In most NC machining companies, operators decide the cutting condition, a pair of spindle speed(S) and table feedrate(F) by experience and subjective judgment. The objective of this study is to develop a cutting condition decision system which utilizes shop data and predicts tool life by neural network and eventually leads to the optimum cutting condition. The production time per piece is considered for an optimization method.
The process of an optimum cutting condition decision by neural network is discussed. Following this process, a series of shop data is stored. And the neural network for prediction tool life is constructed and the optimum cutting condition is recommended from a cutting condition decision system using stored shop data. The results show that the system that is developed here is valid in searching the optimum cutting condition on job operations. Although this method is applied to the flat endmill roughing operation, it can be extended to other cutting operations such as ball endmilling, drilling, and planer and shaper operations. Above processes will be researched for future topic.