Intelligent methodology for sensing, modeling, and control of weld penetration in robotic welding system

Abstract

Purpose

The purpose of this paper is to develop an efficient online monitoring system. It can improve the welding quality through the real‐time analysis of the welding image information.

Design/methodology/approach

In this paper, a set‐variable precision rough set (VPRS) modeling method was improved and the prediction model of back‐side bead width dynamic response for robotic arc welding process is proposed. Back‐side width based on the vision sensor in the compound controller is used. Meantime, a compound intelligent controller is designed with the wire‐feeding rate compensation.

Findings

The dynamical information of the top‐side weld pool can be captured in real‐time. Moreover, VPRS prediction model could provide the back‐side bead width of the weld, which integrated with the fuzzy neural network controller. Therefore, more uniform weld penetration can be achieved with the variation of the assembling gap.

Research limitations/implications

The monitor system requires that the information of the weld pool and the front gap can be extracted precisely. Moreover, the front assembling gap should be limited in a certain interval [0∼3 mm]. This puts forward high request to image processing algorithm and the assembling of the work‐piece.

Practical implications

This monitor system is applicable to the manufacturing of the spherical head petals in rocket storage tank.

Originality/value

The paper demonstrates that the compound intelligent controller based on the VPRS prediction is possible and effective. The experiments show that the real‐time and precision requirements for monitoring and control of weld quality can be satisfied by using this online control system during welding process.

Citation

Lin, T., Chen, H.B., Li, W.H. and Chen, S.B. (2009), "Intelligent methodology for sensing, modeling, and control of weld penetration in robotic welding system", Industrial Robot, Vol. 36 No. 6, pp. 585-593. https://doi.org/10.1108/01439910910994650