JPWO2020157919A1 - Machine learning device and motor control system - Google Patents

Abstract

The machine learning device (10) according to the present invention learns the state variables of the motor driving device (70) that drives the motor (80). The motor drive device (70) includes a rectifier circuit (71), an electrolytic capacitor (72), and an inverter (73). The state variable contains at least one of data on AC power from the AC power source (60), data on DC power received by the electrolytic capacitor (72), and data on AC power received by the motor (80). The machine learning device (10) includes a storage unit (12) and a control unit (11). The storage unit (12) stores a first function (Qt1) in which a state variable, a drive frequency (fc) of the motor (80), and an evaluation value of the drive frequency (fc) are associated with each other. The control unit (11) updates the evaluation value of the drive frequency (fc) according to the degree to which the change of the state variable deteriorates the electrolytic capacitor (72), and outputs the first function (Qt1).

Description

The present invention relates to a machine learning device and a motor control system.

Conventionally, it is known that an electrolytic capacitor can be used as a smoothing capacitor for a motor drive device. For example, Japanese Patent Application Laid-Open No. 2014-103703 (Patent Document 1) discloses an inverter control device that switches a connection state between a smoothing capacitor and a bus and an inverter control method according to temperature conditions. According to the inverter control device, the motor can be driven stably and the life of the smoothing capacitor can be extended.

Japanese Unexamined Patent Publication No. 2014-103703

The motor control device disclosed in Patent Document 1 considers that the case where the ambient temperature of the motor control device is equal to or higher than the reference temperature is severe with respect to the life of the electrolytic capacitor, and disconnects the electrolytic capacitor from the bus in that case. .. The reference temperature is arbitrarily set according to the temperature characteristics of the life of the electrolytic capacitor. The life of the electrolytic capacitor can be calculated by measuring the electrolytic capacitor under various temperature conditions at the time of evaluation of the prototype.

The environment in which the electrolytic capacitor is actually used changes with the passage of time, and often deviates from the environment in the actual machine experiment or the environment in which the reference temperature is determined. Therefore, the protective operation of the electrolytic capacitor using the predetermined reference temperature may not be suitable for the deterioration state of the electrolytic capacitor in the environment in which the electrolytic capacitor is actually used.

The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide control information suitable for the environment in which the electrolytic capacitor is actually used.

The machine learning device according to the present invention learns the state variables of the motor driving device that drives the motor. The motor drive includes a rectifier circuit, an electrolytic capacitor, and an inverter. The rectifier circuit converts the AC power from the AC power supply into DC power. The electrolytic capacitor smoothes the DC power from the rectifier circuit. The inverter converts DC power from the electrolytic capacitor and outputs AC power to the motor. The state variable contains at least one of data about AC power from an AC power source, data about DC power received by an electrolytic capacitor, and data about AC power received by a motor. The machine learning device includes a storage unit and a control unit. The storage unit stores a first function in which the state variable, the drive frequency of the motor, and the evaluation value of the drive frequency are associated with each other. The control unit updates the evaluation value of the drive frequency according to the degree to which the change of the state variable deteriorates the electrolytic capacitor, and outputs the first function.

According to the machine learning apparatus according to the present invention, the electrolytic capacitor is actually used by updating the evaluation value of the drive frequency of the motor in the first function according to the degree to which the change of the state variable deteriorates the electrolytic capacitor. It is possible to provide control information suitable for the environment.

It is a functional block diagram which shows the structure of the motor control system which concerns on Embodiment 1. FIG. It is a flowchart which shows the flow of the learning process about the drive frequency performed by the control part of FIG. It is a flowchart which shows the flow of protection processing of the electrolytic capacitor performed by the inverter control device of FIG. It is a functional block diagram which shows the structure of the motor control system which concerns on Embodiment 2. FIG. It is a flowchart which shows the flow of the learning process about the predicted life performed by the control part of FIG.

Hereinafter, embodiments will be described in detail with reference to the drawings. In principle, the same or corresponding parts in the drawings are designated by the same reference numerals and the description is not repeated.

Embodiment 1.
FIG. 1 is a functional block diagram showing the configuration of the motor control system 1 according to the first embodiment. The motor control system 1 controls the drive of the motor 80 by controlling the motor drive device 70.

As shown in FIG. 1, the motor drive device 70 includes a rectifier circuit 71, an electrolytic capacitor 72, and an inverter 73. The rectifier circuit 71 converts the three-phase (UVW phase) AC power from the AC power supply 60 into DC power. The electrolytic capacitor 72 smoothes the DC power from the rectifier circuit 71. The inverter 73 converts the DC power from the electrolytic capacitor 72 and outputs the three-phase AC power to the motor 80.

The motor control system 1 includes a machine learning device 10, an inverter control device 20, an unbalance rate calculation unit 51, a ripple current measurement unit 52, a ripple voltage measurement unit 53, and a load current measurement unit 54. The machine learning device 10 includes a control unit 11 and a memory 12 (storage unit).

The unbalance rate calculation unit 51 calculates the unbalance rates Ruv, Rvw, and Rwoo between the three phases of the three-phase AC power output from the AC power supply 60, and the control unit 11 and the inverter control device 20 receive the unbalance rate Ruv. Outputs Rvw and Rwoo. The unbalance rate between each phase is the ratio of the value obtained by subtracting the average voltage Vave from each phase voltage to the average voltage Vave of the interphase voltages Vuv, Vvw, and Vwoo (unbalance rate between each phase = (each phase voltage-Vave)). / Vave) is calculated. Vuv is the voltage between the U phase and the V phase. The interphase voltage Vvw is the voltage between the V phase and the W phase. The interphase voltage Vwoo is the voltage between the W phase and the U phase. The average voltage Vave is expressed as (Vuv + Vvw + Vwoo) / 3. The unbalance rate Ruv is expressed as (Vuv-Vave) / Vave. The unbalance rate Rvw is expressed as (Vvw-Vave) / Vave. The unbalance rate Rwoo is expressed as (Vwoo-Vave) / Vave.

The ripple current measuring unit 52 detects the ripple current Irp flowing from the bus to the electrolytic capacitor 72, and outputs the ripple current Irp to the control unit 11 and the inverter control device 20. The ripple voltage measuring unit 53 detects the ripple voltage Vrp generated between the bus and the electrolytic capacitor 72, and outputs the ripple voltage Vrp to the control unit 11 and the inverter control device 20. The load current measuring unit 54 detects the U-phase current Iu, the V-phase current Iv, and the W-phase current Iw output from the inverter 73, and applies the load currents Iu, Iv, and Iw to the control unit 11 and the inverter control device 20. Output.

The control unit 11 learns the state variables of the motor drive device 70 including the data affecting the deterioration of the electrolytic capacitor 72 by using the reinforcement learning algorithm. Reinforcement learning is a reward by repeating that an agent (behavior) in an environment in which a reward is obtained according to a selected action selects an action based on the state of the environment observed at each time. It is a learning algorithm that learns a policy to maximize the expected value of the cumulative value of.

As a cause of deterioration of the electrolytic capacitor 72, the temperature rise due to ESR (Equivalent Series Resistance) of the electrolytic capacitor 72 when the ripple current Irp flows through the electrolytic capacitor 72 can be mentioned. It is known that the ripple current Irp increases as the voltage imbalance rate of the AC power supply 60 increases, and increases as the load current of the motor 80 increases. Therefore, the state variables are the unbalance rate Ruv, Rvw, and Rwoo (data on AC power from the AC power supply), ripple current Irp, and ripple voltage Vrp (electrolytic capacitor) as data affecting the deterioration of the electrolytic capacitor 72. Includes data on DC power received) and load currents Iu, Iv, and Iw (data on AC power received by the motor). The state variable of the motor drive device 70 does not have to include all of the unbalance rate, the ripple current, the ripple voltage, and the load current, and may include at least one of them.

The control unit 11 stores the state variables in the external storage device 90. Examples of the external storage device 90 include a storage device that can be used in a cloud service on the Internet.

Control unit 11, using the general following formula used (1) in Q-learning, and the state s _t of the motor drive device 70, and the action a _t a driving frequency of the motor 80, the evaluation of behavioral a _t the value a is Q value and value behavior associated functions _Q to update _{(s t, a t) (} Q table Qt1). The control unit 11 outputs the Q table Qt1 to the inverter control device 20 as control information of the inverter 73. The Q table Qt1 is stored in the memory 12.

In the formula (1), the state s _t represents a state at time t, is determined by the observed state variable at time t. Time t is the number of times the action selection is repeated. _{The state s 0} when t = 0 is the initial state. If the action _{a t} in state _{s t} is selected, along with reward _{r t + 1} is obtained, the state of the motor drive device 70, a transition from the state _{s t} in _{s t + 1.} Reward _{r t + 1} is associated with the action _{a t} in state _{s t,} stored in the memory 12. The action b is an action that can be selected _{in the state st + 1.} α is the learning rate and γ is the discount rate. The reinforcement learning algorithm used in the control unit 11 is not limited to Q-learning, and may be, for example, TD (Temporal Difference) learning.

The inverter control device 20 uses the Q table Qt1 from the machine learning device 10 to determine the drive frequency having the highest evaluation value in the state specified by the current state variable as the drive frequency fc of the motor 80. The inverter control device 20 outputs the command signal cm corresponding to the drive frequency fc to the inverter 73, and outputs the drive frequency fc to the machine learning device 10. The inverter control device 20 protects the electrolytic capacitor 72 according to the ripple current Irp and the ripple voltage Vrp.

The inverter 73 outputs load currents Iu, Iv, and Iw to the motor 80 by switching the connection state of the switching element between on and off according to the command signal cm from the inverter control device 20. The inverter 73 has either a power running operation (forward conversion operation) for converting AC power into DC power or a regeneration operation (reverse conversion operation) for converting DC power into AC power according to the command signal cm from the inverter control device 20. To do. Corresponding to the operation of the inverter 73, the motor 80 performs an acceleration operation, a constant speed operation, or a deceleration operation.

Generally, the higher the ambient temperature of the motor drive device 70, the greater the influence on the life of the electrolytic capacitor 72. Therefore, as a protective operation for the electrolytic capacitor 72, an operation of disconnecting the electrolytic capacitor 72 from the bus when the ambient temperature of the motor drive device 70 is equal to or higher than the reference temperature can be mentioned. The reference temperature can be appropriately determined by an actual machine experiment or a simulation according to the temperature characteristics of the life of the electrolytic capacitor 72.

The environment in which the electrolytic capacitor 72 is actually used changes with the passage of time, and often deviates from the environment in the actual machine experiment or the environment in which the reference temperature is determined. Therefore, the protective operation of the electrolytic capacitor 72 using the predetermined reference temperature may not be suitable for the deterioration state of the electrolytic capacitor 72.

Therefore, in the motor control system 1, the evaluation value of the drive frequency of the motor 80 is repeatedly evaluated by the machine learning device 10 according to the degree to which the electrolytic capacitor 72 affects the deterioration of the electrolytic capacitor 72 in the environment where the electrolytic capacitor 72 is actually used. Will be updated to. As a result, the machine learning device 10 can provide the inverter control device 20 with control information suitable for the environment in which the electrolytic capacitor 72 is actually used. According to the motor control system 1, deterioration of the electrolytic capacitor 72 can be suppressed by selecting a drive frequency that has a small effect on the deterioration of the electrolytic capacitor 72 in an environment where the electrolytic capacitor 72 is actually used.

FIG. 2 is a flowchart showing the flow of learning processing regarding the drive frequency performed by the control unit 11 of FIG. The process shown in FIG. 2 is called every time the drive frequency fc is output from the inverter control device 20 by a main routine (not shown) that performs integrated control of the machine learning device 10. In the following, the step is simply referred to as S. The inverter control device 20 outputs the command signal cm corresponding to the drive frequency fc equal to or higher than the lower limit value to the inverter 73, and outputs the drive frequency fc to the machine learning device 10, so that the process shown in FIG. 2 is first performed. Called to. The drive frequency of the motor 80 when the process shown in FIG. 2 is first called may be randomly determined in the range of the lower limit value or more. Initial values are preset for the rewards associated with the state and the drive frequency (behavior). Initial values (for example, 0) are preset for each evaluation value in the Q table Qt1.

Hereinafter, the case where the number of learning processes shown in FIG. 2 is the (m + 1) th time will be described. m is a natural number of 0 or more. In the last m-th, the selected driving frequency fc _m is as action a _m, state determined by the state variables and transitions from s _m to s _{m + 1.} Let the reward associated with the drive frequency fc _{m be rm + 1} . The state variable referred to in the (m + 1) th learning process is a state variable corresponding to the state sm _{+ 1.}

As shown in FIG. 2, the control unit 11 determines in S101 whether or not the ripple current Irp is equal to or less than the threshold value Is1 (first reference value). The threshold value Is1 can be appropriately determined by an actual machine experiment or a simulation. When the ripple current Irp is equal to or less than the threshold value Is1 (YES in S101), the control unit 11 _{increases the reward rm + 1} in S102 and advances the process to S104. When the ripple current Irp is larger than the threshold value Is1 (NO in S101), the control unit 11 _{reduces the reward rm + 1} in S103 and advances the process to S104.

The control unit 11 determines in S104 whether or not the ripple voltage Vrp is equal to or less than the threshold value Vth1 (second reference value). The threshold value Vth1 can be appropriately determined by an actual machine experiment or a simulation. When the ripple voltage Vrp is equal to or less than the threshold value Vth1 (YES in S104), the control unit 11 _{increases the reward rm + 1} in S105 and advances the process to S107. When the ripple voltage Vrp is larger than the threshold value Vth1 (NO in S104), the control unit 11 _{reduces the reward rm + 1} in S106 and advances the process to S107.

The control unit 11 determines in S107 whether or not the maximum values Rmax of the unbalance rates Ruv, Rvw, and Rwoo are equal to or less than the threshold value Rth (reference ratio). The threshold value Rth can be appropriately determined by an actual experiment or a simulation. When the maximum value Rmax is equal to or less than the threshold value Rth (YES in S107), the control unit 11 assumes that no voltage imbalance has occurred in the AC power supply 60, _{increases the reward rm + 1} in S108, and proceeds to the process in S110. When the maximum value Rmax is larger than the threshold value Rth (NO in S107), the control unit 11 assumes that a voltage imbalance has occurred in the AC power supply 60, _{reduces the reward rm + 1} in S109, and proceeds to the process in S110.

The control unit 11 determines whether or not the load currents Iu, Iv, and Iw are optimum in S110. Specifically, the control unit 11 determines in S110 whether or not each of the load currents Iu, Iv, and Iw is within the permissible range (reference range). The permissible range is calculated from the unbalance rates Ruv, Rvw, and Rw. When each of the load currents Iu, Iv, and Iw is within the permissible range (reference range) (YES in S110), the control unit 11 _{increases the reward rm + 1} in S111 and advances the process to S113. When any of the load currents Iu, Iv, and Iw is out of the permissible range (NO in S110), the control unit 11 _{reduces the reward rm + 1} in S112 and advances the process to S113. The control unit 11 updates the Q table Qt1 using the equation (1) in S113 and returns the process to the main routine.

By calling the process shown in FIG. 2 every time the drive frequency fc is changed, the evaluation value of the drive frequency, which has little influence on the deterioration of the electrolytic capacitor 72 in the environment where the electrolytic capacitor 72 is actually used, becomes high. The machine learning device 10 can provide the inverter control device 20 with Q table Qt1, which is control information adapted to the environment in which the electrolytic capacitor 72 is actually used.

The processing performed by the control unit 11 may be realized by a computer such as a CPU (Central Processing Unit) executing a program stored in the memory 12, or is realized by a dedicated hardware processing circuit. May be done.

FIG. 3 is a flowchart showing a flow of protection processing of the electrolytic capacitor 72 performed by the inverter control device 20 of FIG. The process shown in FIG. 3 is called at regular time intervals by a main routine (not shown) that performs integrated control of the inverter control device 20.

As shown in FIG. 3, the inverter control device 20 determines in S121 whether or not the ripple current Irp is equal to or less than the threshold value Is2 (third reference value). The threshold value Is2 is larger than the threshold value Is1. The threshold value Is2 is an upper limit value of the current that can be passed through the electrolytic capacitor 72, and is predetermined. When the ripple current Irp is equal to or less than the threshold value Is2 (YES in S121), the inverter control device 20 advances the process to S122. When the ripple current Irp is larger than the threshold value Is2 (NO in S121), the inverter control device 20 advances the process to S123.

The inverter control device 20 determines in S122 whether or not the ripple voltage Vrp is equal to or less than the threshold value Vth2 (fourth reference value). The threshold value Vth2 is larger than the threshold value Vth1. The threshold value Vth2 is an upper limit value of a voltage that can be applied to the electrolytic capacitor 72, and is predetermined. When the ripple voltage Vrp is equal to or less than the threshold value Vth2 (YES in S122), the inverter control device 20 returns the process to the main routine. When the ripple voltage Vrp is larger than the threshold value Vth2 (NO in S122), the inverter control device 20 advances the process to S123. The inverter control device 20 outputs a stop command of the motor 80 to the inverter 73 in S123 and returns the process to the main routine. The inverter 73 stops the motor 80 in response to a stop command from the inverter control device 20.

The processing performed in the inverter control device 20 may be realized by executing a program stored in the memory of the inverter control device 20 by a computer such as a CPU, or a dedicated hardware processing circuit (semiconductor). It may be realized by an integrated circuit).

As described above, according to the motor control system according to the first embodiment, deterioration of the electrolytic capacitor can be suppressed by controlling the motor using control information suitable for the environment in which the electrolytic capacitor is actually used. ..

Embodiment 2.
In the first embodiment, in the framework of reinforcement learning, a case where the machine learning device raises the evaluation value of the drive frequency having a small influence on the deterioration of the electrolytic capacitor by repeating the learning process with the drive frequency of the motor as an action has been described. In the second embodiment, a case where the machine learning device raises the evaluation value of the predicted life of the electrolytic capacitor having a small relative error with the reference life by repeating the learning process by using the life of the electrolytic capacitor as an action together with the motor drive frequency will be described. ..

FIG. 4 is a functional block diagram showing the configuration of the motor control system 2 according to the second embodiment. The configuration of the motor control system 2 is such that the control unit 11 in FIG. 1 is replaced with 11B, and the life prediction device 30 and the display device 40 are added. The control unit 11B has the function of the control unit 11. Since the configurations other than these are the same, the description will not be repeated.

With reference to FIG. 4, the control unit 11B uses the equation (1), and a state _{s t} of the motor drive device 70, and the action _{a t} the prediction lifetime of the electrolytic capacitor 72, in evaluation value of action _{a t} action value and there Q value associated function _Q to update _{(s t, a t) (} Q table Qt2), and outputs a Q table Qt2 the life predicting device 30. The Q table Qt2 is stored in the memory 12.

The control unit 11B acquires data on the life of the electrolytic capacitor 72 from the external server 100 in order to update the evaluation value of the predicted life. The data regarding the life of the electrolytic capacitor 72 is experimental data, simulation data, or a map in which the state variable and the life are associated with the electrolytic capacitor of the same type as the electrolytic capacitor 72. Data on the life of the electrolytic capacitor 72 is provided, for example, by the manufacturer of the electrolytic capacitor 72. The data regarding the life of the electrolytic capacitor 72 may be stored in the memory 12 in advance. The control unit 11B calculates the reference life LSr from the state variable and the data regarding the life of the electrolytic capacitor 72.

The life prediction device 30 receives the unbalance rates Ruv, Rvw, and Rwoo from the unbalance rate calculation unit 51. The life prediction device 30 receives the ripple current Irp from the ripple current measuring unit 52. The life prediction device 30 receives the ripple voltage Vrp from the ripple voltage measuring unit 53. The life prediction device 30 receives load currents Iu, Iv, and Iw from the load current measuring unit 54.

The life prediction device 30 outputs the predicted life LSp having the highest evaluation value in the state specified by the state variable to the display device 40 by using the Q table Qt2 from the control unit 11B. The life prediction device 30 may output the replacement time of the electrolytic capacitor 72 to the display device 40 together with the predicted life LSp. The display device 40 displays the information from the life prediction device 30.

The environment in which the data regarding the life of the electrolytic capacitor 72 is acquired may differ from the environment in which the electrolytic capacitor 72 is actually used. Further, in the motor control system 2, the drive frequency is selected so as to reduce the influence on the deterioration of the electrolytic capacitor 72. Therefore, the reference life LSr derived from the data on the life of the electrolytic capacitor 72 may deviate from the life of the electrolytic capacitor 72 in the environment in which the electrolytic capacitor 72 is actually used.

Therefore, in the motor control system 2, the reference life LSr is not used as it is as the predicted life, but the evaluation value of the predicted life LSp is determined by the machine learning device 10 according to the relative error between the reference life LSr and the predicted life LSp. Updated iteratively. The machine learning device 10 can provide the life prediction device 30 with life data suitable for the environment in which the electrolytic capacitor 72 is actually used. According to the motor control system 2, the accuracy of predicting the life of the electrolytic capacitor 72 can be improved.

FIG. 5 is a flowchart showing the flow of learning processing regarding the predicted life performed by the control unit 11B of FIG. The process shown in FIG. 5 is called every time the drive frequency fc is output from the inverter control device 20 by a main routine (not shown) that performs integrated control of the machine learning device 10. When the process shown in FIG. 5 is called first, an initial value is set for the predicted life. The initial value may be randomly determined. Initial values are preset for rewards associated with states and predicted lifespans (behaviors). Initial values (for example, 0) are set in advance for each evaluation value included in the Q table Qt2.

Hereinafter, the case where the number of times of the learning process shown in FIG. 5 is the (m + 1) th time will be described. m is a natural number of 0 or more. In the last m-th, the selected predicted life LSp _m as the action a _m, state determined by the state variables and transitions from s _m to s _{m + 1.} To distinguish the reward r that is associated with the drive frequency, a reward associated with the expected lifetime LSp _m and w _{m + 1.} The state variable referred to in the (m + 1) th learning process is a state variable corresponding to the state sm _{+ 1.}

As shown in FIG. 5, the control unit 11B determines in S201 whether or not the relative error of the predicted life LSp with respect to the reference life LSr is smaller than the margin of error To1. The relative error of the predicted life LSp with respect to the reference life LSr is the ratio of the absolute value of the difference between the predicted life LSp and the reference life LSr to the reference life LSr. The margin of error To1 is appropriately determined by an actual machine experiment or a simulation.

When the relative error of the predicted life LSp with respect to the reference life LSr is smaller than the margin of error To1 (YES in S201), the control unit 11B _{increases the reward w m + 1} in S202 and advances the process to S204. When the relative error of the predicted life LSp with respect to the reference life LSr is equal to or greater than the margin of error To1 (NO in S201), the control unit 11B _{reduces the reward w m + 1} in S203 and proceeds to the process in S204. The control unit 11B updates the Q table Qt2 using the equation (1) in S204 and returns the process to the main routine.

As described above, according to the motor control system according to the second embodiment, it is possible to suppress the deterioration of the electrolytic capacitor and improve the accuracy of the predicted life of the electrolytic capacitor in the environment where the electrolytic capacitor is actually used. ..

It is also planned that the embodiments disclosed this time will be appropriately combined and implemented within a consistent range. It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown by the claims rather than the above description, and it is intended to include all modifications within the meaning and scope equivalent to the claims.

1,2 Motor control system, 10 Machine learning device, 11,11B control unit, 12 memory, 20 inverter control device, 30 life prediction device, 40 display device, 51 imbalance rate calculation unit, 52 ripple current measurement unit, 53 ripple Voltage measuring unit, 54 load current measuring unit, 60 AC power supply, 70 motor drive, 71 rectifier circuit, 72 electrolytic capacitor, 73 inverter, 80 motor, 90 external storage device, 100 external server.

Claims (12)

It is a machine learning device that learns the state variables of the motor drive device that drives the motor.
The motor drive device is
A rectifier circuit that converts AC power from AC power to DC power,
An electrolytic capacitor that smoothes the DC power from the rectifier circuit,
Including an inverter that converts DC power from the electrolytic capacitor and outputs AC power to the motor.
The state variable includes at least one of data about AC power from the AC power source, data about DC power received by the electrolytic capacitor, and data about AC power received by the motor.
The machine learning device
A storage unit in which the first function in which the state variable, the drive frequency of the motor, and the evaluation value of the drive frequency are associated with each other is stored.
A machine learning device including a control unit that updates the evaluation value of the drive frequency according to the degree to which a change in the state variable deteriorates the electrolytic capacitor and outputs the first function. The state variable includes a ripple current flowing through the electrolytic capacitor as data on the DC power.
The control unit increases the evaluation value of the drive frequency when the ripple current is smaller than the first reference value, and decreases the evaluation value of the drive frequency when the ripple current is larger than the first reference value. The machine learning device according to claim 1. The state variable includes the ripple voltage of the electrolytic capacitor as data on the DC power.
The control unit increases the evaluation value of the drive frequency when the ripple voltage is smaller than the second reference value, and decreases the evaluation value of the drive frequency when the ripple voltage is larger than the second reference value. The machine learning device according to claim 1 or 2. The state variable includes the unbalance rate of the AC power as data on the AC power from the AC power source.
The control unit increases the evaluation value of the drive frequency when the unbalance rate is smaller than the reference ratio, and decreases the evaluation value of the drive frequency when the unbalance rate is larger than the reference ratio. The machine learning device according to any one of claims 1 to 3. The state variable includes the load current flowing through the motor as data on the AC power received by the motor.
The control unit increases the evaluation value of the drive frequency when the load current is within the reference range, and decreases the evaluation value of the drive frequency when the load current is outside the reference range. 4. The machine learning device according to any one of 4. The storage unit stores a second function in which the state variable, the predicted life of the electrolytic capacitor, and the evaluation value of the predicted life are associated with each other.
The control unit updates the evaluation value of the predicted life according to the difference between the reference life and the predicted life of the electrolytic capacitor of the same type as the electrolytic capacitor corresponding to the state variable, and outputs the second function. The machine learning device according to any one of claims 1 to 5. When the ratio of the absolute value of the difference between the predicted life and the reference life to the reference life is smaller than the margin of error, the control unit reduces the evaluation value of the predicted life, and the ratio is larger than the margin of error. The machine learning device according to claim 6, wherein when it is large, the evaluation value of the predicted life is increased. The machine learning device according to any one of claims 1 to 5.
Motor control including an inverter control device that receives the first function from the machine learning device and outputs a command signal corresponding to the drive frequency of the motor to which the highest evaluation value is given in the state variable to the inverter. system. The motor control system according to claim 8, wherein the machine learning device updates the evaluation value of the drive frequency in response to a change in the state variable each time the command signal is output by the inverter control device. The machine learning device according to claim 6 or 7.
An inverter control device that receives the first function from the machine learning device and outputs a command signal corresponding to the drive frequency of the motor to which the highest evaluation value is given in the state variable to the inverter.
A motor control system including a life prediction device that receives the second function from the machine learning device and outputs a predicted life with the highest evaluation value in the state variable. The machine learning device updates the evaluation value of the drive frequency according to the change of the state variable every time the command signal is output by the inverter control device, and the electrolytic capacitor corresponding to the current state variable. The motor control system according to claim 10, wherein the evaluation value is updated according to the difference between the reference life of the electrolytic capacitor of the same type as the above and the predicted life. The inverter control device stops the motor when the ripple current of the electrolytic capacitor exceeds the third reference value and at least one of the cases where the ripple voltage of the electrolytic capacitor exceeds the fourth reference value. , The motor control system according to any one of claims 8 to 11.

Images