According to the grind-hardening test and using the multiple linear regression analysis, the empirical formula of the tangential grinding force is established in this paper. Combined with the heat distribution coefficient formula of Rowe and Pettit, the thickness of the grind-hardening layer is predicted by using the finite element method under different grinding parameters. It draws the influence law of the grinding speed, cutting depth and feed rate to the thickness of the grind-hardening layer. It provided the basis to the drawing up, the application and the optimization of the grind-hardening process.
An improved neural network based on L-M algorithm has been applied to the prediction of the grind-hardening parameters against to the slow convergence rate of conventional BP neural network. And the the neural network model for grind-hardening is established. The neural network prediction system for grind-hardening process has been developed based on L-M algorithm. The functions of system is analyzed, particularly and some pivotal technology to realize the system are put forward.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.