TWI777395B - Positioning control device and positioning method - Google Patents

Abstract

A positioning control device of the present application comprises a position command generating unit, a drive control unit, an evaluation unit and a learning unit. The position command generating unit generates a position command for independently determining the shape of acceleration of an accelerating section and a decelerating section according to a position command parameter. The drive control unit drives a motor in such a manner that the position of the motor follows the position command. The evaluation unit obtains a detection value of acceleration of a controlled object, and calculates an evaluation value related to a positioning performance of the controlled object according to the position of the motor and the detection value of acceleration after deciding the positioning control is completed. The learning unit obtains the relation of the position command parameter and the evaluation value.

Description

Positioning control device and positioning method

The present disclosure relates to a positioning control device and a positioning method for performing positioning control on a control object.

In devices such as electronic component builders and semiconductor manufacturing devices that repeatedly move a head belonging to a control object by driving a servo motor, high-speed control of the servo motor is required to improve production performance. . When the servo motor operates at high speed, mechanical vibration occurs due to the low rigidity of the device. At this time, if the command shape of the position command of the servo motor is appropriately adjusted, high-speed positioning control can be realized even under the influence of mechanical vibration. Therefore, it is required to appropriately adjust the command shape of the position command.

The following Patent Document 1 discloses a technique of adjusting the command shape so as to minimize the vibration of the acceleration of the control object during the movement of the robot in order to reduce the vibration on the movement path of the robot. In this patent document 1, the parameter of the command shape is given and the vibration value when the positioning operation is performed is used as a variable to calculate the evaluation function, and the evaluation value is obtained while changing the parameters slightly to find out the movement of the robot. The magnitude of the vibration on the path becomes the smallest command shape. (prior art literature) (patent literature)

Patent Document 1: Japanese Patent Laid-Open Publication No. Hei 10-143249

(The problem to be solved by the invention)

However, in the technique described in the aforementioned Patent Document 1, in order to make the evaluation value converge in a situation where the relationship between the parameter and the evaluation value is unclear, it is necessary to reduce the parameter change width. However, when the parameter change width is too small, the positioning operation may be difficult. The number of times has increased so much that adjustments are time-consuming. In addition, there is the possibility of being easily trapped in local optimal solutions and failing to reach the true optimal solution.

The present disclosure has been developed in view of the above-mentioned circumstances, and an object of the present disclosure is to obtain a positioning control device capable of adjusting the parameters of the position command for suppressing the vibration of the control object with a smaller number of attempts than the prior art. (Means of Solving Problems)

In order to solve the above-mentioned problems and achieve the object, the positioning control device of the present disclosure is a positioning control device that drives one or more motors to move a control object to a target position. The positioning control device includes a position command generation unit, a drive control unit, an evaluation unit, and a learning unit. The position command generation unit generates a position command for independently determining the shape of the acceleration in the acceleration section and the deceleration section based on the position command parameter. The drive control unit drives the motor so that the motor position indicating the position of the motor follows the position command. The evaluation unit acquires an acceleration detection value indicating the acceleration of the controlled object from the acceleration detection unit, and calculates an evaluation value related to the positioning performance of the controlled object based on the motor position and the acceleration detection value after the completion of the positioning control is determined based on the motor position . The learning section independently changes each shape of the acceleration shape of the position command in the acceleration section and the deceleration section determined according to the position command parameter, and learns the difference between the position command parameter and the evaluation value when the positioning control is executed a plurality of times. relationship, and obtain the relationship between the position command parameter and the evaluation value. (effect of invention)

The positioning control device of the present disclosure achieves that the parameters of the position command for suppressing the vibration of the control object can be adjusted with a smaller number of attempts than the prior art.

Hereinafter, the positioning control device and the positioning method according to the embodiments of the present disclosure will be described in detail with reference to the drawings. In addition, the present disclosure is not limited to the following embodiments.

Implementation type 1. FIG. 1 is a diagram schematically showing an example of the configuration of the positioning control device according to the first embodiment. The positioning control device 10 is a device that drives the motor 1 to move the control object 3 to a target position, and is connected to the motor 1 and the acceleration detector 4 . The motor 1 applies torque and thrust to the controlled object 3 via the ball screw 2 to move the controlled object 3 . The motor 1 only needs to be capable of driving the control objects 3 . Examples of the motor 1 are a rotary servo motor, a linear motor, or a stepping motor.

The control object 3 is moved to a desired target position by the motor 1 . The control object 3 is a machine or part that needs to be positioned and controlled. An example of the control object 3 is an electronic component mounting machine or a head portion of a semiconductor manufacturing apparatus.

The acceleration detector 4 detects the acceleration of the controlled object 3 , and outputs information indicating the detected acceleration value to the positioning control device 10 . The acceleration detection value shows the acceleration belonging to the result of detection by the acceleration detector 4 . The acceleration detector 4 corresponds to an acceleration detection unit.

The positioning control device 10 includes a position command generation unit 11 , a drive control unit 12 , an evaluation unit 13 , and a learning unit 14 .

The position command generation unit 11 generates a position command for driving the motor 1 to move the control object 3 to the target position based on the position command parameter that determines the shape of the position command. The position command generation unit 11 generates a position command for determining the acceleration shape of the acceleration section and the deceleration section based on the position command parameter.

The drive control unit 12 drives the motor 1 so that the motor position indicating the position of the motor 1 follows the position command generated by the position command generation unit 11 .

The evaluation unit 13 obtains the acceleration detection value, and calculates an evaluation value related to the positioning performance of the control object 3 based on the motor position and the acceleration detection value after the completion of the positioning control is determined based on the motor position. That is, the evaluation unit 13 calculates an evaluation value for evaluating the quality of the positioning control performed by the drive control unit 12 based on the motor position and the acceleration detection value of the control object 3 when the positioning control is executed.

The learning unit 14 changes the position command parameter within the parameter range that specifies the upper limit value and the lower limit value of the position command parameter, and learns the position command parameter and the evaluation by the position command parameter when the positioning control with respect to the control object 3 is executed a plurality of times. relationship between the evaluation values calculated by the section 13 . The learning unit 14 independently changes each shape of the acceleration shape of the position command in the acceleration section and the deceleration section determined based on the position command parameter, and learns the relationship between the position command parameter and the evaluation value when the positioning control is executed a plurality of times. relationship to obtain the relationship between the position command parameter and the evaluation value. More specifically, the learning unit 14 determines the position command parameter based on the relational expression obtained by learning.

Hereinafter, the position command generation unit 11 , the drive control unit 12 , the evaluation unit 13 , and the learning unit 14 will be described in further detail.

The position command generation unit 11 generates and outputs a position command of the motor 1 based on the position command parameter. The position command parameter is a parameter that specifies the command shape of the position command. FIG. 2 is a diagram showing an example of a position command used in Embodiment 1, and a speed command, an acceleration command, and a jerk (jerk) obtained from the position command. In FIG. 2, a graph (graph) 210 is a graph showing an example of a position command, the horizontal axis shows time, and the vertical axis shows position. The graph 220 is the first derivative of the position command, the horizontal axis shows the time, and the vertical axis shows the speed. The graph 230 is the second derivative of the position command, the horizontal axis shows time, and the vertical axis shows acceleration. The graph 240 is the jerk (ie jerk (jerk)) of the first derivative of the acceleration command, the horizontal axis shows time, and the vertical axis shows jerk (jerk).

As shown in the graph 230 of FIG. 2 , the acceleration command of Embodiment 1 is a command in a trapezoidal shape indicating the acceleration direction from the first section to the third section, 0 in the fourth section, and 0 in the fifth section from the fifth section. Up to the seventh section is a trapezoidal command indicating the deceleration direction. The first section shows the section where the acceleration starts, the third section shows the section where the acceleration ends, the fifth section shows the section where the deceleration starts, and the seventh section shows the section where the deceleration ends. Let the time length of the mth section be the mth time length Tm. m is an integer from 1 to 7. For example, the time length of the first interval is the first time length T1.

In the acceleration command of FIG. 2 , the trapezoidal shape of the acceleration section from the first section to the third section and the trapezoidal shape of the deceleration section from the fifth section to the seventh section may not be identical, that is, asymmetrical. The first time length T1 and the third time length T3 of the acceleration section may be set to 0, and the shape of the acceleration command may be set to a rectangular shape. In Embodiment 1, the seven parameters from the first time length T1 to the seventh time length T7 are the position command parameters. The command shape is specified according to the position command parameter. The calculation method of the command shape will be explained later.

Returning to FIG. 1 , the drive control unit 12 supplies current to the motor 1 so that the rotational position of the motor 1 follows the position command. For example, the drive control unit 12 calculates the value of the current supplied to the motor 1 according to PID (Proportional-Integral-Differential) control so as to reduce the deviation between the rotational position of the motor 1 and the position command, and The electric current of the value obtained by the calculation is supplied to the motor 1 . In addition, the drive control unit 12 may be any one as long as the rotational position of the motor 1 follows the position command. For example, the drive control unit 12 may perform two-degree-of-freedom control in which feed-forward control is added in addition to feedback control.

Instead of driving the motor 1 so that the rotational position of the motor 1 follows the position command, the drive control unit 12 may detect the position of the control object 3 as a signal for feedback control, and make the position of the control object 3 follow the position command. way to drive motor 1.

The evaluation unit 13 receives the motor position of the motor 1 and the acceleration detection value of the control object 3, calculates and outputs an evaluation value Q for evaluating the quality of the positioning control performed by the drive control unit 12 by a method described later. The drive control unit 12 operates based on the position command, and the position command is calculated based on the position command parameter. Therefore, the evaluation value Q calculated by the evaluation unit 13 depends on the value of the position command parameter. That is, the evaluation value Q can be regarded as an index for evaluating the position command parameter.

Here, a specific calculation method of the evaluation value Q will be described. FIG. 3 shows an example of the time response of the deviation between the position command and the motor position and the time response of the acceleration detection value of the control object when the command shape generated from the position command parameter is used for positioning control in the first embodiment. picture. The graph 310 is a graph showing the time response to the deviation of the position of the motor 1 , the horizontal axis shows time, and the vertical axis shows the deviation of the position of the motor 1 . The graph 320 is a graph showing the time response of the acceleration of the control object 3 , the horizontal axis shows the time, and the vertical axis shows the acceleration of the control object 3 .

As shown in FIG. 3 , the time from the start of the positioning control to the completion of the positioning when the magnitude of the deviation between the position command and the motor position becomes smaller than the predetermined allowable value Ptol is set as the positioning time Tst. When the positioning time Tst is small, the evaluation value Q is set so that the evaluation value Q indicates a large value. In addition, let the maximum value of the vibration amplitude of the acceleration detection value after positioning completion be the acceleration maximum value Aamp. The evaluation value Q is set so that the vibration amplitude of the acceleration detection value in the vicinity of the target position shows a small value. In order to satisfy the above, the evaluation value Q is set by the following formula (1). Q=‑Tst–w×Aamp ･･･(1)

In Equation (1), w is a weighting coefficient and is set to a positive value. According to formula (1), the smaller the positioning time Tst is, the larger the value of the evaluation value Q will be. In addition, the smaller the maximum acceleration value Aamp after positioning is completed, the larger the value of the evaluation value Q will be. That is, in Embodiment 1, the larger the evaluation value Q is, the better the position command parameter can be. However, as long as the evaluation value Q can evaluate the performance of the positioning control, it is not limited to the one defined by the formula (1). For example, the sum of the positioning time Tst and the acceleration maximum value Aamp may be set as the evaluation value Q, and it is determined that the smaller the evaluation value Q is, the better the position command parameter is. In addition, only when the acceleration maximum value Aamp exceeds the allowable value of the acceleration amplitude may be added to the evaluation value Q as a penalty. In addition, the maximum value of the acceleration in the time after a certain time has elapsed from the time when positioning is completed may be used as the maximum acceleration value Aamp for the calculation of the formula (1).

Returning to FIG. 1 , the learning unit 14 takes the evaluation value Q as an input, and learns the relationship between the position command parameter and the evaluation value Q. Specifically, the learning unit 14 includes a neural-like network that takes the position command parameter as an input and the evaluation value Q as an output, and the learning unit 14 performs learning by updating the weighting coefficients of the neural-like network. In the case of updating the weighting coefficients for learning, the neural-like network outputs a good guess corresponding to the evaluation value Q of the position command parameter.

The learning unit 14 uses a neural network-like network to obtain a function that takes the position command parameter as an input and the evaluation value Q as an output, thereby obtaining a relationship between the position command parameter and the evaluation value Q as a learning result. As long as the learning unit 14 can learn the relationship between the position command parameter and the evaluation value Q, the relationship between the position command parameter and the evaluation value Q may be learned by a method other than the method using a neural network-like method.

The learning unit 14 selects and outputs the position command parameter for executing the next positioning control from the predetermined parameter range. When selecting the next position command parameter, the learning unit 14 may select a position command parameter showing a good evaluation value Q based on a function obtained by learning, or may divide a grid (grid) of each position command parameter at equal intervals. ) points to select the position command parameters in sequence. The learning unit 14 has a function of updating the function for calculating the evaluation value Q based on the position command parameter.

The function of the positioning control device 10 of Embodiment 1 will be further described. The learning unit 14 determines a set of position command parameters within the range determined by the parameter range, and outputs the determined position command parameters to the position command generation unit 11 . The position command generation unit 11 calculates a position command based on the input position command parameters.

Describes the calculation method of the position command. The magnitude of the acceleration in the second section is Aa, and the magnitude of the acceleration in the sixth section is Ad. The magnitude Aa of the acceleration in the second section and the magnitude Ad of the acceleration in the sixth section are dependent variables of the position command parameter, so these have no set degrees of freedom. The position command generation unit 11 uses the following equations (2), (3), and (4) to calculate the acceleration command A1(t), Speed command V1(t) and position command P1(t).

[Number 1]

[Number 2]

[Number 3]

The position command generation unit 11 calculates the acceleration command A2(t) in the second section of the time t in the range of "T1≦t<T1+T2" using the following equations (5), (6), and (7), respectively. ), speed command V2(t) and position command P2(t). A2(t)=Aa ･･･(5)

[Number 4]

[Number 5]

The position command generation unit 11 uses the following equations (8), (9), and (10) to calculate the acceleration of the third section in the time t in the range of "T1+T2≦t<T1+T2+T3", respectively Command A3(t), speed command V3(t) and position command P3(t).

[Number 6]

[Number 7]

[Number 8]

The position command generation unit 11 uses the following equations (11), (12), and (13) to calculate the time t in the range of "T1+T2+T3≦t<T1+T2+T3+T4", respectively. Four sections of acceleration command A4(t), velocity command V4(t), and position command P4(t). A4(t)=0 ･･･(11)

[Number 9]

[Number 10]

The position command generation unit 11 calculates the time in the range of "T1+T2+T3+T4≦t<T1+T2+T3+T4+T5" using the following equations (14), (15), and (16), respectively The acceleration command A5(t), the velocity command V5(t), and the position command P5(t) in the fifth section in t.

[Number 11]

[Number 12]

[Number 13]

The position command generation unit 11 uses the following equations (17), (18), and (19) to calculate "T1+T2+T3+T4+T5≦t<T1+T2+T3+T4+T5+T6, respectively. The acceleration command A6(t), the velocity command V6(t), and the position command P6(t) in the sixth section of the time t in the range of '. A6(t)=-Ad ･･･(17)

[Number 14]

[Number 15]

The position command generation unit 11 uses the following equations (20), (21), and (22) to calculate "T1+T2+T3+T4+T5+T6≦t≦T1+T2+T3+T4+T5, respectively. The acceleration command A7(t), the velocity command V7(t), and the position command P7(t) in the seventh section of the time t in the range of +T6+T7".

[Number 16]

[Number 17]

[Number 18]

In the terminal time t=T1+T2+T3+T4+T5+T6+T7, the speed command system must be consistent with 0, and the position command system must be consistent with the moving distance D. Therefore, in the terminal time, the following equations (23) and (24) hold. V7=0 ･･･(23) P7=D ･･･(24)

The magnitude Aa of the acceleration in the second section and the magnitude Ad of the acceleration in the sixth section are determined according to the above equations (5) and (17). As described above, the command shape is calculated based on the position command parameter and the moving distance D.

As described above, and as shown in the graph 230 of FIG. 2 , in the first, third, fifth, and seventh intervals, the acceleration is a linear function of time. Therefore, in these intervals, as shown in the graph 240 of FIG. 2 , the jerk of the first derivative of the acceleration is a constant value other than zero. That is, the first time length T1 , the third time length T3 , the fifth time length T5 , and the seventh time length T7 can be regarded as time for determining the constant value of the jerk to be non-zero. A non-zero certain value is a certain value greater than 0 or a certain value less than 0.

In these intervals, a parameter specifying the magnitude of the jerk can also be selected instead of the time length. For example, when the magnitude of the jerk in the first section is defined as J1, as shown in the following equation (25), the jerk J1 can be calculated using the first time length T1. J1=Aa/T1 ･･･(25)

That is, setting the time of the interval in which the jerk becomes a non-zero constant value is set as a parameter, and setting the magnitude of the jerk as a parameter in the interval in which the jerk becomes a non-zero constant value is equivalent. . As described above, the selection method of the parameters defining the command shape is arbitrary, and the selection of the parameters defining the command shape is not limited to the above method.

As described above, in the command generation method executed by the position command generation unit 11 of Embodiment 1, seven position command parameters are used in order to define the command shape. Compared with the conventional method of specifying the command shape by two parameters of acceleration and velocity, the degree of freedom of the adjustment in the implementation mode 1 is higher than that of the conventional technique. Therefore, if the position command parameter can be adjusted appropriately, the positioning control device 10 can realize the positioning control showing a favorable response even under the influence of the mechanical vibration of the device on which the control object 3 is placed.

On the other hand, in the case where the operator of the device on which the control object 3 is placed operates the device and manually adjusts the above-mentioned seven parameters by erroneous attempts, it requires a lot of labor and a relatively long time. time. Hereinafter, by providing the positioning control device 10 with the evaluation unit 13 and the learning unit 14, the positioning control device 10 will be explained so that the positioning control device 10 can appropriately adjust the position command parameters without the operator's erroneous attempts.

According to the operations of the evaluation unit 13 and the learning unit 14 , the changing of the position command parameters by the learning unit 14 , the positioning control using the changed position command parameters, and the evaluation of the evaluation value Q by the evaluation unit 13 are repeatedly performed. calculate. Next, the operations of the repeatedly executed evaluation unit 13 and the learning unit 14 will be described.

The learning unit 14 selects the position command parameter within the parameter range that defines the upper limit value and the lower limit value of the position command parameter. Hereinafter, the operation of the evaluation unit 13 and the learning unit 14 is executed three times, and the procedure of evaluating the position command parameters up to the third group will be described. The position command parameters of the first group are represented as position command parameters Pr1, the position command parameters of the second group are represented as position command parameters Pr2, and the position command parameters of the third group are represented as position command parameters Pr3. Each of the three groups of position command parameters has seven parameters from the first time length T1 to the seventh time length T7.

The position command parameter Pr1 of the first group is output from the learning unit 14, and the position command generation unit 11 generates a position command based on the position command parameter Pr1 of the first group. Positioning control is performed using the position command generated from the position command parameter Pr1 of the first group. The evaluation unit 13 obtains the positioning time Tst1 and the acceleration maximum value Aamp1 corresponding to the command parameter Pr1 of the first group of positions based on the motor position and the acceleration detection value in this situation. The time from the start of the positioning control to the completion of the positioning when the magnitude of the deviation between the position command and the motor position becomes smaller than the predetermined allowable value Ptol is defined as the positioning time Tst1. In addition, the maximum value of the vibration amplitude of the acceleration detection value after positioning is completed is the acceleration maximum value Aamp1. The evaluation value Q1 of the command parameter Pr1 corresponding to the first group of positions is represented by the following formula (26) according to the formula (1). Q1=-Tst1–w×Aamp1 ･･･(26)

The learning unit 14 receives the evaluation value Q1 and changes the position command parameter to the position command parameter Pr2 of the second group. When changing the position command parameters, the learning unit 14 may select the position command parameters Pr2 of the second group according to the result of the positioning control using the position command parameters Pr1 of the first group, or may use the position command parameters of the first group. Regardless of the result of the positioning control of Pr1, the second group of position command parameters Pr2 is selected in a predetermined manner.

When the learning unit 14 changes the position command parameter, the positioning control is executed using the position command generated from the position command parameter Pr2 of the second group. The evaluation unit 13 obtains the positioning time Tst2 and the acceleration maximum value Aamp2 corresponding to the position command parameter Pr2 of the second group based on the motor position and the acceleration detection value in this situation. The time from the start of the positioning control to the completion of the positioning when the magnitude of the deviation between the position command and the motor position becomes smaller than the allowable value Ptol is defined as the positioning time Tst2. In addition, the maximum value of the vibration amplitude of the acceleration detection value after positioning is completed is the acceleration maximum value Aamp2. The evaluation value Q2 corresponding to the position command parameter Pr2 of the second group is represented by the following formula (27) according to the formula (1). Q2=-Tst2–w×Aamp2 ･･･(27)

The learning unit 14 receives the evaluation value Q2 and changes the position command parameter to the position command parameter Pr3 of the third group. The evaluation unit 13 evaluates the evaluation value Q3 using the formula (1) based on the positioning time Tst3 and the acceleration maximum value Aamp3 in the same manner as in the procedure for obtaining the evaluation value Q1 and the evaluation value Q2. This evaluation value Q3 is represented by the following formula (28). Q3=-Tst3–w×Aamp3 ･･･(28)

The learning unit 14 receives the evaluation value Q3. Through the operations of the evaluation unit 13 and the learning unit 14 so far, the learning unit 14 obtains the evaluation value Q1, the evaluation value Q2, and the evaluation value Q3 corresponding to the three sets of the position command parameter Pr1, the position command parameter Pr2, and the position command parameter Pr3. .

As described above, the evaluation unit 13 and the learning unit 14 repeatedly perform the operation of acquiring the evaluation value Q corresponding to the position command parameter.

The learning unit 14 uses the position command parameter and the evaluation value Q corresponding to the position command parameter as learning data, and performs a learning operation using a neural network. FIG. 4 is a diagram schematically showing an example of a neural-like network used in Embodiment 1. FIG. This type of neural network 400 has an input layer 410 , an intermediate layer 420 and an output layer 430 . The position command parameter is input to the input layer 410 at the left end, and the evaluation value Q is output from the output layer 430 at the right end. As described above, the position command parameter includes seven parameters from the first time length T1 to the seventh time length T7. The weighting coefficients for each node 411 of the input layer 410 to each node 421 of the middle layer 420 can be independently set, but in FIG. 4 , these weighting coefficients are all represented by the same weighting coefficient W1. Similarly, the weighting coefficients for each node 421 of the intermediate layer 420 to the node 431 of the output layer 430 are all represented by the same weighting coefficient W2.

The output value of each node 411 of the input layer 410 is multiplied by the weighting coefficient W1 , and a linear combination of the result obtained by the multiplication is input to each node 421 of the intermediate layer 420 . The output value of each node 421 of the intermediate layer 420 is multiplied by the weighting coefficient W2, and a linear combination of the result obtained by the multiplication is input to the node 431 of the output layer 430. In each node 411 , 421 , and 431 of each layer 410 , 420 , and 430 , for example, an output value may be calculated from an input value by a nonlinear function of a sigmoid function. In the input layer 410 and the output layer 430, the output value can also be a linear combination of the input value.

The learning unit 14 uses the position command parameter and the evaluation value Q to calculate the weighting coefficient W1 and the weighting coefficient W2 of the neural network-like network 400 . The weighting coefficient W1 and the weighting coefficient W2 of the neural network 400 can be calculated by using the error back-propagation method or the gradient descent method in one example. However, the calculation methods of the weighting coefficient W1 and the weighting coefficient W2 are not limited to the above-mentioned methods as long as the calculation method of the weighting coefficient of the neural network-like network 400 can be obtained.

As long as the weighting coefficient W1 and the weighting coefficient W2 of the neural network 400 are determined, the relational expression between the position command parameter and the evaluation value Q can be obtained.

In the above description, an example of learning using the three-layer neural-like network 400 has been exemplified. However, learning using the neural-like network 400 is not limited to the above examples.

Through the operations of the evaluation unit 13 and the learning unit 14 so far, the relational expression obtained by the neural-like network 400 can be obtained.

If the relational expression obtained by the neural network 400 is obtained by the operations of the evaluation unit 13 and the learning unit 14 as described above, a function having the position command parameter as input and the evaluation value Q as output can be obtained. If this function is used, even if the positioning control is not performed for the new position command parameter, the evaluation value Q corresponding to the new position command parameter can be obtained.

Generally speaking, the acceleration detector 4 contains a large amount of noise in the detected value due to the influence of its own installation environment and power supply environment. Therefore, when evaluating the acceleration detection value of the control object 3, it is inevitably affected by noise. Even if the same position command parameter is used for positioning control, there are still many cases due to the obtained acceleration detection value. Different evaluation values Q. According to the operation of the learning unit 14, the evaluation value Q at which the error between the plurality of evaluation values Q obtained under the influence of noise becomes the smallest is obtained, so that an appropriate estimation for the evaluation value Q of the position command parameter can be obtained. value.

Next, the learning unit 14 obtains the position command parameter in which the evaluation value Q becomes the largest by numerical calculation based on the relational expression between the position command parameter and the evaluation value Q. At this time, for example, an optimization algorithm of grid search, random search, or Newton's method may be used.

As described above, the relationship between the command parameter and the evaluation value Q can be learned by the operations of the evaluation unit 13 and the learning unit 14 . In addition to this, a good position command parameter that maximizes the evaluation value Q can be found by using the relational expression. If this relational expression is used, an appropriate estimated value corresponding to the evaluation value Q corresponding to the position command parameter can be obtained without performing the positioning control. Therefore, the positioning control device 10 can find out the positioning control without performing the positioning control using the excellent parameters. excellent parameters.

According to the above, the positioning control device 10 can suppress the vibration of the control object 3 and realize the positioning control in a short time.

In addition, the positioning control device 10 can appropriately adjust the position command parameter according to the motor position and the acceleration detection value of the control object 3 . At this time, the acceleration detector 4 may be connected to the control object 3 in advance. Therefore, even if the stop position of the controlled object 3 is changed, the operator does not need to change the arrangement of the acceleration detector 4 for evaluation.

Therefore, the positioning control device 10 can appropriately adjust the position command parameter without the operator's erroneous attempt.

As described above, in the positioning control device 10 of the first embodiment, it is possible to efficiently adjust the command shape for speeding up the positioning control.

The position command generation unit 11 may determine the shape of the position command signal in such a way that there is a time when the acceleration command signal becomes a constant value greater than zero or a constant value less than zero, and the acceleration command signal causes the position command signal to pass through. Signal after quadratic differentiation. The position command generation unit 11 may determine the shape of the position command signal in such a way that there is a time for the signal with jerk to become a constant value greater than zero or a constant value less than zero, and the jerk signal makes the position command The signal after three micro-signals. The position command generation unit 11 may include information on the time when the signal indicating the jerk becomes a constant value greater than zero or a constant value less than zero in the position command parameter. The position command generation unit 11 may include information indicating the magnitude of the jerk signal at a time when the jerk signal becomes a constant value greater than zero or a constant value less than zero in the position command parameter.

In Embodiment 1, the learning unit 14 obtains a function for calculating an estimated value of the evaluation value Q using the position command parameter as an input. Thereby, a good position command parameter can be selected from the combination of the position command parameter and the evaluation value Q obtained by executing the positioning control. That is, positioning control can be performed using the optimum position command parameters found by learning.

The positioning control device 10 according to the first embodiment includes a learning unit 14 that learns the relationship between the evaluation value Q based on the acceleration detection value of the controlled object 3 and the position command parameter. Thereby, the position command parameter for suppressing the vibration of the control object 3 can be adjusted with a small number of attempts. As a result, an asymmetric multi-degree-of-freedom command shape can be optimized. Furthermore, the position command generation unit 11 is set with a position command parameter obtained by the learning of the learning unit 14, and the position command generation unit 11 generates a position command, whereby high-speed positioning control can be realized. Furthermore, since the evaluation value Q is calculated based on the positioning time Tst from the start of positioning to the determination of the completion of positioning, the positioning control can be adjusted to shorten the positioning time Tst.

Implementation type 2. FIG. 5 is a diagram schematically showing an example of the configuration of the positioning control device according to the second embodiment. Hereinafter, the same parts as those in the first embodiment are given the same reference numerals, and the description thereof is omitted, and the different parts will be described. The positioning control device 20 includes a position command generation unit 11 , a drive control unit 12 , an evaluation unit 13 , and a learning unit 24 .

The learning unit 24 takes the evaluation value Q as an input, and learns the relationship between the position command parameter and the evaluation value Q. Specifically, the learning unit 24 performs learning by updating the function for estimating the mean value and the variance of the evaluation value Q corresponding to the position command parameter. The learning unit 24 can calculate and estimate the average value of the evaluation value Q corresponding to the position command parameter and the variation of the evaluation value Q corresponding to the position command parameter by performing learning. The functions used to calculate the mean and variance may use, in one example, a Gaussian Process model. In this way, the learning unit 24 can obtain the relational expression between the position command parameter and the evaluation value Q.

The learning unit 24 selects a position command parameter for executing the next positioning control, and outputs it to the position command generation unit 11 . The learning unit 24 selects a position command parameter in which the sum of the average value and the variance of the evaluation value Q shows the maximum value based on the learning result in the selection of the next position command parameter.

The learning unit 24 outputs the position command parameter that maximizes the evaluation value Q from the evaluation value Q obtained by the evaluation unit 13 to the position command generation unit 11. The evaluation value Q is executed repeatedly by changing the position command parameter. The positioning control until the predetermined number of times is completed is obtained by the evaluation unit 13 .

The function of the positioning control device 20 of Embodiment 2 will be further described. The learning unit 24 determines a set of position command parameters, and outputs the determined position command parameters to the position command generation unit 11 . The position command generation unit 11 calculates a position command based on the input position command parameters. As described in Embodiment 1, the position command generation unit 11 uses seven position command parameters in order to define the command shape. Compared with the conventional method in which the two parameters of acceleration and velocity are commonly used to specify the command shape, the degree of freedom of the adjustment of the implementation mode 2 is higher than that of the conventional method. Therefore, as long as the position command parameter can be adjusted appropriately, the positioning control device 20 can realize the positioning control showing good response even under the influence of mechanical vibration of the device on which the control object 3 is placed.

FIG. 6 is a flowchart showing an example of the steps of the positioning method of the positioning control device of Embodiment 2. FIG. First, the initial value of the position command parameter is set in the position command generation unit 11 (step S1). The initial value of the position instruction parameter can be any value. Next, the position command generation unit 11 calculates a position command based on the position command parameters set in step S1 (step S2). The drive control unit 12 executes positioning control based on the calculated position command (step S3 ).

Next, the evaluation unit 13 calculates the evaluation value Q using the motor position and the acceleration detection value of the control object 3 (step S4). Then, the learning unit 24 determines whether or not the positioning control has been completed a predetermined number of times (step S5). When the predetermined number of positioning control has not been completed (NO in step S5 ), the learning unit 24 updates the average value for calculating the evaluation value Q based on the position command parameter and the calculated evaluation value Q A function of the variance of the evaluation value Q (step S6).

Then, based on the function updated in step S6, the learning unit 24 obtains the position command parameter in which the sum of the average value of the evaluation value Q and the number of variations becomes the largest (step S7). In addition, the learning unit 24 sets the position command parameter obtained in step S7 to the position command generation unit 11 (step S8 ). Then, in order to execute the positioning control again to obtain the evaluation value Q based on the set position command parameters, the operation of the positioning control device 20 moves to step S2.

In step S5, when the positioning control for a predetermined number of times is completed (“Yes” in step S5), the evaluation value Q of a predetermined number of times is obtained, and the learning unit 24 obtains the evaluation value Q of a predetermined number of times. Among Q, the position command parameter which maximizes the evaluation value Q is selected and set to the position command generation unit 11 (step S9). At this point, the processing ends.

As described above, the learning unit 24 learns the relationship between the position command parameter and the evaluation value Q in step S7, and can obtain the average value and the variance of the evaluation value Q corresponding to the position command parameter. In addition, in step S8, the learning unit 24 obtains a position command parameter that maximizes the sum of the average value of the evaluation value Q and the number of variations. The obtained position command parameters are used for the next positioning control.

Next, the effect obtained by using the position command parameter whose sum of the average value and the variance becomes the largest for the next positioning control will be described. 7 and 8 are diagrams for explaining the effect obtained by the positioning control device of the second embodiment.

Here, the process of selecting the position command parameter of the third group after the operations of the evaluation unit 13 and the learning unit 24 are executed twice will be described. The position command parameters of the first group are expressed as position command parameters Pr11, the position command parameters of the second group are expressed as position command parameters Pr12, and the position command parameters of the third group are expressed as position command parameters Pr13.

For the convenience of description, FIG. 7 and FIG. 8 simplify the position command parameters into one dimension and display them. In FIGS. 7 and 8 , the horizontal axis shows the position command parameter, and the vertical axis shows the evaluation value Q. When the actions of the evaluation unit 13 and the learning unit 24 are performed twice, as indicated by the circles in FIG. 7, the evaluation value Q11 corresponding to the position command parameter Pr11 and the evaluation value corresponding to the position command parameter Pr12 are obtained Value Q12. The learning unit 24 performs learning based on the obtained evaluation value Q11 and evaluation value Q12, and updates the function for calculating the average value and the variance of the evaluation value Q corresponding to the position command parameter.

The curve AV showing the average value and the curve AD showing the sum of the average value and the variance shown in FIG. 7 are calculated based on the function obtained by the learning unit 24 . As shown in FIG. 7 , as indicated by the midpoint between the position command parameter Pr11 and the position command parameter Pr12 , the greater the distance from the acquired data, the higher the uncertainty of the evaluation value Q, and the larger the variance. By the operation of the learning unit 24, the position command parameter Pr13 corresponding to the point P of the asterisk in FIG. 7 in which the sum of the average value and the variance of the evaluation value Q becomes the largest is selected as the next position command parameter.

Using the position command parameter Pr13 to calculate the position command and perform positioning control, as a result, as shown in Fig. 8, the evaluation value Q13 can be obtained. Here, it is assumed that the evaluation value Q13 is larger than the evaluation value Q11 and the evaluation value Q12. When the adjustment is completed at this stage, since the evaluation value Q13 becomes the largest, the position command parameter Pr13 becomes the most excellent parameter when the adjustment is completed.

In the stage of selecting the position command parameter Pr13 of the third group tentatively, not the maximum value of the sum of the average value of the evaluation value Q and the number of variations, but the maximum value of the average value of the evaluation value Q is selected. At this time, in FIG. 7 , since the maximum value of the curve AV of the average value is not the point of the position command parameter Pr13, the position command parameter Pr13 is not selected as the position command parameter of the third group. Therefore, when the maximum value of the average value of the evaluation value Q is selected, there is a possibility that a good parameter cannot be selected.

As described above, the coefficient of variation tends to increase at points farther from the data obtained in the past. The average value tends to increase from the point that it is estimated to be good based on the data acquired in the past. That is, the positioning control device 20 selects the point at which the sum of the average value and the variance becomes the largest as the next position command parameter, so that the balance between the search and the operation to obtain the relatively large evaluation value Q can be well maintained. , at the end of the adjustment, the position command parameter that obtains a relatively large evaluation value Q can be found.

Therefore, the positioning control device 20 of the embodiment 2 can appropriately adjust the position command parameters without causing the operator to make erroneous attempts. As described above, the positioning control device 20 can efficiently perform the adjustment of a favorable command shape for speeding up the positioning control. In addition, in the positioning control device 20 of the second embodiment, the learning unit 24 obtains a function that outputs an estimated value of the estimated value Q corresponding to the position command parameter, or a function that outputs an estimated value of the average value of the estimated value Q and the number of variances as a relation. Thereby, by estimating the distribution of the evaluation value Q, it is possible to adjust the balance between the search and the operation.

In the above description, the positioning control device 20 selects the point where the sum of the average value and the variance of the evaluation value Q becomes the largest as an example of the next position command parameter, but the second embodiment is not limited to this. In one example, the positioning control device 20 may select, as the next position command parameter, the position command parameter corresponding to the point where the value obtained by adding twice the variance and the average value of the evaluation value Q becomes the largest. In addition, in other examples, the positioning control device 20 may also use the average value and the variance of the learned evaluation function, and use the EI (Expected Improvement: Expected Improvement) function and the PI (Probability of Improvement: Improvement Probability) function. or other acquisition function to calculate the point that becomes the argument to the next position command. That is, in Embodiment 2, it is sufficient to use a function including the mean value and the variance of the evaluation value Q to calculate the point that becomes the next position command parameter.

In the second embodiment, the positioning control device 20 selects the point where the sum of the average value and the variance of the evaluation value Q becomes the largest, as the next position command parameter. At this time, when the positioning control device 20 finds the point where the sum of the average value of the evaluation value Q and the number of variations becomes the largest, it can sequentially calculate the average value of the evaluation value Q from the grid points in which the position command parameters are divided at equal intervals. value and variance, and select the position command parameter whose average value and variance of the evaluation value Q become the largest among the grid points. In addition, when the positioning control device 20 finds the point where the sum of the average value and the variance of the evaluation value Q becomes the largest, it can also select the average value and variance of the evaluation value Q by random search based on the virtual random function. The number becomes the largest position command parameter.

Implementation type 3. FIG. 9 is a diagram schematically showing an example of the configuration of the positioning control device of Embodiment 3. FIG. Hereinafter, the same parts as those in the first embodiment are given the same reference numerals, and the description thereof is omitted, and the different parts will be described.

The positioning control device 30 is a device that drives the motor 1 and the motor 5 to move the control object 3 to the target position, and is connected to the motor 1 , the motor 5 and the acceleration detector 4 . Here, the motor 1 is used to drive the control object 3 in the X-axis direction, and the motor 5 is used to drive the motor 1 in the Y-axis direction perpendicular to the X-axis. The motor 1 applies torque and thrust to the controlled object 3 via the ball screw 2 to move the controlled object 3 in the X-axis direction. The motor 1 only needs to be capable of driving the control objects 3 . The motor 5 moves the motor 1 in the Y-axis direction via the ball screw 6 . The motor 5 only needs to be capable of driving the motor 1 . Examples of the motor 1 and the motor 5 include a rotary servo motor, a linear motor, or a stepping motor.

The control object 3 is moved to a desired target position by the motor 1 and the motor 5 . The control object 3 is a machine or part that needs to be positioned and controlled. An example of the control object 3 is an electronic component mounting machine or a head portion of a semiconductor manufacturing apparatus.

The positioning control device 30 includes an X-axis position command generation unit 31X, a Y-axis position command generation unit 31Y, an X-axis drive control unit 32X, a Y-axis drive control unit 32Y, an evaluation unit 33 , and a learning unit 34 .

The X-axis position command generation unit 31X and the Y-axis position command generation unit 31Y generate the position command parameters for driving the motor 1 and the motor 5 respectively to move the control object 3 to the target position based on the position command parameters that determine the shape of the position command. location command. Specifically, the X-axis position command generation unit 31X generates an X-axis position command for determining the acceleration shape of the acceleration section and the deceleration section based on the X-axis position command parameter. The Y-axis position command generation unit 31Y generates a Y-axis position command for determining the acceleration shape of the acceleration section and the deceleration section based on the Y-axis position command parameter. Regarding the generation of position commands in the X-axis direction and the Y-axis direction, the position command generation unit 11 to which Embodiment 1 is applied is an X-axis position command generation unit 31X and a Y-axis position command generation unit 31Y, respectively.

The X-axis drive control unit 32X outputs the X-axis current that drives the motor 1 so that the motor 1 follows the X-axis position command generated by the X-axis position command generation unit 31X. The Y-axis drive control unit 32Y outputs a Y-axis current that drives the motor 5 so that the motor 1 follows the Y-axis position command generated by the Y-axis position command generation unit 31Y. Regarding the control of the motor 1 in the X-axis direction and the control of the motor 5 in the Y-axis direction, those to which the drive control unit 12 of the first embodiment is applied are the X-axis drive control unit 32X and the Y-axis drive control unit 32Y, respectively. That is, the operation of the X-axis drive control unit 32X and the Y-axis drive control unit 32Y is the same as the operation of the drive control unit 12 of the first embodiment.

The evaluation unit 33 calculates the value for evaluation based on the X-axis motor position indicating the position of the motor 1 and the Y-axis motor position indicating the position of the motor 5 and the acceleration detection value of the control object 3 when the positioning control of the control object 3 is executed. The evaluation value Q of the quality of positioning control. The evaluation unit 33 calculates the evaluation value Q regarding the positioning performance based on the X-axis motor position, the Y-axis motor position, and the acceleration detection values when the positioning control regarding the control object 3 is executed. The function of the evaluation unit 33 is basically the same as that of the evaluation unit 13 of the first embodiment.

The learning unit 34 changes the position command parameter within the parameter range that defines the upper limit value and the lower limit value of the position command parameter of the X axis and the Y axis, and learns the situation when the positioning control on the control object 3 is executed a plurality of times. The relationship between the X-axis position command parameter, the Y-axis position command parameter, and the evaluation value Q calculated by the evaluation unit 33 .

The learning unit 34 independently changes each shape of the shape of the acceleration in the acceleration section and the deceleration section determined by the position command parameter, and learns the X-axis position command parameter and the Y-axis position command when the positioning control is executed a plurality of times The relationship between the parameter and the evaluation value Q. Then, as a result of the learning, the learning unit 34 obtains a relational expression between the X-axis position command parameter, the Y-axis position command parameter, and the evaluation value Q. More specifically, the learning unit 34 determines the position command parameters of the X-axis and the Y-axis based on the relational expressions obtained by learning.

Here, the command shapes generated by the X-axis position command generation unit 31X and the Y-axis position command generation unit 31Y are the same as the command shapes shown in Embodiment 1, respectively. That is, the seven parameters about the X-axis are the X-axis position command parameters; the seven parameters about the Y-axis are the Y-axis position command parameters. At this time, the X-axis position command parameter and the Y-axis position command parameter do not need to be the same parameter.

Hereinafter, the evaluation unit 33 and the learning unit 34 will be described in further detail.

The evaluation unit 33 receives the X-axis motor position, the Y-axis motor position, and the acceleration detection value of the control object 3, calculates and outputs the evaluation value Q for evaluating the quality of the positioning control by the method described later. The X-axis drive control unit 32X and the Y-axis drive control unit 32Y operate according to the X-axis position command and the Y-axis position command, respectively. The X-axis position command and the Y-axis position command are based on the X-axis position command parameter and the Y-axis position command, respectively. parameters are calculated. Therefore, the evaluation value Q calculated by the evaluation unit 33 depends on the values of the X-axis position command parameter and the Y-axis position command parameter. That is, the evaluation value Q can be regarded as an index for evaluating the X-axis position command parameter and the Y-axis position command parameter.

Next, a specific calculation method of the evaluation value Q will be described. Figure 10 shows the time response of the deviation between the X-axis position command and the X-axis motor position, the Y-axis position command and the Y-axis position command when the positioning control is performed by using the X-axis position command parameter and the Y-axis position command parameter in the implementation form 3 A graph showing the time response of the deviation of the motor position and the time response of the acceleration detection value of the control object. The graph 1010 is a graph showing the time response to the deviation of the position of the motor 1 on the X axis, the horizontal axis shows the time, and the vertical axis shows the deviation of the position of the motor 1 . The graph 1020 is a graph showing the time response to the deviation of the position of the motor 5 on the Y-axis, the horizontal axis shows time, and the vertical axis shows the deviation of the position of the motor 5 . The graph 1030 is a graph showing the time response of the acceleration of the control object 3 , the horizontal axis shows the time, and the vertical axis shows the acceleration of the control object 3 .

As shown in the graph 1010, the time from the start of the X-axis positioning to the completion of the X-axis positioning when the magnitude of the deviation between the X-axis position command and the X-axis motor position becomes smaller than the predetermined allowable value Ptol is set as the X-axis positioning time TstX. Similarly, as shown in the graph 1020, the time from the start of the positioning of the Y-axis to the completion of the positioning of the Y-axis when the magnitude of the deviation between the Y-axis position command and the Y-axis motor position becomes smaller than the predetermined allowable value Ptol is set as Y-axis positioning time TstY. The allowable value Ptol may be different on the X-axis and the Y-axis.

The time for the control object 3 to reach the vicinity of the target position is the longer time between the X-axis positioning time TstX and the Y-axis positioning time TstY. That is, by comparing the X-axis positioning time TstX and the Y-axis positioning time TstY at the time of positioning execution, and setting the longer time as the evaluation value Q, the time required for the control object 3 to reach the vicinity of the target position can be shortened. make adjustments.

In addition, as shown in the graph 1030, the maximum value of the vibration amplitude of the acceleration detection value after the positioning of the axis with the longer positioning time Tst is defined as the acceleration maximum value Aamp. In addition, let the allowable value of the vibration amplitude of the acceleration detection value be an acceleration allowable value Atol. The evaluation value Q is set so that the vibration amplitude of the acceleration detection value in the vicinity of the target position shows a small value. In order to satisfy the above, the evaluation value Q is set by the following formula (29). Q=‑max(TstX,TstY)–γ×max(0,Aamp–Atol) ･･･(29)

where γ is a positive value. In addition, max(x1, x2) is a function that outputs the larger of the two arguments x1 and the argument x2. According to Equation (29), the smaller the value of the motor's positioning time Tst of which one of the X-axis positioning time TstX and the Y-axis positioning time TstY is larger, the larger the value of the evaluation value Q will be. At this time, the positioning time Tst of the motor, which is the smaller of the X-axis positioning time TstX and the Y-axis positioning time TstY, does not contribute to the evaluation value Q. In addition, in the case where the maximum acceleration value Aamp after the positioning is completed is larger than the allowable acceleration value Atol, the smaller the maximum acceleration value Aamp is, the larger the value of the evaluation value Q is. In the case where the acceleration maximum value Aamp is smaller than the acceleration allowable value Atol, the acceleration maximum value Aamp does not contribute to the evaluation value Q.

FIG. 10 shows an example in which the Y-axis positioning time TstY is longer than the X-axis positioning time TstX. In this case, the longer Y-axis positioning time TstY than the positioning time Tst contributes to the evaluation value Q. In addition, in FIG. 10, as an example, the acceleration maximum value Aamp after the completion of the positioning of the Y-axis with a longer positioning time Tst is set to be smaller than the acceleration allowable value Atol. The evaluation value Q is calculated as described above, whereby the positioning time Tst of the multi-axis positioning control and the magnitude of the acceleration after the positioning is completed can be evaluated.

From the above, in Embodiment 3, the larger the evaluation value Q is, the better the position command parameter can be. However, the evaluation value Q is not limited to the one defined by the formula (29) as long as it can evaluate the positioning control.

The learning unit 34 takes the evaluation value Q as an input, and learns the relationship between the X-axis position command parameter, the Y-axis position command parameter, and the evaluation value Q. Specifically, the X-axis position command parameter and the Y-axis position command parameter are used as input parameters to learn the function of the average value of the output evaluation value Q and the estimated value of the variance. The learning method is the same as that of the second embodiment.

By the operation of the learning unit 34, the average value and the variance of the evaluation value Q corresponding to the X-axis position command parameter and the Y-axis position command parameter can be obtained. Furthermore, as in the second embodiment, the learning unit 34 obtains the X-axis position command parameter and the Y-axis position command parameter that maximize the sum of the average value and the variance of the evaluation value Q. The obtained X-axis position command parameters and Y-axis position command parameters are used for the next positioning control.

By the operation of the learning unit 34, the balance between the search and the operation for obtaining the relatively large evaluation value Q can be well maintained, and the position command parameter for obtaining the relatively large evaluation value Q can be found at the end of the adjustment.

In the third embodiment, an example in which both the X-axis and the Y-axis are operated simultaneously is shown, but the X-axis may be stopped and only the Y-axis may be operated to adjust the shape of the position command. For example, each time the adjustment of the Y-axis is completed, the position is slightly moved in the X-axis direction, whereby the optimal position command shape of the Y-axis corresponding to the position of each X-axis can be adjusted. According to Embodiment 3, regardless of the stop position of the control object 3, the position command shape can be optimized based on the acceleration detection value. Therefore, the operator's time and effort to change the installation position of the acceleration detector 4 is not required.

In addition, in Embodiment 3, the positioning control in the two directions of the X axis and the Y axis is taken as an example, but the positioning control of three or more axes can also generate position commands in the same way.

According to the positioning control device 30 of Embodiment 3, similarly to Embodiments 1 and 2, the position command parameters of a plurality of axes can be appropriately adjusted without the operator's erroneous attempt. As a result, according to the positioning control device 30 of the third embodiment, it is possible to efficiently perform adjustment of a favorable command shape for speeding up the positioning control.

Further, in the third embodiment, the evaluation value Q is calculated based on the positioning time Tst of the longest motor among the one or more motors. Thereby, there is also an effect that the positioning control can be adjusted in a short time for the positioning time Tst of the multi-axis system.

Here, the hardware configuration of the positioning control devices 10 to 30 described in Embodiments 1 to 3 will be described. FIG. 11 is a diagram schematically showing an example of a hardware configuration for realizing the positioning control device of Embodiments 1 to 3. FIG. In addition, since the positioning control apparatuses 10 to 30 have the same hardware structure, the hardware structure of the positioning control apparatus 10 is demonstrated here.

The positioning control device 10 is connected to a processor 71 and a memory 72 via a bus wire 73 . Examples of the processor 71 include a CPU (Central Processing Unit; central processing unit) or a system LSI (Large Scale Integration; large integrated circuit). Examples of the memory 72 include RAM (Random Access Memory) belonging to the main memory device, ROM (Read Only Memory), and HDD (Hard Disk Drive) belonging to the auxiliary memory device. Or SSD (Solid State Drive; solid state hard disk).

When a part or all of the functions of the position command generation part 11 , the drive control part 12 , the evaluation part 13 and the learning part 14 are realized by the processor 71 , the part or all of the functions are realized by the processor 71 and the Software (software), firmware (firmware), or a combination of software and firmware to achieve. The software or firmware is recorded in the form of programs and stored in the memory 72 . The processor 71 realizes some or all of the functions of the position command generation unit 11 , the drive control unit 12 , the evaluation unit 13 , and the learning unit 14 by reading and executing the program stored in the memory 72 .

When some or all of the functions of the position command generation unit 11 , the drive control unit 12 , the evaluation unit 13 and the learning unit 14 are realized by the processor 71 , the positioning control device 10 is stored in the memory 72 : A program in which a part or all of the steps executed by the command generation unit 11 , the drive control unit 12 , the evaluation unit 13 and the learning unit 14 are finally executed. The program stored in the memory 72 can be regarded as causing the computer to execute some or all of the steps or methods executed by the position command generation unit 11 , the drive control unit 12 , the evaluation unit 13 , and the learning unit 14 .

The configuration disclosed in the above-mentioned embodiment shows an example of the content of the present invention, and can be combined with other generally known techniques, and the embodiments can also be combined with each other, and can be omitted or changed within the scope of not departing from the gist. part of the composition.

1,5: Motor 2,6: Ball screw 3: control object 4: Acceleration detector 10, 20, 30: Positioning Controls 11: Position command generation part 12: Drive Control Department 13,33: Evaluation Department 14, 24, 34: Learning Department 31X: X-axis position command generation part 31Y: Y-axis position command generator 32X: X-axis drive control section 32Y: Y-axis drive control part 71: Processor 72: Memory 73: Bus Wire 210, 220, 230, 240, 310, 320, 1010, 1020, 1030: Graph 400: Neural-like network 410: Input layer 411, 421, 431: Node 420: middle layer 430: output layer Aamp: Acceleration maximum value Atol: Allowable acceleration value AD: Curve of mean and sum of variance AV: Curve of Average P: asterisk point Pr11, Pr12, Pr13: Position command parameters Ptol: allowable value Q, Q11, Q12, Q13: Evaluation value S1~S9: Steps T1~T7: The first time is long ~ the seventh time is long Tst: positioning time TstX: X-axis positioning time TstY: Y-axis positioning time W1, W2: Weighting coefficient

FIG. 1 is a diagram schematically showing an example of the configuration of the positioning control device according to the first embodiment. FIG. 2 is a diagram showing an example of a position command used in Embodiment 1, and a speed command, an acceleration command, and a jerk obtained from the position command. 3 is a diagram showing an example of the time response of the deviation between the position command and the motor position and the time response of the acceleration detection value of the control object when positioning control is performed using the command shape generated from the position command parameter in Embodiment 1. FIG. 4 is a diagram schematically showing an example of a neural network used in Embodiment 1. FIG. FIG. 5 is a diagram schematically showing an example of the configuration of the positioning control device according to the second embodiment. FIG. 6 is a flowchart (flowchart) showing an example of a program of the positioning method of the positioning control device of Embodiment 2. FIG. FIG. 7 is a diagram for explaining the effect obtained by the positioning control apparatus of Embodiment 2. FIG. FIG. 8 is a diagram for explaining the effect obtained by the positioning control device of Embodiment 2. FIG. FIG. 9 is a diagram schematically showing an example of the configuration of the positioning control device of Embodiment 3. FIG. Figure 10 shows the time response of the deviation between the X-axis position command and the X-axis motor position, the Y-axis position command and the Y-axis motor position when the positioning control is performed using the X-axis position command parameter and the Y-axis position command parameter in the implementation form 3 The time response of the deviation and the time response of the acceleration detection value of the control object are graphs. FIG. 11 is a diagram schematically showing an example of a hardware configuration for realizing the positioning control apparatuses of Embodiments 1 to 3. FIG.

1: Motor

2: Ball screw

3: control object

4: Acceleration detector

10: Positioning control device

11: Position command generation part

12: Drive Control Department

13: Evaluation Department

14: Learning Department

Claims (5)

A positioning control device is a positioning control device that drives one or more motors to move a control object to a target position, and includes a position command generation unit that generates accelerations that independently determine acceleration sections and deceleration sections based on position command parameters. the position command of the shape; the drive control unit drives the motor in such a way that the motor position indicating the position of the motor follows the position command; the evaluation unit obtains the acceleration detection value indicating the acceleration of the control object from the acceleration detection unit, The evaluation value of the positioning performance of the control object is calculated based on the motor position and the acceleration detection value after the completion of the positioning control is determined based on the motor position; Each shape of the acceleration shape of the position command in the acceleration section and the deceleration section, and learn the relationship between the position command parameter and the evaluation value when the positioning control is performed a plurality of times, and obtain the position command parameter and the above The relational expression of the evaluation value, wherein the evaluation value is calculated according to the positioning time from the start of the positioning to the determination of the completion of the positioning. The positioning control device of claim 1, wherein the evaluation value is calculated based on the positioning time of the motor with the longest positioning time among the one or more motors. The positioning control device according to claim 1 or 2, wherein the learning section obtains a function that outputs an estimated value of the estimated value corresponding to the position command parameter, or an estimate that outputs an average value and a variance of the estimated value A function of the value as the aforementioned relational expression. The positioning control device according to claim 1 or 2, wherein the learning section changes one or more of the motors according to the relational expression between the position command parameter and the evaluation value. The positional directive parameter. A positioning method, which uses a positioning control device including a position command generation part, a drive control part, an evaluation part and a learning part to drive one or more motors to move a control object to a target position, the positioning method comprising; The generating unit generates a position command that independently determines the shape of the acceleration in the acceleration section and the deceleration section based on the position command parameter; the drive control section drives the motor so that the motor position indicating the position of the motor follows the position command The step of obtaining the acceleration detection value indicating the acceleration of the control object by the evaluation unit, and calculating the positioning performance of the control object according to the motor position and the acceleration detection value after the completion of the positioning control is determined according to the motor position. The step of evaluating the value of The step of obtaining the relational expression between the position command parameter and the evaluation value, wherein the evaluation value is calculated according to the positioning time from the start of the positioning to the determination of the completion of the positioning.

Images