Temperature control device for rotating electrical machines

Abstract

To appropriately supply cooling oil to a rotary electric machine and cool the rotary electric machine effectively.SOLUTION: On the basis of a difference between a prediction value of a temperature of a rotary electric machine 100 and an actual measured value of the temperature of the rotary electric machine 100, an occurrence of an out-of-oil state in the rotary electric machine 100 is detected. In accordance with whether the out-of-oil condition occurs, the supply of cooling oil to the rotary electric machine 100 is controlled.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a temperature control device for a rotating electrical machine. [Background technology]

[0002] If operation is continued when the temperatures of the stator and rotor that make up a rotating electric machine exceed a limit temperature, demagnetization of the permanent magnets may occur, resulting in a decrease in output torque, and therefore it is necessary to appropriately control the temperature of the rotating electric machine.

[0003] In a configuration in which the oil cooling system on the stator side and the oil cooling system on the rotor side are separated, a technology has been disclosed in which thermocouples are installed in the part of the oil cooling system where the cooling oil passes before and after cooling the rotor, the inlet and outlet temperatures of the cooling oil are measured, and the rotor temperature is estimated from an estimation formula using the weight of the rotor operating conditions derived from the relationship between the motor torque and rotation speed (Patent Document 1).

[0004] Furthermore, in a motor generator having a housing with a supply oil passage and a discharge oil passage, with a variable throttle valve provided in the discharge oil passage, a technology has been disclosed in which when the predicted heat generation of the motor generator is small, the supply flow rate and discharge flow rate are controlled to decrease, thereby lowering the circulation flow rate of cooling oil while maintaining the oil level height, and when the predicted heat generation of the motor generator is large, the supply flow rate and discharge flow rate are controlled to increase, thereby raising the circulation flow rate of cooling oil while maintaining the oil level height (Patent Document 2). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2000-23421 A [Patent Document 2] JP 2013-207957 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the conventional technology, since it is assumed that the cooling oil is supplied as expected, there is no function to detect "oil shortage", and when unintended "oil shortage" occurs, there is a delay in taking measures such as increasing the flow rate of cooling oil to improve the cooling effect. Also, in order to prevent "oil shortage" from occurring, an excessive amount of cooling oil is often constantly supplied, which increases the work of the oil pump and the drag loss due to the cooling oil. [Means for solving the problem]

[0007] One aspect of the present invention is a temperature control device for a rotating electric machine that detects the occurrence of an oil-out condition in the rotating electric machine based on the difference between a predicted value of the temperature of the rotating electric machine and an actual measured value of the temperature of the rotating electric machine, and controls the supply of cooling oil to the rotating electric machine depending on whether or not the oil-out condition has occurred.

[0008] Here, it is preferable to detect the occurrence of the oil shortage state when there is a difference between the predicted value when the rotating electric machine is in a wet state and the measured value of the rotating electric machine that is greater than or equal to a predetermined reference value.

[0009] It is also preferable to detect the occurrence of the oil-out state when the difference between the predicted value when the rotating electric machine is in a dry state and the measured value of the rotating electric machine is within a predetermined reference value.

[0010] It is also preferable to store the state of the rotating electric machine when the out-of-oil state occurs as a condition for the out-of-oil state based on the difference between the predicted value and the measured value, and to detect the occurrence of the out-of-oil state of the rotating electric machine when the actual state of the rotating electric machine satisfies the condition for the out-of-oil state.

[0011] It is also preferable that the state of the rotating electric machine includes at least one of the rotation speed and output torque of the rotating electric machine, the current and voltage of a stator coil, and the temperature and flow rate of cooling oil.

[0012] In addition to the state of the rotating electric machine, it is preferable to store information about the vehicle in which the rotating electric machine is mounted as a condition for the out-of-oil state, and to detect the occurrence of the out-of-oil state of the rotating electric machine when the actual state of the rotating electric machine and the information about the vehicle satisfy the condition for the out-of-oil state.

[0013] In addition to the state of the rotating electric machine, it is preferable to store the position of the vehicle calculated from map information of a navigation system of the vehicle in which the rotating electric machine is mounted as a condition for the out-of-oil state, and to detect the occurrence of the out-of-oil state of the rotating electric machine when the actual state of the rotating electric machine and the position of the vehicle satisfy the condition for the out-of-oil state.

[0014] It is also preferable that the predicted value is predicted by a machine learning model. It is also preferable that the machine learning model is trained by machine learning so as to output the predicted value of the temperature of the rotating electric machine using the rotation speed and output torque of the rotating electric machine, the current and voltage of a stator coil, and the flow rate and temperature of cooling oil as inputs. Effect of the Invention

[0015] According to the present invention, it is possible to appropriately supply cooling oil to a rotating electric machine, and it is possible to effectively cool the rotating electric machine. [Brief description of the drawings]

[0016] [Figure 1] 1 is a diagram showing a configuration of a rotating electric machine according to an embodiment of the present invention; [Diagram 2] 1 is a diagram showing an example of the configuration of a vehicle equipped with a rotating electric machine according to an embodiment of the present invention; [Diagram 3] 5A to 5C are diagrams illustrating a supply state of cooling oil in the embodiment of the present invention. [Figure 4] FIG. 1 is a diagram illustrating an example of a deep learning model in an embodiment of the present invention. [Diagram 5] 5A to 5C are diagrams illustrating a process for detecting an "out-of-oil state" in an embodiment of the present invention. [Figure 6]FIG. 2 is a diagram illustrating information related to a vehicle according to an embodiment of the present invention. [Figure 7] FIG. 4 is a flowchart showing a learning process for a function of determining an out-of-oil state in an embodiment of the present invention. [Figure 8] FIG. 4 is a diagram illustrating an example of a method for controlling cooling oil in an embodiment of the present invention. [Figure 9] 5 is a diagram illustrating an example of a relationship between a measured value and a predicted value of a rotating electric machine according to an embodiment of the present invention. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] As shown in FIG. 1, a rotating electric machine 100 according to an embodiment of the present invention includes a rotor 10, a shaft 12, a stator 14, bearings 16, a casing 18, an inverter 20, a battery 22, a control unit 24, an oil pump 26, a motor 28, and an oil pan 30.

[0018] 2 shows an example of a vehicle 200 equipped with a rotating electric machine 100. The vehicle 200 runs by transmitting power output from the rotating electric machine 100, which is a power source, to driving wheels (tires) 108 via a transmission 102, a differential gear 104, and a drive shaft 106. In particular, a portion formed by the rotating electric machine 100, the transmission 102, and the differential gear 104 is referred to as an electric drive train (or electric drive system).

[0019] The rotor 10 is a part that rotates in the rotating electric machine 100. The rotor 10 includes a rotor core magnet 10a and a rotor core electromagnetic steel plate 10b. The shaft 12 is connected so as to rotate together with the rotor 10. The shaft 12 is used to transmit the rotational torque output from the rotor 10 to the outside of the rotating electric machine 100. The stator 14 is a part that is stationary relative to the rotor 10 in the rotating electric machine 100. The stator 14 includes a stator coil 14a and a stator core electromagnetic steel plate 14b. The rotor 10, the shaft 12, and the stator 14 are housed in a casing 18. A bearing 16 is disposed between the shaft 12 and the casing 18, allowing the rotor 10 to rotate smoothly together with the shaft 12.

[0020] The voltage and frequency of the power supplied from the battery 22 are adjusted by the inverter 20 to control the current flowing through the stator coil 14a of the rotating electric machine 100. When the current appropriately controlled by the inverter 20 flows through the stator coil 14a, a rotating magnetic field is created in the stator 14. The magnetic interaction between the rotating magnetic field and the rotor core magnet 10a generates a rotational torque in the rotor 10, causing the rotor 10 to rotate.

[0021] The control unit 24 is also called an on-board computer and includes a calculation device for processing information, a storage device for storing information, etc. The control unit 24 calculates the torque required for the rotating electric machine 100 based on information such as the accelerator pedal operation amount operated by the driver and the vehicle speed, and then issues a command to the inverter 20 to control the current flowing through the stator coil 14a according to the required torque.

[0022] When a current flows through the stator coil 14a, a part of the power is lost, causing the stator coil 14a to heat up. When the rotor 10 rotates, eddy currents flow through the rotor core electromagnetic steel plate 10b, generating heat. To cool the rotating electric machine 100 that is heated by the heat generated, cooling oil is supplied from an oil pump 26. The oil pump 26 is driven by a motor 28. The cooling oil that has absorbed heat from the rotor 10 and the stator 14 is returned to the oil pan 30 and is cooled by dissipating heat to the outside air. A radiator (not shown) may be used to increase the efficiency of heat exchange with the outside air. The cooling oil also functions as a lubricant, smoothing the movement of sliding parts such as the bearings 16.

[0023] Here, in the operation of the electric drive system, it is extremely important to control the temperature of the rotating electric machine 100 within an appropriate range. If the temperature of the rotor core magnets 10a arranged in the rotor 10 exceeds an allowable value, the magnets will cool, and there is a risk of irreversible demagnetization occurring, in which the magnetic force does not return even if the temperature returns to normal. If irreversible demagnetization occurs, the upper limit of the torque that the rotating electric machine 100 can output will decrease, and the performance of the rotating electric machine 100 will decrease. Also, if the temperature of the stator coil 14a exceeds the allowable value, the insulating coating will break down, causing a short circuit, and other damage to the entire electric drive system.

[0024] In the conventional technology, it is assumed that the cooling oil always applies to the rotating electric machine as expected at the time of design. However, when the vehicle 200 equipped with the electric drive system actually travels on a road, the flow of the cooling oil may be disturbed due to the acceleration or change in attitude of the vehicle 200, and the cooling oil may not be applied to the desired location.

[0025] In this way, a state in which cooling oil is not supplied properly to the rotating electric machine for some reason and the required cooling effect cannot be obtained is called an "oil-out state." A state in which no cooling oil is applied to the rotating electric machine is called a "dry state." In particular, a state in which the flow rate of cooling oil supplied by the oil pump 26 is kept to zero or a very small amount from the beginning and no cooling oil is applied to the rotating electric machine is called a "completely dry state," not a state in which the "oil-out state" occurs unintentionally. On the other hand, a state in which cooling oil is applied to the rotating electric machine as expected is called a "wet state."

[0026] With reference to FIG. 3, the "wet state" and the "oil-out state" of the rotating electric machine will be described. FIG. 3(a) shows a case where the rotating electric machine is in a "wet state". In the "wet state", the cooling oil that has passed through the oil passage in the casing 18 is appropriately supplied to predetermined locations such as the stator coil 14a of the stator 14 and the end of the stator core electromagnetic steel plate 14b, and the rotating electric machine can be cooled as intended in the design. On the other hand, FIG. 3(b) shows a case where the rotating electric machine is in an "oil-out state". Due to factors such as the rotating electric machine being tilted, the cooling oil flowing out of the casing 18 is generally biased to the left and flows down, and the cooling oil is not applied to desired locations such as the end of the stator coil 14a (circled portion in the figure). In the "oil-out state", the temperature of the rotating electric machine may rise abnormally. Therefore, it is necessary to detect the "oil-out state" in order to avoid irreversible demagnetization of the rotor core magnet 10a and insulation breakdown of the stator coil 14a.

[0027] As described above, the cause of the "out-of-oil state" is assumed to be a disruption in the flow of cooling oil due to changes in the acceleration or posture of the vehicle 200. It is difficult to significantly change the acceleration or posture of the vehicle 200 in tests on a bench or chassis stand conducted during the development of an electric drive system, and it is not possible to clarify all of the conditions under which the "out-of-oil state" occurs during the development stage. It is also assumed that the flow of cooling oil may be impaired due to impurities that have entered the oil passages or cooling oil leakage due to deterioration of the seals in the oil passages over time, resulting in the "out-of-oil state." However, it is also difficult to detect such a situation in advance.

[0028] In order to avoid the "oil shortage state," the flow rate of cooling oil pumped from the oil pump 26 may be increased so that the rotating electric machine is sufficiently covered with cooling oil. However, supplying a large amount of cooling oil increases the workload of the oil pump 26, which is not directly related to driving the vehicle 200, and the electric power consumption of the vehicle 200 (the distance the vehicle 200 can travel with a certain amount of power consumption) worsens. Furthermore, if the rotor 10 rotates with a large amount of cooling oil being applied, drag loss increases, and the electric power consumption worsens. Therefore, when the current flowing through the rotating electric machine is small, such as during coasting, and the amount of heat generated within the rotating electric machine is small, it is necessary to reduce the flow rate of cooling oil as much as possible to reduce losses.

[0029] In the rotating electric machine 100 of this embodiment, an "out-of-oil state" is detected while the vehicle 200 equipped with the rotating electric machine 100 is traveling, and information on the occurrence is stored and accumulated in an on-board computer for learning, thereby appropriately controlling the flow rate of cooling oil in advance under similar driving conditions to avoid the "out-of-oil state," thereby improving the durability and reliability of the electric drive system.

[0030] In the rotating electric machine 100, an "out-of-oil state" is detected using a predicted value of the temperature in the electric drive system calculated by the machine learning and deep learning models and an actual measured value of the temperature of the rotating electric machine. Machine learning technology is used to predict the temperature of the rotating electric machine. Machine learning may include deep learning. Examples of machine learning models that can be used to predict data include decision trees, support vector machines, and deep learning.

[0031] FIG. 4 shows an example of a deep learning model for predicting the temperature of a rotating electric machine. The deep learning model is composed of an input layer, an intermediate layer, and an output layer. The input layer, intermediate layer, and output layer are each composed of a single-layer or multi-layer neural network. The number of layers and the number of elements in each layer are not limited to the example of FIG. 4. Information such as the rotation speed of the rotor 10, the output torque, the current and voltage of the stator coil 14a, the flow rate and temperature of the cooling oil, etc. are input to the input layer. In the intermediate layer, processing based on machine learning is performed on the information input to the input layer. The output layer outputs predicted values ​​of the temperatures of each part in the rotating electric machine 100 (the stator coil 14a, the stator core electromagnetic steel plate 14b, the rotor 10, the rotor core magnet 10a, etc.).

[0032] In the deep learning model, learning parameters such as weight coefficients and activation functions for nodes constituting a neural network are learned. Specifically, learning is performed so that the predicted values ​​of the temperatures of each part output by the model and the values ​​of the temperatures of each part measured in a bench test or the like are more consistent under various operating conditions input to the input layer for the rotating electric machine 100. By storing the deep learning model after completion of learning in an on-board computer, it is possible to obtain predicted values ​​of the temperatures of each part of the rotating electric machine 100 by inputting information such as the rotation speed of the rotor 10, the output torque, the current and voltage of the stator coil 14a, and the flow rate and temperature of the cooling oil into the deep learning model.

[0033] FIG. 5 shows an overview of a method for detecting an "oil-out state." As shown in FIG. 5(a), in a state where cooling oil is flowing at a flow rate A that causes the rotating electric machine 100 to be in a "wet state," the predicted value and measured value of the temperature of the rotating electric machine 100 are almost the same. In addition, the measured value of the temperature of the rotating electric machine 100 at the flow rate A indicates a value lower than the predicted value of the temperature in a "completely dry state." In other words, it indicates that cooling oil is appropriately applied to the rotating electric machine 100, and the rotating electric machine 100 is sufficiently cooled. On the other hand, as shown in FIG. 5(b), in a state where cooling oil is flowing at a flow rate B that is reduced from the flow rate A, the predicted value and measured value of the temperature of the rotating electric machine 100 deviate. In addition, the measured value of the temperature of the rotating electric machine 100 at the flow rate B indicates a value close to the predicted value in a "completely dry state." In other words, it can be determined that the rotating electric machine 100 is in an "oil-out state" in which cooling oil is not sufficiently applied to desired locations even when cooling oil is flowing at a flow rate B.

[0034] Therefore, as shown in Fig. 5(b), information on the driving state when the predicted value and the measured value of the temperature of the rotating electric machine 100 diverge is stored in the storage device of the on-board computer, and learning is performed so that the "out-of-oil state" can be detected from the information on the driving state. It is preferable to update and learn the information for determining the "out-of-oil state" while the vehicle 200 is operating.

[0035] Here, the information indicating the operating condition preferably includes information related to the vehicle, such as the speed V, acceleration dV / dt, and attitude (α, β) of a vehicle 200 equipped with the rotating electric machine 100, as well as the rotation speed, output torque, current and voltage of the stator coil 14a, the temperature of the cooling oil, and the flow rate of the cooling oil, of the rotating electric machine 100, which are used when predicting the temperature of the rotating electric machine 100, as shown in Fig. 6. The speed and acceleration of the vehicle 200 can be detected by mounting a speed sensor and an acceleration sensor on the vehicle 200. Also, the speed, acceleration, and attitude of the vehicle 200 can be detected by mounting a gyro sensor on the vehicle 200.

[0036] Instead of acquiring information about vehicle 200 from various sensors mounted on vehicle 200, the position of the vehicle may be determined from map information of a navigation system and the determined information may be stored in a storage device as information about the vehicle. By utilizing a navigation system, the temperature control of rotating electric machine 100 according to the present embodiment can be applied even to low-cost vehicles that cannot be equipped with various sensors. In addition, by utilizing information provided by other vehicles, the time required for learning can be shortened.

[0037] FIG. 7 shows a flowchart of the learning process of the function of judging the "out-of-oil state". In step S10, information such as the rotation speed of the rotor 10, the output torque, the current and voltage of the stator coil 14a, the flow rate and temperature of the cooling oil, the temperature of each part of the rotating electric machine 100, and the speed, acceleration, and attitude of the vehicle 200 are input to the on-board computer. In step S12, the temperature of each part of the rotating electric machine 100 is predicted based on the input information using a deep learning model for temperature prediction. In step S14, it is determined whether or not the conditions for judging the "out-of-oil state" in the rotating electric machine 100 need to be updated. If the conditions for judging the "out-of-oil state" need to be updated, the process proceeds to step S16, and if the conditions do not need to be updated, the process proceeds to step S18.

[0038] In step S16, the conditions for determining whether an "out-of-oil state" has occurred are updated as follows: Determining whether an "out-of-oil state" has occurred and updating the information is roughly divided into two processes: (1) adding an occurrence condition to the storage device, and (2) deleting an occurrence condition from the storage device.

[0039] (1) Additional processing for the occurrence condition of "out of oil" The process of adding the condition for the occurrence of an "out-of-oil state" is a process of adding a condition for determining a state in which the deep learning model predicts a temperature that indicates a "wet state" but the actual measurement results in a temperature that indicates an "out-of-oil state." If any of the following formulas (1) to (3) is satisfied, the information on the rotating electric machine 100 and the vehicle 200 acquired in step S10 is added to the storage device as a condition for the occurrence of an "out-of-oil state." (Number 1) T M -T P,W >T th (1) (Number 2) T P,D -T M <T th (2) (Number 3) T M -T P,W >T P,D -T M (3) Here, T M : Measured temperature of the rotating electric machine 100, T P,W : Prediction of the temperature of the rotating electrical machine 100 in a "wet state", T th : a given threshold, T P,D : Shows the predicted temperature value of the rotating electrical machine 100 in a "completely dry state."

[0040] (2) Deletion of the conditions for the occurrence of "out of oil" The process of deleting the conditions for the occurrence of an "out-of-oil state" is a process of deleting the conditions for determining a state in which the deep learning model predicted a temperature to indicate an "out-of-oil state" but the actual measurement showed a temperature to indicate a "wet state." If any of the following formulas (4) to (6) is satisfied, the information on the rotating electric machine 100 and the vehicle 200 acquired in step S10 is deleted from the conditions for the occurrence of an "out-of-oil state" stored in the storage device. (Number 4) T M -T P,W <T th (4) (Number 5) T P,D -TM >T th (5) (Number 6) T M -T P,W <T P,D -T M (6)

[0041] After the update process of the occurrence condition of the "oil shortage state" is performed in step S16 as described above, it is determined in step S18 whether the rotating electric machine 100 is in the "oil shortage state", and the supply of cooling oil to the rotating electric machine 100 is controlled based on the determination result. Specifically, a target value of the flow rate of the cooling oil is determined based on information on the operating conditions of the rotating electric machine 100, such as the occurrence or non-occurrence of the "oil shortage state", the rotation speed of the rotating electric machine 100, the output torque, the current and voltage of the stator coil 14a, the temperature of each part of the rotating electric machine 100, and the temperature of the cooling oil, and the actual flow rate is controlled to follow the target value. In addition, as for the control of the flow rate of the cooling oil, a method of controlling the rotation speed of the oil pump 26 with a small motor can be used. Also, as shown in FIG. 8, a control valve such as a flow rate control valve 32 may be arranged somewhere in the oil passage of the cooling oil to control the flow rate of the cooling oil.

[0042] As a result, an appropriate flow rate of cooling oil is applied to the rotating electrical machine 100, so that the temperature of each part of the rotating electrical machine 100 is controlled within a normal range.

[0043] In addition, by appropriately updating and learning the situation when the "out-of-oil state" occurs, it is possible to avoid the "out-of-oil state" by taking measures such as increasing the flow rate of cooling oil in advance when a similar operating situation is encountered again. This makes it possible to prevent an abnormal increase in temperature of the rotating electric machine 100 and to avoid accumulation of damage to the permanent magnets in the rotating electric machine 100 and the insulating coating of the stator coil 14a.

[0044] Furthermore, by knowing in advance the conditions under which the vehicle will be in an "oil-out state," it is possible to reduce the flow rate of cooling oil to the limit in conditions where there is no need to quickly cool the rotating electric machine 100, such as during coasting. This makes it possible to reduce the work (loss) of the oil pump 26 for supplying cooling oil and the drag loss of cooling oil associated with the rotation of the rotating electric machine 100, thereby improving the power consumption of the vehicle 200.

[0045] FIG. 9 shows an example of the temperatures of the stator coil 14a and the stator core electromagnetic steel plate 14b when an "oil shortage state" is detected.

[0046] 9(a) shows the measured temperature values ​​of the stator coil 14a and the stator core electromagnetic steel plate 14b in the rotating electric machine 100 when the cooling oil is flowing at a flow rate of 4 [L / min] while the rotating electric machine 100 is operating at a constant rotation speed and constant output torque, and the predicted temperature values ​​(wet predicted values) predicted by the deep learning model. Also shown is the predicted temperature value (completely dry predicted value) in a state where the flow rate of the cooling oil is set to zero.

[0047] 9(a), when the cooling oil was supplied at a flow rate of 4 [L / min], the measured temperature value of the rotating electric machine 100 and the wet predicted value matched, and showed a lower value than the completely dry predicted value. In other words, the cooling oil was appropriately applied to the rotating electric machine 100, and the desired cooling effect was obtained.

[0048] 9(b) shows the measured temperature values ​​of the stator coil 14a and the stator core electromagnetic steel plate 14b in the rotating electric machine 100 when the flow rate of the cooling oil is reduced to 2 [L / min] while the rotating electric machine 100 is operating at a constant rotation speed and constant output torque, as in the case of FIG. 9(a), and the predicted temperature values ​​(wet predicted values) predicted by the deep learning model. Also shown is the predicted temperature value (completely dry predicted value) when the flow rate of the cooling oil is set to zero.

[0049] 9(b), a discrepancy was observed between the measured temperature values ​​of the stator coil 14a and the stator core electromagnetic steel plate 14b in the rotating electric machine 100 and the wet predicted values ​​output by the deep learning model, and the temperature of each part of the rotating electric machine 100 rose. From these results, it was determined that the rotating electric machine 100 was in an "oil-out state."

[0050] As described above, the "out-of-oil state" of the rotating electric machine 100 can be detected or predicted by determining the "out-of-oil state" based on a comparison between the measured value of the temperature of the rotating electric machine 100 and the predicted value of the deep learning model, and storing the information at the time of the determination in the storage device of the on-board computer. This makes it possible to suppress the occurrence and accumulation of damage to each part of the rotating electric machine 100 caused by a sudden rise in the temperature of the rotating electric machine 100 due to an inappropriate application of cooling oil to the rotating electric machine 100. In addition, loss in the oil pump 26 and the like can be reduced, and the fuel efficiency of the rotating electric machine 100 and the vehicle 200 can be improved. [Explanation of symbols]

[0051] 10 rotor, 10a rotor core magnet, 10b rotor core electromagnetic steel plate, 12 shaft, 14 stator, 14a stator coil, 14b stator core electromagnetic steel plate, 16 bearing, 18 casing, 20 inverter, 22 battery, 24 control unit, 26 oil pump, 28 motor, 30 oil pan, 32 flow control valve, 100 rotating electric machine, 102 transmission, 104 differential gear, 106 drive shaft, 108 drive wheel (tire), 200 vehicle.

Claims

1. 1. A temperature control device for a rotating electric machine, the temperature control device detecting an occurrence of an oil-out state of the rotating electric machine based on a difference between a predicted value of a temperature of the rotating electric machine and an actual measured value of the temperature of the rotating electric machine, and controlling a supply of cooling oil to the rotating electric machine depending on whether or not the oil-out state has occurred, A temperature control device for a rotating electric machine, characterized in that it detects the occurrence of an oil-out state when the difference between the predicted value when the rotating electric machine is in a dry state and the measured value of the rotating electric machine is within a predetermined reference value.

2. 2. The temperature control device for a rotating electric machine according to claim 1, Furthermore, the temperature control device for a rotating electric machine is characterized in that it detects the occurrence of an oil-out state when there is a difference between the predicted value when the rotating electric machine is in a wet state and the measured value of the rotating electric machine that is greater than a predetermined reference value.

3. 3. The temperature control device for a rotating electric machine according to claim 1, A temperature control device for a rotating electric machine, characterized in that the state of the rotating electric machine when the oil-out state occurs is stored as a condition for the oil-out state based on the difference between the predicted value and the measured value, and the occurrence of the oil-out state of the rotating electric machine is detected when the actual state of the rotating electric machine satisfies the condition for the oil-out state.

4. The temperature control device for a rotating electrical machine according to claim 3, 13. A temperature control device for a rotating electric machine, wherein the state of the rotating electric machine includes at least one of a rotation speed and an output torque of the rotating electric machine, a current and a voltage of a stator coil, and a temperature and a flow rate of a cooling oil.

5. The temperature control device for a rotating electric machine according to claim 3 or 4, A temperature control device for a rotating electric machine, characterized in that in addition to the state of the rotating electric machine, information of the vehicle in which the rotating electric machine is mounted is stored as a condition for the out-of-oil state, and the occurrence of the out-of-oil state of the rotating electric machine is detected when the actual state of the rotating electric machine and the information of the vehicle satisfy the condition for the out-of-oil state.

6. The temperature control device for a rotating electric machine according to claim 3 or 4, A temperature control device for a rotating electric machine, characterized in that in addition to the state of the rotating electric machine, the position of the vehicle in which the rotating electric machine is mounted, calculated from map information of a navigation system of the vehicle, is stored as a condition for the out-of-oil state, and the occurrence of the out-of-oil state of the rotating electric machine is detected when the actual state of the rotating electric machine and the position of the vehicle satisfy the condition for the out-of-oil state.

7. The temperature control device for a rotating electric machine according to any one of claims 1 to 6, A temperature control device for a rotating electrical machine, characterized in that the predicted value is predicted by a machine learning model.

8. The temperature control device for a rotating electric machine according to claim 7, The temperature control device for a rotating electric machine, characterized in that the machine learning model has been machine-learned to input the rotational speed and output torque of the rotating electric machine, the current and voltage of the stator coil, and the flow rate and temperature of cooling oil, and output the predicted value of the temperature of the rotating electric machine.

Images