student from 01.01.2023 until now
student
The article focuses on finding an economic justification for abandoning outdated maintenance schedules in favor of an AI and ML-based CBM approach. Why is this important? Traditional maintenance strategies have long been criticized for the fact that huge amounts of money (about 30-40% of the budget) are simply wasted due to "scheduled" repairs, while every fifth unplanned failure adds headaches and unplanned expenses to the enterprise. To minimize these losses, it is proposed to use a combination of the LSTM neural network and XGBoost gradient boosting. The tests proved the viability of the approach: maintenance costs were reduced by 24%, equipment downtime by 31%, and the predictability of accidents was increased to the level of 0.89 (Precision). To top it all off, practical guidelines are given for the implementation of smart CBM systems in order to really reduce the cost of operation.
artificial intelligence, machine learning, actual condition maintenance, CBM, residual resource forecasting, maintenance and repair, industrial operation, neural networks, gradient boosting, digitalization of production
1. Fedotova G. A. Sovremennye problemy standartizacii nadezhnosti v tehnike / G. A. Fedotova, I. A. Sher // Vestnik Irkutskogo gosudarstvennogo tehnicheskogo universiteta. – 2018. – T. 22, № 2(133). – S. 142-152.
2. Oksak I. V. Optimizaciya processov TOIR, strategicheskie podhody i metody povysheniya effektivnosti / I. V. Oksak // Ustoychivoe razvitie Rossii - 2025 : Sbornik statey IV Vserossiyskoy nauchno-prakticheskoy konferencii, Petrozavodsk, 28 avgusta 2025 goda. – Petrozavodsk: Mezhdunarodnyy centr nauchnogo partnerstva "Novaya Nauka" (IP Ivanovskaya I.I.), 2025. – S. 80-99
3. Grishin A. A. Issledovanie effektivnosti algoritmov klassifikacii, ispol'zuyuschih derev'ya resheniy, dlya ekonomicheskogo prognozirovaniya na osnove aposteriornyh dannyh / A. A. Grishin, S. P. Stroev // Vestnik Tehnologicheskogo universiteta. – 2018. – T. 21, № 9. – S. 180-186
4. Korablev Yu. A. Prognozirovanie ostatochnogo sroka poleznogo ispol'zovaniya tehnologicheskogo oborudovaniya metodom glubokogo obucheniya LSTM / Yu. A. Korablev // Izvestiya YuFU. Tehnicheskie nauki. – 2025. – № 5(247). – S. 277-288
5. Sovremennoe sostoyanie metodov mashinnogo obucheniya v prilozheniyah obrabotki odnomernyh signalov / B. I. Valeev, A. I. Sadykova, A. N. Salahutdinova [i dr.] // Elektronika, fotonika i kiberfizicheskie sistemy. – 2022. – T. 2, № 3. – S. 86-95
