Imaging feature analysis-based intelligent laser cleaning using metal color difference and dynamic weight dispatch corrosion texture

Abstract

To improve the laser cleaning efficiency of Q235 carbon steel, an imaging analysis-based intelligent technique is proposed. Both offline and online computations are designed. Regarding the offline procedure, first, the corrosion images are accumulated to compute the gray-level co-occurrence matrix (GLCM) and the concave-convex region features. Second, different laser cleanings are performed to obtain various cleaned images. Third, a new cleaning performance evaluation method is developed: a metal color difference feature and a dynamic weight dispatch (DWD) corrosion texture are computed. Finally, a particle swarm optimization (PSO)-support vector machine (SVM) is utilized to forecast the laser process parameters. The corresponding laser parameters include power, linear velocity, and line spacing. For the online computation, after the GLCM and the concave-convex region features are computed, an iterative computation is used to tune the process parameters: the random laser parameters are generated constantly, and the iteration is performed and terminated only if the PSO-SVM output is positive. The experimental results have shown that the cleaning efficiency of this method can be improved, and the qualified rate is 92.5%.