Development of an intelligent system for tool wear monitoring applying neural networks

• Autorzy: Antić, A. , Hodolič, J. , Soković, M.
• Języki publikacji: EN

Abstrakty

EN

Purpose: The objective of the researches presented in the paper is to investigate, in laboratory conditions, the application possibilities of the proposed system for tool wear monitoring in hard turning, using modern tools and artificial intelligence (AI) methods. Design/methodology/approach: On the basic theoretical principles and the use of computing methods of simulation and neural network training, as well as the conducted experiments, have been directed to investigate the adequacy of the setting. Findings: The paper presents tool wear monitoring for hard turning for certain types of neural network configurations where there are preconditions for up building with dynamic neural networks. Research limitations/implications: Future researches should include the integration of the proposed system into CNC machine, instead of the current separate system, which would provide synchronization between the system and the machine, i.e. the appropriate reaction by the machine after determining excessive tool wear. Practical implications: Practical application of the conducted research is possible with certain restrictions and supplement of adequate number of experimental researches which would be directed towards certain combinations of machining materials and tools for which neural networks are trained. Originality/value: The contribution of the conducted research is observed in one possible view of the tool monitoring system model and it’s designing on modular principle, and principle building neural network.

Słowa kluczowe

PL

wytwarzanie; przetwarzanie; obróbka; metody sztucznej inteligencji; zużycie narzędzia; monitorowanie

EN

manufacturing; processing; machining; artificial intelligence methods; tool wear; monitoring

• Czasopismo: Journal of Achievements in Materials and Manufacturing Engineering
• Rocznik: 2006
• Tom: Vol. 14, nr 1-2
• Strony: 146--151
• Opis fizyczny: Bibliogr. 15 poz., rys., tab., wykr.

Twórcy

autor

Antić, A.

• Faculty of Technical Sciences, University of Novi Sad, Trg D. Obradovića 6, 21000 Novi Sad, Serbia & Montenegro

autor

Hodolič, J.

• Faculty of Technical Sciences, University of Novi Sad, Trg D. Obradovića 6, 21000 Novi Sad, Serbia & Montenegro

autor

Soković, M.

• Faculty of Mechanical Engineering, University of Ljubljana, Askerceva 6, SI-1000 Ljubljana, Slovenia,

Bibliografia

• [1] C. Scheffer, H. Kratz, P.S. Heyns, F. Klocke: Development of a tool wear-monitoring system for hard turning, International Journal of Machine Tools &Manufacture 43, (2003), 973–985.
• [2] M. Balazinski, E. Czogala, K. Jemielniak, J. Leski: Tool condition monitoring using artificial intelligence methods, Engineering Applications of Artificial Intelligence 15, (2002), 73–80.
• [3] B. Siek: On-line indirect tool wear monitoring in turning with artificial neural networks, a review of more than a decade of research, Mechanical Systems and Signal Processing 16(4), (2002), 487–546.
• [4] D.E. Dimla Sr., P.M. Lister: On-line metal cutting tool condition monitoring. II: tool-state classification using multilayer perception neural networks, International Journal of Machine Tools &Manufacture 40, (2000), 769–781.
• [5] Shang-Liang Chen, Y.W. Jen: Data fusion neural network for tool condition monitoring in CNC milling machining, International Journal of Machine Tools &Manufacture 40, (2000), 381–400.
• [6] U. Zuperl, F. Cus, M. Milfelner: Fuzzy control strategy for adaptive force control in end milling, COMENT Worldwide Congress on Materials and Manufacturing Engineering and Technology, Glivice-Wisla, Poland, 2005, pp3.399.
• [7] T. Ozel, A. Nadgir, Prediction of flank wear by using back propagation neural network modeling when cutting hardened H-13 steel with chamfered and honed CBN tools, International Journal of Machine Tools &Manufacture 42, (2002), 287–297.
• [8] R. Kothamasu, S.H. Huang, Intelligent tool wear estimation for hard turning: Neural-Fuzzy modelling and model evaluation, Proceedings of the Third International Conference on Intelligent Computation in Manufacturing Engineering, Ischia, Italy, 2002, 343–346.
• [9] C. Scheffer, P.S. Heyns: An industrial tool wear monitoring system for interrupted turning, Mechanical Systems and Signal Processing 18 (2004), 1219–1242.
• [10] A. Antic, J. Hodolic, R. Gatalo, M. Stevic, Contribution to the development of the multi-sensor system for tool monitoring, Annals of DAAAM &Proceedings of the 12th international DAAAM Symposium, Vienna, Austria, 2001, 009-010.
• [11] A. Antic: A Contribution to the development of tool monitoring system in flexible manufacturing systems, Master’s thesis, Faculty of Technical Sciences, 2002.
• [12] F. Cus, M. Milfelner, J. Balic An overview of data acquisition system for cutting force measuring and optimization in milling Contemporary, COMENT Worldwide Congress on Materials and Manufacturing Engineering and Technology, Glivice Wisla, Poland, 2005, pp 1.368.
• [13] J.S. Son, D.M. Lee, I.S. Kim, S.G. Choi: A Study on On-line learning Neural Network for Prediction for Rolling Force in Hot-rolling Mill, COMENT Worldwide Congress on Materials and Manufacturing Engineering and Technology, GliviceWisla, Poland, 2005, pp 3.355.
• [14] P. D. Lippman, "Neural Computing – theory and practice", Van Nostrand Reinhold N. Y., 1989.
• [15] M. Riedmiller, and H. Braun, A direct adaptive method for faster back-propagation learning: The RPROP algorithm, Proceedings of the IEEE International Conference on Neural Networks, 1993.