Weld tracking application adaptive fuzzy control method

Abstract

The invention discloses a weld tracking application adaptive fuzzy control method comprising the following steps: 1, fuzzifying an obtained discrepancy e and a deviation change rate (e<.>=de / dt) so as to obtain a fuzzy variable deviation E and a deviation change rate EC; 2, combining with expert knowledge and operation experiences, and building fuzzy rules according to the deviation e and deviation change rate ec; 3, inputting the inputted fuzzy variable deviation E and the deviation change rate EC into a fuzzy inference engine so as to obtain a fuzzy output value U; 4, using a maximum value method to defuzzify, and converting the fuzzy output value U into an accurate value u; 5, introducing a controller scale factor ki (i=1, 2,..n) and a controller quantification factor ku, and setting input / output fuzzy universe and a fuzzy rule function; 6, real time updating the fuzzy rule function according to the input / output value changes, and calculating and outputting a offset voltage value of a controlled object. The method can adjust the fuzzy controller parameters in a control process, thus solving the problems that the control process is unstable, poor in dynamic performance and rough in the process.

Description

technical field [0001] The invention relates to the field of seam tracking control, in particular to an adaptive fuzzy control method for seam feature points. Background technique [0002] After getting the displacement that the welding robot needs to move, because the mathematical model of the robot is unknown, these discrete deviation values ​​cannot be sent directly to the robot controller. At the same time, because the mechanical system has a certain lag compared with the visual inspection system, if there is no effective control algorithm, it is easy to cause periodic chattering at the end of the welding torch during the welding process. Due to the non-linear and time-varying nature of the controlled process and other accidental errors, while the fuzzy rule base and membership functions in traditional fuzzy control are fixed, which makes the control process unstable, the dynamic performance deteriorates, and the control process is rough. In order to solve this problem, ...

AI Technical Summary

Problems solved by technology

[0002] After obtaining the displacement that the welding robot needs to move, these discrete deviation values ​​cannot be directly sent to the robot controller because the mathematical model of the robot is unknown

At the same time, because the mechanical system has a certain lag compared with the visual inspection system, if there is no effective control algorithm, it is easy to cause periodic chattering at the end of the welding torch during the welding process. Due to the non-linear and time-varying nature of the controlled process and other accidental errors, while the fuzzy rule base and membership functions in traditional fuzzy control are fixed, which makes the control process unstable, the dynamic performance deteriorates, and the control process is rough. In order to solve this problem, it is necessary to control the process Adjusting parameters of fuzzy controller in real time

Images