The Optimization of The Zinc Electroplating Bath Using Machine Learning And Genetic Algorithms (NSGA-II)

In this study, our aim is to predict the compositions of zinc electroplating bath using machine learning method and optimize organic additives with NSGA-II (Non-dominated Sorting Genetic Algorithm) optimization algorithm. Mask RCNN was utilized classify coated plates according their appearance. The names classes were defined as ”Full Bright”, Fail”, ”HCD Fail” ”LCD Fail”. intersection over union (IoU) values model determined in range 93–97%. Machine algorithms, MLP, SVR, XGB, RF, trained classification panels whose detected by RCNN. training, electrodeposition specified input output. From models, RF gave highest F1 scores for all classes. are 0.95, 0.91, 1 0.80 respectively. algorithm (NSGA-II) used bath. models objective function. ranges additives, which should be bath, determined.