ANFIS for high-pressure waterjet cleaning prediction

The prediction of high pressure waterjet coating removal was very crucial to the optimization of cleaning parameters to save energy and improve productivity. This paper proposed a method of using an adaptive-network-based fuzzy inference system (ANFIS) for the modeling and predicting of high pressure cleaning process. A group of cleaning experiments was conducted for the removing of epoxy paint using high-pressure pure waterjets and the experimental data were used for the training of the ANFIS system. Three parameters were selected as the main factors of affecting the cleaning width. Bell-shaped membership functions were used for the training of the data. The results showed that the average prediction error was 6.97%, better than the Fuzzy logic method.