JP2018190079A - Control device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a control device capable of more accurately detecting a power failure.SOLUTION: A control device 200 for causing an industry machine to execute retreat operation in detecting an occurrence of a power failure includes: a power supply voltage prediction part 206 for predicting a predicted voltage of a power source 201 on the basis of a power supply voltage prediction function having a parameter related at least to a time as a variable; a threshold voltage determination part 209 for determining a threshold voltage being determination reference of the occurrence of the power failure on the basis of a threshold voltage determination function having at least the predicted voltage, the parameter related to the time, a parameter showing power failure occurrence states of the previous time or earlier as variables; a power failure detection part 210 for determining that the power failure occurs in the case that an actual measurement voltage of the power source is less than the threshold voltage determined by the threshold voltage determination part; and a retreat operation command part 211 for instructing the industry machine to perform retreat operation in the case that the power failure detection part 210 determines that the power failure occurs.SELECTED DRAWING: Figure 1

Description

  The present specification discloses a control device for an industrial machine that is driven by electric power from a power source, and causes the industrial machine to execute a retreat operation when the occurrence of a power failure is detected.

  Generally, in industrial machines such as machine tools and production robots, AC power supplied from an AC power source (for example, commercial power source) is once converted into DC power by a converter, and then converted to AC power by an inverter. A drive motor provided for each drive shaft is driven by electric power. In such an industrial machine, a technique is known that performs a protection operation (retraction operation) of each drive motor when a power failure of an AC power supply is detected.

  For example, Patent Document 1 discloses a control device that determines a power failure when a state in which the value of the power supply voltage is less than the power failure detection level continues for a predetermined duration or longer and performs a protection operation (evacuation operation). ing. This control device has a learning unit that updates a function for changing the power failure detection level and the duration time every time a power failure occurs. According to the technique of Patent Document 1, since the function for changing the power failure detection level and the duration is updated and learned each time a power failure occurs, the occurrence of the power failure can be accurately detected to some extent.

Japanese Patent No. 5964488

  However, in Patent Document 1, once a power failure detection level and duration as a power failure detection criterion are set, they cannot be reset unless a power failure is detected, and continue to take constant values. However, the actual power supply voltage fluctuates in a long cycle depending on the date and time, day of the week, season, and the like. Therefore, in the technique of Patent Document 1, there is a possibility that erroneous detection of a power failure may occur.

  For example, the power supply voltage usually tends to be high in the morning and low in the daytime. Here, assume that a power outage occurred in the morning. In the control device of Patent Document 1, when learning is performed at the timing of this morning power failure, the function is updated so that the power failure can be detected even when the power supply voltage is high, and the power failure detection level is set higher. When such a power failure detection level is applied even in the daytime when the power supply voltage is low, there is a risk that a slight fluctuation (reduction) in the power supply voltage is erroneously detected as a power failure. In this case, the machine tool stops its operation after executing the evacuation operation. As a result, the machine tool is stopped despite the fact that there is no actual power failure, resulting in a decrease in productivity.

  On the other hand, consider a case where a power outage occurs in the daytime. In this case, the control device of Patent Document 1 performs learning at the timing of a power failure in the daytime and updates the function so that the power failure can be detected when the power supply voltage is low, so the power failure detection level is set lower. If such a power failure detection level is applied even in the morning when the power supply voltage is high, there may be a detection through that cannot be detected as a power failure even if the power supply voltage decreases due to the power failure. When the detection through occurs, the retreat operation cannot be performed sufficiently, and there is a risk that the tool or workpiece collides and is damaged.

  Furthermore, in the technique of Patent Document 1, since the power failure detection level and the duration time are not updated unless a power failure occurs, it can be said that the power failure detection accuracy is low overall.

  Therefore, the present specification discloses a control device that can detect a power failure more accurately.

  The control device disclosed in this specification is a control device that controls an industrial machine that is driven by electric power from a power source, and causes the industrial machine to execute a retreat operation when a power outage is detected. A power supply voltage prediction unit that predicts a predicted voltage of the power supply based on a power supply voltage prediction function having at least a parameter related to time as a variable, and at least the predicted voltage, a parameter related to time, Based on a threshold voltage determination function having a parameter indicating a power outage occurrence status as a variable, a threshold voltage determination unit that determines a threshold voltage that is a determination criterion for the occurrence of the power outage, and an actual voltage of the power supply is the threshold voltage determination The power failure detection unit that determines that the power failure has occurred when the threshold voltage is less than or less than the threshold voltage determined by the unit, and the power failure has occurred in the power failure detection unit If it is the cross-sectional, and an evacuation operation command section for instructing the operation of the saving the industrial machine, characterized in that.

  The power supply voltage prediction unit may update the power supply voltage prediction function by learning at a timing when the power failure detection unit determines that the power failure has occurred or when a predetermined prediction period has elapsed. In this case, in the learning by the power supply voltage prediction unit, a reward is determined based on at least a prediction error that is a difference value between the predicted voltage and the measured voltage, and the voltage prediction function is set so that the reward increases. May be updated.

  Further, the threshold voltage determination unit may update the threshold voltage determination function by learning at a timing when the power failure detection unit determines that the power failure has occurred. In this case, in the learning by the power supply voltage predicting unit, a reward is based on at least an evacuation error that is a difference value between the evacuation amount command amount instructed to the industrial machine and the evacuation amount actual value actually moved by the industrial machine. And the threshold voltage determination function may be updated so that the reward increases.

  The parameter relating to time may include at least one of time, date, day of the week, and season. The parameter indicating the power outage occurrence status may include at least a predicted voltage immediately before the occurrence of the power outage and an actually measured voltage.

  According to the control device disclosed in the present specification, even when the power supply voltage fluctuates in a long cycle with time, the threshold voltage can be appropriately set following the fluctuation. As a result, it is possible to secure a sufficient amount of evacuation while minimizing the number of executions of the evacuation operation.

It is a functional block diagram which shows the function structure of the control apparatus of the machine tool in this invention. It is a flowchart which shows the flow of a power failure detection process.

  Hereinafter, a control device for an industrial machine will be described. FIG. 1 is a block diagram illustrating a functional configuration of the control device 200. The control device 200 controls the movement of one or more movable parts provided in the industrial machine. The industrial machine may be any machine that operates by receiving power from an external power source in a factory or business office, and may be, for example, a machine tool or an industrial robot. The machine tool may be a machine for performing processing such as cutting, drilling, grinding, polishing, rolling, forging, and bending on metal, wood, stone, resin, and the like, and may be, for example, a lathe or a machining center. In the following, a control device for a machine tool will be described as an example.

  A machine tool (industrial machine) has one or more movable parts, and each movable part is driven by one or more drive motors 204. Although FIG. 1 illustrates only one drive motor 204, a plurality of drive motors 204 may be provided.

  The drive motor 204 is driven by electric power from an AC power supply 201 (for example, commercial power supply). Specifically, AC power supplied from the AC power source 201 is once converted into DC power by the converter 202. Thereafter, the DC power is further converted into AC power by the inverter 203 and supplied to the drive motor 204. Further, the voltage of the AC power supply 201 is detected by a voltage sensor (not shown), and is input to the control device 200 described later as an actual measurement voltage Vr. The inverter 203 includes an inverter circuit having a plurality of switching elements and a driver that drives the inverter circuit. The driver incorporates a memory that stores parameters relating to the drive motor 204.

  The drive motor 204 is a motor for moving the movable part. The rotational position of the drive motor 204 is detected as a motor detection position P by the position sensor 214. The detected motor detection position P is stored in a memory provided in the driver of the inverter 203.

  The control device 200 controls driving of the machine tool. The control device 200 includes a CPU that performs various calculations, a storage device that stores various control parameters, control programs, functions, and the like, a communication interface that enables data input and output, and the like. FIG. 1 is a functional block diagram showing a functional configuration of the control device 200. Although FIG. 1 mainly shows only functions related to detection of occurrence of power failure, the control device 200 also has a position control function of the drive motor 204 and the like. Since such a position control function of the drive motor 204 can be realized by using a known conventional technique, a detailed description thereof is omitted here.

  As shown in FIG. 1, the control device 200 is necessary for detecting a power failure, a power failure detection unit 210 that detects a power failure of the AC power supply 201, a retreat operation command unit 211 that instructs execution of a retreat operation when a power failure is detected. A machine learning device that optimizes various parameters by learning.

  Whether the power failure detection unit 210 compares the measured voltage Vr of the AC power supply 201 with the threshold voltage Vth output from the machine learning device at every specified control cycle Tc during operation of the machine tool. Judge whether or not. As a result of the comparison, when the measured voltage Vr is equal to or higher than the threshold voltage Vth, the power failure detection unit 210 determines that a power failure does not occur. On the other hand, when the measured voltage Vr is less than the threshold voltage Vth, it is determined that a power failure occurs, and a signal indicating the occurrence of a power failure, that is, a power failure detection signal is output to the evacuation operation command unit 211 and the machine learning device.

  When the save operation command unit 211 receives a power failure detection signal, the save operation command unit 211 outputs a save command to the inverter 203. The inverter 203 that has received the retraction command drives the drive motor 204 so that the drive motor 204 retreats by a predetermined retraction amount command value L *. At this time, the inverter 203 stores the motor detection position P1 when the retract command is received and the motor detection position P2 when the drive motor 204 stops after the retract movement.

  The machine learning device determines a threshold voltage Vth that is a criterion for occurrence of a power failure while learning, and includes an AC power supply voltage recording unit 205, an AC power supply voltage prediction unit 206, a threshold voltage determination unit 209, and a prediction command unit. 207 and a clock 208. The prediction command unit 207 outputs a prediction command to the AC power supply voltage prediction unit 206 at a timing when the machine tool is activated or a power supply voltage prediction function fe described later is updated.

  The AC power supply voltage prediction unit 206 predicts the predicted value of the AC power supply voltage, that is, the predicted voltage Ve, based on the power supply voltage prediction function fe. When the AC power supply voltage predicting unit 206 receives the prediction command, the AC power supply voltage predicting unit 206 calculates a group of the predicted voltages Ve from the present to the time T after the lapse of the specified prediction period Te (Te << Tc). That is, the time series Ve (t) of the predicted voltage Ve for each control cycle Tc is calculated.

  The power supply voltage prediction function fe is a function that predicts a power supply voltage using at least a parameter related to time as a variable. The parameter relating to time includes at least one of time t, date d, day of week w, season s. The reason why the power supply voltage prediction function fe has a parameter related to time as a variable is that the power supply voltage fluctuates in a long cycle depending on the date, day of the week, season, and the like. For example, the power supply voltage generally tends to be lower in the morning than in the middle of the night and in the daytime to nighttime than in the morning. Also, the power supply voltage tends to be higher on holidays than on weekdays. Also, the power supply voltage tends to be higher in spring and autumn than in summer and winter, when demand for air conditioning is high. The power supply voltage prediction function fe has a parameter related to time as a variable, and is a function simulating a change in power supply voltage with respect to the variable (time). The predicted voltage Ve calculated based on the power supply voltage prediction function fe is determined along with the values of variables (time t, date d, day w, season s, etc.) used in the calculation, as well as AC power supply voltage recording unit 205 and threshold voltage determination. Is output to the unit 209.

  Further, the AC power supply voltage prediction unit 206 learns and updates the power supply voltage prediction function fe at the timing when the time T is reached or when the occurrence of a power failure is detected. The power supply voltage prediction function fe is learned so that the power supply voltage prediction error Err_V becomes small. The prediction error Err_V is, for example, a value obtained from the deviation ΔV between the predicted voltage Ve and the actually measured voltage Vr obtained at each control cycle Tc, and is, for example, the mean square value of the deviation ΔV obtained at each control cycle Tc. .

Although it does not specifically limit as a learning algorithm, For example, the case where a reinforcement learning algorithm is used is demonstrated. In reinforcement learning, an agent (acting subject) in a certain environment observes the current state and decides an action to be taken. Agents get rewards from the environment by selecting actions, and learn how to get the most rewards through a series of actions. As a typical technique of reinforcement learning, Q-learning and TD learning (TD-learning) are known. For example, in the case of Q learning, a general update expression (action value table) of the action value function Q (s, a) is expressed by Expression 1.

In Equation 1, _{s t} represents the environment at time t, _{a t} represents the action at time t. The action a _t changes the environment to s _{t + 1} . r _{t + 1} represents a reward obtained by a change in the environment, γ represents a discount rate, and α represents a learning coefficient. The prediction of the power supply voltage, when applied to Q-learning, prediction voltage Ve behavioral a _t becomes, the power supply voltage prediction function fe is the environmental s _t. Also, the reward r increases as the power supply voltage prediction error Err_V decreases.

  The AC power supply voltage recording unit 205 includes an actual measurement voltage Vr detected by the voltage sensor, a predicted voltage Ve output from the AC power supply voltage prediction unit 206, and values of variables used when calculating the predicted voltage Ve (for example, time And the parameter value) are stored in association with each other. Instead of the detection value of the voltage sensor, a voltage value provided from an electric power company or the like through the Internet may be stored as the actual measurement voltage Vr.

  Next, the threshold voltage determination unit 209 will be described. The threshold voltage determination unit 209 determines a threshold voltage Vth, which is a determination criterion for the occurrence of a power failure, based on the threshold voltage determination function fv. Specifically, when the threshold voltage determination unit 209 receives the time series Ve (t) of the predicted voltage Ve from the AC power supply voltage prediction unit 206, the time T when a predetermined prediction period Te (Te << Tc) has elapsed from the present time. A group of threshold voltages Vth up to is calculated. That is, the time series Vth (t) of the threshold voltage Vth for each control cycle Tc is calculated.

  The threshold voltage determination function fv has at least the predicted voltage Ve calculated by the AC power supply voltage prediction unit 206, a parameter related to time, and a parameter indicating the power outage occurrence status before the previous time as variables, and the threshold voltage Vth. Is a function that predicts As described above, the parameter related to time includes at least one of time t, date d, day of week w, and season s. The parameters indicating the power outage occurrence status include at least the predicted voltage Ve and the measured voltage Vr immediately before the occurrence of the power outage (for example, 10 seconds before). Since the threshold voltage determination function fv has the predicted voltage Ve as a variable, it is possible to determine the threshold voltage Vth according to the power supply voltage (predicted voltage Ve) that varies in a long cycle according to time. For example, the threshold voltage Vth can be calculated to be higher at the timing when the predicted voltage Ve is high, and the threshold voltage can be calculated to be lower at the timing when the predicted voltage Ve is low. Further, by having a parameter related to time and a power failure occurrence situation before the previous time as variables, the threshold voltage Vth can be calculated in consideration of the reliability of the predicted voltage Ve. For example, when the fluctuation of the power supply voltage is large, it can be considered that the prediction accuracy of the power supply voltage is lowered and the reliability of the predicted voltage Ve is low. In addition, it can be considered that the reliability of the predicted voltage Ve is low even when the difference between the predicted voltage Ve and the measured voltage Vr immediately before the occurrence of the previous power failure is large. Therefore, in such a case, the threshold voltage Vth may be set higher in order to prevent a power failure detection through. The threshold voltage Vth calculated based on the threshold voltage determination function fv is output to the power failure detection unit 210.

  Further, the threshold voltage determination unit 209 learns and updates the threshold voltage determination function fv at the timing when the occurrence of a power failure is detected. The threshold voltage determination function fv is learned so that the save error Err_L is small. The evacuation error Err_L is a difference value between the specified evacuation amount command value L * and the evacuation amount actual measurement value Lr that is the actual evacuation amount. The actual retracted amount Lr is a difference value between the motor detection position P1 at the start of the retracting operation stored in the inverter 203 and the motor detection position P2 at the end of the retracting operation.

The learning algorithm is not particularly limited as in the learning of the power supply voltage prediction function fe. For example, reinforcement learning such as Q learning or TD learning can be used. The determination of the threshold voltage, the case of applying the Q-learning, the threshold voltage Vth action a _t becomes, the threshold voltage decision function fv, the environmental s _t. Also, the reward r increases as the evacuation error Err_L decreases. If there are a plurality of drive motors 204, a plurality of evacuation errors Err_L are also obtained. In this case, the reward r may be increased as the statistical values (square mean value, maximum value, integrated value, etc.) of the plurality of evacuation errors Err_L are smaller.

  Next, the detection process of the occurrence of a power failure by the control device 200 as described above will be described. FIG. 2 is a flowchart showing the flow of detection processing for occurrence of a power failure. Although not described in the flowchart, the AC power supply voltage recording unit 205 always has a measured voltage Vr of the AC power supply 201 and a time series Ve (t) of the predicted voltage Ve calculated from the AC power supply voltage prediction unit 206. And the parameter values (time t, date d, day w, season s, etc.) used for the calculation are continuously recorded.

  When the machine tool is activated, the prediction command unit 207 outputs a prediction command to the AC power supply voltage prediction unit 206 (S301). Receiving the prediction command, the AC power supply voltage prediction unit 206 calculates the time series Ve (t) of the predicted voltage from the current time to the time T after the prediction period Te has elapsed (S302). For this calculation, the AC power supply voltage prediction unit 206 acquires a parameter related to time with reference to the clock 208 and applies the parameter to the power supply voltage prediction function fe. If the predicted voltage time series Ve (t) can be calculated, the AC power supply voltage predicting unit 206 uses the calculated power supply voltage recording unit 205 and the threshold voltage together with the values of the variables used for the calculation. The data is output to the determination unit 209.

  The threshold voltage determination unit 209 calculates a time series Vth (t) of the threshold voltage from the current time to the time T after the prediction period Te has elapsed (S303). Specifically, the threshold voltage determination unit 209 refers to the AC power supply voltage recording unit 205 and acquires the predicted voltage Ve and the actual measurement voltage Vr immediately before the previous power failure as parameters indicating the previous power failure occurrence status. To do. Then, the threshold voltage determination unit 209, the parameter indicating the power failure occurrence status before the previous time, the predicted voltage Ve input from the AC power supply voltage prediction unit 206, and the value of the variable used for the calculation (the value of the parameter related to time) Are applied to the voltage determination function fv to calculate the time series Vth (t) of the threshold voltage. The calculated time series Vth (t) is sent to the power failure detection unit 210.

  The power failure detection unit 210 monitors whether or not a power failure occurs (S304). Specifically, the power failure detection unit 210 compares the current threshold voltage Vth and the measured voltage Vr, and determines that a power failure occurs when the measured voltage Vr is less than the threshold voltage Vth. In this case, the process proceeds to step S307. On the other hand, when the measured voltage Vr is equal to or higher than the threshold voltage Vth, the power failure detection unit 210 determines that a power failure does not occur. In this case, the occurrence of power failure is continuously monitored until time T is reached (S306).

  When it is determined that a power failure occurs (Yes in S304), the power failure detection unit 210 outputs a power failure detection signal to the evacuation operation command unit 211. When the retreat operation command unit 211 receives the power failure detection signal, the retreat operation command unit 211 commands the inverter 203 to execute a retreat operation that retreats by the retraction amount command value L *. The inverter 203 that has received the retreat operation command drives the drive motor 204 to retreat by the retreat amount command value L * (S307). Further, the inverter 203 acquires and stores the detection position P1 of the drive motor 204 when the retracting operation is started and the detection position P2 of the drive motor 204 when the retracting operation is completed.

When the saving operation is completed, the threshold voltage determination unit 209 subsequently updates the threshold voltage determination function fv by learning (S308). Specifically, the threshold voltage determination unit 209 calculates the actual retracted amount L = P1-P2 from the detection position P1 and the detected position P2 stored in the inverter 203, and further calculates the actual retracted amount L. The saving error Err_L = | L−L * |, which is a difference value from the saving amount command value L *, is calculated. Then, the threshold voltage determining unit 209, action threshold voltage Vth of the power failure _{a t,} the voltage decision function fv used for calculation of the threshold voltage Vth as environmental _{s t,} so saving error Err_L becomes smaller (reward The voltage determination function fv is updated so that it becomes larger.

The AC power supply voltage prediction unit 206 updates the prediction function fe by learning at the timing when the voltage determination function fv is updated (that is, when a power failure occurs) or when the time T is reached (S309). Specifically, the AC power supply voltage predicting unit 206 refers to the AC power supply voltage recording unit 205 and acquires a prediction error Err_V that is a difference between the past predicted voltage Ve and the actually measured voltage Vr. AC power supply voltage prediction unit 206, behavior prediction voltage Ve _{a t,} the power supply voltage prediction function fe used to calculate the threshold voltage Vth as environmental _{s t,} so that the prediction error Err_V decreases (as reward increases ), The power supply voltage prediction function fe is updated. If the power supply voltage prediction function fe is updated, the process returns to step S301 and the same processing is repeated.

  As is clear from the above description, the control device 200 disclosed in this specification predicts a power supply voltage that fluctuates over a long period as the predicted voltage Ve, and calculates the threshold voltage Vth with reference to the predicted voltage Ve. . In this case, the threshold voltage Vth fluctuates so as to follow the power supply voltage even if a power failure does not occur, so that the occurrence of the power failure can be detected more accurately. Further, in the control device 200 disclosed in this specification, the power supply voltage prediction function fe and the voltage determination function fv are appropriately updated by learning. Therefore, the predicted voltage Ve and the threshold voltage Vth can be determined more appropriately. In particular, the power supply voltage prediction function fe is updated when a predetermined prediction period Te times out even if no power failure occurs. Therefore, even when a power failure does not occur for a long period of time, the predicted voltage Ve can be accurately predicted, and hence the occurrence of the power failure can be detected more accurately.

  The configuration described so far is merely an example. At least the predicted voltage Ve is calculated based on the power supply voltage prediction function fe having a parameter relating to time as a variable, and the threshold voltage Vth is determined according to the predicted voltage Ve. If so, other configurations may be changed as appropriate. For example, in the above description, the power supply voltage prediction function fe may have another parameter as a variable in addition to the parameter related to time. As other parameters, for example, parameters related to temperature can be considered. The threshold voltage determination function fv may also have other parameters as variables in addition to the predicted voltage Ve, a parameter related to time, and a parameter indicating the power outage occurrence status before the previous time. As other parameters, for example, parameters related to the characteristics of the industrial machine (for example, the time required for executing the save operation) can be considered. In the description so far, the predicted voltage Ve and the threshold voltage Vth for the predicted period Te are calculated in a lump, but these may be calculated at any time.

200 Control Device, 201 AC Power Supply, 202 Converter, 203 Inverter, 204 Drive Motor, 205 AC Power Supply Voltage Recording Unit, 206 AC Power Supply Voltage Prediction Unit, 207 Prediction Command Unit, 208 Clock, 209 Threshold Voltage Determination Unit, 210 Power Failure Detection Unit 211 Retraction operation command unit 214 Position sensor.

Claims (7)

A control device that controls an industrial machine that is driven by power from a power source, and when the occurrence of a power failure is detected, the control device that causes the industrial machine to perform a retreat operation,
A power supply voltage prediction unit that predicts a predicted voltage of the power supply based on a power supply voltage prediction function having at least a parameter related to time as a variable;
A threshold value for determining a threshold voltage that is a criterion for determining the occurrence of a power failure based on a threshold voltage determination function having at least the predicted voltage, a parameter relating to the time, and a parameter indicating the power failure occurrence status before the previous time as variables. A voltage determining unit;
A power failure detection unit that determines that the power failure has occurred when the measured voltage of the power source is less than or less than the threshold voltage determined by the threshold voltage determination unit;
When it is determined that the power failure has occurred in the power failure detection unit, a retreat operation command unit that instructs the industrial machine to perform a retreat operation,
A control device comprising: The control device according to claim 1,
The power supply voltage prediction unit is configured to update the power supply voltage prediction function by learning at a timing when the power failure detection unit determines that the power failure has occurred, or when a predetermined prediction period has elapsed. Control device. The control device according to claim 2,
In the learning by the power supply voltage prediction unit, a reward is determined based on at least a prediction error that is a difference value between the predicted voltage and the measured voltage, and the voltage prediction function is updated so that the reward increases. A control device characterized by that. The control device according to any one of claims 1 to 3,
The control device, wherein the threshold voltage determination unit updates the threshold voltage determination function by learning at a timing when the power failure detection unit determines that the power failure has occurred. The control device according to claim 4,
In the learning by the power supply voltage predicting unit, a reward is determined based on at least a save error that is a difference value between a save amount command amount instructed to the industrial machine and an actual save value that the industrial machine has actually moved. In addition, the control device updates the threshold voltage determination function so that the reward increases. The control device according to any one of claims 1 to 5,
The control device characterized in that the parameter relating to time includes at least one of time, date, day of the week, and season. The control device according to any one of claims 1 to 6,
The parameter indicating the power outage occurrence status includes at least a predicted voltage immediately before the occurrence of the power outage and an actually measured voltage.

Images