Electrode wear prediction in milling electrical discharge machining based on radial basis function neural network
- 140 Downloads
- 1 Citations
Abstract
Milling electrical discharge machining (EDM) enables the machining of complex cavities using cylindrical or tubular electrodes. To ensure acceptable machining accuracy the process requires some methods of compensating for electrode wear. Due to the complexity and random nature of the process, existing methods of compensating for such wear usually involve off-line prediction. This paper discusses an innovative model of electrode wear prediction for milling EDM based upon a radial basis function (RBF) network. Data gained from an orthogonal experiment were used to provide training samples for the RBF network. The model established was used to forecast the electrode wear, making it possible to calculate the real-time tool wear in the milling EDM process and, to lay the foundations for dynamic compensation of the electrode wear on-line. This paper demonstrates that by using this model prediction errors can be controlled within 8%.
Key words
milling electrical discharge machining (EDM) electrode wear prediction radial basis function (RBF) neural networkCLC number
TG 661References
- [1]Yu Z Y, Masuzawa T, Fujino M. Micro-EDM for three-dimensional cavities-development of uniform wear method [J]. CIRP Annals-Manufacturing Technology, 1998, 47(1): 169–172.CrossRefGoogle Scholar
- [2]Zhao W S. Advance electrical discharge machining technology, electrical discharge milling machining [M]. Beijing: National Defense Industry Press, 2003 (in Chinese).Google Scholar
- [3]Dauw D. On the derivation and application of a real-time wear sensor in EDM [J]. CIRP Annals—Manufacturing Technology, 1986, 35(1): 111–116.CrossRefGoogle Scholar
- [4]Bleys P, Kruth J P, Lauwers B. Sensing and compensation of tool wear in milling EDM [J]. Journal of Materials Processing Technology, 2004, 149: 139–146.CrossRefGoogle Scholar
- [5]Tricarico C, Forel B, Orhant E. Measuring device and method for determining the length of an electrode [P]. US: 6072143. 2000-06-06.Google Scholar
- [6]Mizugaki Y. Contouring electrical discharge machining with on-machine measuring and dressing of a cylindrical graphite [C]// Proceedings of the 1996 IEEE IECON 22nd International Conference V3. Taipei: IEEE Press, 1996: 1514–1517.CrossRefGoogle Scholar
- [7]Feng T, Xiao-mei X U, Tso S K, et al. Application of evolutionary neural network in impact acoustics based nondestructive inspection of tile-wall [C]// Proc International Conference on Communications, Circuits and Systems. Hong Kong: IEEE Press, 2005: 974–978.CrossRefGoogle Scholar
- [8]Poggio T, Girosi F. Networks for approximation and learning [J]. Proc IEEE, 1990, 78(10): 1481–1497.CrossRefGoogle Scholar
- [9]Park J, Sandberg I W. Approximation and radial basis function networks neural computation [J]. Neural Computation, 1993, 5(2): 305–316.CrossRefGoogle Scholar
- [10]Sanner R M, Slotine J J E. Gaussian networks for direct adaptive control [J]. IEEE Transactions on Neural Networks, 1992, 3(6): 837–863.CrossRefGoogle Scholar
- [11]Chen S, Billings S A, Cowan C F N, et al. Practical identification of narmax models using radial basis functions [J]. International Journal of Control, 1990, 52(6): 1327–1350.MATHCrossRefMathSciNetGoogle Scholar
- [12]Chen S, Cowan C F N, Grant P M. Orthogonal least squares learning algorithm for radial basis function networks [J]. IEEE Transactions on Neural Networks, 1991, 2(2): 302–309.CrossRefGoogle Scholar
- [13]Chen X G. Artificial neural network technology and application [M]. Beijing: China Electric Power Press, 2003 (in Chinese).Google Scholar