Neural Network-based Dynamic Planning Model for Process Parameter Determination

Determining such process parameters as rotational speed, feed rate, depth of cut, and width of cut is the critical function that affects not only machining productivity but also quality of a finished part. In the paper, a dynamic planning model is developed to determine efficient process parameters for roughly machining a pocket type of process feature in the shop floor. A neural network structure is proposed to implement the dynamic planning model. The learning patterns used for training the neural network are acquired through simulation-based optimization procedures. The procedure finds an optimal set of process parameters for each set of operating factors by considering the machining costs, cutting forces, and machining power. A prototype system is developed and experimented to demonstrate the feasibility of the proposed model. Due to the dynamic planning model approach, the fatal weaknesses of conventional processing parameter determination can be conquered by its efficient, dynamic, and adaptive planning ability