Control device and control method
The control device and method address camera inaccuracies in deburring by adjusting force and position parameters using regression analysis, ensuring consistent and efficient burr removal across workpieces.
Patent Information
- Application Number
- JP2019119764
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2019-06-27
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2039-06-27
AI Technical Summary
Existing deburring systems fail to accurately detect burrs due to camera inaccuracies, leading to inconsistent deburring results between experts and beginners, as they do not automatically correct force control parameters at burr-detection blind spots.
A control device and method that utilizes a camera to measure workpiece contours, generates machining trajectories, and adjusts force and position parameters using regression analysis to identify and correct burrs missed by the camera, employing a regression model to optimize deburring for subsequent workpieces.
The system effectively removes burrs undetected by the camera, reducing processing time and minimizing variations in deburring results across operators, thereby enhancing precision and efficiency.
Smart Images

Figure 0007586632000001 
Figure 0007586632000002 
Figure 0007586632000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a control device and a control method. [Background technology]
[0002] When deburring a workpiece that has been machined by cutting or the like, a machining trajectory required for deburring may be created based on the contour of the workpiece detected by measuring the shape of the workpiece using a camera. In this case, the machine performs deburring by pressing a grinder against the workpiece with a constant force using force control along the machining trajectory created based on the contour detected by the camera. However, due to insufficient camera accuracy, there are some places where burrs cannot be detected. In such cases, for the places where burrs could not be detected, the worker adjusts the force control parameters to correct the processing trajectory and performs deburring again. In this way, the worker removes the burr by checking whether the burr remains and performing deburring again. For this reason, when there are places where burrs cannot be detected due to insufficient camera accuracy, there may be a difference in the results of deburring between an experienced person and a beginner in terms of setting the force control parameters such as the pressing force and the advancement speed. In this regard, a technique is known in which the occurrence of burrs is detected by observing the output value from a sensor installed in a machine, the position and posture data at that time are stored, and in the next deburring, only the part where the sensor output value was large (the part where burrs are occurring) is repeated, or the conditions such as the pressing force and the advancement speed in that part are changed. For example, see Patent Document 1. However, the invention described in Patent Document 1 does not create a processing trajectory required for deburring based on the contour of the workpiece detected by measuring the shape of the workpiece with a camera. In addition, it does not estimate the part where burrs could not be detected due to insufficient accuracy of the camera, and automatically correct the parameters of the force control in that part. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Publication No. 6-23682 Summary of the Invention [Problem to be solved by the invention]
[0004] In a deburring system, when deburring is performed along a machining trajectory created based on the contour of the workpiece detected by measuring the shape of the workpiece with a camera, it is desirable to estimate the locations where burrs could not be detected due to insufficient camera precision and automatically correct the force control parameters at those locations to remove the burrs. [Means for solving the problem]
[0005] (1) One aspect of a control device disclosed herein is a control device for controlling a machine device that performs a deburring process on a plurality of workpieces, the control device including: a data acquisition unit that acquires contour data indicating the contour of the workpiece measured by a camera provided on a movable member of the machine device; a trajectory determination unit that generates machining trajectory data indicating a machining trajectory for the workpiece from the contour data; a status observation unit that observes, as status data, position data indicating the position of the movable member that is periodically detected by a position detection unit provided on the movable member during the deburring process and force data indicating a force or moment pressing the workpiece that is periodically detected by a force detection unit provided on the movable member; and a status observation unit that measures a shape of the workpiece by the camera. a parameter adjustment unit which adjusts parameters related to force commands and / or position commands to identify a portion of the workpiece having a burr that could not be detected by the camera based on a deviation between a machining trajectory created based on the contour of the workpiece detected by the camera and contour data of the workpiece indicated by the position data and / or a deviation between the force indicated by the force data and a predetermined pressing force set in advance, and to remove the identified burr; and a regression analysis unit which performs a regression analysis of the adjustment amount of the parameters and the amount of burr after the adjustment in a first deburring process for the workpiece, and generates a regression model, and the parameter adjustment unit adjusts the parameters using the regression model in a deburring process for a second or subsequent workpiece.
[0006] (2) One aspect of the control method of the present disclosure is a control method executed by a computer to control a machine device performing a deburring process on a plurality of workpieces, the control method including: a data acquisition step of acquiring contour data indicating the contour of the workpiece measured by a camera provided on a movable member of the machine device; a trajectory determination step of generating machining trajectory data indicating a machining trajectory for the workpiece from the contour data; a status observation step of observing, as status data, position data indicating the position of the movable member periodically detected by a position detection unit provided on the movable member during the deburring process and force data indicating a force or moment pressing the workpiece periodically detected by a force detection unit provided on the movable member; the parameter adjustment step of adjusting parameters related to force commands and / or position commands in order to identify portions of the workpiece containing burrs that could not be detected by the camera based on a deviation between a machining trajectory created based on the contour of the workpiece detected by measuring the shape of the workpiece and the contour data of the workpiece indicated by the position data and / or a deviation between the force indicated by the force data and a predetermined pressing force that has been set in advance, and to remove the identified burrs; and a regression analysis step of performing a regression analysis on the adjustment amounts of the parameters and the amount of burrs after the adjustment in a burr removal process for a first workpiece, to generate a regression model, wherein the parameter adjustment step adjusts the parameters using the regression model in a burr removal process for a second or subsequent workpiece. Effect of the Invention
[0007] According to one embodiment, the parameters can be adjusted so that burrs that cannot be detected due to insufficient camera accuracy can also be removed. [Brief description of the drawings]
[0008] [Figure 1] FIG. 2 is a functional block diagram showing an example of a functional configuration of a deburring system according to an embodiment. [Diagram 2] FIG. 1 illustrates an example of a robot. [Figure 3A]11 is a diagram showing an example of a deburring trajectory and position data relating to a contour of a workpiece indicated by time-series data of positions in a first deburring process. FIG. [Figure 3B] 11 is a diagram showing an example of a deburring trajectory and position data relating to a contour of a workpiece indicated by time-series data of positions in a first deburring process. FIG. [Figure 3C] 11 is a diagram showing an example of a deburring trajectory and position data relating to a contour of a workpiece indicated by time-series data of positions in a first deburring process. FIG. [Figure 4A] 3D is a diagram showing an example of time-series data of the pressing force in the first deburring shown in FIGS. 3A to 3C. FIG. [Figure 4B] FIG. 4 is a diagram showing an example of time-series data of the moving speed in the X-axis direction in the first deburring shown in FIGS. 3A to 3C. [Figure 4C] FIG. 13 is a diagram showing an example of a deburring trajectory. [Diagram 5] 3C and position data relating to the contour of the workpiece observed from time-series position data by a state observing unit. FIG. [Figure 6] FIG. 1 is a diagram showing an example in which the contour of a workpiece is divided into regions of a predetermined size. [Figure 7] FIG. 7 is a diagram showing an example of a pattern obtained by classifying the contour shapes in each region in FIG. 6. [Figure 8] 4 is a flowchart illustrating an adjustment process of the control device. [Figure 9] 9 is a flowchart illustrating detailed processing contents of the deburring process for the first workpiece shown in step S1 of FIG. 8. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] An embodiment will be described below with reference to the drawings. <One embodiment> 1 is a functional block diagram showing an example of the functional configuration of a deburring system according to an embodiment. As shown in FIG. 1, the deburring system includes a machine 10 and a control device 20.
[0010] The machine 10 and the control device 20 may be directly connected to each other via a connection interface (not shown). The machine 10 and the control device 20 may be connected to each other via a network such as a LAN (Local Area Network). In this case, the machine 10 and the control device 20 may include a communication unit (not shown) for communicating with each other via such a connection.
[0011] The mechanical device 10 is, for example, a machine tool, an industrial robot, etc. In the following, the mechanical device 10 will be described as an industrial robot (hereinafter, also referred to as "robot 10"). FIG. 2 is a diagram illustrating an example of the robot 10. 2, the robot 10 is a six-axis vertical articulated robot and has six joint axes 11(1)-11(6) and an arm unit 12 connected by each of the joint axes 11(1)-11(6). The robot 10 drives a movable member (hereinafter also referred to as a "manipulator") such as the arm unit 12 by driving a servo motor (not shown) disposed in each of the joint axes 11(1)-11(6) based on a drive command from the control device 20. In addition, a camera 13, a force sensor 14, and a grinder 15, for example, are attached to the tip of the manipulator of the robot 10, for example, the tip of the joint axis 11(6).
[0012] Although the robot 10 is a six-axis vertical articulated robot, it may be a vertical articulated robot other than a six-axis robot, or may be a horizontal articulated robot, a parallel link robot, or the like. In the following description, when there is no need to distinguish between the joint axes 11(1)-11(6), they will be collectively referred to as the "joint axis 11."
[0013] The camera 13 is, for example, a digital camera, and is provided at the tip of a manipulator of the robot 10 as shown in Fig. 2. The camera 13 measures the contour of the workpiece 30 to be deburred by photographing the workpiece 30 that is placed on a workbench 40. The camera 13 outputs contour data indicating the measured contour to the control device 20 via a connection interface (not shown). The force sensor 14 is, for example, a six-axis force sensor, and is provided at the tip of a manipulator of the robot 10. The force sensor 14 detects the pressing force of a grinder 15 (described later) against the workpiece 30 periodically at a predetermined sampling time. The force sensor 14 outputs force data indicating the detected pressing force to the control device 20 via a connection interface (not shown). A position sensor (not shown), such as a rotary encoder, is attached to the servo motor (not shown) of the joint axis 11 to measure the position and orientation of the tip of the manipulator. The position sensor (not shown) may output position data indicating the measured position and orientation to the control device 20 via a connection interface (not shown). The predetermined sampling time may be set appropriately depending on the operation of the robot 10, the environment of the factory in which the robot 10 is placed, and the like. The grinder 15 is provided at the tip of the manipulator of the robot 10 and removes burrs generated on the workpiece 30 .
[0014] <Control device 20> 1 and 2, the control device 20 is a robot control device (also called a "robot controller") that outputs drive commands to the robot 10 based on a program and controls the operation of the robot 10. In addition, in Fig. 2, a teaching pendant 25 that teaches the robot 10 an operation is connected to the control device 20. As shown in FIG. 1, the control device 20 according to this embodiment includes a data acquisition unit 201, a trajectory determination unit 202, a state observation unit 203, a force command calculation unit 204, a position command calculation unit 205, a speed command unit 206, a memory unit 207, a deviation calculation unit 208, a parameter adjustment unit 209, and a regression analysis unit 210. The control device 20 includes a processor (not shown) such as a central processing unit (CPU) to realize the operation of the functional blocks in Fig. 1. The control device 20 also includes auxiliary storage devices (not shown) such as a read only memory (ROM) or hard disk drive (HDD) that stores various control programs, and a main storage device (not shown) such as a random access memory (RAM) for storing data temporarily required for the processor to execute a program.
[0015] In the control device 20, the arithmetic processing unit reads the OS and application software from the auxiliary storage device, and performs arithmetic processing based on the OS and application software while expanding the read OS and application software in the main storage device. Based on the results of this calculation, the control device 20 controls each piece of hardware. In this way, the processing by the functional blocks in Fig. 2 is realized. In other words, the control device 20 can be realized by the cooperation of hardware and software.
[0016] The data acquisition unit 201 acquires, for example, contour data of the workpiece 30 measured by the camera 13. The data acquisition unit 201 also acquires force data indicating the pressing force of the grinder 15 measured by the force sensor 14. The data acquisition unit 201 also acquires position data indicating the position and attitude measured by a position sensor (not shown) attached to a servo motor (not shown) of the joint shaft 11. The data acquisition unit 201 also acquires CAD (Computer-Aided Design) data of the workpiece 30 from a higher-level device (not shown).
[0017] The trajectory determination unit 202 generates, from the contour data of the workpiece 30 measured by the camera 13, machining trajectory data that indicates the machining trajectory of the manipulator (grinder 15) in the deburring process.
[0018] The state observing unit 203 acquires, as state data, time series data of the pressing force detected by the force sensor 14 and time series data of the position of the manipulator (grinder 15) detected by a position sensor (not shown), which are observed during the deburring process performed along the machining trajectory generated by the trajectory determining unit 202. The state observing unit 203 stores the acquired time series data of the pressing force and time series data of the position in the storage unit 207, which will be described later.
[0019] The force command calculation unit 204 calculates the deviation between the pressing force observed by the state observation unit 203 and a force command calculated using parameters adjusted by a parameter adjustment unit 209 described later, and outputs a force command corresponding to the deviation to the speed command unit 206. Furthermore, when performing the first deburring process on the first workpiece 30, the force command calculation unit 204 performs force control so that the grinder 15 constantly presses the workpiece 30 with a preset predetermined pressing force.
[0020] The position command calculation unit 205 determines the deviation between the position of the manipulator (grinder 15) observed by the state observation unit 203 and a position command calculated using parameters adjusted by the parameter adjustment unit 209 described later, and outputs a position command corresponding to the deviation to the speed command unit 206.
[0021] The speed command unit 206 outputs a speed command corresponding to the force command output by the force command calculation unit 204 and the position command output by the position command calculation unit 205 to the robot 10. The robot 10 drives the servo motors (not shown) of the joint axes 11 based on the received speed command, presses the grinder 15 against the workpiece 30 with the pressing force indicated by the force command, and moves the grinder 15 along the machining trajectory according to the position command and the speed command.
[0022] The memory unit 207 is an SSD (Solid State Drive), HDD, etc., and has a force data area 220 that stores the time-series data of the pressing force observed by the state observation unit 203, and a position data area 221 that stores the time-series data of the position. Further, the memory unit 207 may have a burr data area 222 that stores data indicating the burr portion specified by the parameter adjustment unit 209 described later.
[0023] The deviation calculation unit 208 calculates, for example, the deviation between the machining trajectory (hereinafter also referred to as the "deburring trajectory") created based on the contour of the workpiece 30 measured and detected by the camera 13 and the data related to the contour of the workpiece 30 indicated by the time-series data of the position in the position data area 221, and / or the deviation between the time-series data of the pressing force in the force data area 220 and a preset predetermined pressing force. More specifically, in the first deburring of the first workpiece 30, for example, the deviation calculation unit 208 acquires from the memory unit 207 the time-series data of the pressing force and the position when the surface of the workpiece 30 observed by the state observation unit 203 follows with a constant pressing force. The deviation calculation unit 208 calculates, from the acquired time-series data of the pressing force and the position, the deviation between the deburring trajectory and the position data related to the contour of the workpiece 30 indicated by the time-series data of the position (hereinafter also referred to as the "deburring trajectory deviation"), and / or the deviation between the time-series data of the pressing force and a preset predetermined pressing force (hereinafter also referred to as the "deviation of the pressing force").
[0024] FIGS. 3A to 3C are diagrams showing an example of the deviation between the deburring trajectory and the position data related to the contour of the workpiece 30 indicated by the time-series data of the position in the first deburring process. FIG. 3A shows the position of the grinder 15 at the start of deburring when time t = 0. FIG. 3B shows the position of the grinder 15 deburring the first burr A1 that cannot be detected due to the insufficient accuracy of the camera 13 at time t = a (0 < a < b). FIG. 3C shows the position of the grinder 15 deburring the second burr A2 that cannot be detected due to the insufficient accuracy of the camera 13 at time t = b. 3A to 3C, the dashed line indicates the deburring trajectory, and the solid line indicates the position data (trajectory traced by force control) related to the contour of the workpiece 30 observed from the time-series position data by the state observation unit 203. Although not shown in the figure, at the position of the burr detected by measuring the shape of the workpiece 30 by the camera 13, it is considered that there is no deviation between the burr removal trajectory and the position data relating to the contour of the workpiece 30 observed from the time series data of the position by the state observation unit 203 (the trajectory traced by force control) (solid line).
[0025] 3A and 3B, the first burr A1 exists at a position where the grinder 15 traces with a constant pressing force between time t=0 and time t=a. This shows that at the portion of burr A1, the burr removal trajectory (dashed line) deviates from the position data related to the contour of the workpiece 30 observed by the state observation unit 203 from the time-series data of the position (trajectory traced by force control) (solid line). 3C, a second burr A2 exists at a location where the grinder 15 traces with a constant pressing force between time t=a and time t=b. This shows that even at the location of burr A2, there is a deviation between the burr removal trajectory (dashed line) and the position data (trajectory traced by force control) (solid line) relating to the contour of the workpiece 30 observed by the state observation unit 203 from the time-series data of the position.
[0026] Fig. 4A is a diagram showing an example of time-series data (status data) of the pressing force in the first deburring shown in Fig. 3A to Fig. 3C. Fig. 4B is a diagram showing an example of time-series data (status data) of the moving speed in the X-axis direction in the first deburring shown in Fig. 3A to Fig. 3C. Fig. 4C is a diagram showing an example of a deburring trajectory. As shown in Fig. 4A, at time t = a, b, the pressing force of the grinder 15 is increased due to the burrs A1 and A2 that could not be detected due to insufficient accuracy of the camera 13, even though the pressing force of the grinder 15 is tracing with a preset constant pressing force. Similarly, as shown in Fig. 4B, at time t = a, b, the moving speed of the grinder 15 is decelerated due to the burrs A1 and A2. In addition, as shown in Fig. 4C, it can be seen that the burrs A1 and A2 are not detected on the deburring trajectory due to insufficient accuracy of the camera 13.
[0027] As described above, the parameter adjustment unit 209 identifies burrs in the workpiece 30 that could not be detected due to insufficient accuracy of the camera 13, based on the deburring trajectory deviation and / or the pressing force deviation calculated by the deviation calculation unit 208. The parameter adjustment unit 209 adjusts parameters related to the force command and / or the position command in order to remove burrs from the identified portions. The parameters related to the force command and / or the position command include a position target value, a pressing force, a moving speed, a number of repetitions, a moving speed, and a control gain. Here, the "number of repetitions" is the number of times that deburring is repeated for a specified burr portion. Also, the "control gain" is a reaction speed for controlling the pressing force to be constant in the deburring process.
[0028] FIG. 5 is a diagram showing an example of the deburring trajectory deviation between the deburring trajectory (dashed line) shown in FIG. 3A to FIG. 3C and the position data (trajectory traced by force control) (solid line) relating to the contour of the workpiece 30 observed from the time-series position data by the state observation unit 203. 5, the parameter adjustment unit 209 can identify portions (locations) where the deburring trajectory deviation is equal to or greater than a predetermined threshold value α and / or the pressing force deviation is equal to or greater than a predetermined threshold value β as burrs A1, A2 that could not be detected due to insufficient accuracy of the camera 13. The parameter adjustment unit 209 stores the identified burrs A1, A2 in the validator area 222 of the storage unit 207.
[0029] Then, the parameter adjustment unit 209 adjusts any one of the pressing force, the advancement speed, the number of repetitions, the advancement direction, and the control gain for the identified burrs A1 and A2. For example, the parameter adjustment unit 209 may increase the number of repetitions parameter for a burr portion where the change in pressing force is large and there is a deviation between the deburring trajectory and the actual trajectory. Alternatively, the parameter adjustment unit 209 may decrease the advancement speed for a burr portion where the change in pressing force is large and the angle between the direction in which the pressing force changes and the advancement direction of the grinder 15 is large. Note that the parameter adjustment unit 209 may adjust the pressing force to be weaker or to be zero for a portion (location) where no burrs are generated, for example.
[0030] The parameter adjustment unit 209 adjusts parameters for the identified burrs A1 and A2 to generate a second machining trajectory (i.e., a position target value) and a force target value proportional to the deviation between the first machining trajectory and the actual trajectory and / or the deviation of the pressing force. In order to perform the second deburring process on the first workpiece 30, the parameter adjustment unit 209 outputs the position target value to the position command calculation unit 205 and outputs the force target value to the force command calculation unit 204. Then, the speed command unit 206 outputs a speed command according to the force command calculated by the force command calculation unit 204 and the position command calculated by the position command calculation unit 205 to the robot 10, and performs the second deburring process.
[0031] The parameter adjustment unit 209 performs the same deburring process for the third and subsequent times until the deviation (for simplicity, also referred to as "workpiece contour deviation") between the contour data of the workpiece 30 obtained by pattern matching the shape based on the CAD data of the workpiece 30 with the contour data detected by the camera 13 and the position data related to the contour of the workpiece 30 observed from the time-series position data by the state observation unit 203 (the trajectory traced by force control) becomes equal to or less than a preset allowable value. Then, the parameter adjustment unit 209 ends the deburring process when the workpiece contour deviation becomes equal to or less than a preset allowable value.
[0032] The regression analysis unit 210 as a learning device may perform regression analysis of, for example, the amount of adjustment of the parameters in the deburring process for the first workpiece 30 and the amount of burrs after the adjustment, to generate a regression model. More specifically, the regression analysis unit 210 may divide the contour features into regions of a predetermined size based on the contour data of the first workpiece 30 measured by the camera 13, and classify the contour shapes in each divided region into patterns. In the deburring process for the first workpiece 30, the regression analysis unit 210 may associate each classified pattern with the burr portion identified by the parameter adjustment unit 209, and generate a regression model for each pattern.
[0033] FIG. 6 is a diagram showing an example in which the contour of the workpiece 30 is divided into regions R1-R24 of a predetermined size. 6, the regression analysis unit 210 divides the contour of the workpiece 30 into 24 regions R1-R24. The sizes of the regions R1-R24 and the number of regions may be appropriately determined depending on the shape of the contour of the workpiece 30, the required accuracy of deburring, and the like. Fig. 7 is a diagram showing an example of patterns PA1-PA4 obtained by classifying the contour shapes in each region in Fig. 6. In Fig. 7, the workpiece 30 is shown as a black region. Also, the number of patterns is not limited to four, and may be any number other than four. As shown in FIG. 7, the regression analysis unit 210 classifies the contour shapes in each of the regions R1-R24 into four patterns PA1-PA4. That is, the regression analysis unit 210 classifies the contour shapes in the regions R4, R8, R11, R18, and R21 into pattern PA1. The regression analysis unit 210 also classifies the contour shapes in the regions R2, R3, R5, R7, R9, R10, R12-R17, R19, R20, R22, and R24 into pattern PA2. The regression analysis unit 210 also classifies the contour shapes in the regions R6 and R23 into pattern PA3. The regression analysis unit 210 also classifies the contour shape in the region R1 into pattern PA4.
[0034] The regression analysis unit 210 assumes that the same burr exists at the same location if the patterns have the same contour, and associates each of the patterns PA1-PA4 with the location of the burr identified by the parameter adjustment unit 209 to generate a regression model for each of the patterns PA1-PA4. Then, in the deburring process for the second and subsequent workpieces 30, the parameter adjustment unit 209 adjusts the parameters for each pattern using the regression model corresponding to the pattern detected from the contour data of the workpiece 30 measured by the camera 13. Thereby, the control device 20 can adjust the parameters according to the pattern of the contour shape of the workpiece 30, thereby reducing the number of times of machining.
[0035] <Adjustment process of the control device 20> Next, the operation of the control device 20 according to this embodiment in relation to the adjustment process will be described. Fig. 8 is a flowchart illustrating the adjustment process of the control device 20. Fig. 9 is a flowchart illustrating the detailed process contents of the deburring process for the first workpiece shown in step S1 of Fig. 8. In step S1, the control device 20 performs a deburring process on the first workpiece 30. Note that a detailed flow of the deburring process on the first workpiece 30 will be described later with reference to FIG. In step S2, the control device 20 performs the deburring process on the second or subsequent workpiece 30. The deburring process on the second or subsequent workpiece 30 will be described in detail later. In step S3, the control device 20 determines whether or not the deburring process has been performed on all of the workpieces 30. If the deburring process has not been performed on all of the workpieces 30, the process returns to step S2. On the other hand, if the deburring process has been performed on all of the workpieces 30, the process ends.
[0036] Next, with reference to FIG. 9, the deburring process for the first workpiece 30 shown in step S1 of FIG. 8 will be described in detail.
[0037] In step S11 , the data acquisition unit 201 acquires contour data of the first workpiece 30 measured by the camera 13 .
[0038] In step S12, the regression analysis unit 210 classifies the shape of the contour of the workpiece 30 for each of the patterns PA1-PA4 from the contour data acquired in step S11.
[0039] In step S13, the trajectory determination unit 202 generates processing trajectory data (deburring trajectory) of the manipulator (grinder 15) in the deburring process from the contour data of the first workpiece 30 acquired in step S11.
[0040] In step S14, the speed command unit 206 outputs a speed command to the robot 10 according to the force command calculated by the force command calculation unit 204 and the position command calculated by the position command calculation unit 205 so that the grinder 15 constantly presses the first workpiece 30 with a predetermined pressing force set in advance to follow it, and performs the first deburring process.
[0041] In step S15, the deviation calculation unit 208 calculates the deburring trajectory deviation and / or the pressing force deviation between the deburring trajectory in the first deburring process and the position data related to the contour of the workpiece 30 observed by the state observation unit 203 from the position time series data.
[0042] In step S16, the parameter adjustment unit 209 identifies, as a burr portion, a portion where the deviation of the deburring trajectory calculated in step S15 is equal to or greater than a threshold value α and / or where the deviation of the pressing force is equal to or greater than a preset threshold value β.
[0043] In step S17, the parameter adjustment unit 209 adjusts any one of the parameters of the pressing force, the advancement speed, the number of repetitions, the advancement speed, and the control gain in order to remove the burrs in the identified portion.
[0044] In step S18, the speed command unit 206 outputs a speed command to the robot 10 according to the force command calculated by the force command calculation unit 204 and the position command calculated by the position command calculation unit 205 based on the parameters adjusted in step S17, and performs the next (second, etc.) deburring of the burr detected in step S16.
[0045] In step S19, the regression analysis unit 210 performs regression analysis on the parameter adjustment amount in the deburring process in step S18 and the burr amount after the adjustment for each of the contour patterns PA1-PA4 classified in step S12, and generates (updates) a regression model.
[0046] In step S20, the parameter adjustment unit 209 calculates the workpiece trajectory deviation in the deburring process in step S18.
[0047] In step S21, the parameter adjustment unit 209 judges whether or not the workpiece trajectory deviation calculated in step S20 is equal to or less than a preset allowable value. If the workpiece trajectory deviation is equal to or less than the allowable value, the process proceeds to step S2 in Fig. 1. On the other hand, if the workpiece trajectory deviation is greater than the allowable value, the process returns to step S17. The deburring process for the first workpiece shown in step S1 of FIG. 8 has been described above.
[0048] Next, a description will be given of the deburring process for the second or subsequent workpiece 30 shown in step S2 of Fig. 8. Note that the deburring process for the second or subsequent workpiece 30 is similar to the deburring process for the first workpiece 30 shown in Fig. 9, and only the differences will be described. (1) In the deburring process for the second or subsequent workpiece 30, the processes from step S14 to step S16 and step S19 are omitted. (2) In the deburring process for the second or subsequent workpiece 30, in step S17, the parameter adjustment unit 209 adjusts one of the parameters of the pressing force, the advancing speed, the number of repetitions, the advancing speed, and the control gain using a regression model for each of the patterns PA1-PA4 generated in the deburring process for the first workpiece 30 in step S1.
[0049] As described above, the control device 20 according to one embodiment performs a first deburring operation on the first workpiece 30 by tracing the surface of the workpiece 30 with a preset, predetermined (constant) pressing force, and judges whether the deviation of the contour data is equal to or greater than a threshold value α and / or the deviation of the pressing force is equal to or greater than a preset threshold value β. Based on the judgment result, the control device 20 identifies the portion (location) of the burr that cannot be detected due to insufficient accuracy of the camera 13. The control device 20 adjusts parameters such as the pressing force and performs a second or subsequent deburring operation on the burr in the detected portion, thereby performing a regression analysis of the parameter adjustment amount and the burr amount, and generates a regression model. This allows the control device 20 to adjust the parameters so that burrs that cannot be detected due to insufficient camera accuracy can also be removed. Furthermore, the control device 20 can shorten the deburring processing time for the next workpiece 30 by adjusting the parameters for the first deburring processing for the second or subsequent workpiece 30 using the regression model. Furthermore, by using a regression model, the control device 20 can reduce the difference in deburring results between an experienced person and a beginner, thereby reducing the burden on the worker.
[0050] Although one embodiment has been described above, the control device 20 is not limited to the above-described embodiment, and includes modifications and improvements within the scope of achieving the object.
[0051] <Variation 1> In the above embodiment, the regression analysis unit 210 performs regression analysis on the parameter adjustment amount in the deburring process for the first workpiece 30 and the burr amount after the adjustment for each of the classified contour patterns PA1-PA4 to generate a regression model, but is not limited to this. For example, the regression analysis unit 210 may generate one regression model by treating the entire workpiece 30 as one pattern. <Variation 2> Also, for example, in the above embodiment, the parameter adjustment unit 209 adjusted one of the pressing force, the advancement speed, the number of repetitions, the advancement speed, and the control gain, but it may adjust two or more parameters.
[0052] In one embodiment, each function included in the control device 20 can be realized by hardware, software, or a combination of these. Here, being realized by software means being realized by a computer reading and executing a program.
[0053] The program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memory (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable media include electric signals, optical signals, and electromagnetic waves. The transitory computer readable media can provide the program to the computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path.
[0054] In addition, the steps of writing a program to be recorded on a recording medium include not only processes that are performed chronologically according to the order, but also processes that are not necessarily performed chronologically but are executed in parallel or individually.
[0055] In other words, the control device of the present disclosure can take various forms having the following configurations. (1) The control device 20 of the present disclosure is a control device that controls a machine 10 that performs a deburring process on a plurality of workpieces 30, and includes a data acquisition unit 201 that acquires contour data indicating the contour of the workpiece 30 measured by a camera 13 provided on a movable member of the machine 10, a trajectory determination unit 202 that generates machining trajectory data indicating the machining trajectory for the workpiece 30 from the contour data, a state observation unit 203 that observes, as state data, position data indicating the position of the movable member that is periodically detected by a position detection unit provided on the movable member during the deburring process and force data indicating the force or moment pressing the workpiece 30 that is periodically detected by a force detection unit (force sensor 14) provided on the movable member, and a shape of the workpiece 30 measured by the camera 13. The apparatus further includes a parameter adjustment unit 209 that adjusts parameters related to the force command and / or position command to identify portions A1, A2 of the workpiece 30 having burrs that could not be detected by the camera 13 based on the deviation between the machining trajectory created based on the contour of the workpiece 30 detected by measuring and the contour data of the workpiece 30 indicated by the position data and / or the deviation between the force indicated by the force data and a predetermined pressing force set in advance, and to remove the identified burrs A1, A2; and a regression analysis unit 210 that performs regression analysis on the adjustment amount of the parameters and the amount of burr after the adjustment in the deburring process for the first workpiece 30, and generates a regression model, and the parameter adjustment unit 209 adjusts the parameters using the regression model in the deburring process for the second or subsequent workpieces 30. According to this control device 20, the parameters can be adjusted so that burrs that cannot be detected due to insufficient camera accuracy can also be removed. (2) The parameter adjustment unit 209 may adjust, as a parameter, any one of the pressing force, the moving direction, the moving speed, the number of repetitions, or the control gain. By doing so, the pressing force of the grinder 15 can be adjusted according to the identified burr portion. (3) The regression analysis unit 210 divides the characteristics of the contour data of the workpiece 30 detected by measuring the shape of the workpiece 30 with the camera 13 into regions of a predetermined size based on the contour data, classifies the characteristics of the contour data in each of the divided regions R1-R24 into multiple patterns PA1-PA4, and generates a regression model for each of the multiple patterns PA1-PA4 by matching each of the classified multiple patterns PA1-PA4 with the identified burr portion, and the parameter adjustment unit 209 may adjust the parameters using the regression model corresponding to the pattern detected from the contour data. In this way, the number of times of machining can be reduced by adjusting the parameters according to the pattern of the contour shape of the workpiece 30. (4) The control method of the present disclosure is a control method executed by a computer to control a machine 10 performing a deburring process on a plurality of workpieces 30, and includes a data acquisition step of acquiring contour data indicating the contour of the workpiece 30 measured by a camera 13 provided on a movable member of the machine 10, a trajectory determination step of generating machining trajectory data indicating a machining trajectory for the workpiece 30 from the contour data, a status observation step of observing, as status data, position data indicating the position of the movable member detected periodically by a position detection unit provided on the movable member during the deburring process and force data indicating a force or moment pressing the workpiece detected periodically by a force detection unit provided on the movable member, and a shape of the workpiece 30 by the camera 13. The method includes a parameter adjustment step of adjusting parameters related to the force command and / or position command to identify portions A1, A2 of the workpiece 30 having burrs that could not be detected by the camera 13 based on the deviation between the machining trajectory created based on the contour of the workpiece 30 detected by measuring the contour and the contour data of the workpiece 30 indicated by the position data and / or the deviation between the force indicated by the force data and a predetermined pressing force set in advance, and to remove the identified burrs A1, A2; and a regression analysis step of performing regression analysis on the parameter adjustment amount and the burr amount after the adjustment in the deburring process for the first workpiece 30 to generate a regression model, and the parameter adjustment step adjusts parameters using the regression model in the deburring process for the second or subsequent workpieces 30. This control method can achieve the same effect as (1). [Explanation of symbols]
[0056] 10 Mechanical devices (robots) 13. Camera 14 Force Sensor 15 Grinder 20 Control device 201 Data Acquisition Department 202 Orbit determination part 203 Status Observation Unit 209 Parameter Adjustment Section 210 Regression Analysis Section
Claims
1. A control device for controlling a machine device that performs a deburring process on a plurality of workpieces, a data acquisition unit that acquires contour data indicating a contour of the workpiece measured by a camera provided on a movable member of the machine; a trajectory determination unit that generates machining trajectory data indicating a machining trajectory for the workpiece from the contour data; a state observation unit which observes, as state data, position data indicating a position of the movable member which is periodically detected by a position detection unit provided on the movable member, and force data indicating a force or moment pressing the workpiece which is periodically detected by a force detection unit provided on the movable member, during the deburring process including the deburring process for a first workpiece which moves along a machining trajectory corresponding to the machining trajectory data while pressing the workpiece with a movable member with a predetermined pressing force set in advance; a parameter adjustment unit that specifies a portion of the workpiece having a burr that could not be detected by the camera based on a deviation between a machining trajectory created based on a contour of the workpiece detected by measuring the shape of the workpiece with the camera and data related to the contour of the workpiece indicated by the position data and / or a deviation between a force indicated by the force data and a predetermined pressing force that is set in advance, and adjusts parameters related to a force command and / or a position command in order to remove the specified burr; a regression analysis unit that performs regression analysis on an adjustment amount of the parameter in the deburring process for the first workpiece and a burr amount after deburring based on the adjusted parameter for the identified burr to generate a regression model, The parameter adjustment unit adjusts the parameters using the regression model as arguments for the amount of burr after deburring, in a deburring process for a second or subsequent workpiece, using the deviation between a machining trajectory created based on the contour of the workpiece corresponding to the amount of burr after deburring based on the adjusted parameters for the identified burr and data related to the contour of the workpiece indicated by the position data of the movable member detected by the position detection unit during the deburring process and / or the deviation between a force indicated by force data pressing the workpiece detected by the force detection unit and a predetermined pressing force.
2. The control device according to claim 1 , wherein the parameter adjustment unit adjusts, as the parameter, any one of a pressing force, a moving direction, a moving speed, a number of repetitions, and a control gain.
3. the regression analysis unit divides features of the contour data of the workpiece detected by measuring the shape of the workpiece with the camera into regions of a predetermined size based on the contour data, classifies features of the contour data in each of the divided regions into a plurality of patterns, and generates the regression model for each of the plurality of patterns by associating each of the classified patterns with the identified burr portion; 3. The control device according to claim 1, wherein the parameter adjustment unit adjusts the parameters by using the regression model according to a pattern detected from the contour data.
4. A control method for controlling a machine device that performs a deburring process on a plurality of workpieces, the method comprising: a data acquisition step of acquiring contour data indicating a contour of the workpiece measured by a camera provided on a movable member of the machine; a trajectory determination step of generating machining trajectory data indicating a machining trajectory for the workpiece from the contour data; a state observation step of observing, as state data, position data indicating a position of the movable member periodically detected by a position detection unit provided on the movable member and force data indicating a force or moment pressing the workpiece, which is periodically detected by a force detection unit provided on the movable member, during the deburring process including the deburring process for a first workpiece moving along a machining trajectory corresponding to the machining trajectory data while pressing the workpiece with a movable member with a predetermined pressing force set in advance; a parameter adjustment step of identifying a portion of the workpiece having a burr that could not be detected by the camera based on a deviation between a machining trajectory created based on a contour of the workpiece detected by measuring the shape of the workpiece with the camera and data related to the contour of the workpiece indicated by the position data and / or a deviation between a force indicated by the force data and a predetermined pressing force set in advance, and adjusting parameters related to a force command and / or a position command in order to remove the identified burr; A regression analysis step of performing regression analysis on the adjustment amount of the parameter in the deburring process for the first workpiece and the burr amount after deburring based on the adjusted parameter for the identified burr to generate a regression model, The parameter adjustment step is a control method in which, in a deburring process for a second or subsequent workpiece, the parameters are adjusted using the regression model with the deviation between a machining trajectory created based on the contour of the workpiece corresponding to the amount of burr after deburring based on the adjusted parameters for the identified burr and data related to the contour of the workpiece indicated by the position data of the movable member detected by the position detection unit during the deburring process and / or the deviation between a force indicated by force data pressing the workpiece detected by the force detection unit and a predetermined pressing force as an argument for the amount of burr after deburring.
Citation Information
Patent Citations
Machine vision-based industrial robot flexible grinding method and system
CN109732625A
Polishing method by robot having inner force sensor
JP1993220656A
Control device for robot
JP1994023682A
Control method for grinder working robot
JP1994312344A
Finish machining device
JP2006058961A
