CN110640744A - Industrial robot with fuzzy control of motor - Google Patents
Industrial robot with fuzzy control of motor Download PDFInfo
- Publication number
- CN110640744A CN110640744A CN201911019911.8A CN201911019911A CN110640744A CN 110640744 A CN110640744 A CN 110640744A CN 201911019911 A CN201911019911 A CN 201911019911A CN 110640744 A CN110640744 A CN 110640744A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- control
- industrial robot
- workpiece
- error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007246 mechanism Effects 0.000 claims abstract description 34
- 230000033001 locomotion Effects 0.000 claims abstract description 30
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 17
- 239000012636 effector Substances 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 11
- 210000000707 wrist Anatomy 0.000 claims description 10
- 238000013139 quantization Methods 0.000 claims description 8
- 238000002955 isolation Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 7
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 239000003638 chemical reducing agent Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 235000002566 Capsicum Nutrition 0.000 claims description 2
- 239000006002 Pepper Substances 0.000 claims description 2
- 235000016761 Piper aduncum Nutrition 0.000 claims description 2
- 235000017804 Piper guineense Nutrition 0.000 claims description 2
- 244000203593 Piper nigrum Species 0.000 claims description 2
- 235000008184 Piper nigrum Nutrition 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000007774 longterm Effects 0.000 claims description 2
- 150000003839 salts Chemical class 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 6
- 238000005314 correlation function Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 231100000481 chemical toxicant Toxicity 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 239000003440 toxic substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/10—Programme-controlled manipulators characterised by positioning means for manipulator elements
- B25J9/106—Programme-controlled manipulators characterised by positioning means for manipulator elements with articulated links
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
Abstract
An industrial robot with fuzzy control of motor is composed of industrial robot control system, sensor system, control system, network integrated control system, visual tracking system and executing mechanism, the sensor system is connected to the industrial robot control system, tracking camera under end executor for real-time observing and measuring the position of moving workpiece relative to executing mechanism, tracking camera for acquiring the image of moving workpiece, image processing for recognizing the shape of moving workpiece and obtaining the center of workpiece, comparing it with the result of last recognition to generate error signal, feedback signal, fuzzy control unit for calculating out relative control signal, and moving command, the motion of the actuator is tracked.
Description
Technical Field
The invention belongs to the field of industrial robots, and particularly relates to an industrial robot with a fuzzy control motor.
Background
With the current level of industrial automation becoming higher and higher, industries are gaining more and more importance, and they can skillfully and accurately perform complex tasks that may not be accomplished at all by people due to environmental or other factors. The industrial robot is mainly applied to automobile part manufacturing and assembling, mechanical automatic manufacturing, toxic chemical product production, standard assembly line operation, high-risk environment equipment installation, nuclear radiation field operation, extreme environment operation and the like.
The precise control of the servo motor is the key to how the industrial robot can realize precise machining.
Disclosure of Invention
The invention provides an industrial robot with fuzzy control of a motor, which aims to solve the technical problem of how to realize the accurate control of the servo motor of the industrial robot through the fuzzy control,
the technical scheme of the invention is as follows: an industrial robot with fuzzy control of a motor comprises an industrial robot control system, a sensor system, an operation system, a network integrated control system, a visual tracking system and an execution mechanism, wherein the sensor system is connected with the industrial robot control system,
the control system receives data of the sensor system and the visual tracking system through the network integrated control system and sends a control instruction to the industrial robot control system, the industrial robot control system controls the execution mechanism, the sensor system is arranged on the execution mechanism and monitors the pose state of the execution mechanism in real time, the sensor system and the visual tracking system are also connected with the industrial robot control system and used for feeding back the working state of the execution mechanism in real time and monitoring the surrounding environment,
wherein the industrial robot control system comprises a demonstrator and a motion controller,
wherein the control system comprises an industrial personal computer,
wherein the visual tracking system comprises an RGB camera, a laser scanner, a tracking camera and a radio frequency transmitting and receiving device,
wherein the sensor system comprises a plurality of six-axis sensors, an optical sensor, a motion sensor and a Hall current sensor,
wherein the actuating mechanism comprises a mechanical part and an electric part,
the mechanical part comprises a base, a connecting piece, a big arm, a small arm, a wrist, an end effector and a rotary joint,
the tracking camera is arranged right below the end effector, the position of the moving workpiece relative to the actuating mechanism is observed and measured in real time, the tracking camera is used for collecting images of the moving workpiece, the shape of the moving workpiece is identified through image processing, the center of the workpiece is obtained, the center of the workpiece is compared with the last identification result to generate an error signal, the obtained error signal of the moving workpiece is used as a feedback signal and is input into a fuzzy control device of an industrial personal computer, a corresponding control signal is calculated through a fuzzy control method, and the control signal is sent to the actuating mechanism in a motion instruction mode.
The invention has the beneficial effects that:
(1) the precise control of the servo motor of the industrial robot is automatically and effectively realized through fuzzy control, and the waste on efficiency and the inaccuracy on precision caused by repeated modification of manual setting are reduced;
(2) the optical coupling isolation circuit greatly improves the reliability of hardware;
(3) by using secondary communication, flexible control over the industrial robot is realized;
(4) the actuating mechanism adopts a parallelogram, so that the rigidity of the whole structure is increased, and the stability of the system is improved;
(5) the central position of the workpiece is accurately obtained by using an image processing algorithm, so that the robot can accurately grab the workpiece conveniently.
Drawings
Fig. 1 is a block diagram of an industrial robot system of the present invention;
FIG. 2 is a mechanical block diagram of the actuator of the present invention;
FIG. 3 is a flow chart of an electrical fuzzy control method of the present invention;
FIG. 4 is a schematic diagram of the fuzzy control method of the present invention;
FIG. 5 is a flowchart of a workpiece center position acquisition process of the present invention;
Detailed Description
The invention will be further described with reference to the accompanying drawings.
An industrial robot with fuzzy control of a motor comprises an industrial robot control system, a sensor system, an operation system, a network integrated control system, a visual tracking system and an execution mechanism, wherein the sensor system is connected with the industrial robot control system,
the control system receives data of the sensor system and the visual tracking system through the network integrated control system and sends a control instruction to the industrial robot control system, the industrial robot control system controls the execution mechanism, the sensor system is arranged on the execution mechanism and monitors the pose state of the execution mechanism in real time, the sensor system and the visual tracking system are also connected with the industrial robot control system and used for feeding back the working state of the execution mechanism in real time and monitoring the surrounding environment,
wherein the industrial robot control system comprises a demonstrator and a motion controller,
wherein the control system comprises an industrial personal computer,
wherein the visual tracking system comprises an RGB camera, a laser scanner, a tracking camera and a radio frequency transmitting and receiving device,
wherein the sensor system comprises a plurality of six-axis sensors, an optical sensor, a motion sensor and a Hall current sensor,
wherein the actuating mechanism comprises a mechanical part and an electric part,
the network integrated control system searches for industrial robots existing in the local area network and is connected to corresponding motion controllers, the motion sensors are operated and the six-axis sensors are cleared, the motion sensors collect pose information of end effectors of the execution mechanisms to guide the motion of the industrial robots, and the pose information is displayed on a screen of the demonstrator in real time.
Industrial robot communication is divided into two stages: the first-level communication is communication between a control system and an industrial robot control system, and adopts a serial communication technology or a network communication technology; the second-level communication is communication among the industrial robot control system, the sensor system and the visual tracking system, and adopts an industrial field bus communication technology.
The mechanical part comprises a base, a connecting piece, a big arm, a small arm, a wrist, an end effector and a rotary joint, wherein the rotary joint is respectively positioned between the base and the connecting piece, between the connecting piece and the big arm, between the big arm and the small arm and between the wrist and the end effector, the base is a bearing base part and is fixed on the ground or a support, the connecting piece is a supporting part of the big arm and realizes the rotation function of the robot, the connecting piece rotates on the base, the big arm is a supporting part of the small arm, the swinging of the big arm changes the stroke of the end effector in the horizontal direction, the pitching of the small arm realizes the position transformation of the end effector in the vertical direction, and the rotary joint of the end effector of the wrist adjusts the rotation angle and the position of a bearing.
The joint seat of the base is connected with a rotary joint with the axis vertical to the ground, the joint seat is arranged on the base and used for supporting the big arm, the small arm and the connecting rod for keeping the wrist horizontal are arranged on the joint seat, the big arm, the small arm and the connecting rod form a parallelogram, the rigidity of the whole arm is increased, the easy control performance of the wrist is met through the superposition effect of a serial parallelogram mechanism, the wrist is a flange plate, and a vacuum chuck is connected to the flange plate according to different requirements of a user.
The structure increases the rigidity of the whole arm part, the interaction of the parallelograms increases the rigidity of the whole robot transmission system, reduces the robot vibration caused under the conditions of starting and sudden stop, enlarges the stroke, reduces the system inertia, saves the cost, simultaneously increases the stability of the system, simplifies the control of the pose of the robot by utilizing the parallelogram principle of the transfer robot, reduces the difficulty of process control, and can shorten the working period and the research, development and design cost of the robot.
Wherein, the power part comprises an encoder, a decoding circuit, an optical coupling isolation circuit, a permanent magnet synchronous servo motor (PMSM), a speed reducer and an intelligent power control module (IPM), a Hall current sensor collects the phase current of U and V of the permanent magnet synchronous servo motor and feeds back the phase current to the motion controller, the encoder feeds back the actual position of the permanent magnet synchronous servo motor to the motion controller in real time through the decoding circuit, the motion controller receives the target position information through a serial bus, the target position, the actual position and the actual current are subjected to single-shaft logic control in the motion controller, the pulse width modulation is output through the time sequence scheduling of vector control and is provided for the intelligent power control module through the optical coupling isolation circuit and converted into a power control signal, the optical coupling isolation circuit realizes the complete isolation of the control part circuit and the power part circuit, the reliability of hardware is greatly improved, the intelligent power control, the output shaft of the permanent magnet synchronous servo motor is connected with a speed reducer, the speed reducer is connected with a rotary joint of the mechanical part, and the speed reducer is controlled by a motion controller to realize fine adjustment of actions.
The tracking camera is arranged right below the end effector, the position of the moving workpiece relative to the execution mechanism is observed and measured in real time, the tracking camera is used for collecting images of the moving workpiece, the shape of the moving workpiece is identified by image processing, the center of the workpiece is obtained, the center of the workpiece is compared with the last identification result to generate an error signal, the obtained error signal of the moving workpiece is used as a feedback signal and is input into a fuzzy control device of an industrial personal computer, a corresponding control signal is calculated by a fuzzy control method, the control signal is sent to the execution mechanism in a motion instruction mode to track the action of the execution mechanism, and the tracking process is as follows:
step 1, a tracking camera is used for collecting images of a moving workpiece, and the collected image information is transmitted to an industrial personal computer through a network cable and stored in an internal memory of the industrial personal computer;
step 2, reading image information of the workpiece, identifying the shape and the mass center characteristic of the moving workpiece by utilizing image processing, and comparing the shape and the mass center characteristic with a last identification result to generate an error signal;
step 3, inputting an error signal of the obtained moving workpiece as a feedback signal into a fuzzy control device of the industrial personal computer, calculating a corresponding control signal by using a fuzzy control method, and sending the control signal to an execution mechanism in the form of a motion instruction;
step 4, after the execution mechanism obtains the received instruction signal, finishing the motion movement according to the requirement, and finishing the tracking task of the moving workpiece by the tracking camera;
and 5, when the industrial personal computer sends the control command to the executing mechanism, the servo device of the executing mechanism enters the next servo period to continuously complete the same task as the previous servo period.
Wherein, the fuzzy control device of the industrial personal computer specifically is: the fuzzy control device comprises a differentiator, a fuzzification interface, an output quantity conversion module, a reasoning machine and a knowledge base, wherein the load estimation module provides measured load voltage of a servo motor to the differentiator through a band-pass filter, the differentiator subtracts set load voltage input by an operator from the measured load voltage to obtain an error value E, the error value E obtains an error change rate dE/dt through the differentiator, the error value E and the error change rate dE/dt are provided to the fuzzification interface, fuzzification assignment is carried out on the error value E and the error change rate dE/dt to respectively obtain a fuzzification error value ME and a fuzzification error change value MEC, the fuzzification error value ME and the fuzzification error change value MEC are provided to the reasoning machine, the reasoning machine fuzzifies the fuzzification error value ME and the fuzzification error change value MEC according to input and output membership vector values in the knowledge base and a logic reasoning rule to obtain a, the output quantity conversion module converts the fuzzy control quantity MU into an actual control quantity U, and controls the power supply to provide voltage for the servo motor according to the actual control quantity U.
The fuzzy control device is a programmable logic controller, and RS232 communication is adopted between the programmable logic controller and a processor of the main controller.
The fuzzy control method specifically comprises the following steps: according to the selected parameters PL, PB, PM, PS, ZO, NS, NM, NB and BL of language variables of the operator, respectively representing positive oversize, positive center, positive small, zero, negative small, negative center, negative large and negative oversize, and the corresponding fuzzy sets { -n, -n +1,. 9.. 0.. 9.. n-1, n }, n 4,nis a primary fuzzy set variable;
determination of the quantization factor, keN/e, wherein keIs the error value quantization factor, e is the measured maximum error value, kec＝n/ec，kecIs the error rate quantization factor, ec is the measured maximum error rate,
if m is less than or equal to keE≤m+1,m<n, the blurring error value ME is rounded keE, m is a secondary fuzzy set variable;
if k iseE<-n, the fuzzification error value ME is-n;
if k iseE>n, the fuzzification error value ME is n;
if m is less than or equal to kecE≤m+1,m<n, then the blurring error variation value MEC is k rounded offecE；
If k isecE<-n, the blurring error variation value MEC is-n;
if k isecE>And n, the fuzzification error variation value MEC is n.
Wherein the knowledge base comprises a database and a rule base,
the fuzzy membership vector values of the input variables and the output variables are stored in the database, the vector values are a set of corresponding values of the input variables and the output variables after discretization through corresponding domains and the like, if the corresponding domains are continuous, the corresponding domains can be used as membership functions, for the input fuzzy variables, the membership functions are stored in the database, and data are provided for an inference engine in a fuzzy inference relationship.
The rule base stores fuzzy rules, which are formed on the basis of long-term accumulated experience of operators and expert knowledge and are expressed by related vocabularies of logical relations, such as if-then, else, end, and, or the like.
The accurate control of the servo motor of the industrial robot can be automatically and effectively realized through fuzzy control, and the waste of efficiency and the inaccuracy of precision caused by repeated modification of manual setting are reduced.
The specific process of acquiring the center position of the workpiece by using image processing is as follows:
step 1, acquiring original images of a workpiece conveying line and a workpiece, wherein a lens optical axis of an RGB (red, green and blue) camera is parallel to the workpiece conveying line;
and 2, enhancing the image, and respectively filtering and denoising the RGB values in the original image. Filtering and denoising the original image, wherein the noise comprises equipment noise, salt and pepper noise and quantization noise, and the filtering process of the noise is shown as the following formula:
wherein, a rectangular coordinate system x-0-y, f is established by taking the center of the original image as the originR(x,y)、fG(x,y)、fB(x, y) are R, G, B-valued functions of the pixel at coordinate (x, y) in the original image, respectively, where x ═ 0,1, … … 255, y ∈ (0,1, … … 255), and FR(x,y)、FG(x,y)、FB(x, y) is a function of the filtered R, G, B value, N × N is a size representing a truncated window, N ═ 3,5,7. > preferably N ═ 3, and P represents a set of points made up of pixels within the window;
the filtering mode filters the RGB values of the pixels respectively, inhibits useless information and well reserves the color information of the original picture;
and 3, segmenting the image to obtain a target image of the workpiece.
Step 3.1, converting the RGB color space to generate a new color space U1U2U3。
Filtered FR(x,y)、FG(x,y)、FB(x, y) becomes the corresponding coefficient function via the following transformation:
wherein, U1(x, y) is a red-green correlation function, U2(x, y) is a red-blue correlation function, U3(x, y) is a green-blue correlation function;
and 3.2, distinguishing the workpiece from the workpiece conveying line.
Constructing a segmentation function G for workpieces and workpiece conveyor linesS(x, y) Using U1(x,y)、U2(x, y) as a judgment condition:
wherein, TSIs a segmentation threshold;
segmentation threshold TSMay be a predetermined fixed value, e.g. TS＝4。
And 4, denoising the image.
The image of the target workpiece is obtained through calculation, but some small-area noise, namely speckle noise on the image, exists inevitably, the speckle noise is obviously not the image of the workpiece and needs to be filtered, and the opening calculation and the closing calculation of mathematical morphology are used for denoising, wherein the opening calculation and the closing calculation of mathematical morphology are used for denoising
Step 4.1, constructing a binary segmentation function G'A(x, y) dividing the function G first before operationA(x, y) binarizing, wherein the binary segmentation function is as follows:
step 4.2, using open operation, firstly carrying out corrosion operation on the binary image and then carrying out expansion operation;
and 4.3, using closed operation. Firstly, performing expansion operation on the binary image and then performing corrosion operation;
step 4.4, generating the final workpiece objective function GF(x, y). Binary image and segmentation function G 'after opening and closing calculation'APerforming AND operation on the binary image composed of (x, y), and performing AND operation on G in the region of 1 valueAThe values of (x, y) are assigned one by one according to the coordinates to form a final workpiece target function GF(x,y)；
Step 5, obtaining the central position (x) of the workpiece targetcen,ycen). Its aim at lets industrial robot can fix a position the position of work piece, and then realizes snatching.
Obtaining a maximum response value in the image by using a Gaussian filter, further determining the central position of a target in the image, and constructing a Gaussian response value function as follows:wherein, δ is a scale factor and can be set according to actual conditions;
for GF(x, y) performing convolution calculation to obtain a Gaussian convolution response function:
h(x,y)＝GF(x,y)*g(x,y)，
the coordinates when the maximum value of h (x, y) is calculated, that is, the center position (x) of the targetcen,ycen)。
The above-described embodiment merely represents one embodiment of the present invention, but is not to be construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (10)
1. An industrial robot with fuzzy control of a motor comprises an industrial robot control system, a sensor system, an operation system, a network integrated control system, a visual tracking system and an execution mechanism, wherein the sensor system is connected with the industrial robot control system,
the industrial robot control system comprises a demonstrator and a motion controller,
the control system comprises an industrial personal computer,
the visual tracking system comprises an RGB camera, a laser scanner, a tracking camera and a radio frequency transmitting and receiving device,
the sensor system comprises a plurality of six-axis sensors, an optical sensor, a motion sensor and a Hall current sensor,
the actuator comprises a mechanical part and an electric part,
the mechanical part comprises a base, a connecting piece, a big arm, a small arm, a wrist, an end effector and a rotary joint,
the tracking camera is arranged right below the end effector and used for observing and measuring the position of the moving workpiece relative to the execution mechanism in real time, the tracking camera is used for collecting images of the moving workpiece, the shape of the moving workpiece is identified by image processing, the center of the workpiece is obtained, the center of the workpiece is compared with the last identification result to generate an error signal, the obtained error signal of the moving workpiece is used as a feedback signal and is input into a fuzzy control device of the industrial personal computer, a corresponding control signal is calculated by a fuzzy control method, the control signal is sent to the execution mechanism in the form of a motion instruction, and the motion of the execution mechanism is tracked.
2. The industrial robot with fuzzy motor control according to claim 1, wherein the fuzzy control device of the industrial computer is specifically: the fuzzy control device comprises a differentiator, a fuzzification interface, an output quantity conversion module, a reasoning machine and a knowledge base, wherein the load estimation module provides measured load voltage of a servo motor to the differentiator through a band-pass filter, the differentiator subtracts set load voltage input by an operator from the measured load voltage to obtain an error value E, the error value E obtains an error change rate dE/dt through the differentiator, the error value E and the error change rate dE/dt are provided to the fuzzification interface, fuzzification assignment is carried out on the error value E and the error change rate dE/dt to respectively obtain a fuzzification error value ME and a fuzzification error change value MEC, the fuzzification error value ME and the fuzzification error change value MEC are provided to the reasoning machine, the reasoning machine fuzzifies the fuzzification error value ME and the fuzzification error change value MEC according to input and output membership vector values in the knowledge base and a logic reasoning rule to obtain a, the output quantity conversion module converts the fuzzy control quantity MU into an actual control quantity U, and controls the power supply to provide voltage for the servo motor according to the actual control quantity U.
3. A fuzzy controlled industrial robot of motor according to claim 2 characterized in that the fuzzy control means is a programmable logic controller, and RS232 communication is used between the programmable logic controller and the processor of the master controller.
4. An industrial robot with fuzzy motor control as claimed in claim 1, characterized in that the fuzzy control method is embodied as: selecting parameters PL, PB, PM, PS, ZO, NS, NM, NB and BL according to language variables of an operator, wherein the parameters respectively represent positive oversize, positive centering, positive small, zero, negative small, negative centering, negative large and negative oversize, and a corresponding fuzzy set is { -n, -n +1,. once.. 0,. once.. n-1, n }, n is 4, and n is a primary fuzzy set variable;
determination of the quantization factor, keN/e, wherein keIs the error value quantization factor, e is the measured maximum error value, kec＝n/ec，kecIs the error rate quantization factor, ec is the measured maximum error rate,
if m is less than or equal to keE≤m+1,m<n, the blurring error value ME is rounded keE, m is a secondary fuzzy set variable;
if k iseE<-n, the fuzzification error value ME is-n;
if k iseE>n, the fuzzification error value ME is n;
if m is less than or equal to kecE≤m+1,m<n, then the blurring error variation value MEC is k rounded offecE；
If k isecE<-n, the blurring error variation value MEC is-n;
if k isecE>And n, the fuzzification error variation value MEC is n.
5. A motor fuzzy controlled industrial robot according to claim 2 characterized in that: wherein the knowledge base comprises a database and a rule base,
the fuzzy membership vector values of the input variables and the output variables are stored in the database, the vector values are a set of corresponding values of the input variables and the output variables after discretization through corresponding domains and the like, if the corresponding domains are continuous, the corresponding domains can be used as membership functions, for the input fuzzy variables, the membership functions are stored in the database, and data are provided for an inference engine in a fuzzy inference relationship.
The rule base stores fuzzy rules, and the fuzzy rules are formed on the basis of long-term accumulated experience of operators and expert knowledge and are expressed by related logical relation vocabularies.
6. A motor fuzzy controlled industrial robot according to claim 1 characterized in that the tracking procedure is as follows:
step 1, a tracking camera is used for collecting images of a moving workpiece, and the collected image information is transmitted to an industrial personal computer through a network cable and stored in an internal memory of the industrial personal computer;
step 2, reading image information of the workpiece, identifying the shape and the mass center characteristic of the moving workpiece by utilizing image processing, and comparing the shape and the mass center characteristic with a last identification result to generate an error signal;
step 3, inputting an error signal of the obtained moving workpiece as a feedback signal into a fuzzy control device of the industrial personal computer, calculating a corresponding control signal by using a fuzzy control method, and sending the control signal to an execution mechanism in the form of a motion instruction;
step 4, after the execution mechanism obtains the received instruction signal, finishing the motion movement according to the requirement, and finishing the tracking task of the moving workpiece by the tracking camera;
and 5, when the industrial personal computer sends the control command to the executing mechanism, the servo device of the executing mechanism enters the next servo period to continuously complete the same task as the previous servo period.
7. The industrial robot with fuzzy motor control of claim 1, wherein the specific process of obtaining the center position of the workpiece by using image processing is as follows:
step 1, acquiring original images of a workpiece conveying line and a workpiece, wherein a lens optical axis of an RGB (red, green and blue) camera is parallel to the workpiece conveying line;
and 2, enhancing the image, and respectively filtering and denoising the RGB values in the original image. Filtering and denoising an original image, wherein the noise comprises equipment noise, salt and pepper noise and quantization noise;
step 3, image segmentation is carried out, and a workpiece target image is obtained;
step 4, denoising the image, namely denoising by using opening operation and closing operation of mathematical morphology;
and 5, acquiring the central position of the workpiece target, and enabling the industrial robot to position the workpiece so as to realize grabbing.
8. A motor fuzzy controlled industrial robot according to claim 1 characterized by: the rotary joints are respectively positioned between the base and the connecting piece, between the connecting piece and the large arm, between the large arm and the small arm and between the wrist and the end effector, the base is a bearing base part and is fixed on the ground or a support, the connecting piece is a supporting part of the large arm and realizes the rotation function of the robot, the connecting piece rotates on the base, the large arm is a supporting part of the small arm, the swing of the large arm changes the stroke of the end effector in the horizontal direction, the pitching of the small arm realizes the position change of the end effector in the vertical direction, and the rotary joints of the end effector of the wrist adjust the rotation angle and the position of a bearing target.
9. The industrial robot with fuzzy motor control of claim 1, wherein the power part comprises an encoder, a decoding circuit, an optical coupling isolation circuit, a permanent magnet synchronous servo motor (PMSM), a speed reducer and an intelligent power control module (IPM), a hall current sensor collects U-phase and V-phase currents of the permanent magnet synchronous servo motor and feeds the U-phase and V-phase currents back to the motion controller, the encoder feeds an actual position of the permanent magnet synchronous servo motor back to the motion controller in real time through the decoding circuit, the motion controller receives target position information through a serial bus, the target position, the actual position and the actual current are subjected to single-axis logic control in the motion controller, and pulse width modulation is output through time sequence scheduling of vector control and provided to the intelligent power control module through the optical coupling isolation circuit and converted into a power control signal.
10. The industrial robot with fuzzy motor control of claim 1, wherein the control system receives data from the sensor system and the vision tracking system through the network integrated control system and sends control commands to the industrial robot control system, the industrial robot control system controls the actuator, the sensor system is mounted on the actuator and monitors the pose state of the actuator in real time, and the sensor system and the vision tracking system are further connected with the industrial robot control system for feeding back the working state of the actuator in real time and monitoring the surrounding environment.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811321420 | 2018-11-07 | ||
| CN2018113214204 | 2018-11-07 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110640744A true CN110640744A (en) | 2020-01-03 |
Family
ID=69013511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911019911.8A Pending CN110640744A (en) | 2018-11-07 | 2019-10-24 | Industrial robot with fuzzy control of motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110640744A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111901569A (en) * | 2020-08-11 | 2020-11-06 | 上海柏楚电子科技股份有限公司 | Monitoring processing method, device, equipment and medium for dynamically tracking cutting head |
| CN112792821A (en) * | 2021-04-01 | 2021-05-14 | 北京科技大学 | Method and system for deblurring of vision of moving robot under inertia assisted facilitation exposure |
| CN116442250A (en) * | 2023-06-20 | 2023-07-18 | 东莞市嘉翼智能装备有限公司 | Self-adaptive intelligent control method, system and storage medium for linear motor |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1806940A (en) * | 2006-01-23 | 2006-07-26 | 湖南大学 | Defective goods automatic sorting method and equipment for high-speed automated production line |
| CN103336966A (en) * | 2013-07-15 | 2013-10-02 | 山东奥泰机械有限公司 | Weed image identification method applied to intelligent agricultural machine |
| CN105945950A (en) * | 2016-06-03 | 2016-09-21 | 广东伊雪松机器人设备有限公司 | Fixture capable of facilitating carrying of workpieces, palletizing robot and operation method of palletizing robot |
| CN106179625A (en) * | 2016-07-09 | 2016-12-07 | 青岛大学 | A kind of grinding chemical mechanical system to spindle motor fuzzy control |
| CN107738255A (en) * | 2017-09-26 | 2018-02-27 | 山东工商学院 | Mechanical arm and the Mechanical arm control method based on Leap Motion |
-
2019
- 2019-10-24 CN CN201911019911.8A patent/CN110640744A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1806940A (en) * | 2006-01-23 | 2006-07-26 | 湖南大学 | Defective goods automatic sorting method and equipment for high-speed automated production line |
| CN103336966A (en) * | 2013-07-15 | 2013-10-02 | 山东奥泰机械有限公司 | Weed image identification method applied to intelligent agricultural machine |
| CN105945950A (en) * | 2016-06-03 | 2016-09-21 | 广东伊雪松机器人设备有限公司 | Fixture capable of facilitating carrying of workpieces, palletizing robot and operation method of palletizing robot |
| CN106179625A (en) * | 2016-07-09 | 2016-12-07 | 青岛大学 | A kind of grinding chemical mechanical system to spindle motor fuzzy control |
| CN107738255A (en) * | 2017-09-26 | 2018-02-27 | 山东工商学院 | Mechanical arm and the Mechanical arm control method based on Leap Motion |
Non-Patent Citations (1)
| Title |
|---|
| 刘雷: "基于FPGA的六轴工业机器人伺服***设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111901569A (en) * | 2020-08-11 | 2020-11-06 | 上海柏楚电子科技股份有限公司 | Monitoring processing method, device, equipment and medium for dynamically tracking cutting head |
| CN112792821A (en) * | 2021-04-01 | 2021-05-14 | 北京科技大学 | Method and system for deblurring of vision of moving robot under inertia assisted facilitation exposure |
| CN112792821B (en) * | 2021-04-01 | 2021-06-25 | 北京科技大学 | Method and system for deblurring of vision of moving robot under inertia assisted facilitation exposure |
| CN116442250A (en) * | 2023-06-20 | 2023-07-18 | 东莞市嘉翼智能装备有限公司 | Self-adaptive intelligent control method, system and storage medium for linear motor |
| CN116442250B (en) * | 2023-06-20 | 2023-08-11 | 东莞市嘉翼智能装备有限公司 | Self-adaptive intelligent control method, system and storage medium for linear motor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Applying a 6-axis mechanical arm combine with computer vision to the research of object recognition in plane inspection | |
| CN110202583B (en) | Humanoid manipulator control system based on deep learning and control method thereof | |
| CN110640744A (en) | Industrial robot with fuzzy control of motor | |
| CN111243017B (en) | Intelligent robot grabbing method based on 3D vision | |
| CN111633644A (en) | Industrial robot digital twin system combined with intelligent vision and operation method thereof | |
| CN110640743A (en) | Monocular industrial robot with visual tracking function | |
| CN110223345B (en) | Point cloud-based distribution line operation object pose estimation method | |
| CN110666801A (en) | Grabbing industrial robot for matching and positioning complex workpieces | |
| CN111462154A (en) | Target positioning method and device based on depth vision sensor and automatic grabbing robot | |
| CN108196453A (en) | A kind of manipulator motion planning Swarm Intelligent Computation method | |
| CN110640741A (en) | Grabbing industrial robot with regular-shaped workpiece matching function | |
| CN110000795A (en) | A kind of method of Visual servoing control, system and equipment | |
| CN114571153A (en) | Weld joint identification and robot weld joint tracking method based on 3D point cloud | |
| CN111015649A (en) | Driving and controlling integrated control system | |
| Lee | The study of mechanical arm and intelligent robot | |
| CN112257293A (en) | Non-standard object grabbing method and device based on ROS | |
| Han et al. | Grasping control method of manipulator based on binocular vision combining target detection and trajectory planning | |
| Kragic et al. | Model based techniques for robotic servoing and grasping | |
| CN113681552A (en) | Robot hybrid object five-dimensional grabbing method based on cascade neural network | |
| Zhao et al. | POSITIONING AND GRABBING TECHNOLOGY OF INDUSTRIAL ROBOT BASED ON VISION. | |
| CN113681560B (en) | Method for operating articulated object by mechanical arm based on vision fusion | |
| CN115194774A (en) | Binocular vision-based control method for double-mechanical-arm gripping system | |
| Lin et al. | Inference of 6-DOF robot grasps using point cloud data | |
| CN115464651A (en) | Six groups of robot object grasping system | |
| CN110640739A (en) | Grabbing industrial robot with center position recognition function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200806 Address after: Room 1207, building 8, block B, R & D Park, Ningbo, Zhejiang Province, 315000 Applicant after: Zhang Huanhuan Address before: 315000 No.014, 3 / F, building 2, No.128 Jingyuan Road, Ningbo hi tech Zone, Zhejiang Province Applicant before: NINGBO SAILANG TECHNOLOGY Co.,Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200103 |