{"title":"Tool Failure Detection Based on Statistical Analysis of Metal Cutting Acoustic Emission Signals","authors":"Othman Belgassim, Krzysztof Jemielniak","volume":50,"journal":"International Journal of Mechanical and Mechatronics Engineering","pagesStart":378,"pagesEnd":386,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/2812","abstract":"The analysis of Acoustic Emission (AE) signal\r\ngenerated from metal cutting processes has often approached\r\nstatistically. This is due to the stochastic nature of the emission\r\nsignal as a result of factors effecting the signal from its generation\r\nthrough transmission and sensing. Different techniques are applied in\r\nthis manner, each of which is suitable for certain processes. In metal\r\ncutting where the emission generated by the deformation process is\r\nrather continuous, an appropriate method for analysing the AE signal\r\nbased on the root mean square (RMS) of the signal is often used and\r\nis suitable for use with the conventional signal processing systems.\r\nThe aim of this paper is to set a strategy in tool failure detection in\r\nturning processes via the statistic analysis of the AE generated from\r\nthe cutting zone. The strategy is based on the investigation of the\r\ndistribution moments of the AE signal at predetermined sampling.\r\nThe skews and kurtosis of these distributions are the key elements in\r\nthe detection. A normal (Gaussian) distribution has first been\r\nsuggested then this was eliminated due to insufficiency. The so\r\ncalled Beta distribution was then considered, this has been used with\r\nan assumed \u03b2 density function and has given promising results with\r\nregard to chipping and tool breakage detection.","references":"[1] Belgasim O., Jemielniak K., Tool condition monitoring, a review,\r\nPreceedings of Al Azhar engineering fourth international conference,\r\nDecember 1995\r\n[2] Jemielniak k., Belgassim O., Characteristics of acoustic emission sensors\r\nemployed for tool condition monitoring, preceedings of VII workshop\r\non supervision and diagnostics of machining systems, Karpacz - Poland,\r\n(CIRP) March 1996\r\n[3] Spiegel M., Theory and problems of probability and statistics, Schaum-s\r\noutline series, McGraw_Hill Inc. 1975\r\n[4] Ndeeb C., Pflueg C., Real-time monitoring of chip form in turning\r\nprocesses with Acoustic Emission using thin film sensors, Transactions\r\nof NAMRI\/SME Volume XXIV, 1996\r\n[5] Kannatey-Asibu E., Investigation of the metal cutting process using\r\nacoustic emission signal analysis, Ph.D. Thesis, University of\r\nCalifornia, Berkeley. 1980\r\n[6] Whitehouse D., Beta functions for surface typology, Ann. CIRP, 27\r\n(1978) 491-497\r\n[7] Kannatey-Asibu E, Dornfeld D, A study of tool wear using statistical\r\nanalysis of metal cutting acoustic emission, Wear Journal, 76 (1982)\r\n247-261\r\n[8] Gabriel V., Matusky J., Pru\u015bek A., \u017ci\u017cka J., Study of machining process\r\nby acoustic emission method, Proc. of IV int. conf. on monitoring &\r\nautomatic supervision in manufacturing - Miedzeszyn- CIRP (1995)\r\n143-148\r\n[9] Jemielniak K., : Detection of Cutting Edge Breakage In Turning,\r\nAnnals Of The CIRP 41\/1: 97-100, 1992","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 50, 2011"}