Knowledge-based neural network for surface roughness prediction of ball-end milling

Theoretical modeling for surface roughness of ball-end milling generally results in low prediction accuracy due to the lack of machining information, excessive computational costs, and uncertainty of manual adjustment parameters. Besides, data-driven methods are limited in practical applications due to the lack of theoretical support or 'black-box problems' of neural network. To deal with these problems as mentioned above, this paper presents a coupling model for surface roughness prediction by combining the theoretical model of surface roughness and the datadriven approach. The core process is the secondary modeling with regard to the predictive result of theoretical model, which is realized by utilizing the knowledge-based neural networks with radial basis functions (KBaNN_RBF). Firstly, a theoretical model is established for the surface roughness prediction of ball-end milling by using the tool parameters and machining parameters. The output of the theoretical model is embedded into KBaNN_RBF as a priori knowledge. Secondly, low-dimensional features are extracted from the monitoring signals and adopted as the input of KBaNN_RBF for secondary modeling. And, the network structure is optimized by utilizing particle swarm optimization (PSO). Finally, ball-end milling experiment is carried out to verify the effectiveness of the presented KBaNN_RBF. Experimental results show that KBaNN_RBF is highly effective in improving the prediction accuracy and compressing the confidence interval (CI). Moreover, the comparison results show that the effectiveness of KBaNN_RBF is far superior to the traditional methods, such as back propagation neural network (BPNN) and support vector machine (SVM). This paper provides theoretical guidance for accurate monitoring of surface roughness in real industrial settings.