A fuzzy approach for on-line error compensation during robotic welding

During robot welding operations in the manufacturing industry there is a need to modify on-line the welding path due to a mismatch in the position of the components to be welded. These positioning errors are due to multiple factors such as ageing of the components in the part conveyor system, clamp fixtures, disturbances, etc. Therefore, robot reprogramming is needed which requires a stop in the production line and consequently an increment in production costs. In this article, we present an alternative solution to this problem that involves the use of structured lighting using a low-cost laser beam, a CMOS camera and a Fuzzy Controller. To validate the proposed control system, a robotic cell was designed using an industrial KUKA KR16 robot for welding metallic plates. The method was evaluated experimentally under lateral and vertical positioning errors. The control interface includes apart from the misalignment correction, the on/off control of the welding power supply, arc voltage and current adjustment, welding torch speed and the control of the distance between the torch's tip and the welding plate. Obtained results using the experimental design method showed a maximum error of 1.6mm, which is considered appropriate for the welding of industrial beads in metallic plates and which demonstrates the method's effectiveness in practical situations.