Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling
- 134 Downloads
Due to the demands of Computer-Integrated Manufacturing (CIM), the Tool Condition Monitoring (TCM) system, as a major component of CIM, is essential to improve the production quality, optimize the labor and maintenance costs, and minimize the manufacturing loses with the increase in productivity. To look for a reliable, efficient, and cost-effective solution, various monitoring systems employing different types of sensing techniques have been developed to detect the tool conditions as well as to monitor the abnormal cutting states. This paper explores the use of audible sound signals as sensing approach to detect the cutting tool wear and failure during end milling operation by using the Support Vector Machine (SVM) learning model as a decision-making algorithm. In this study, sound signals collected during the machining process are analyzed through frequency domain to extract signal features that correlate actual cutting phenomenon. The SVM method seeks to provide a linguistic model for tool wear estimation from the knowledge embedded in this machine learning approach. The performance evaluation results of the proposed algorithm have shown accurate predictions in detecting tool wear under various cutting conditions with rapid response rate, which provides the good solution for in-process TCM. In addition, the proposed monitoring system trained with sufficient signals collected from different positions has been proved to be position independent to monitor the tool wear conditions.
KeywordsTool condition monitoring Tool wear Audible sound Machine learning Support vector machine
Unable to display preview. Download preview PDF.
The authors gratefully acknowledge support from the Gleason Doctoral Fellowship program for this research, and would like to thank Ray Ptucha for his insightful suggestion into this work.
- 7.Jemielniak K, Kosmol J (1995) Tool and process monitoring-state of art and future prospects. Scientific papers of the institute of mechanical engineering and automation of the Technical University of Wroclaw 61:90–112Google Scholar
- 9.Chen JC, Huang LH, Lan AX, Lee S (1999) Analysis of an effective sensing location for an in-process surface recognition system in turning operations. J Ind Technol 15(3):1–6Google Scholar
- 16.Jones J, Wu Y (1996) Cutting tool’s power consumption measured, US Patent. US 5–587-931Google Scholar
- 17.Zhou Y, Orban P, Nikumb S (1995) Sensors for intelligent machining-a research and application survey. In Systems, man and cybernetics, 1995. Intelligent systems for the 21st century. IEEE International Conference on (vol 2, pp 1005–1010). IEEEGoogle Scholar
- 21.Iwata K, Moriwaki T (1977) An application of acoustic emission measurement to in-process sensing of tool wear. Ann CIRP 26(1):21–26Google Scholar
- 23.Delio T, Tlusty J, Smith S (1992) Use of audio signals for chatter detection and control. J Eng Ind 114(2):146–157Google Scholar
- 25.Raja E, Sayeed S, Samraj A, Kiong LC, Soong LW (2011) Tool flank wear condition monitoring during turning process by SVD analysis on emitted sound signal. Eur J Sci Res 49(4):503–509Google Scholar
- 28.Anderson DA, Dias WA (1988) Method for monitoring cutting tool wear during a machining operation. US Patent: 4,744,242Google Scholar
- 33.Sun J, Hong GS, Rahman M, Wong YS (2004) The application of nonstandard support vector machine in tool condition monitoring system. In Electronic Design, Test and Applications, Proceedings. DELTA 2004. Second IEEE International Workshop on (pp 295–300). IEEEGoogle Scholar
- 36.Ripley BD (2007) Pattern recognition and neural networks. Cambridge University Press, Cambridge, pp 354–354Google Scholar
- 37.Ting Ming K (2010) Confusion matrix. In: Claude S, Webb G (eds) Encyclopedia of Machine Learning. Springer US, pp 209–209Google Scholar