification model M and the seal temperature estimation program in advance.

[0070] In the above embodiment, the oil seal to be estimated may be changed. For example, the execution device 91 of the control device 90 may estimate the temperature of the second oil seal 85B. In this case, the storage device 92 may previously store a relationship specification model M for estimating the temperature of the second oil seal 85B. In the above configuration, in step S11 of the data collection control, the execution device 91 may acquire, as the specific rotational speed, the wheel speed WS corresponding to the second oil seal 85B from among the multiple wheel speeds WS at the time of processing step S11.

[0071] In the above embodiment, the rotating body device may be changed. For example, the rotating body device may be a device applied to a device other than the vehicle 100. An example of the rotating body device described above is a motor device. In other words, the seal temperature estimation device may estimate the temperature of an oil seal of a rotating body device applied to a device other than the vehicle 100. That is, the seal temperature estimation device may be able to estimate the temperature of the oil seal of a rotating body device that includes a case, a rotating body, and an oil seal. As above, the seal temperature estimation device may be applied to a device other than the vehicle 100. [Explanation of symbols]

[0072] 10...internal combustion engine 15...crankshaft 20...damper 26...drive shaft 26A...first drive shaft 26B...second drive shaft 27...drive wheel 30...transaxle 35...case 40...planetary gear mechanism 50...reduction mechanism 60...differential 71...first motor generator 71A...rotating shaft 72...second motor generator 72A...rotating shaft 72B...connecting gear 80...oil supply device 85A...first oil seal 85B...second oil seal 90...control device 91...execution device 92...storage device 92A...control program M...related specification model 100...vehicle 101...accelerator operation amount sensor 102...wheel speed sensor 103...acceleration sensor 104...oil temperature sensor 105...outside air temperature sensor

Claims

1. The present invention is directed to a rotating body device including a case, a rotating body rotatably supported on the case, and an oil seal interposed between the case and the rotating body, an execution device and a storage device; the storage device stores a relationship definition model that outputs an index value indicating the temperature of the oil seal when multiple types of input data are input, the plurality of types of input data include time series data of the rotation speed of the rotating body and time series data of the temperature of oil inside the case, 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 Seal temperature estimation device.

2. the rotating body device is mounted on a vehicle, The plurality of types of input data includes time-series data of the tilt angle of the vehicle. The seal temperature estimation device according to claim 1 .

3. the rotating body device is mounted on a vehicle, The plurality of types of input data includes time-series data of the speed of the vehicle. The seal temperature estimation device according to claim 1 or 2.

4. The plurality of types of input data includes time series data of the air temperature outside the case. The seal temperature estimation device according to claim 1 or 2.

5. The present invention is directed to a rotating body device including a case, a rotating body rotatably supported on the case, and an oil seal interposed between the case and the rotating body, The present invention is applied to a seal temperature estimation device including an execution device and a storage device, the storage device stores a relationship definition model that outputs an index value indicating the temperature of the oil seal when multiple types of input data are input, the plurality of types of input data include time series data of the rotation speed of the rotating body and time series data of the temperature of oil inside the case, 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 Seal temperature estimation program.

Images