Prediction of Laser Cutting Roughness in Intelligent Manufacturing Mode Based on ANFIS

In order to predict the roughness of laser cutting effectively and improve the quality level of laser cutting, the adaptive neural fuzzy inference system (ANFIS) model which combined the adaptive learning ability of neural network and the experience knowledge of fuzzy inference system is established. The prediction results based on laboratory data are compared with the values predicted by BP neural network model, and the influence of process parameters on laser cutting roughness is analyzed. The results show that convergence speed of ANFIS model is faster and predictive values are in conformity with the measured values. Its performance is superior to the BP neural network model in the error dimensions, training speed and convergence precision, furthermore it can predict laser cutting roughness through gas pressure, cutting speed and cutting seam width accurately.