Intelligent method for monitoring the state of lubricating oil
Source abstract
Abstract
Mathematical decision-making methods for estimating the state of lubricating oil have been analyzed. It has been demonstrated that the most promising direction for solving problems of determining the performance of oil taking into account the existing uncertainty, ambiguity, incompleteness, and fuzziness of information on the object is the application of an expert system based on fuzzy logic, which provides objective and more substantiated decisions. The intelligent decision-making method on the state of lubricating oil and the structural diagram of the fuzzy logic method based on the Mamdani algorithm have been developed. An example of the implementation of the developed method for monitoring the lubricating oil state has been given based on the analysis of the following diagnostic parameters: total oil contamination measured in three spectral ranges, chemical destruction factor, and oil viscosity. A conclusion has been drawn on oil serviceability based on the analysis of the integrated numerical oil state factor. It has been demonstrated that the developed method provides a real-time objective estimation of oil serviceability and makes it possible to perform the timely maintenance of the tribosystem.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Power Transformer Diagnostics and Insulation · Coal Combustion and Slurry Processing · Petroleum Processing and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (8)
Show source-provided references
1. Drewes, E. and Anderhub, J., Fuzzy logic and neural networks, Kompressor. Tekhn. Pnevmat., 2012, no. 3, pp. 7–11.
2. Zhernakov, S.V., Ivanova, N.S., and Ravilov, R.F., Checking and diagnosis of technical condition of GTE oil system with use of neural network technology, Vestn. Ufimsk. Gos. Aviats. Tekhn. Univ., 2012, vol. 16, no. 2, pp. 210–220
3. Abu-Siada, A., Lai, S.P., and Islam, S.M., A novel fuzzy-logic approach for furan estimation in transformer oil, IEEE Trans. Power Deliv., 2012, no. 2, pp. 469–474.10.1109/TPWRD.2012.2186986 ↗
4. Kosterev, N.V., Bardik, E.I., Vozhakov, R.V., and Kurach, T.Yu., Fuzzy algorithms of technical state estimation and prediction of residual resource of electrical equipment, Naukovi Pratsi Donets. Nat. Tekhn. Univ.–Elektrotekhn. Energ., 2008, vol. 140, no. 8, pp. 65–70.
5. Ramezani, S. and Yousofi, M., A fuzzy rule based system for fault diagnosis, using oil analysis results, Int. J. Indust. Engineer. Product. Res., 2011, vol. 22, no. 2, pp. 91–98.
6. Markova, L.V., Makarenko, V.M., Semenyuk, M.S., Zozulya, A.P., Kong, H., and Han, H.-G., A magnetoelastic viscometer for on-line monitoring of viscosity of lubricating oils, J. Frict. Wear, 2011, vol. 32, no. 1, pp. 41–48.10.3103/S1068366611010090 ↗
7. Markova, L.V., Myshkin, N.K., Makarenko, V.M., Semenyuk, M.S., Kong, H., Han, H.-G., and Ossia, S.V., Integral detector for condition monitoring of lubricants in friction units Trenie Iznos, 2008, vol. 29, no. 4, pp. 399–408.10.3103/S1068366608040119 ↗
8. Shtovba, S.D., Introduction into the theory of fuzzy sets and fuzzy logic. http://www.matlab.exponenta.ru/fuzzylogic/index.php