Application of Data Mining in Fault Diagnosis

Abstract:

Knowledge is the most valuable asset of manufacturing enterprises. Their core competitiveness is improved only by strengthening the management of knowledge. Data mining is the most powerful tool which discovers knowledge from large amounts of data. Fault diagnose is one of earliest application domains of data mining. This paper introduces data mining models for manufacturing applications. By using text mining techniques, this paper introduces the application of concept description function, classification function, clustering function in fault diagnosis.

• Periodical: Advanced Materials Research (Volumes 616-618)
• Pages: 1671-1674
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.616-618.1671
• Online since: December 2012
• Authors: Jun Tan
• Keywords: Classification, Clustering, Concept Description, Data Mining (DM), Fault Diagnosis

References

[1] Harding, J.A., Shahbaz, M., Srinivas, &Kusiak, A. (2006). Data mining in manufacturing: A review. American Society of Mechanical Engineers. Journal of Manufacturing Science and Engineering, 128(4), 969-976

DOI: 10.1115/1.2194554

[2] Lee, S.G., &Ng, Y.C. Hybrid case-based reasoning for on-line product fault diagnosis. International Journal of Advanced Manufacturing Technology, 27,823-840 (2006)

DOI: 10.1007/s00170-004-2235-z

[3] Fountain, T., Dietterich, T., &Sudyka, B. Data mining for manufacturing control: An application in optimizing IC test. Exploring artificial intelligence in the new millennium, G. lakemeyer and B. Nebel, eds., Morgan Kaufmann, San Francisco,CA,pp.381-400

[4] Maki, H., Teranishi, Y. Development of Automated Data Mining System for Quality Control in Manufacturing. Lecture Notes in Computer Science, Springer-Verlag, Berlin, pp.93-100 (2001)

DOI: 10.1007/3-540-44801-2_10

[5] Maki, H., Maeda, A., Morita, T., &Akimori, H. Applying data mining to data analysis in manufacturing. International conference on advances in production management systems, pp.324-331 (2000)

DOI: 10.1007/978-0-387-35569-6_40

[6] Shen, L., Tay, F.E.H., Qu, L.S., &Shen, Y. Fault diagnosis using rough set theory. Computers in industry, 43, 61-72 (2000)

DOI: 10.1016/s0166-3615(00)00050-6

[7] Kusiak, A. Rough set theory: a data mining tool for semiconductor manufacturing. IEEE Transactions on Electronics Packaging Manufacturing, 24(1), 44-50 (2001)

DOI: 10.1109/6104.924792

[8] Dengiz, O., Smith, A.E., &Nettleship, I. Two stage data mining for flaw identification in ceramics manufacturing. International Journal of Productive Research, 44(14), 2839-1851 (2006)

DOI: 10.1080/00207540500534454

[9] Irani, K.B., Cheng, J., Fayyad, U.M., &Qian, Z. Applying machine learning to semiconductor manufacturing. IEEE Expert, 8(1), 41-47. (1993)

DOI: 10.1109/64.193054

[10] Skormin, V.A., Gorodetski, V.I., &PopYack, I.J. Data mining technology for failure of prognostic of avionics. IEEE Transactions on Aerospace and Electronics Systems, 38(2), 388-401. (2002)

DOI: 10.1109/taes.2002.1008974

[11] Jeong, M.K., Lu, J.C., Huo,X., Vidakovic,B., &Chen, D. Wavelet-based data reduction techniques for process fault detection. Technometrics, 48(1), 26-40 (2006)

DOI: 10.1198/004017005000000553

[12] Rojas, A., Nandi, A.K. Practical scheme for fast detection and classification of rolling element bearing faults using support vector method. Mechanical Systems and Signal Processing, 20, 1523-1536. (2006)

DOI: 10.1016/j.ymssp.2005.05.002