CN115648227A - Robot motion trajectory neural network fuzzy control optimization method - Google Patents
Robot motion trajectory neural network fuzzy control optimization method Download PDFInfo
- Publication number
- CN115648227A CN115648227A CN202211679876.4A CN202211679876A CN115648227A CN 115648227 A CN115648227 A CN 115648227A CN 202211679876 A CN202211679876 A CN 202211679876A CN 115648227 A CN115648227 A CN 115648227A
- Authority
- CN
- China
- Prior art keywords
- neural network
- robot
- fuzzy
- robot motion
- controller
- 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.)
- Granted
Links
Images
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention provides a robot motion trajectory neural network fuzzy control optimization method, which comprises the following steps: step S1, generating a robot motion reference track meeting the continuity requirement
(ii) a S2, designing a neural network fuzzy controller, wherein the neural network fuzzy controller comprises: fuzzification, fuzzy reasoning and defuzzification, and then referring to the motion reference track of the robot in the step 1
Inputting the data into the neural network fuzzy controller; and S3, optimizing the adjustment parameters of the neural fuzzy controller by utilizing a genetic algorithm to realize rapid adjustment of the parameters of the controller and realize optimization.
Description
Technical Field
The invention relates to the technical field of industrial robots, in particular to a robot motion trajectory neural network fuzzy control optimization method.
Background
In the past decades, industrial robot control is mostly established on the principle of a three-loop controller, and various robot control systems appear in order to improve the output precision of the robot control systems. The neural network fuzzy controller has a good control effect on the output error of the robot. In the past, most tests are carried out under the no-load condition of a neural network fuzzy controller, and it is found that the robot is easily interfered by load factors when moving under the load condition, so that the output error of the robot is larger.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks mentioned.
Therefore, the invention aims to provide a robot motion trajectory neural network fuzzy control optimization method.
In order to achieve the above object, an embodiment of the present invention provides a robot motion trajectory neural network fuzzy control optimization method, including the following steps:
step S1, generating a robot motion reference track meeting the continuity requirement
；
S2, designing a neural network fuzzy controller, wherein the neural network fuzzy controller comprises: fuzzification, fuzzy inference and defuzzification, and then referring the motion reference track of the robot in the step S1
Inputting the data into the neural network fuzzy controller;
and S3, optimizing the adjustment parameters of the neural fuzzy controller by utilizing a genetic algorithm to realize rapid adjustment of the parameters of the controller and realize optimization.
Further, in the step S1, the robot movement track
Comprises the following steps:
wherein, t 0 、t f Initial and final movement moments;
is a reference track q 0 、q' 0 、q f 、q' f Initial and final positions and velocities; a is a 0 、 a 1 、 a 2 、 a 3 Respectively, the coefficients of a third order polynomial.
Further, in the step S2, the robot motion is referenced to the input trajectory
And (4) performing input normalization gain, fuzzy subset form, fuzzy reasoning, defuzzification and output gain, and then transmitting to the industrial robot to obtain the motion trail q of the industrial robot.
Further, in the step S3, 6 parameters optimized using a genetic algorithm include: the objective function of the 2 blurred input normalized gains and the deblurred output gains of the 4 dispersion adjusters is the absolute sum of all joint errors over the entire trajectory.
According to the robot motion trajectory neural network fuzzy control optimization method, parameters of a neural network fuzzy control algorithm and a genetic algorithm optimization controller are realized. According to the method, under the condition that the robot is loaded, after the genetic algorithm is adopted for optimization, the angular displacement tracking error of the moving joint of the robot is obviously reduced, and the parameters can be adjusted by utilizing the genetic algorithm optimization controller, so that the parameters of the controller are quickly adjusted, and the purpose of reducing the error is achieved; the calculation process is less in time consumption and high in real-time performance.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a robot motion trajectory neural network fuzzy control optimization method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a robot motion trajectory neural network fuzzy control optimization method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a regulator in the form of a neural network in accordance with an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The invention provides a robot motion trajectory neural network fuzzy control optimization method, which adopts a genetic algorithm to optimize a neural network fuzzy controller and aims to improve the robot control precision under the load condition by selecting proper optimization parameters and objective functions.
As shown in fig. 1 and fig. 2, the robot motion trajectory neural network fuzzy control optimization method according to the embodiment of the present invention includes the following steps:
step S1, generating a robot motion reference track meeting the continuity requirement
。
In this step, the trajectory is generated by a third order polynomial to guarantee the robot continuity requirement.
Robot motion track
Comprises the following steps:
wherein, t 0 、t f Initial and final movement moments;
is a reference track q 0 、q' 0 、q f 、q' f Initial and final position and velocity; a is 0 、 a 1 、 a 2 、 a 3 Respectively, the coefficients of a third order polynomial.
S2, designing a neural network fuzzy controller, wherein the neural network fuzzy controller comprises: fuzzification, fuzzy inference and defuzzification, and then referring to the motion reference track of the robot in the step S1
Inputting the data into a neural network fuzzy controller.
In particular, for the input robot motion reference track
And inputting normalized gain, fuzzy subset form, fuzzy reasoning, defuzzification and output gain, and then transmitting to the industrial robot to obtain the motion trail q of the industrial robot.
The controller parameters are adjusted by learning each joint on line by adopting a neural fuzzy inference system method so as to obtain good control performance. A modulator structure in the form of a neural network is shown in figure 3. It contains the continuous error of the ith joint
And error variation
As input, and drive torque per joint
As an output.
Specifically, FIG. 3 is a diagram of an implementation of neural fuzzy control, input
And
is the joint error and error variation, first column A 1 ,A 2 ,B 1 ,B 2 Corresponding to the normalized gain function, the second column corresponds to the calculation of the fuzzy subset, the third column corresponds to the fuzzy reasoning, the fourth column corresponds to the defuzzification processing, and the 5 th column corresponds to the calculation of the output gain, namely the output of the joint moment.
And S3, optimizing the adjustment parameters of the neural fuzzy controller by utilizing a genetic algorithm to realize rapid adjustment of the parameters of the controller and realize optimization.
Referring to FIG. 2, the overall system input is the joint position error, an
And (3) outputting the robot joint torque through 5 steps of a neural fuzzy controller, wherein the 5 steps are respectively calculating normalization gain, constructing a fuzzy subset, performing fuzzy reasoning calculation, performing deblurring calculation and calculating output gain. The three steps of calculating the normalized gain, constructing the fuzzy subset and calculating the output gain have adjustable parameters to participate in the calculation, so that the method is related to a genetic algorithm, namely the method described in the figure.
According to the robot motion trajectory neural network fuzzy control optimization method, parameters of a neural network fuzzy control algorithm and a genetic algorithm optimization controller are realized. According to the invention, under the condition that the robot has a load, after the genetic algorithm is adopted for optimization, the angular displacement tracking error of the moving joint of the robot is obviously reduced, and the parameters can be adjusted by utilizing the genetic algorithm optimization controller, so that the parameters of the controller can be quickly adjusted, and the purpose of reducing the error is achieved; the calculation process is less in time consumption and high in real-time performance.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that those skilled in the art may make variations, modifications, substitutions and alterations within the scope of the present invention without departing from the spirit and scope of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. A robot motion trajectory neural network fuzzy control optimization method is characterized by comprising the following steps:
step S1, generating a robot motion reference track meeting the continuity requirement
；
S2, designing a neural network fuzzy controller, wherein the neural network fuzzy controller comprises: fuzzification, fuzzy inference and defuzzification, and then referring the motion reference track of the robot in the step 1
Inputting the data into the neural network fuzzy controller;
and S3, optimizing the adjustment parameters of the neural fuzzy controller by utilizing a genetic algorithm to realize rapid adjustment of the parameters of the controller and realize optimization.
2. The robot motion trajectory neural network fuzzy control optimization method of claim 1, wherein in the step S1, the robot motion trajectory
Comprises the following steps:
wherein, t 0 、t f Initial and final movement moments;
is a reference track q 0 、q' 0 、q f 、q' f Initial and final positions and velocities; a is 0 、 a 1 、 a 2 、 a 3 Respectively, the coefficients of a third order polynomial.
3. The robot motion trajectory neural network fuzzy control optimization method of claim 1, wherein in the step S2, the input robot motion reference trajectory is subjected to
And (4) performing input normalization gain, fuzzy subset form, fuzzy reasoning, defuzzification and output gain, and then transmitting to the industrial robot to obtain the motion trail q of the industrial robot.
4. The robot motion trajectory neural network fuzzy control optimization method of claim 1, wherein in said step S3, 6 parameters optimized using a genetic algorithm comprise: the objective function of the 2 blurred input normalized gains and the deblurred output gains of the 4 dispersion adjusters is the absolute sum of all joint errors over the entire trajectory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211679876.4A CN115648227B (en) | 2022-12-27 | 2022-12-27 | Robot motion trajectory neural network fuzzy control optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211679876.4A CN115648227B (en) | 2022-12-27 | 2022-12-27 | Robot motion trajectory neural network fuzzy control optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115648227A true CN115648227A (en) | 2023-01-31 |
| CN115648227B CN115648227B (en) | 2023-03-31 |
Family
ID=85022475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211679876.4A Active CN115648227B (en) | 2022-12-27 | 2022-12-27 | Robot motion trajectory neural network fuzzy control optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115648227B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05265512A (en) * | 1992-03-17 | 1993-10-15 | Hitachi Ltd | Learning type controller and fuzzy inference device |
| WO1994022074A1 (en) * | 1993-03-24 | 1994-09-29 | National Semiconductor Corporation | Fuzzy logic design generator using a neural network to generate fuzzy logic rules and membership functions for use in intelligent systems |
| US20070255454A1 (en) * | 2006-04-27 | 2007-11-01 | Honda Motor Co., Ltd. | Control Of Robots From Human Motion Descriptors |
| CN101122777A (en) * | 2007-09-18 | 2008-02-13 | 湖南大学 | Large condenser underwater operation environment two-joint robot control method |
| CN108717262A (en) * | 2018-05-14 | 2018-10-30 | 湖南大学 | A kind of abnormal curved surface tracking and system based on moment characteristics learning neural network |
| CN110471281A (en) * | 2019-07-30 | 2019-11-19 | 南京航空航天大学 | A kind of the Varied scope fuzzy control system and control method of Trajectory Tracking Control |
| CN111618864A (en) * | 2020-07-20 | 2020-09-04 | 中国科学院自动化研究所 | Robot model prediction control method based on adaptive neural network |
| CN111844020A (en) * | 2020-06-11 | 2020-10-30 | 马鞍山职业技术学院 | Manipulator trajectory tracking control system based on fuzzy neural network |
| US20220152817A1 (en) * | 2020-11-18 | 2022-05-19 | Dibi (Chongqing) Intelligent Technology Research Institute Co., Ltd. | Neural network adaptive tracking control method for joint robots |
-
2022
- 2022-12-27 CN CN202211679876.4A patent/CN115648227B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05265512A (en) * | 1992-03-17 | 1993-10-15 | Hitachi Ltd | Learning type controller and fuzzy inference device |
| WO1994022074A1 (en) * | 1993-03-24 | 1994-09-29 | National Semiconductor Corporation | Fuzzy logic design generator using a neural network to generate fuzzy logic rules and membership functions for use in intelligent systems |
| US20070255454A1 (en) * | 2006-04-27 | 2007-11-01 | Honda Motor Co., Ltd. | Control Of Robots From Human Motion Descriptors |
| CN101122777A (en) * | 2007-09-18 | 2008-02-13 | 湖南大学 | Large condenser underwater operation environment two-joint robot control method |
| CN108717262A (en) * | 2018-05-14 | 2018-10-30 | 湖南大学 | A kind of abnormal curved surface tracking and system based on moment characteristics learning neural network |
| CN110471281A (en) * | 2019-07-30 | 2019-11-19 | 南京航空航天大学 | A kind of the Varied scope fuzzy control system and control method of Trajectory Tracking Control |
| CN111844020A (en) * | 2020-06-11 | 2020-10-30 | 马鞍山职业技术学院 | Manipulator trajectory tracking control system based on fuzzy neural network |
| CN111618864A (en) * | 2020-07-20 | 2020-09-04 | 中国科学院自动化研究所 | Robot model prediction control method based on adaptive neural network |
| US20220152817A1 (en) * | 2020-11-18 | 2022-05-19 | Dibi (Chongqing) Intelligent Technology Research Institute Co., Ltd. | Neural network adaptive tracking control method for joint robots |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115648227B (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109465825B (en) | RBF neural network self-adaptive dynamic surface control method for flexible joint of mechanical arm | |
| CN108388114B (en) | Flexible mechanical arm composite control method based on output redefinition | |
| CN110181510B (en) | Mechanical arm trajectory tracking control method based on time delay estimation and fuzzy logic | |
| Alavandar et al. | Adaptive Neuro-Fuzzy Inference System based control of six DOF robot manipulator. | |
| CN106970636B (en) | Control system and control method for controlling speed of aircraft | |
| CN115157238A (en) | Multi-degree-of-freedom robot dynamics modeling and trajectory tracking method | |
| CN113341719A (en) | AGV trajectory tracking control method integrating TEB algorithm and fuzzy control | |
| Moham | Design a fuzzy PID controller for trajectory tracking of mobile robot | |
| Jia et al. | Optimization of control parameters based on genetic algorithms for spacecraft attitude tracking with input constraints | |
| Mohammed et al. | Trajectory tracking control and robustness analysis of a robotic manipulator using advanced control techniques | |
| CN111273544A (en) | Radar pitching motion control method based on prediction RBF feedforward compensation type fuzzy PID | |
| CN113359421A (en) | Composite control system and method for piezoelectric precision gas flow valve | |
| CN115648227B (en) | Robot motion trajectory neural network fuzzy control optimization method | |
| Zhang et al. | Adaptive control of discrete-time nonlinear systems using ITF-ORVFL | |
| CN111367168B (en) | Feedforward parameter design method based on fuzzy logic | |
| Alavandar et al. | New hybrid adaptive neuro-fuzzy algorithms for manipulator control with uncertainties–Comparative study | |
| CN109176529B (en) | Self-adaptive fuzzy control method for coordinated movement of space robot | |
| Yang et al. | Nonlinear adaptive control for manipulator system with gear backlash | |
| JP3515267B2 (en) | Multi-layer neural network learning device | |
| CN114879508A (en) | Grinding robot path tracking control method based on model prediction control | |
| Peng et al. | Trajectory-tracking control for mobile robot using recurrent fuzzy cerebellar model articulation controller | |
| Bibi et al. | Robust direct adaptive controller for a class of uncertain nonlinear systems using petri type 2 fuzzy neural networks (PT2FNN) as a new approximator | |
| Hajipour et al. | Optimized neuro observer-based sliding mode control for a nonlinear system using fuzzy static sliding surface | |
| Siddikov et al. | Structural-parametric adaptation of fuzzy-logical control system | |
| CN112180918A (en) | Synchronous control method and system for double mobile robots |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |