Methodology of Diagnostic Knowledge Acquisition

• Autorzy: Moczulski W.
• Języki publikacji: EN

Abstrakty

EN

The paper deals with a comprehensive methodology concerning knowledge acquisition on machinery for the purpose of expert systems suitable for aiding of diagnostic inference. The methodology includes selected methods of diagnostic knowledge representation, methods of knowledge acquisition from domain experts and from previously classified examples, methods of assessment of previously acquired knowledge and a scenario of knowldge acquisition process. All the methods have been implemented in a Knowledge Acquisition System. Moreover, some examples of applications of the elaborated methodology have been given.

Słowa kluczowe

EN

machinery diagnostics; knowledge acquisition; domain experts; machine learning; knowledge discory

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2001
• Tom: vol. 49, nr 2
• Strony: 337--357
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Moczulski W.

• Silesian University of Technology, Department of Machine Design Fundamentals, Konarskiego 18A, 44-100 Gliwice, Poland (Politechnika Śląska, Katedra Podstaw Konstyrukcji Maszyn)

Bibliografia

• [1] Cz. Cempel, Vibroacoustic dignostics of machinery (in Polish), PWN, Warszawa 1989.
• [2] W. Cholewa, Real-time expert systems for technical diagnostics, 15th IMACS World Congress on Scientific Computation, Modelling and Applied Mathemathics, Proceedings, 6 (1997) 715-720, Berlin.
• [3] W. Cholewa, Kiciński, Machinery diagnostics. Inverted diagnostic models, (in Polish), Monographs - Machine Building and Exploitation, Silesian Technical University, Gliwice 1997.
• [4] M. Dąbrowski, M. Michalewicz, Z. Raś, Intelligent information systems, Proceedings of the Conference "Practical Aspects of Artificial Intelligence III" , Wigry. Inst. of Computer Science PAS, Warsaw 1994.
• [5] J. Dougherty, R. Kohavi, M. Sahami, Supervised and unsupervised discretization of continuous features, A. Prieditis, S. Russell, Machine Learning: Proceedings of the 12th International Conference, Morgan Kaufman, San Francisco, CA 1995.
• [6] A. Giordana, L. Saitta, F. Bergadano, F. Brancadori, D. De Marchi, ENIGMA: a system that learns diagnostic knowledge, IEEE Trans. on Knowledge and Data Engineering, 5, 1, (Feb. 1993) 15-28.
• [7] J. W. Grzymała-Busse, Managing uncertainty in machine learning from examples, in: [4], 70-84.
• [8] ISO 2372, Mechanical vibrations of machin es with operating speeds from 10 to 200 rev/s - basis for specifying evaluation standards (1974).
• [9] K. A. Kaufman, INLEN: A methodology and integrated system for knowledge discovery in databases, Dissertation. George Mason University, Fairfax, VA 1997.
• [10] P. Kostka, Expert system for application of multi-dimensional signal analysis for investigations of rotor vibrations (in Polish), M. Sc. Thesis, Dept. of Fundamentais of Machine Design, Silesian Tech. University, Gliwice 1997.
• [11] P. Kostka, Example of application of machine learning methods for knowledge acquisition on rotating machin ery, ed.: M. Kłopotek, M. Michalewicz, Z. Raś, Proceedings of the Workshop "Intelligent Information Systems" IIS'98, 235-238, Institute of Computer Science PAS, Warsaw 1998.
• [12] R. S. Michalski, A theory and methodology of inductive learning, Artificial Intelligence, 20 (1983) 111-16l.
• [13] R. S. Michalski, Machine learning, Data mining and knowledge discovery. Principles and aplications, Tutorial on the Workshop "Intelligent Information Systems" IIS'97, Zakopane. Institute of Computer Science PAS, Warszawa 1997.
• [14] W. Moczulski, Methods of knowledge acquisition for the needs of machinery diagnostics, (in Polish), Series: Mechanics No. 130, Silesian Tech. University, Gliwice 1997.
• [15] W. Moczulski, Methodology of knowledge acquisition for machinery diagnostics, Computer Assisted Mechanics and Engineering Sciences, 2,1, (1999) 163-175.
• [16] W. Moczulski, Methods of diagnostic knowledge acquisition concerning industrial turbine sets, 3rd International Conference " Acoustical and Vibratory Surveillance Methods and Diagnostic Techniques", Conference Proceedings, 1 (1998) 145-154, Paris-Senlis.
• [17] W. Moczulski, Acquisition of diagnostic knowledge from examples concerning complex technical states, ed.: M. Kłopotek, M. Michalewicz, Z. Raś, Proceedings of the Workshop "Intelligent Information Systems" IIS'99, (1999) 80-91, Institute of Computer Science PAS, Warsaw 1999.
• [18] W. Moczulski et al., Knowledge acquisition for the needs of technical diagnostics, (in Polish), Report of the Grant No. 8 T11F 020 09, Dept. of Fundamentals of Machine Design, Silesian Tech. University, Gliwice 1997.
• [19] W. Moczulski, M. Wyleżoł, Acquisition of empirical relationships for the needs of machinery diagnostics, (in Polish), 3rd National Conference "Knowledge Engineering and Expert Systems", II (1997) 160-164, Technical University, Wrocław.
• [20] W. Moczulski, J. M. Żytkow, Automated search for knowledge on machinery diagnostics, ed.: M. Kłopotek, M. Michalewicz, Z. Raś, Proceeding of Workshop "Intelligent Information Systems", IIS'97 held in Zakopane, (1997) 194-203, Institute of Computer Science PAS, Warsaw.
• [21] Z. Pawlak, Rough sets. Theoretical aspects of reasoning about data, Kluwer Academic Publishers 1991.
• [22] J. R.. Quinlan, Induction of decision trees, Machine Learning, 1 (1986) 81-106.
• [23] J. R. Quinlan, C4.5 programs for machine leaming, Morgan Kaufmann, San Mateo, CA 1993.
• [24] S. M. Weiss, L Kapouleas, An empirical comparison of pattern recognition, neural nets, and machine learning classification methods, Proceedings of 11th International Joint Conference on Artificial Intelligence, (1989).
• [25] J. Wnek, K. Kaufman, E. Bloedorn, R. S. Michalski, Selective induction learning system AQ15c: the method and user's guide, Center for Machine Learning and Inference, George Mason University, Fairfax, VA 1995.
• [26] M. Wyleżoł, Electronic Form-Editor for Acquisition of Empirical Rules for Diagnostic Purposes (in Polish), 1st National Conference "Computer Methods and Systems in Scientific Research and Engineering Design", Conference Proceedings, (1997) 179-184, University of Mining and Metallurgy, Cracow.
• [27] M. Wyleżoł, Electronic form-editor for acquisition of empirical rules from experts for the purpose of diagnostics, ed.: M. Kłopotek, M. Michalewicz, Z. Raś, Proceedings of the Workshop "Intelligent Information Systems" 118'98, (1998) 231-234, Institute of Computer Science PAS, Warsaw.