Theoretical Aspects of the Patterns Recognition Statistical Theory Used for Developing the Diagnosis Algorithms for Complicated Technical Systems

International Conference on Information Technologies in Business and Industry 2016

计算机科学;经济学;工业技术

Obozov, A.A.^1 ; Serpik, I.N.^2 ; Mihalchenko, G.S.^3 ; Fedyaeva, G.A.^4

Department of Thermal Engines, Bryansk State Technical University, Bryansk, Russia^1

Department of Mechanics, Bryansk State Engineering and Technology University, Bryansk, Russia^2

Department of the Rolling Stock of Railways, Bryansk State Technical University, Bryansk, Russia^3

Department of Electronic, Radio-Electronic and Electro-Technical Systems, Bryansk State Technical University, Bryansk, Russia^4

关键词: Complicated systems;    Complicated technical systems;    Diagnosis algorithms;    Marine Diesel Engines;    Posteriori probability;    Recognition algorithm;    Statistical approach;    Technical diagnosis;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/803/1/012109/pdf
DOI  :  10.1088/1742-6596/803/1/012109

来源: IOP

【 摘 要 】

In the article, the problem of application of the pattern recognition (a relatively young area of engineering cybernetics) for analysis of complicated technical systems is examined. It is shown that the application of a statistical approach for hard distinguishable situations could be the most effective. The different recognition algorithms are based on Bayes approach, which estimates posteriori probabilities of a certain event and an assumed error. Application of the statistical approach to pattern recognition is possible for solving the problem of technical diagnosis complicated systems and particularly big powered marine diesel engines.