WO2018220751A1 - 状態監視装置、並びに機器システム - Google Patents
状態監視装置、並びに機器システム Download PDFInfo
- Publication number
- WO2018220751A1 WO2018220751A1 PCT/JP2017/020280 JP2017020280W WO2018220751A1 WO 2018220751 A1 WO2018220751 A1 WO 2018220751A1 JP 2017020280 W JP2017020280 W JP 2017020280W WO 2018220751 A1 WO2018220751 A1 WO 2018220751A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- state
- motor control
- motor
- value
- state monitoring
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
- H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
- H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
- H02P21/18—Estimation of position or speed
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
- H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
- H02P21/20—Estimation of torque
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/0004—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
- H02P23/0018—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using neural networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P29/00—Arrangements for regulating or controlling electric motors, appropriate for both AC and DC motors
Definitions
- the present invention relates to a state monitoring device that estimates the state of a device system that includes a device driven by a motor, and a device system that includes the state monitoring device.
- the motor control device includes a motor, a real machine unit including a mechanism unit driven by the motor and a motor control unit, and a simulation model unit including a motor model, a mechanism model unit, and a control model unit.
- a simulation model unit including a motor model, a mechanism model unit, and a control model unit.
- inertia obtained from the rigid body model is set as an initial value.
- the actual machine part and the simulation model part operate according to the position command given from the host controller.
- the position feedback amount detected by the position detector in the actual machine unit is compared with the model position feedback amount in the simulation model unit.
- the inertia value set in the simulation model unit is changed so that they match.
- the present invention provides a state monitoring device that can estimate the state of a device system that is difficult to model, and a device system including the state monitoring device.
- a state monitoring apparatus is a state monitoring apparatus for a device system including a device driven by a motor controlled by a motor control unit, and is a motor that is a state variable in the motor control unit.
- Motor control internal value creation means for creating a control internal value
- state estimation means for estimating the state of the device system based on the motor control internal value created by the motor control internal value creation means.
- an apparatus system is an apparatus system including an apparatus driven by a motor, and includes an actuator operated by a driving force of the motor, and a motor control means for controlling the motor.
- a motor control internal value creating means for creating a motor control internal value that is a state variable in the motor control means, and a state for estimating the state of the device system based on the motor control internal value created by the motor control internal value creating means
- An estimation unit and an information transmission unit that displays information related to the state of the device system estimated by the state estimation unit.
- the present invention it is possible to estimate the state of the device system that is difficult to model by estimating the state of the device system based on the motor control internal value.
- FIG. 1 shows a configuration of a device system that is a first embodiment of the present invention and includes a state monitoring device. It is a block diagram which shows the structure of a motor control means. It is a block diagram which shows the structure of a motor control internal value preparation means. It is a block diagram which shows the structural example of a state calculation means. It is a block diagram which shows the structural example of a state calculation means. It is a block diagram which shows the structural example of an information transmission means. The structure of an electric current command preparation part is shown. The structure of the equipment system provided with the state monitoring apparatus which is Example 2 of this invention is shown. The structural example of a state estimation means update means is shown.
- An example of updating the state estimation model is shown.
- the structure of the apparatus system provided with the state monitoring apparatus which is Example 3 of this invention is shown.
- the structure of the equipment system provided with the state monitoring apparatus which is Example 4 of this invention is shown.
- 9 shows a configuration of a machine tool system that is Embodiment 5 of the present invention.
- the structure of the vehicle equipment system which is Example 6 of this invention is shown.
- the state of a complicated device system that is difficult to model by a transfer function is estimated using a motor control internal value that is highly relevant to the state of the device system.
- the equipment system which can reduce the burden of an equipment worker using the estimated state is comprised.
- the state of the device system is the state of the device itself, for example, whether there is an abnormality in the operating state, the degree of deterioration of the device, etc., and the state of the product manufactured by the device system, such as quality, It is.
- the state quantity is an index indicating the state of the device system.
- the state quantity is estimated using a motor control internal value without using special means (such as complicated simulation).
- FIG. 1 shows an example of a time change (time series data) of a motor characteristic value in the present embodiment.
- ⁇ m , Im, and Vm are the motor speed, motor current, and motor voltage in the actual machine, respectively.
- the time change of the square root of the square sum of the q-axis voltage command value Vq and the d-axis voltage command Vd which are motor control internal values is shown.
- the motor is driven by an inverter and controlled by so-called vector control so that the motor current becomes a constant value.
- the motor rotation speed ( ⁇ m ) pulsates.
- the device system includes a current sensor and a voltage sensor, but does not include a motor rotation speed sensor, information (Im, Vm) related to the motor current and the motor voltage can be obtained. It is difficult to detect or estimate the load pulsation from the above information.
- the square root sum of the q-axis voltage command value Vq and the d-axis voltage command Vd includes information on motor pulsation.
- the motor current vibrates in the initial stage, but the motor current is constant by pulsating the q-axis voltage command value Vq and the d-axis voltage command Vd by the motor current constant control.
- the motor current Im
- Vm motor voltage
- pulsation information appears in the square sum square root of the q-axis voltage command value Vq and the d-axis voltage command Vd. That is, based on the q-axis voltage command value Vq and the d-axis voltage command Vd that are motor control internal values, the motor load that is one state quantity of the device system can be estimated.
- FIG. 2 shows a configuration of a device system that is a first embodiment of the present invention and includes a state monitoring device.
- an arithmetic processing device such as a microcomputer functions as a control device and a state monitoring device by executing a predetermined program (the same applies to other embodiments).
- the first embodiment includes an inverter 1 and a motor 2 that is rotationally driven by the inverter 1 as a power source. Further, the first embodiment includes an actuator 3 that is driven by a motor 2 to perform a mechanical operation.
- the inverter 1 is controlled by motor control means 4 to which a so-called vector control method is applied.
- the motor control means 4 acquires information such as motor current, motor voltage, rotor position information, and rotation speed from the inverter 1 or the motor 2, and based on the information, the motor control means 4 A voltage command value for driving 2 is created. Then, the motor control means 4 gives the created voltage command value to the inverter 1.
- the external data acquisition means 10 is composed of sensors installed in the device system other than the motor 2 and the inverter 1, and acquires the device temperature, the outside air temperature, the upper command value of the device, and the like.
- the state estimation means 5 is a motor control internal value creation means 6 that creates a motor control internal value, and a state calculation that calculates the state quantity of the device system based on the motor control internal value created by the motor control internal value creation means 6. Means 7 are provided.
- the motor control internal value creation means 6 includes time-series data acquired by a current sensor, a voltage sensor and a position sensor, which are installed separately from the motor control means 4 in the input part or output part of the motor 2, Based on the data acquired by the external data acquisition means 10, a motor control internal value that is a state variable in the motor control means 4 and is related to the state of the device system is created.
- the state calculation means 7 has a state estimation model, and based on the motor control internal value created by the motor control internal value creation means 6 using the state estimation model, the state of the device system, that is, the state of the device itself, A state quantity indicating the state (quality, etc.) of the product manufactured by the device is calculated.
- the state estimation means 5 inputs the data acquired by each of the aforementioned sensors and the external data acquisition means 10, creates a motor control internal value created from the input data, and creates the motor control internal value created Or information on the state of the device system indicated by the state quantity (hereinafter referred to as “estimated state”) is output.
- the estimated state output from the state estimation unit 5 is transmitted to the information transmission unit 8 and the motor control unit update unit 9 described later.
- the information transmitting unit 8 displays information on the state of the device system, for example, information on the state of the device itself and its change, or information on the quality of the product and its change. It notifies the worker who uses the device system and the administrator of the device system by voice, lamp, etc. Thereby, it is possible to reduce the work load in grasping the maintenance time of the equipment, grasping the situation at the time of quality change and equipment adjustment work.
- the motor control means update means 9 changes the motor control means 4, that is, the control command, control parameter, or control software based on the estimated state output from the state estimation means 5. For example, when the quality of the product has changed, the motor control means updating means 9 changes the motor control means 4 so as to suppress the change in quality. As a result, the adjustment work of the device system can be automated, so that the workload is reduced.
- FIG. 3 is a block diagram showing the configuration of the motor control means 4.
- the command from the host controller is the position command ⁇ *, but it may be a speed (rotation speed) command ⁇ * or a torque command Trq *.
- the block diagram of the motor control means 4 is a block diagram and a boundary on the right side of the boundary line A in FIG. It is a block diagram on the right side of the line B.
- the speed command creating unit 101 calculates the position feedback value ⁇ m measured by the sensor and the position command value ⁇ *. Based on the difference, a speed command ⁇ * is created and output.
- the torque command creating unit 102 creates and outputs a torque command Trq * based on the difference between the speed (rotation speed) feedback value ⁇ m actually measured by the sensor and the speed command ⁇ *. To do.
- the current command creation unit 103 creates a current command on the dq axis in the rotating coordinate system, that is, a d-axis current command Id * and a q-axis current command Iq * based on the torque command Trq *. And output.
- the voltage command generation unit 104 receives the difference between the d-axis current feedback value Id and the d-axis current command Id *, and the q-axis current feedback values Iq and q Based on the difference from the shaft current command Iq *, a voltage command on the dq axis, that is, a d-axis voltage command Vd * and a q-axis voltage command Vq * is generated and output.
- the d-axis current feedback value Id and the q-axis current feedback value Iq are obtained by measuring the U-phase current feedback value Iu, the V-phase current feedback value Iv, and the W-phase current feedback value Iw of the motor that are actually measured by the sensor. It is obtained by three-phase to two-phase conversion by the two-phase conversion unit 106.
- the two-phase / three-phase converter 105 receives the d-axis voltage command Vd * and the q-axis voltage command Vq *, the d-axis voltage command Vd * and the q-axis voltage command Vq * are converted into the U-phase voltage command Vu *, V Phase voltage command Vv * and W phase voltage command Vw * are converted, and these voltage commands are output to inverter 1.
- the state estimation unit 5 includes the motor control internal value creation unit 6 and the state calculation unit 7. Therefore, first, the motor control internal value creation means 6 will be described, and then the state calculation means 7 will be described.
- FIG. 4 is a block diagram showing the configuration of the motor control internal value creating means 6.
- the motor control internal value creating means 6 is, in other words, an inverse model of the motor control means 4 shown in FIG. That is, the motor control internal value creating means 6 is the speed command creating section 101, torque command creating section 102, current command creating section 103, voltage command creating section 104, 2 phase / 3 phase in the motor control means 4 (see FIG. 3).
- the speed command creation unit inverse model 111, the torque command creation unit inverse model 112, the current command creation unit inverse model 113, and the voltage command creation unit inverse model 114 respectively.
- a three-phase / two-phase converter 115 and a three-phase / two-phase converter 116 are provided.
- the command from the host controller to the motor control means 4 is the position command ⁇ *, but it may be a torque command Trq * or a speed command ⁇ *.
- the block diagram of the motor control internal value creating means 6 is shown by the boundary line C in FIG. A block diagram on the right side, a block diagram on the right side of the boundary line D, and a block diagram on the right side of the boundary line E are shown.
- the motor control internal value creation means 6 is acquired by a current sensor, a voltage sensor, and a position sensor that are installed separately from the motor control means 4 in the input part or output part of the motor 2. Or three or more of the motor three-phase voltage feedback values Vu, Vv, and Vw, the motor three-phase current feedback values Iu, Iv, and Iw, the speed feedback value ⁇ m, and the position feedback value ⁇ m.
- the state variables of the motor control means 4 are ⁇ *, ⁇ m, ⁇ *, ⁇ m, Trq *, Id *, Iq *, Id, Iq, Vd *, Vq *, Vu *. , Vv *, Vw *, Vu, Vv, Vw, Iu, Iv, Iw, the difference between the command value and the actually measured value, the output value of the proportionalizer, integrator, and differentiator constituting the controller is the motor control internal value. It is. That is, one or more of these motor control internal values in the motor control means 4 are created by the motor control internal value creation means 6.
- the motor control internal value creating means 6 shown in FIG. 4 creates and uses the state variable of the motor control means 4 during the process of the motor control means 4.
- the state variables for example, Id *, Iq *, Id, Iq, Vd *, Vq *
- the first embodiment can be applied to various state estimations of a wide variety of device systems.
- 5 and 6 are block diagrams showing an example of the configuration of the state calculation means 7.
- the state calculation means 7 (see FIG. 2) is based on at least one motor control internal value created by the motor control internal value creation means 6, and thus the state of the device system, that is, the state of the device itself and the device.
- the state quantity indicating the state (quality, etc.) of the product manufactured by is calculated.
- the state calculation means 7 may calculate the state quantity based on the data (such as the temperature of the device) acquired by the external data acquisition means 10 (see FIG. 2) in addition to the motor control internal value. 5 and 6, the motor control internal values (X1 to Xn) and the data (Z1 to Zn) acquired by the external data acquisition unit 10 are input to the state calculation unit 7.
- X1 to Xn represent motor control internal values
- Z1 to Zn represent information acquired by the external data acquisition means 10.
- At least one motor control internal value is input to the state calculation means 7. Further, the presence / absence and the number of inputs of information acquired by the external data acquisition unit 10 to the state calculation unit 7 are arbitrary.
- the type and number of information acquired by the motor control internal value and the external data acquisition unit 10 input to the state calculation unit 7 are set according to the configuration of the state calculation unit (for example, a statistical model described later). .
- Xn, Zn, and Cn are set to the same “n” for convenience, but this “n” can be any number of Xn, Zn, and Cn. This does not mean that the number of Xn, Zn and Cn is the same.
- the state calculation means 7 has a regression equation as a statistical model used for state quantity calculation.
- the state calculation unit 7 includes a feature amount calculation unit 121 that sets a feature amount that serves as an explanatory variable of the regression equation, and a state amount based on the regression equation based on the feature amount set by the feature amount calculation unit 121.
- Computation means 122 for calculating (object variable) is provided.
- the feature quantity calculation means 121 inputs Xn and Zn, and calculates a feature quantity (explanatory variable) Cn to be input to the calculation means 122 based on the input Xn and Zn.
- the feature quantity calculation means 121 outputs the Xn or Zn instantaneous data as it is without processing it as the feature quantity Cn, or results of frequency analysis of the Xn or Zn instantaneous data in a predetermined time interval (amplitude, phase, etc.), An effective value, average value, standard deviation, maximum value or minimum value in a predetermined time interval, an overshoot amount or a peak value in a predetermined time interval are output.
- the number of feature quantities Cn may be singular or plural depending on the regression equation.
- the feature amount calculation means 121 outputs a predetermined amount calculated from the motor control internal value, for example, active power, reactive power, square root sum square of Vq and Vd as shown in FIG. Also good. Further, a disturbance torque estimated by a so-called observer may be used as the feature amount. Note that these feature amounts may be output after further frequency analysis, statistical calculation (average), or the like.
- the calculation means 122 receives the feature quantities C1 to Cn output from the feature quantity calculation means 121, and calculates state quantity estimated values (Ya, Yb) based on the feature quantities C1 to Cn.
- a one-dimensional regression equation is used in which the feature quantity C1 is an explanatory variable and the state quantity Y indicating the state of the device and the quality of the product is an objective variable.
- the calculation means 122 outputs the calculated value Ya of the regression equation for Ca as the current state quantity (estimated value).
- the computing means 122 outputs the standard deviation Yb of the state quantity with respect to Ca as the state quantity (estimated value).
- the regression equation an average state quantity can be estimated, and a variation amount of the state quantity can also be estimated. Therefore, it is possible to estimate the state of the device or product and to estimate the occurrence rate of the state.
- the state estimation means 5 may output the calculated state quantity (estimated value) as the estimated state, or information on the state of the equipment system indicated by the state quantity (for example, the operating state of the equipment and the quality of the product) May be output as the estimated state.
- the regression equation in the calculation means 122 is obtained in advance by statistical modeling or the like using motor control internal value data acquired in the past, device state monitoring data when the data is acquired, and product inspection results. Desired.
- FIG. 6 shows a configuration example of other state calculation means 7.
- the state calculation means 7 has a clustering result as a statistical model used for state quantity calculation.
- the state calculation unit 7 is based on the feature amount calculation unit 123 having the same function as the feature amount calculation unit 121 in FIG. 5 described above and the feature amount set by the feature amount calculation unit 121.
- a classification unit 124 that calculates a state quantity based on a clustering result related to the product state.
- the classification unit 124 obtains a range in which a device or a product shows a predetermined state (for example, a normal state) in a feature amount space (two-dimensional (C1, C2 in FIG. 6)) obtained in advance by clustering, and a feature amount.
- the feature amounts C1 to Cn set by the calculation means 121 that is, the distances from the spatial points in the feature amount space are calculated. Then, based on the calculated distance, it is determined whether or not the state of the device or the product is a predetermined state. Then, the classification unit 124 outputs a state quantity (estimated value) Y3 according to the determination result.
- the classification unit 124 when the input feature values C1 and C2 are Ca and Cb, respectively, , Cb) and the product quality normal range (cluster) in the same space.
- the classification unit 124 outputs the calculated distance or a predetermined amount corresponding thereto as a state quantity (estimated value) Y3.
- the calculated distance for example, Euclidean distance or Mahalanobis distance can be used.
- the state estimation unit 5 may output the calculated state quantity (estimated value) as an estimated state, or information on the state of the equipment system indicated by the state quantity (for example, whether there is an abnormality in equipment or product quality). May be output as the estimated state.
- the state of the device or the product is a predetermined state (for example, a normal state).
- the feature amount space is not limited to a two-dimensional space, and may be a three-dimensional or more multi-dimensional space. Further, a plurality of ranges (clusters) of predetermined state quantities for determining the distance may be used. Thereby, it can be determined whether the state of the device or the product is a plurality of predetermined states.
- the clustering results used by the classification unit 124 are machine learning and artificial intelligence using motor control internal values acquired in the past, device state monitoring data when the data is acquired, and product inspection results. Or the like in advance.
- the information transmission unit 8 displays the estimated state output from the state estimation unit 5 by an image, sound, or the like. Moreover, you may display the feature-value used in the state estimation means 5 with an estimated state. Further, the temporal transition of the estimated state may be displayed. Such a display allows the operator to accurately grasp the current state of the device or product. Note that the reference value and threshold value of the state quantity, the meaning indicated by the data (for example, information regarding the necessity of adjustment of the device), and the like may be displayed at the same time. Thereby, the worker can accurately determine whether the state of the device or the product is good or not.
- the information display means includes image display means such as a display, sound display means such as an alarm device, and lighting display means such as a rotation warning light (so-called patrol lamp).
- image display means such as a display
- sound display means such as an alarm device
- lighting display means such as a rotation warning light (so-called patrol lamp).
- the information transmission means 8 compares the state quantity estimated value Ya with a predetermined threshold value, and if it is equal to or greater than the threshold value, activates the alarm device or the rotation warning light.
- FIG. 7 is a block diagram showing a configuration example of the information transmission means 8.
- This configuration example displays data on state quantities (estimated values) and feature quantities, and processes these data to create information related to the state of devices and products, and an information processing section A display for displaying information created by 125 is provided.
- the amount of change ⁇ C of the feature amount C1 is calculated.
- the worker since the index relating to the adjustment work is displayed, the worker can adjust the equipment accurately and the burden on the worker in the equipment adjustment work is reduced.
- the motor control means update means 9 updates the motor control command value and control parameter in the motor control means according to the estimated state output from the state estimation means 5. For example, the motor control means updating means 9 compares the state quantity (estimated value) with a predetermined threshold value, and increases or decreases preset motor control command values and control parameters according to the comparison result.
- the motor control means updating means 9 may change the motor control command value and the control parameter using a predetermined function instead of the threshold value. Furthermore, when there are a plurality of input state quantities (estimated values), the motor control means updating means 9 searches for a motor control command value and a motor control parameter to be changed using device learning, and searches for the motor control searched. The command value and the motor control parameter may be changed according to the plurality of state quantities (estimated values).
- the device learning for example, reinforcement learning such as Q learning can be applied.
- the motor control software itself may be changed without being limited to the motor control command value and the motor control parameter.
- the equipment can be automatically adjusted according to the state of the equipment or the product. Thereby, the work burden of the worker can be reduced.
- the motor control internal value that affects the state of the device system is estimated from the sensor information or the information acquired by the external data acquisition unit. Then, by estimating the state of the device system based on the estimated motor control internal value, it is possible to estimate the state of the device system that is difficult to model using a transfer function or the like.
- the motor control internal value creating unit 6 creates the motor control internal value based on data acquired by a sensor installed separately from the motor control unit 4. You may create based on the sensor for this.
- the device system can be provided with a state monitoring function without increasing the number of sensors.
- a state monitoring device including the state estimating means 5 in FIG. 2 is installed in an equipment system by providing a sensor independently for state monitoring, the wiring of the sensor for the motor control means 4 is changed or the characteristics are readjusted. Do not need. Therefore, the state monitoring device can be easily installed in the equipment system. In particular, a state monitoring device can be easily provided for an existing device system. Further, since the state monitoring device does not affect the operation of the motor control unit, readjustment of the motor control unit becomes unnecessary, and control of the motor can be maintained regardless of the operation of the state control device.
- FIG. 9 shows a configuration of a device system that is a second embodiment of the present invention and includes a state monitoring device.
- FIG. 9 shows a configuration of a device system that is a second embodiment of the present invention and includes a state monitoring device.
- the regression equation and the clustering result used by the state calculation unit 17 are updated according to the state of the device system. For this reason, as shown in FIG. 9, a state quantity acquisition unit 20 and a state estimation unit update unit 21 are added to the device system of the first embodiment.
- the state quantity acquisition means 20 extracts the data used in the state estimation means update means 21, that is, the recorded actual state quantity, from a record (not shown) of the actual state of the device system.
- a record is, for example, a past maintenance record related to a device or a past quality inspection record related to a product.
- the contents of the maintenance record include, for example, the failure location of the equipment, the failure status (for example, the failure status (folding, chipping) of the machining tool of the machine tool), the operation time until failure, the occurrence location of an abnormality that does not lead to failure, This is the operating time until a state or abnormality occurs.
- the contents of the quality inspection record are, for example, the surface roughness of the cut material processed by the cutting device, the viscosity of the kneaded material kneaded by the kneader, and the presence or absence of burrs and warpage in the product by the injection molding machine. These records are often converted into electronic data and databased. Therefore, the state quantity acquisition means 20 may be configured using software that can handle SQL (Structured Query Query Language) that can execute database operations.
- SQL Structured Query Query Language
- the state estimation means update means 21 inputs data extracted by the state quantity acquisition means 20, at least one motor control internal value associated with this data, and information output by the state calculation means 17, and inputs these information. Based on this, the regression equation and clustering result used in the state calculation means 17 are updated.
- the data of the motor control internal value inputted by the state estimating means updating means 21 is data when the data (equipment maintenance result, product inspection result, etc.) inputted from the state quantity obtaining means 20 is obtained. Yes, it is recorded in association with the recording of the status of the device system. Accordingly, the corresponding motor control internal value is input to the state estimating means updating means 21 in accordance with the extraction of the data (recorded actual state quantities) by the state quantity obtaining means 20.
- information from the external data acquisition unit 22 is also input to the state estimation unit update unit 21, but the specification of the information from the external data acquisition unit 22 is arbitrary. Note that the state calculation means can be updated with high accuracy by using the information from the external data acquisition means 22 together.
- FIG. 10 shows a configuration example of the state estimation means update means 21.
- motor control internal values, device and product state quantities, and external data input to the state estimation means update means 21 are accumulated in the data storage means 201 for a certain period of time in the past.
- the acquisition period of the data to be stored, the timing to store, and the amount of data are set in advance.
- the data stored in the data storage unit 201 is input to the feature amount calculation unit 202.
- the function of the feature amount calculating unit 202 is the same as that of the feature amount calculating units 121 and 123 (FIGS. 5 and 6) in the first embodiment.
- the feature amount of the motor control internal value calculated by the feature amount calculation unit 202 is input to the model creation unit 203.
- the model creation unit 203 constructs a regression equation by statistical modeling or device learning based on the input feature amount and the state amount read from the data storage unit 201, or performs clustering by device learning or artificial intelligence. When the regression equation is constructed and clustered, modeling is executed using the state quantity and the feature quantity as the objective variable and the explanatory variable, respectively.
- the model change determination unit 204 includes a state estimation model (regression equation, clustering result, etc.) created by the model creation unit 203 and a state estimation model currently used for state estimation (a regression equation set in the state calculation unit). And the clustering result) are determined to determine whether it is necessary to change the parameters of the currently used state estimation model or to determine whether it is necessary to change the model itself.
- the model change determination unit 204 outputs the determination result as change information. Based on this change information, the state estimation unit 15 updates the state estimation model set in the state calculation unit 17.
- the update of the state estimation model may be performed every predetermined period or irregularly. Further, when the regression equation is output from the model creating unit 203, if the currently used regression equation and the regression equation output from the model creating unit 203 are in the same form (for example, both are linear), only the parameters are updated, If the form of the expression has changed, it is preferable to update the entire expression. When the classing result is output from the model creating unit 203, it is preferable to update the currently used clustering result to the result output from the model creating unit 203.
- FIG. 11 shows an example of updating the state estimation model when the state estimation model is represented by a regression equation.
- the form of the regression equation changes with time, and the entire equation is updated.
- the state estimation model is updated by the state estimation unit updating unit 21, even if the state of the device or the product changes with time, the state estimation accuracy is improved. Can be secured.
- FIG. 12 shows the configuration of a device system that is a third embodiment of the present invention and includes a state monitoring device.
- the motor control means 34 creates a voltage command value to be given to the inverter 31 as in the first embodiment, and also has a function as the motor control internal value creation means 6 in the first embodiment.
- the configuration of the motor control unit 34 is the same as that of the first embodiment (see FIG. 3), but the motor control unit 34 is configured to generate motor control internal values (Id, Iq, Vd *, Vq *, Trq *, ⁇ *, etc.) are output to the state calculating means 37.
- the equipment system since the motor control means also serves as the motor control internal value creation means, and the sensor for motor control is also used for creating the motor control internal value, the equipment system can be simplified.
- FIG. 13 shows the configuration of a device system that is a fourth embodiment of the present invention and includes a state monitoring device.
- a state quantity acquisition unit 50 and a state estimation unit update unit 51 are added to the device system of the third embodiment. That is, in the third embodiment, as in the above-described second embodiment (FIG. 9), the regression formula and clustering result used by the state calculation unit 47 are updated according to the state of the device system.
- the device system can be simplified and the accuracy of state estimation can be ensured even if the state of the device or the product changes with time.
- FIG. 14 shows a configuration of a machine tool system including a milling machine, which is Embodiment 5 of the present invention.
- This device system includes a state monitoring unit similar to that in the fourth embodiment (see FIG. 13).
- the actuator driven by the motor is an end mill 403 which is a milling machine processing tool.
- the motor control means 408 controls the inverter 405 to drive the motor 404 and the end mill 403.
- External data acquisition means 406 acquires information such as the cutting feed rate and cutting position from the milling machine controller. Further, the state quantity acquisition means 407 acquires the inspection result of the surface roughness of the plate material cut by the milling machine from the quality inspection database 401. These acquired data and the motor control internal value output by the motor control unit 408 are input to the state estimation unit update unit 410 to create and update a regression equation used in the state estimation unit 409. The state estimation means 409 estimates the quality of the cut object during cutting using the regression equation.
- the information transmission means 411 mills the quality estimation result of the cutting object calculated by the state estimation means 409, the explanatory variable (feature value of the motor control internal value) used for estimating the quality, and their changes. Display on a nearby display.
- the configuration of the first embodiment or the second embodiment may be applied to the configuration of the state estimation unit of the fifth embodiment.
- the quality of the cut object can be quantitatively confirmed in real time. Thereby, when an operator grasps
- the system configuration of the fifth embodiment is not limited to a machine tool system including a milling machine, but can be applied to other machine tool systems including a drilling machine using a drill blade as a processing tool.
- FIG. 15 shows the configuration of a vehicle equipment system that is Embodiment 6 of the present invention.
- This device system includes a state monitoring unit similar to that in the fourth embodiment (see FIG. 13).
- the vehicle is, for example, an electric railway vehicle or an electric vehicle.
- the actuator driven by the motor is a wheel 303.
- the motor control means 308 controls the inverter 305 to drive the motor 304 and the wheels 303.
- External data acquisition means 306 acquires information such as weather and temperature.
- the state quantity acquisition unit 307 acquires the replacement timing and failure factor of the wheel 303 from the maintenance database 301.
- the acquired data and the motor control internal value output by the motor control unit 308 are input to the state estimation unit update unit 310 to create and update the clustering result used in the state estimation unit 309.
- the state estimation means 309 estimates the wheel replacement time and failure time using the clustering result.
- the information acquired by the external data acquisition unit 306 and the state quantity acquisition unit 307, and the motor control internal value may be acquired from another vehicle in addition to the own vehicle.
- the information transmission means 311 includes estimation results of the wheel replacement time and failure time estimated by the state estimation means 309, and explanatory variables (features of motor control internal values) used for estimating the wheel replacement time and failure time. Change) is displayed on a display installed in the driver's seat 302.
- the motor control means updating means 312 performs an output limiting operation for extending the life of the equipment when the replacement time or failure time is close to the motor or wheel replacement time or failure time estimated by the state estimation means 309. As described above, the control command value and the control parameter of the motor control means 308 are changed. As a result, the state of the wheel and the like can be quantitatively confirmed in real time, thereby reducing the work load related to grasping the state of the wheel and analyzing the cause of failure performed by the inspector. Furthermore, since life-extending operation can be performed automatically, sudden stoppage of operation can be prevented.
- the sixth embodiment it is possible to grasp the wheel replacement time and failure time with high accuracy. Thereby, the frequency of maintenance is reduced, the work load is reduced, and the maintenance cost is reduced. In addition, since the equipment is maintained at an appropriate time and failure can be prevented, the reliability of the equipment is improved.
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Control Of Electric Motors In General (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Control Of Ac Motors In General (AREA)
Abstract
Description
Claims (15)
- モータ制御手段によって制御されるモータによって駆動される機器を備える機器システムの状態監視装置において、
センサ情報に基づいて、前記モータ制御手段における状態変数であるモータ制御内部値を作成するモータ制御内部値作成手段と、
前記モータ制御内部値作成手段によって作成される前記モータ制御内部値に基づいて、前記機器システムの状態を推定する状態推定手段と、
を備えることを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
前記機器システムの前記状態は、前記機器の状態あるいは前記機器による製造物の状態であることを特徴とする状態監視装置。 - 請求項2に記載の状態監視装置において、
前記モータ制御内部値は、位置指令、位置フィードバック値、速度指令、速度フィードバック値、トルク指令、d軸電流指令、q軸電流指令、d軸電流フィードバック値、q軸電流フィードバック値、d軸電圧指令、q軸電圧指令、モータ電圧指令、モータ電圧フィードバック値、モータ電流フィードバック値、フィードバック値と指令値との偏差、比例器の出力、積分器の出力、微分器の出力の内のいずれかを含むことを特徴とする状態監視装置。 - 請求項3に記載の状態監視装置において、
前記センサ情報は、位置フィードバック値、速度フィードバック値、モータ電圧フィードバック値、モータ電流フィードバック値の内のいずれかを含むことを特徴とする状態監視装置。 - 請求項2に記載の状態監視装置において、
前記状態推定手段は、統計的モデルに基づいて前記機器システムの前記状態を推定することを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
前記モータ制御内部値作成手段は前記モータ制御手段の逆モデルによって構成されることを特徴とする状態監視装置。 - 請求項1または請求項6に記載の状態監視装置において、
前記センサ情報は、前記モータ制御手段あるいは前記モータにおける入力部あるいは出力部に、前記モータ制御手段用とは別に設けられるセンサによって取得されることを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
さらに、前記状態推定手段によって推定される前記機器システムの前記状態に関わる情報を表示する情報伝達手段を備えることを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
さらに、前記状態推定手段によって推定される前記機器システムの前記状態に応じて、前記モータ制御手段を更新するモータ制御手段更新手段を備えることを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
さらに、前記機器システムの状態に関する過去のデータを取得する状態量取得手段と、
前記状態量取得手段によって取得される前記データに基づいて、前記状態推定手段を更新する状態推定手段更新手段と、
を備えることを特徴とする状態監視装置。 - 請求項10に記載の状態監視装置において、
前記データは、前記機器のメンテナンス結果または前記機器による製造物の品質検査結果であることを特徴とする状態監視装置。 - 請求項1に記載の状態監視装置において、
前記モータ制御内部値作成手段は、前記モータ制御手段に含まれ、かつ前記モータ制御手段から前記状態変数を出力する手段であることを特徴とする状態監視装置。 - モータによって駆動される機器を備える機器システムにおいて、
前記モータの駆動力によって操作されるアクチュエータと、
前記モータを制御するモータ制御手段と、
前記モータ制御手段における状態変数であるモータ制御内部値を作成するモータ制御内部値作成手段と、
前記モータ制御内部値作成手段によって作成される前記モータ制御内部値に基づいて、前記機器システムの状態を推定する状態推定手段と、
前記状態推定手段によって推定される前記機器システムの前記状態に関わる情報を表示する情報伝達手段と、
を備えることを特徴とする機器システム。 - 請求項13に記載の機器システムにおいて、
前記アクチュエータは工作機械における加工用ツールであり、
さらに、前記工作機械による製造物の品質検査結果を取得する状態量取得手段と、
前記状態量取得手段によって取得される前記品質検査結果に基づいて、前記状態推定手段を更新する状態推定手段更新手段と、
を備えることを特徴とする機器システム。 - 請求項13に記載の機器システムにおいて、
前記アクチュエータは車両が備える車輪であり、
さらに、前記車両のメンテナンス結果を取得する状態量取得手段と、
前記状態量取得手段によって取得される前記メンテナンス結果に基づいて、前記状態推定手段を更新する状態推定手段更新手段と、
を備えることを特徴とする機器システム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019521603A JP6899897B2 (ja) | 2017-05-31 | 2017-05-31 | 状態監視装置、並びに機器システム |
EP17911990.4A EP3633851A4 (en) | 2017-05-31 | 2017-05-31 | STATUS MONITORING DEVICE AND DEVICE SYSTEM |
PCT/JP2017/020280 WO2018220751A1 (ja) | 2017-05-31 | 2017-05-31 | 状態監視装置、並びに機器システム |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2017/020280 WO2018220751A1 (ja) | 2017-05-31 | 2017-05-31 | 状態監視装置、並びに機器システム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018220751A1 true WO2018220751A1 (ja) | 2018-12-06 |
Family
ID=64454680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/020280 WO2018220751A1 (ja) | 2017-05-31 | 2017-05-31 | 状態監視装置、並びに機器システム |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3633851A4 (ja) |
JP (1) | JP6899897B2 (ja) |
WO (1) | WO2018220751A1 (ja) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6850458B1 (ja) * | 2019-11-22 | 2021-03-31 | ディエスピーテクノロジ株式会社 | Ai搭載型モータ状態量推定システムおよびモータモデル用機械学習方法 |
WO2022004417A1 (ja) | 2020-07-01 | 2022-01-06 | 株式会社日立産機システム | 動力伝達機構の管理装置、動力伝達機構の管理方法 |
JPWO2022186382A1 (ja) * | 2021-03-05 | 2022-09-09 | ||
TWI824444B (zh) * | 2021-04-28 | 2023-12-01 | 日商Sumco股份有限公司 | 狀態判定裝置以及狀態判定方法 |
DE102023125011A1 (de) | 2022-10-11 | 2024-04-11 | Sumitomo Heavy Industries, Ltd. | Steuervorrichtung, spritzgiessmaschine und steuerverfahren |
TWI839828B (zh) * | 2021-12-24 | 2024-04-21 | 日商日立產機系統股份有限公司 | 動力傳達機構之管理裝置、動力傳達機構之管理方法及管理系統 |
JP7574170B2 (ja) | 2021-11-12 | 2024-10-28 | 株式会社日立製作所 | 状態分析装置、及び状態推定方法 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH096432A (ja) * | 1995-06-14 | 1997-01-10 | Mitsubishi Electric Corp | 制御システムの異常検知装置 |
JP2004260891A (ja) | 2003-02-25 | 2004-09-16 | Yaskawa Electric Corp | モータの制御装置及び制御方法 |
JP2007265361A (ja) * | 2006-03-30 | 2007-10-11 | Nisshinbo Ind Inc | 製造工程に使用されるツール情報を管理,運用する方法 |
JP2008116317A (ja) * | 2006-11-03 | 2008-05-22 | Toyota Motor Corp | ハイブリッド車両の検査システムおよび検査方法 |
JP2014048929A (ja) * | 2012-08-31 | 2014-03-17 | Brother Ind Ltd | 制御装置及び画像形成システム |
WO2016147360A1 (ja) * | 2015-03-18 | 2016-09-22 | 三菱電機株式会社 | 駆動機寿命評価装置及び駆動機寿命評価方法 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4932636B2 (ja) * | 2007-08-10 | 2012-05-16 | ダイキン工業株式会社 | 圧縮機内部状態推定装置及び空気調和装置 |
JP5644820B2 (ja) * | 2012-08-17 | 2014-12-24 | 株式会社安川電機 | モータ制御装置 |
JP6194466B2 (ja) * | 2013-04-11 | 2017-09-13 | パナソニックIpマネジメント株式会社 | モータ駆動装置 |
-
2017
- 2017-05-31 JP JP2019521603A patent/JP6899897B2/ja active Active
- 2017-05-31 WO PCT/JP2017/020280 patent/WO2018220751A1/ja active Application Filing
- 2017-05-31 EP EP17911990.4A patent/EP3633851A4/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH096432A (ja) * | 1995-06-14 | 1997-01-10 | Mitsubishi Electric Corp | 制御システムの異常検知装置 |
JP2004260891A (ja) | 2003-02-25 | 2004-09-16 | Yaskawa Electric Corp | モータの制御装置及び制御方法 |
JP2007265361A (ja) * | 2006-03-30 | 2007-10-11 | Nisshinbo Ind Inc | 製造工程に使用されるツール情報を管理,運用する方法 |
JP2008116317A (ja) * | 2006-11-03 | 2008-05-22 | Toyota Motor Corp | ハイブリッド車両の検査システムおよび検査方法 |
JP2014048929A (ja) * | 2012-08-31 | 2014-03-17 | Brother Ind Ltd | 制御装置及び画像形成システム |
WO2016147360A1 (ja) * | 2015-03-18 | 2016-09-22 | 三菱電機株式会社 | 駆動機寿命評価装置及び駆動機寿命評価方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3633851A4 |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6850458B1 (ja) * | 2019-11-22 | 2021-03-31 | ディエスピーテクノロジ株式会社 | Ai搭載型モータ状態量推定システムおよびモータモデル用機械学習方法 |
JP7489686B2 (ja) | 2019-11-22 | 2024-05-24 | ディエスピーテクノロジ株式会社 | Ai搭載型モータ状態量推定システム |
WO2022004417A1 (ja) | 2020-07-01 | 2022-01-06 | 株式会社日立産機システム | 動力伝達機構の管理装置、動力伝達機構の管理方法 |
TWI772085B (zh) * | 2020-07-01 | 2022-07-21 | 日商日立產機系統股份有限公司 | 動力傳遞機構之管理裝置及動力傳遞機構之管理方法 |
JPWO2022186382A1 (ja) * | 2021-03-05 | 2022-09-09 | ||
WO2022186382A1 (ja) * | 2021-03-05 | 2022-09-09 | 株式会社タダノ | 故障予兆検出システムおよび作業車 |
JP7501777B2 (ja) | 2021-03-05 | 2024-06-18 | 株式会社タダノ | 故障予兆検出システムおよび作業車 |
TWI824444B (zh) * | 2021-04-28 | 2023-12-01 | 日商Sumco股份有限公司 | 狀態判定裝置以及狀態判定方法 |
JP7574170B2 (ja) | 2021-11-12 | 2024-10-28 | 株式会社日立製作所 | 状態分析装置、及び状態推定方法 |
TWI839828B (zh) * | 2021-12-24 | 2024-04-21 | 日商日立產機系統股份有限公司 | 動力傳達機構之管理裝置、動力傳達機構之管理方法及管理系統 |
DE102023125011A1 (de) | 2022-10-11 | 2024-04-11 | Sumitomo Heavy Industries, Ltd. | Steuervorrichtung, spritzgiessmaschine und steuerverfahren |
Also Published As
Publication number | Publication date |
---|---|
EP3633851A1 (en) | 2020-04-08 |
JP6899897B2 (ja) | 2021-07-07 |
JPWO2018220751A1 (ja) | 2020-04-02 |
EP3633851A4 (en) | 2020-12-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6899897B2 (ja) | 状態監視装置、並びに機器システム | |
JP6867358B2 (ja) | 状態判定装置及び状態判定方法 | |
KR101489116B1 (ko) | 구동 기계의 부하 특성 추정 장치 | |
CN106020124A (zh) | 伺服马达控制装置以及碰撞检测方法 | |
CN110920009B (zh) | 状态判定装置以及状态判定方法 | |
JP2020138265A (ja) | びびり振動判定装置、機械学習装置及びシステム | |
JP6764516B1 (ja) | 工作機械および表示装置 | |
JP7010861B2 (ja) | 状態判定装置及び状態判定方法 | |
Rojas et al. | Comments on “Predictive torque control of induction machines based on state-space models” | |
WO2016185589A1 (ja) | 故障診断装置及び故障診断方法 | |
KR20160057305A (ko) | 전동 기계 및 표시 방법 | |
Chang et al. | Big data analysis of a mini three-axis CNC machine tool based on the tuning operation of controller parameters | |
TWI772085B (zh) | 動力傳遞機構之管理裝置及動力傳遞機構之管理方法 | |
JP6928031B2 (ja) | 制御装置及び制御システム | |
CN110376970A (zh) | 参数决定辅助装置和记录有程序的计算机可读介质 | |
JP6867503B2 (ja) | 機器制御システム | |
JP6773740B2 (ja) | 状態判定装置及び状態判定方法 | |
US20240028020A1 (en) | State determination device and state determination method | |
US11316452B2 (en) | Electronic device and control method thereof | |
CN115616976A (zh) | 数控系统的健康度监控方法及健康度监控系统 | |
US20210183184A1 (en) | Motion system health management using multidimensional modeling using motor operational parameters | |
JP6781845B2 (ja) | 工作機械の監視システム | |
JP7132024B2 (ja) | モータ制御装置 | |
US20240385082A1 (en) | Management Device for Power Transmission Mechanism, Management Method for Power Transmission Mechanism, and Management System | |
JP4632171B2 (ja) | モータ制御装置および制御方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17911990 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2019521603 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2017911990 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2017911990 Country of ref document: EP Effective date: 20200102 |