Identification of Cyclic Changes in the Operation Mode of the Production Facility Based on the Monitoring Data
Nina Davydenko , Igor Korobiichuk , Liudmyla Davydenko , Michał Nowicki , Volodymyr Davydenko
AbstractThe article deals with the issues of formalizing the change of the actual conditions of the operation mode of the production facility. The purpose of the article is to develop a mechanism for identifying these changes based on the analysis of data obtained from the monitoring system the operation mode of the facility. The expediency of using the pattern recognition apparatus for solving the issue is substantiated. As an indicator of changing operation conditions, it is suggested to use the profile of the relevant factor of the external environment described by morphometric indicators. The two-step procedure is proposed based on the successive use of pattern recognition algorithms without and with training. It provides the formation of knowledge about the possible states of the facility operation conditions and the construction of classifier to determine the accordance to one of them. Structurally-parametric identification of the classifier model is performed by the group method of data handling. The use of the proposed mechanism will contribute to the effective planning of operation modes of production facilities, the determination of time ranges for supporting such modes, their control, and the prevention of non-typical operation modes.
|Publication size in sheets||0.5|
|Book||Szewczyk Roman, Krejsa Jiří, Nowicki Michał, Ostaszewska-Liżewska Anna (eds.): Mechatronics 2019: Recent Advances Towards Industry 4.0, Advances in Intelligent Systems and Computing, vol. 1044, 2020, Springer, ISBN 978-3-030-29992-7, [978-3-030-29993-4], 515 p., DOI:10.1007/978-3-030-29993-4|
|Keywords in English||pattern recognition, relevant factor profile, morphometric parameters, group method of data handling, classifier|
|Score||= 20.0, 10-01-2020, MonographChapterAuthor|
|Publication indicators||= 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.