论文信息 - A Novel Artificial Neural Networks Force Model for End Milling

A Novel Artificial Neural Networks Force Model for End Milling

The physical process of multipoint metal cutting depends on a large number of parameters that are strongly interlinked. A number of empirical and semimechanistic models are described in the literature. This paper uses the artificial neural networks (ANNs) approach to evolve a comprehensive model for critical process parameters, such as cutting force, based on a set of input machining conditions. A set of eight input variables is chosen to represent the machining conditions, and process parameters (such as maximum force and mean force) are predicted. Exhaustive experimentation is conducted to develop the model and to validate it. The model is tested for a typical machining scenario found in industry, namely pocket-milling. Excellent agreement between the simulated and experimental forces is found.

H. El-Mounayri | V. Tandon | H. El-Mounayri | V. Tandon

[1] Jie Zhang,et al. Knowledge-based approach for improvement of CNC part programs , 1994 .

[2] C. Wang,et al. Neural Network based Adaptive Control and Optimisation in the Milling Process , 1999 .

[3] Tae Jo Ko,et al. Adaptive Optimization of Face Milling Operations Using Neural Networks , 1998 .

[4] Wei-Hua Chieng,et al. Adaptive control optimization in end milling using neural networks , 1995 .

[5] Qiang Liu,et al. On-line monitoring of flank wear in turning with multilayered feed-forward neural network , 1999 .

[6] T. Warren Liao,et al. Manufacturing Process Modeling and Optimization Based on Multi-Layer Perceptron Network , 1998 .

[7] Bernard Widrow,et al. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[8] O. Nelles,et al. An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.