Vehicle control device

Abstract

The present invention relates to a vehicle control device.SOLUTION: A vehicle control device that is used in a vehicle including an electric motor having a permanent magnet and a notification device that notifies an occupant of information and controls at least the notification device, estimates a margin time period using a learned model obtained by learning using a neural network that receives temperature data which is time-series data of a temperature of the electric motor and outputs the margin time period as a time period until predetermined demagnetization occurs in the permanent magnet, and the temperature data, and controls the notification device such that predetermined notification is performed when the margin time period is less than a predetermined time period.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a vehicle control device. [Background technology]

[0002] Conventionally, a vehicle control device of this type has been proposed for use in a vehicle equipped with an electric motor having a permanent magnet (see, for example, Patent Document 1). This device estimates the temperature of the permanent magnet based on a trained model that uses the average value of the stator temperature of the electric motor as an input variable and an estimated value of the temperature of the permanent magnet as an output variable, and on the average value of the stator temperature. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-76117 Summary of the Invention [Problem to be solved by the invention]

[0004] Although the above-mentioned vehicle control device estimates the temperature of the permanent magnet, it is not possible to estimate how much time remains until a certain level of demagnetization occurs in the permanent magnet that would reduce the performance of the electric motor, and therefore the occupants are unable to recognize that a certain level of demagnetization may occur in the permanent magnet.

[0005] The vehicle control device of the present disclosure has a primary purpose of making an occupant aware that a predetermined demagnetization may occur in a permanent magnet. [Means for solving the problem]

[0006] The vehicle control device of the present disclosure employs the following means to achieve the above-mentioned main object.

[0007] The vehicle control device of the present disclosure includes: A vehicle control device is used in a vehicle including an electric motor having a permanent magnet and an alarm device that notifies an occupant of information, and controls at least the alarm device, The temperature data is input as time-series data of the temperature of the electric motor, and the margin time is output as the time until a predetermined demagnetization occurs in the permanent magnet. The margin time is estimated using the temperature data and a trained model obtained by training using a neural network, and the temperature data is used, and when the margin time is less than the predetermined time, the alarm device is controlled so that a predetermined alarm is issued. The gist of this is as follows.

[0008] The vehicle control device disclosed herein estimates the margin time using a trained model obtained by training using a neural network that inputs temperature data, which is time-series data on the temperature of the electric motor, and outputs a margin time, which is the time until a predetermined demagnetization occurs in the permanent magnet, and controls the alarm device to issue a predetermined alert when the margin time is less than the predetermined time. As a result, the vehicle occupant can be made aware that the predetermined demagnetization may occur in the permanent magnet. Here, the "predetermined demagnetization" may be demagnetization to the extent that the electric motor is no longer able to output sufficient torque for driving. The "predetermined time" is a time determined in advance through experiments, analysis, machine learning, or the like as a threshold for determining whether there is a margin time until the predetermined demagnetization occurs in the permanent magnet of the electric motor. The "predetermined alert" may be an alert indicating that there is not enough time until the predetermined demagnetization occurs in the permanent magnet of the electric motor, an alert urging the occupant to visit a repair shop or dealer, an alert using an alarm sound, or the like. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic configuration diagram of an electric vehicle 20 equipped with a vehicle control device according to an embodiment of the present disclosure. [Figure 2] 4 is a flowchart showing an example of a processing routine executed by an ECU 60. [Figure 3] FIG. 1 is an explanatory diagram illustrating a method for constructing a trained model. DETAILED DESCRIPTION OF THE INVENTION

[0010] An embodiment of the present disclosure will be described with reference to the drawings. Fig. 1 is a schematic diagram of an electric vehicle 20 equipped with a vehicle control device according to an embodiment of the present disclosure. As shown in the figure, the electric vehicle 20 includes a motor 32, an inverter 34, a battery 36 serving as an electricity storage device, a cooling device 40, a lubrication device 50, and an electronic control unit (hereinafter referred to as "ECU") 60 serving as a control device.

[0011] The motor 32 is configured as a three-phase AC motor and includes a rotor with a permanent magnet embedded in the rotor core and a stator with a three-phase coil wound around the stator core. The rotor of the motor 32 is connected to a drive shaft 26 that is connected to the drive wheels 22 a, 22 b via a differential gear 24.

[0012] The inverter 34 is used to drive the motor 32 and is connected to the battery 36 via a power line 37. The inverter 34 includes six switching elements, namely, transistors T11 to T16, and six diodes D11 to D16. The transistors T11 to T16 are arranged in pairs, two at a time, on the source side and two at the sink side of the positive and negative lines of the power line 37. The junctions of the paired transistors T11 to T16 are connected to the three-phase (U-phase, V-phase, W-phase) coils of the motor 32, respectively. The six diodes D11 to D16 are connected in parallel to the six transistors T11 to T16, respectively. When a voltage is applied to the inverter 34, the ECU 60 adjusts the proportion of the on-time of the paired transistors T11 to T16, thereby generating a rotating magnetic field in the three-phase coils and driving the motor 32 to rotate.

[0013] The battery 36 is configured as a lithium ion secondary battery or a nickel-metal hydride secondary battery, and is connected to the inverter 34 via the power line 37 as described above.

[0014] The cooling device 40 has a circulation flow path 42, a radiator 44, and an electric pump 46. The circulation flow path 42 is configured as a flow path for circulating the cooling water through the motor 32, the inverter 34, the battery 36, and the radiator 44 in this order. The electric pump 46 circulates the cooling water through the circulation flow path 42. Note that the circulation flow path 42 may also be configured as a flow path for circulating the cooling water through the inverter 34, the motor 32, the battery 36, and the radiator 44 in this order.

[0015] The lubrication device 50 includes an oil pan 52 attached to the bottom of the motor 32 housed in a case and storing lubricating oil, as well as an oil pump that is powered by electricity from an auxiliary battery (not shown) and that sucks in the lubricating oil stored in the oil pan 52 and pressurizes it to the motor housed in the case. When the oil pump is driven, the lubricating oil is supplied from the top of the motor 32 and returns to the oil pan 52 via the motor 32, thereby preventing the motor 32 from overheating and lubricating sliding parts such as the rotor of the motor 32.

[0016] The ECU 60 includes a microcomputer with a CPU, ROM, RAM, flash memory, input / output ports, and communication ports, as well as various drive circuits and logic ICs. The ECU 60 receives signals from various sensors via its input ports. For example, the ECU 60 receives a rotational position θm from a rotational position sensor that detects the rotational position of the rotor of the motor 32 and phase currents Iu, Iv, and Iw from three current sensors that detect the phase currents of each phase of the motor 32. The ECU 60 also receives a motor temperature αm from a temperature sensor 32t attached to the motor 32. The ECU 60 also receives a coolant temperature αw from a temperature sensor 48 attached to the circulation flow path 42 of the cooling device 40 and a coolant flow rate Qw from a flow rate sensor 49 that detects the flow rate of the coolant in the circulation flow path 42. The ECU 60 also receives an oil temperature Toil from an oil temperature sensor 54 that detects the temperature of the lubricating oil stored in an oil pan 52 of the lubrication device 50. The ECU 60 also receives inputs of a start signal from a power switch, a shift position SP from a shift sensor 62 that detects the operating position of a shift lever 61, an accelerator opening Acc from an accelerator pedal position sensor 64 that detects the amount of depression of an accelerator pedal 63, a brake pedal position BP from a brake pedal position sensor 66 that detects the amount of depression of a brake pedal 65, and a vehicle speed V from a vehicle speed sensor 67.

[0017] The ECU 60 outputs various control signals via an output port. For example, the ECU 60 outputs a control signal to the transistors T11 to T16 of the inverter 34, a control signal to the electric pump 46 of the cooling device 40, and a control signal to the speaker 68. The ECU 60 calculates the electrical angle θe and rotation speed Nm of the motor 32 based on the rotational position θm of the rotor of the motor 32. The ECU 60 stores time-series data of the motor temperature αm from the temperature sensor 32t for a predetermined period of time in a flash memory together with temperature data Dtm. The ECU 60 calculates the actual torque Tm output from the motor 32 based on the phase currents Iu, Iv, and Iw of the motor 32. Here, the "predetermined period of time" may be, for example, several minutes.

[0018] In the electric vehicle 20 of this embodiment configured in this manner, the ECU 60 sets the required torque Td* required of the drive shaft 26 based on the accelerator opening Acc and the vehicle speed V, sets the torque command Tm* of the motor 32 so that the set required torque Td* is output to the drive shaft 26, and performs switching control of the transistors T11 to T16 of the inverter 34 so that the motor 32 is driven by the torque command Tm*.

[0019] Next, the operation of the electric vehicle 20 of this embodiment configured as described above will be described, in particular the operation performed when notifying the occurrence of a predetermined demagnetization of the permanent magnet of the motor 32. Figure 2 is a flowchart showing an example of a processing routine executed by the ECU 60. This routine is repeatedly executed at predetermined time intervals (for example, every few msec).

[0020] When this routine is executed, the CPU of the ECU 60 inputs the temperature data Dtm, the oil temperature Toil from the oil temperature sensor 54, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw from the flow rate sensor 49 (S100). Then, using a trained model created in advance and stored in ROM, and the temperature data Dtm, the oil temperature Toil, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw input in S100, the CPU estimates the margin time tm as the time until a predetermined demagnetization occurs in the permanent magnet of the motor 32 (S110). Here, the "predetermined demagnetization" may be demagnetization to the extent that the motor 32 is no longer able to output sufficient torque for driving. FIG. 3 is an explanatory diagram for explaining a method of constructing the trained model. As shown in the figure, the ECU 60 has a trained model stored in advance in its ROM. The trained model is constructed using a neural network that inputs temperature data Dtm, oil temperature Toil, torque command Tm*, actual torque Tm, and coolant flow rate Qw and outputs tm. The oil temperature Toil is used as an input because the trained model reflects the cooling of the motor 32 by the lubrication device 50, i.e., the cooling of the permanent magnets, to accurately estimate the tm. The torque command Tm* and actual torque Tm are used as input because the difference between the torque command Tm* and the actual torque Tm is used as an input because the trained model reflects the cooling of the motor 32 by the cooling device 40, i.e., the cooling of the permanent magnets, to accurately estimate the tm. The coolant flow rate Qw is used as an input because the trained model reflects the cooling of the motor 32 by the cooling device 40, i.e., the cooling of the permanent magnets, to accurately estimate the tm. The ECU 60 inputs the temperature data Dtm, the oil temperature Toil, the torque command Tm*, and the coolant flow rate Qw into the trained model thus constructed, and estimates the obtained output as the margin time tm.

[0021] Next, it is determined whether the remaining time tm is less than a predetermined time tmref (S120). The predetermined time tmref is a threshold value for determining whether there is a time until the predetermined demagnetization occurs in the permanent magnet of the motor 32, and is set to 30 days, 45 days, 60 days, or the like. If the remaining time tm is equal to or greater than the predetermined time tmref, it is determined that there is a time until the predetermined demagnetization occurs in the permanent magnet of the motor 32, and therefore it is safe to use the electric vehicle 20, and the routine is terminated. If the remaining time tm is less than the predetermined time tmref, it is determined that there is not enough time until the predetermined demagnetization occurs in the permanent magnet of the motor 32, and the speaker 68 is controlled to issue a predetermined notification (S130), and the routine is terminated. An example of the "predetermined notification" is a first notification, which is an audio notification that there is not enough time until the predetermined demagnetization occurs in the permanent magnet of the motor 32. Note that instead of or in addition to the first notification, an audio notification or an alarm notification urging the user to visit a repair shop or dealer may be issued. Such a notification can make the occupant aware that there is a possibility that demagnetization of the permanent magnet may occur.

[0022] According to the electric vehicle 20 of this embodiment described above, the margin time tm is estimated using a trained model obtained by training using a neural network that inputs the temperature data Dtm, the oil temperature Toil from the oil temperature sensor 54, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw and outputs the margin time tm, as well as the temperature data Dtm, the oil temperature Toil from the oil temperature sensor 54, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw, and by controlling the speaker 68 to issue a specified notification when the margin time tm is less than the specified time tmref, the occupants can be made aware that demagnetization of the permanent magnet may occur.

[0023] In the above-described embodiment, a trained model is constructed using a neural network that inputs the temperature data Dtm, the oil temperature Toil from the oil temperature sensor 54, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw and outputs the margin time tm. However, the input only needs to include at least the temperature data Dtm, and the oil temperature Toil from the oil temperature sensor 54, the torque command Tm*, the actual torque Tm, and the coolant flow rate Qw do not necessarily have to be included as inputs.

[0024] In the above-described embodiment, the speaker 68 is controlled to issue a predetermined notification in S130. However, if the electric vehicle 20 is equipped with a display device that visually displays information, the display device may be controlled to issue a predetermined notification in S130. In this case, an example of the "predetermined notification" may be a third notification that visually displays a message indicating that there is not enough time left until a predetermined demagnetization occurs in the permanent magnet of the motor 22. Instead of or in addition to the third notification, a notification may be issued by displaying a message urging the driver to visit a repair shop or dealer, or by lighting up a predetermined icon.

[0025] The correspondence between the main elements of the embodiment and the main elements of the invention described in the "Means for Solving the Problem" section will be explained below. In the embodiment, the motor 32 corresponds to the "electric motor," the speaker 68 corresponds to the "alarm device," and the ECU 60 corresponds to the "vehicle control device."

[0026] The correspondence between the main elements of the embodiments and the main elements of the invention described in the "Means for Solving the Problem" section does not limit the elements of the invention described in the "Means for Solving the Problem" section, since the embodiments are examples for specifically explaining the mode for implementing the invention described in the "Means for Solving the Problem" section. In other words, the interpretation of the invention described in the "Means for Solving the Problem" section should be based on the description in that section, and the embodiments are merely specific examples of the invention described in the "Means for Solving the Problem" section.

[0027] The above describes the forms for implementing the present disclosure using embodiments, but the present disclosure is not limited to these embodiments in any way, and it goes without saying that the present disclosure can be implemented in various forms within the scope that does not deviate from the gist of the present disclosure. [Industrial Applicability]

[0028] The present disclosure is applicable to the vehicle control device manufacturing industry and the like. [Explanation of symbols]

[0029] 20 electric vehicle, 22a, 22b drive wheels, 24 differential gear, 26 drive shaft, 32 motor, 32t temperature sensor, 34 inverter, 36 battery, 37 power line, 40 cooling device, 42 circulation flow path, 44 radiator, 46 electric pump, 48 temperature sensor, 49 flow rate sensor, 50 lubrication device, 52 oil pan, 54 temperature sensor, 60 electronic control unit (ECU), 61 shift lever, 62 shift sensor, 63 accelerator pedal, 64 accelerator pedal position sensor, 65 brake pedal, 66 brake pedal position sensor, 67 vehicle speed sensor.

Claims

[Claim 1] A vehicle control device is used in a vehicle including an electric motor having a permanent magnet and an alarm device that notifies an occupant of information, and controls at least the alarm device, The temperature data is input as time-series data of the temperature of the electric motor, and the margin time is output as the time until a predetermined demagnetization occurs in the permanent magnet. The margin time is estimated using the temperature data and a trained model obtained by training using a neural network, and the temperature data is used, and when the margin time is less than the predetermined time, the alarm device is controlled so that a predetermined alarm is issued. Vehicle control device.

Images