A KNOWLEDGE-BASED ADAPTIVE-CONTROL ENVIRONMENT FOR AN INDUSTRIAL LASER CUTTING SYSTEM

A hierarchically structured environment that integrates a knowledge-ba sed expert system, adaptive process control and pattern recognition te chniques for controlling a laser cutting process is described. Knowled ge of the laser cutting process for different materials is organised a nd encoded into a rule-based system. An adaptive control algorithm bas ed on on-line recursive parameter estimation and on-line control law s ynthesis was adopted for the highly non-linear cutting process control . Cutting speed was selected as the major control variable. Irradiance emitted from the cut front is used for the feedback signal to this ad aptive controller. The irradiance signal feeds the recursive parameter estimator for system identification. Techniques of pattern recognitio n, which have been well developed in coherent optics, were applied to assess cut quality by characterising the exit spark cone images of the gas assisted laser cutting process. Images from the cutting processes were grabbed, edge enhanced and correlated with a synthetic discrimin ant function filter which was synthesised from reference images known to give good cut quality. Results from digital simulations based on th ese pattern recognition algorithms are also presented.