With the continuous in-depth study of metal cutting mechanism and the development of computer technology, people have established a computer-aided optimization program system for cutting data, which provides new methods and means for selecting the optimal cutting parameters. As a new technology in the field of artificial intelligence research, neural networks have non-linear characteristics and information distribution. When dealing with multiple input and multiple output systems, it eliminates the complicated correlation analysis of various variables required by traditional modeling methods. The purpose of this article is to study the application and development of neural network technology for mechanical automation processing parameters. This article trains the sample set, learns the statistical law of the sample set, and saves the learned information in the weight. When the non-sample set mode is input, the BP network in the ideal neural network is highly nonlinear. The mapping ability is not limited by the number of inputs and outputs. In specific research applications, the original program can be freely modified as needed. This paper uses BP network as a research tool, trains BP network by using a large amount of experimental data, studies and analyzes several influencing factors of error remapping phenomenon, and uses BP network to solve the basic method of remapping problem, and initially established the feasibility of the method. Experimental research shows that this article is the ideal output data (actual data) for network testing and the network output data. From these data, it can be seen that the network training output and the ideal output error are controlled below 5%. It can be seen that the training result of the network is successful.
展开▼
