Design, implementation and testing of a fuzzy control scheme for laser welding

Abstract

A fuzzy logic controller (FLC) scheme has been developed for laser welding. Process light emissions are measured and combined to determine the current status of the welding process. If the process is not in a desired welding state, the FLC will adapt the laser power. The FLC has been demonstrated for the laser welding of zinc coated steel sheets in an overlap configuration. Experiments showed that the controller is capable of steering the process towards full penetration keyhole welding, avoiding both blowholes as well as lack of penetration. Under the presence of different process disturbances, like changes in focal position and material thickness, the controller proved to be able to maintain full penetration keyhole welding. The architecture of the controller is generic, thus facilitating an implementation for the laser welding process of other materials or configurations.

Review of laser welding monitoring

“…Experimental results show that the system can ensure full penetration even when the focus position and material thickness vary. 111 Aarts and Sibillano have also proved that based on the electron temperature measured by spectrometer, adaptive control on weld penetration can be realised by varying laser out-put power as shown in Fig. 22.…”

Progress and perspectives of in-situ optical monitoring in laser beam welding: Sensing, characterization and modeling

“…In laser-based manufacturing field, such data-driven approaches have been extensively studied in the past and are based on autoregressive exogenous (ARX) model [154]- [155], cluster analysis [156], fuzzy logic (FL) [156]- [161] or on supervised learning algorithms including multivariate regression (MR) [162]- [163], multi-layer perceptron (MLP) [164]- [165], and decision trees (DT) [166]- [167], as well as K-nearest neighbors (KNN) [168]- [169]. Once the eigenvector has been established, effective identification and classification of different welding status or defects can be realized by using advanced modeling technology.…”

Multi-sensor measurement and data fusion technology for manufacturing process monitoring: a literature review

“…Furthermore, in [73], Sibillano et al analyzed the plasma's spectra under aluminum laser welding, while Palanco et al [74] analyzed the spectra of plasma under aluminum welding. Finally, in order to control the weld penetration, Jauregui [75] utilized four photodiodes for detection during the laser welding processes.…”