Motor control device

Abstract

A motor control device according to an embodiment of the present invention comprises: a motor driving unit including a plurality of switches and supplying driving power to drive a motor; a sensing unit that measures an output current of the motor driving unit; and a control unit that controls the plurality of switches, wherein the control unit estimates a phase current of the motor driving unit by using the output current measured by the sensing unit, estimates a temperature estimation parameter by using the estimated phase current, estimates the temperature of the motor by using the temperature estimation parameter, and controls the plurality of switches according to the estimated temperature.

Description

motor control unit

[0001] The present invention relates to a motor control device.

[0002] Motors generate heat during operation and are affected by temperature changes caused by heat. High-efficiency motor control requires temperature information. Attaching a temperature sensor to a motor reduces its effectiveness due to issues such as increased durability and sensor cost.

[0003] If a motor does not have a temperature sensor attached, high-frequency voltage or current can be injected to estimate the motor temperature, utilizing high-frequency parameters. Research has been conducted to estimate high-frequency rotor resistance and stator inductance using this method, and these values ​​can be mapped to temperature to indirectly estimate the temperature. In this case, interpolation using a one- or two-dimensional table is used to map the estimated parameters to the temperature of the area where the parameters were estimated. However, interpolation using a table limits high-performance mapping due to the nonlinearity of parameter estimation. Furthermore, the injection of high-frequency voltage or current can cause noise.

[0004] The technical problem to be solved by the present invention is to provide a motor control device and a motor temperature estimation method that estimate the temperature of a motor using a single current sensor.

[0005] In order to solve the above technical problem, a motor control device according to an embodiment of the present invention includes a motor driving unit including a plurality of switches and supplying driving power to drive a motor; a sensing unit measuring an output current of the motor driving unit; and a control unit controlling the plurality of switches, wherein the control unit estimates a phase current of the motor driving unit using the output current measured by the sensing unit, estimates a temperature estimation parameter using the estimated phase current, estimates a temperature of the motor using the temperature estimation parameter, and controls the plurality of switches according to the estimated temperature.

[0006] In addition, the temperature estimation parameter includes at least one of a winding resistance of a motor stator and a magnetic flux intensity of a motor rotor, and the control unit can estimate the temperature estimation parameter when an estimation condition for each preset temperature estimation parameter is satisfied.

[0007] In addition, the estimation condition for the winding resistance of the motor stator may include a condition that is less than or equal to a first speed value and greater than or equal to a first torque value, and the estimation condition for the magnetic flux intensity of the motor rotor may include a condition that is more than or equal to a second speed value and less than or equal to a second torque value.

[0008] Additionally, the first speed value may be smaller than the second speed value, and the first torque value may be larger than the second torque value.

[0009] In addition, the sensing unit includes one current sensor that measures the current of the DC link of the plurality of switches, and the control unit can estimate the three-phase current from the measured value of the current sensor in the effective voltage angle range.

[0010] In addition, the control unit can estimate the phase current by adjusting the timing of the switching cycle of the plurality of switches.

[0011] In addition, the temperature estimation parameter includes at least one of a winding resistance of a motor stator and a magnetic flux intensity of a motor rotor, and the control unit includes a neural network trained to estimate a temperature from the temperature estimation parameter, and can estimate a winding temperature from the winding resistance of the motor stator and a magnet temperature of the motor rotor using the neural network.

[0012] Additionally, the control unit can estimate the winding temperature or the magnet temperature as the temperature of the motor.

[0013] Additionally, the training set for the neural network may include speed, torque, position information, and temperature estimation parameters of the motor and actual temperatures of the configuration corresponding to the temperature estimation parameters.

[0014] Additionally, the motor drive unit may include an inverter.

[0015] In order to solve the above technical problem, a motor temperature estimation method according to one embodiment of the present invention includes a step of measuring an output current of a DC link of a motor drive unit that includes a plurality of switches and supplies a driving power for driving a motor; a step of estimating a phase current of the motor drive unit using the measured output current; a step of estimating a temperature estimation parameter using the estimated phase current; and a step of estimating a temperature of the motor using the temperature estimation parameter.

[0016] In addition, the temperature estimation parameter includes at least one of a winding resistance of a motor stator and a magnetic flux intensity of a motor rotor, and the step of estimating the temperature estimation parameter can estimate the temperature estimation parameter when an estimation condition for each preset temperature estimation parameter is satisfied.

[0017] In addition, the estimation condition for the winding resistance of the motor stator includes a condition of being less than or equal to a first speed value and greater than or equal to a first torque value, and the estimation condition for the magnetic flux intensity of the motor rotor includes a condition of being greater than or equal to a second speed value and less than or equal to a second torque value, and the first speed value may be less than the second speed value, and the first torque value may be greater than the second torque value.

[0018] In addition, the step of estimating the phase current of the motor drive unit can estimate the three-phase phase current from the measured output current in the effective voltage angle range.

[0019] In addition, the temperature estimation parameter includes at least one of a winding resistance of a motor stator and a magnetic flux intensity of a motor rotor, and the step of estimating the temperature of the motor may estimate the winding temperature from the winding resistance of the motor stator using a neural network trained to estimate the temperature from the temperature estimation parameter, estimate the magnet temperature of the motor rotor, and estimate the winding temperature or the magnet temperature as the temperature of the motor.

[0020] According to embodiments of the present invention, the temperature of a motor can be indirectly measured using only the sensors of the motor drive system, without the need for additional temperature sensors. This reduces the need for maintenance of the motor control device, which requires consideration for economic benefits and harsh environments. Furthermore, since it can be implemented in a motor control device, it eliminates the need for an additional external computing source.

[0021] In addition, since it is possible to estimate phase current and parameters using only a single current sensor of the DC-link, the need for maintenance and management of the current sensor can be reduced, and the cost of the current sensor can also be reduced. In addition, since it is possible to determine only when current restoration is possible without additional voltage injection for phase current restoration using only a single current sensor of the DC-link, and current restoration is performed only at that point, noise and efficiency deterioration can be prevented.

[0022] Furthermore, nonlinear characteristics that could not be effectively mapped using the existing table-based mapping method can be effectively mapped using the neural network-based method.

[0023] Figure 1 is a block diagram of a motor control device according to one embodiment of the present invention.

[0024] Fig. 2 illustrates an implementation example of a motor control device according to an embodiment of the present invention.

[0025] FIGS. 3 to 11 are drawings for explaining a process in which a motor control device according to an embodiment of the present invention estimates the temperature of a motor.

[0026] Fig. 12 is a flowchart of a motor temperature estimation method according to an embodiment of the present invention.

[0027] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings.

[0028] However, the technical idea of ​​the present invention is not limited to some of the embodiments described, but can be implemented in various different forms, and within the scope of the technical idea of ​​the present invention, one or more of the components between the embodiments can be selectively combined or substituted for use.

[0029] In addition, terms (including technical and scientific terms) used in the embodiments of the present invention may be interpreted as having a meaning that can be generally understood by a person of ordinary skill in the technical field to which the present invention belongs, unless explicitly and specifically defined and described, and terms that are commonly used, such as terms defined in a dictionary, may be interpreted in consideration of the contextual meaning of the relevant technology.

[0030] Additionally, the terms used in the embodiments of the present invention are intended to describe the embodiments and are not intended to limit the present invention.

[0031] In this specification, the singular may also include the plural unless specifically stated otherwise in the phrase, and when it is described as “A and / or at least one (or more) of B, C”, it may include one or more of all combinations that can be combined with A, B, C.

[0032] Additionally, in describing components of embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and are not intended to limit the nature, order, or sequence of the components.

[0033] And, when a component is described as being 'connected', 'coupled', or 'connected' to another component, it may include not only cases where the component is 'connected', 'coupled', or 'connected' directly to the other component, but also cases where the component is 'connected', 'coupled', or 'connected' by another component between the component and the other component.

[0034] Additionally, when described as being formed or arranged "above" or "below" each component, "above" or "below" includes not only cases where the two components are in direct contact with each other, but also cases where one or more other components are formed or arranged between the two components. Furthermore, when expressed as "above" or "below," the meaning may include not only the upward direction but also the downward direction based on one component.

[0035] Figure 1 is a block diagram of a motor control device according to one embodiment of the present invention.

[0036] A motor control device (100) according to an embodiment of the present invention is composed of a motor driving unit (110), a sensing unit (120), and a control unit (130), and may include a power supply unit, a memory, or a communication unit (not shown).

[0037] The motor drive unit (110) includes a plurality of switches and supplies driving power to drive the motor (200). The motor (200) supplying the driving power may be a three-phase motor, and the motor drive unit (110) may be configured with a plurality of switches to supply three-phase power to the motor (200). As shown in Fig. 2, it may be configured with three upper switches and three lower switches connected in series with each of the upper switches, thereby supplying three-phase power to the motor (200). The motor drive unit (110) may be configured with an inverter.

[0038] The motor (200) may be a position-control motor that controls position, or a clutch-driven motor that controls position. The clutch may be a device that controls the power transmission of a vehicle, and may be a clutch-driven motor of a vehicle including an artificial intelligence neural network. It goes without saying that the clutch may be used to control various other motors.

[0039] The sensing unit (120) measures the output current of the motor driving unit (110). The sensing unit (120) may include a current sensor. The sensing unit (120) may include a shunt resistor for measuring the current. The motor driving unit (110) may be configured as a three-phase power switch, as shown in FIG. 2, and the sensing unit (120) may be configured as a single shunt resistor connected to the output terminal of the DC link of the switch. The difference in voltage between the two ends of the shunt resistor may be used to measure the current flowing through the shunt resistor.

[0040] The control unit (130) controls a plurality of switches. The control unit (130) can supply driving power to the motor (200) by controlling the on / off of the plurality of switches. The plurality of switches of the motor drive unit (110) can be configured as MOSFETs, and the control unit (130) can supply a gate voltage to each switch to turn it on / off, thereby supplying three-phase power to the motor (200).

[0041] The control unit (130) can estimate the temperature when controlling a plurality of switches and control the plurality of switches according to the estimated temperature. The motor (200) may generate heat during operation or its temperature may change depending on the environment. Since the efficiency of the motor (200) is affected by the temperature, temperature information of the motor (200) is required for high-efficiency control of the motor (200). To this end, the control unit (130) estimates the temperature of the motor (200) using the output current measured by the sensing unit (120).

[0042] The control unit (130) estimates the phase current of the motor drive unit (110) using the output current measured by the sensing unit (120), estimates a temperature estimation parameter using the estimated phase current, estimates the temperature of the motor using the temperature estimation parameter, and controls the plurality of switches according to the estimated temperature.

[0043] The control unit (130) can estimate a temperature estimation parameter used to estimate the temperature from the output current measured by the sensing unit (120), and estimate the temperature of the motor using the temperature estimation parameter.

[0044] Here, the temperature estimation parameter may include at least one of the winding resistance of the motor stator and the magnetic flux intensity of the motor rotor. The motor (200) includes a stator and a rotor. The rotor may be a mover. Here, the stator may include a winding coil, and the rotor may include a magnet. When power is supplied to the winding coil, an induced current is generated, which may cause the magnet to rotate or move, thereby driving the motor. The motor may rotate or move in one direction or both directions. The motor (200) may be a position control motor that does not continuously rotate or move, but rotates or moves at different positions. For example, it may be a clutch drive motor.

[0045] The control unit (130) can estimate the temperature estimation parameter if the estimation conditions for each preset temperature estimation parameter are satisfied. The control unit (130) can estimate the temperature estimation parameter satisfying the estimation conditions when the estimation conditions are satisfied, rather than estimating the temperature estimation parameter in real time or periodically. The estimation conditions may include conditions suitable for measuring the temperature estimation parameter.

[0046] If the estimation conditions are not satisfied, the temperature estimation parameters may not be estimated. Alternatively, the temperature estimation parameters may be estimated in real time or periodically without estimation conditions, or when an alarm is triggered or a command is received from an external controller.

[0047] As shown in Fig. 3, when the stator winding resistance estimation condition is satisfied, the stator winding resistance estimation can be performed, and when the rotor magnet flux intensity estimation condition is satisfied, the rotor magnet flux intensity estimation can be performed.

[0048] The estimation condition for the winding resistance of the motor stator may include a condition of being less than or equal to a first speed value and greater than or equal to a first torque value, and the estimation condition for the magnetic flux intensity of the motor rotor may include a condition of being greater than or equal to a second speed value and less than or equal to a second torque value. Here, the first speed value may be less than the second speed value, and the first torque value may be greater than the second torque value.

[0049] The control unit (130) can perform temperature estimation parameter estimation for the winding resistance of the motor stator when the speed of the motor is lower than or equal to the first speed value and the torque of the motor is higher than or equal to the first torque value. That is, the winding resistance of the motor stator can be estimated under a condition in which a large torque is applied to the motor (200) at a low speed. For example, the winding resistance of the motor stator can be estimated in situation 1 of FIG. 4. Situation 1 of FIG. 4 may be a condition in which a large torque is applied while the motor (200) is stopped. When the motor (200) is a clutch-driven motor, the clutch may be pressed to fix the position, but a situation in which a large force is applied may be occurred.

[0050] The control unit (130) can perform temperature estimation parameter estimation for the magnetic flux intensity of the motor rotor when the speed of the motor is equal to or greater than the second speed value and the torque of the motor is equal to or less than the second torque value. That is, the magnetic flux intensity of the motor rotor can be estimated under a condition in which a low torque is applied to the motor (200) at a high speed. For example, the magnetic flux intensity of the motor rotor can be estimated in situation 2 of FIG. 4. Situation 2 of FIG. 4 may be a condition in which a low torque is applied or the magnitude of the torque is reduced while the motor (200) moves quickly. When the motor (200) is a clutch-driven motor, the force applied to the clutch may be reduced while the clutch is pressed, thereby reducing the force applied to the clutch and causing the clutch to move quickly.

[0051] In case of situation 3 or 4 in Fig. 4, it is not suitable to estimate the winding resistance of the motor stator or the magnetic flux intensity of the motor rotor. That is, in that state, the temperature estimation parameter estimation condition is not satisfied, and therefore, temperature estimation parameter estimation may not be performed.

[0052] The winding resistance of the motor stator or the magnetic flux strength of the motor rotor can be estimated using the following mathematical formula.

[0053] [Mathematical Formula 1]

[0054]

[0055]

[0056] The above mathematical equation is a formula that organizes the voltage equation into the winding resistance of the motor stator or the magnetic flux of the motor rotor. is the winding resistance of the motor stator, is the magnetic flux intensity of the motor rotor.

[0057] Here, the superscript * indicates the command value, and above the symbol The letters represent the estimated values ​​of the corresponding variables. represents the dq-axis voltage and current on the rotor synchronous reference frame. And ω_r represents the rotor electrical angular speed, and L_dq represents the dq-axis inductance, respectively. As shown in the above formula, depending on the speed and torque ranges, and The weight of the protest related to this will vary depending on the estimated conditions. and Each temperature estimation parameter can be derived under conditions suitable for estimating.

[0058] The control unit (130) can estimate the phase current of the three phases from the measured values ​​of the current sensor in the effective voltage angle range. The sensing unit (120) may include one current sensor that measures the current of the DC link of the plurality of switches, and the control unit (130) must measure all three phases using one current sensor, but it is difficult to obtain information on each phase at all times. Fig. 5 shows the voltage angle, and there is a region (510) where the phase current can be restored with the sensing value of one current sensor and a region (520) where it is difficult to restore.

[0059] The control unit (130) is in the effective voltage angle range (510), which is a restorable area. The temperature estimation parameters can be derived by restoring the current. In restoring the current, the current can be restored using the DPWM (Discontinuous PWM) method rather than the SVPWM (Space-Vector PWM) method.

[0060] Here, SVPWM (Space Vector Modulation) is a method of generating a PWM (Pulse Width Modulation) signal to control multiple switches, and generating a modulated voltage required to drive the motor at the desired speed or torque, and DPWM (Discontinuous Pulse Width Modulation) is a method of modulating the switching point so that it is not continuous.

[0061] When restoring current through the DPWM method of Fig. 5, an area (520) where restoration is theoretically impossible is created, as shown in Fig. 6, and in that area, errors in values ​​may occur, as shown in Fig. 7. To prevent this, temperature estimation parameter calculation can be performed in the restorable area (510).

[0062] The control unit (130) can estimate the phase current by adjusting the timing of the switching cycle of the plurality of switches. The control unit (130) can expand the range of the effective voltage angle, which is the current recovery possible region, by adjusting the timing of the switching cycle of the plurality of switches. The current recovery impossible region (520) can be divided into a thick region (521) and a thin region (522), as shown in FIG. 8. In the region 521, the duty at which the switches of each phase (A, B, C) of the plurality of switches maintain an on state is different, as shown in FIG. 8. In the region 521, the turn-on / off timing of phase A and the turn-on / off timing of phase B can be adjusted, thereby creating a section in which they are turned on alone, and thereby current can be recovered even at the corresponding voltage angle. In the case of the 522 area, it is difficult to create conditions for current restoration by simply adjusting the timing of the switching cycle, and the duty must be increased, which requires additional voltage application, which may cause noise such as noise and vibration.

[0063] The control unit (130) can widen the effective voltage angle by adjusting the switching cycle timing only for areas where current restoration is possible by adjusting the switching cycle timing. Thus, as shown in FIG. 9, a significant portion of the current restoration-impossible area (520) can be changed to a current restoration-enabled area (530). This enables more accurate current restoration.

[0064] The control unit (130) can estimate more accurate temperature estimation parameters by performing a current restoration process and a temperature estimation parameter estimation process.

[0065] The control unit (130) includes a neural network trained to estimate temperature from temperature estimation parameters, and can estimate the winding temperature from the winding resistance of the motor stator and the magnet temperature of the motor rotor using the neural network.

[0066] The control unit (130) can estimate the temperature using the estimated temperature estimation parameter and the driving information at the corresponding point in time. At this time, more accurate temperature estimation is possible using a neural network. Here, the neural network may include a feedforward neural network (FNN), and may include various neural networks such as an artificial neural network (ANN), a convolutional neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN).

[0067] A neural network model can be formed as follows:

[0068] [Equation 2]

[0069]

[0070] Here, the input data is are the speed, position, and torque information at the part where the magnetic flux of the rotor is estimated, respectively. are the speed, position, and torque information at the part where the winding resistance of the stator is estimated, respectively. The output data of the neural network is is the temperature of the motor rotor magnet estimated from the magnetic flux intensity of the motor rotor, is the temperature of the motor stator winding estimated from the winding resistance of the motor stator. The neural network is a neural network model that estimates the temperature of each part using input data. As shown in Fig. 10, the input data is normalized (scaled) to match the size level between variables, and the output value goes through a process of matching the size with the actual physical value through the inverse process of normalization for each output data.

[0071] A neural network can be trained to estimate temperature from temperature estimation parameters, and a training set for the neural network can include speed, torque, position information, and temperature estimation parameters of the motor and actual temperatures of a configuration corresponding to the temperature estimation parameters.

[0072] The control unit (130) can estimate the winding temperature or the magnet temperature as the temperature of the motor (200). If one of the winding temperature or the magnet temperature is estimated, the control unit (130) can estimate the corresponding temperature as the temperature of the motor (200), and if the winding temperature and the magnet temperature are estimated, the higher temperature of the two temperatures can be estimated as the temperature of the motor (200).

[0073] Fig. 11 is a result of comparing the motor temperature estimation result of the motor control device according to an embodiment of the present invention with actual data, and it can be confirmed that the difference between the temperature estimation value and the actual temperature is within ±5 degrees.

[0074] Fig. 12 is a flowchart of a motor temperature estimation method according to an embodiment of the present invention. A detailed description of each step in Fig. 11 corresponds to the detailed description of Figs. 1 to 11, and thus, any redundant description will be omitted.

[0075] In order to estimate the temperature of the motor using a single current sensor, the output current of the DC link of the motor drive unit is measured in step S11, and the phase current of the motor drive unit is estimated using the measured output current in step S12. Here, the motor drive unit includes a plurality of switches and can supply driving power to drive the motor.

[0076] In estimating the phase current of the above motor drive unit, the three-phase phase current can be estimated from the measured output current within the effective voltage angle range. In addition, the effective voltage angle range can be expanded by adjusting the timing of the switching cycles of multiple switches, thereby estimating the phase current.

[0077] Thereafter, in step S13, a temperature estimation parameter is estimated using the estimated phase current. The temperature estimation parameter includes at least one of the winding resistance of the motor stator and the magnetic flux intensity of the motor rotor, and steps S11 to S13 may be performed to estimate the temperature estimation parameter when the estimation conditions for each preset temperature estimation parameter are satisfied.

[0078] Here, the estimation condition for the winding resistance of the motor stator includes a condition that is less than or equal to a first speed value and greater than or equal to a first torque value, and the estimation condition for the magnetic flux intensity of the motor rotor includes a condition that is greater than or equal to a second speed value and less than or equal to a second torque value, and the first speed value may be less than the second speed value, and the first torque value may be greater than the second torque value. That is, the winding resistance of the motor stator is estimated under low-speed and high-torque conditions, and the magnetic flux intensity of the motor rotor is estimated under high-speed and low-torque conditions.

[0079] After estimating the temperature estimation parameters, the temperature of the motor is estimated at step S14 using the temperature estimation parameters. In estimating the temperature of the motor, a neural network trained to estimate the temperature from the temperature estimation parameters is used to estimate the winding temperature from the winding resistance of the motor stator, estimate the magnet temperature of the motor rotor, and estimate the winding temperature or the magnet temperature as the temperature of the motor.

[0080]

[0081] Embodiments of the present invention allow for estimating motor temperature using a single current sensor, without the need for additional temperature sensors. This reduces the need for maintenance of motor control devices, which require consideration for economic benefits and harsh environments. Furthermore, since it can be implemented in a motor control device, it eliminates the need for additional external computing resources.

[0082] In addition, since it is possible to estimate phase current and parameters using only a single current sensor of the DC-link, the need for maintenance and management of the current sensor can be reduced, and the cost of the current sensor can also be reduced. In addition, since it is possible to determine only when current restoration is possible without additional voltage injection for phase current restoration using only a single current sensor of the DC-link, and current restoration is performed only at that point, noise and efficiency deterioration can be prevented.

[0083] Furthermore, nonlinear characteristics that could not be effectively mapped using the existing table-based mapping method can be effectively mapped using the neural network-based method.

[0084] Meanwhile, embodiments of the present invention can be implemented as computer-readable code on a computer-readable recording medium. Computer-readable recording media include all types of recording devices that store data that can be read by a computer system.

[0085] As described above, the present invention has been described with specific details such as specific components and limited examples and drawings, but these are provided only to help a more general understanding of the present invention, and the present invention is not limited to the above examples, and those with ordinary knowledge in the field to which the present invention pertains can make various modifications and variations from this description.

[0086] Therefore, the idea of ​​the present invention should not be limited to the described embodiments, and all things that are equivalent or equivalent to the claims described below as well as the claims are considered to fall within the scope of the idea of ​​the present invention.

Claims

1. A motor drive unit including a plurality of switches and supplying driving power to drive a motor; A sensing unit that measures the output current of the above motor driving unit; and A control unit that controls the above plurality of switches is included, The above control unit, A motor control device that estimates the phase current of the motor drive unit using the output current measured by the sensing unit, estimates a temperature estimation parameter using the estimated phase current, estimates the temperature of the motor using the temperature estimation parameter, and controls the plurality of switches according to the estimated temperature.

2. In paragraph 1, The above temperature estimation parameter includes at least one of the winding resistance of the motor stator and the magnetic flux strength of the motor rotor, The above control unit, A motor control device that estimates the temperature estimation parameter when the estimation condition for each preset temperature estimation parameter is satisfied.

3. In paragraph 2, The estimation conditions for the winding resistance of the above motor stator include conditions below the first speed value and above the first torque value, A motor control device including a condition that the estimated condition for the magnetic flux strength of the motor rotor is greater than or equal to a second speed value and less than or equal to a second torque value.

4. In paragraph 3, A motor control device wherein the first speed value is smaller than the second speed value and the first torque value is larger than the second torque value.

5. In paragraph 1, The above sensing unit, comprising one current sensor for measuring the current of the DC link of the plurality of switches; The above control unit, A motor control device that estimates three-phase current from the measured values ​​of the current sensor in the effective voltage range.

6. In paragraph 5, The above control unit, A motor control device that estimates the phase current by adjusting the switching timing of the switching cycle of the plurality of switches.

7. In paragraph 1, The above temperature estimation parameter includes at least one of the winding resistance of the motor stator and the magnetic flux strength of the motor rotor, The above control unit, A motor control device comprising a neural network trained to estimate temperature from temperature estimation parameters, and estimating winding temperature from winding resistance of the motor stator and estimating magnet temperature of the motor rotor using the neural network.

8. In paragraph 7, The above control unit, A motor control device that estimates the temperature of the motor based on the temperature of the winding or the temperature of the magnet.

9. In paragraph 7, The training set for the above neural network is, A motor control device including speed, torque, position information, and temperature estimation parameters of the motor and actual temperature of the configuration corresponding to the temperature estimation parameters.

10. In paragraph 1, The above motor drive unit is a motor control device including an inverter.

Images