Innovation science and technologiy 1-tom 6-san (2025)
SANOAT KORXONALARIDA USKUNALAR HOLATINI SUN’IY INTELLEKT ORQALI BASHORATLASH
Sultonov Ikromjon Shukhratjon ugli, Dr Maya Sari SE MM, Adon Asep Miftahuddin
Annotaciya
This article examines predictive maintenance (PdM) systems for predicting equipment conditionusing artificial intelligence (AI) in industrial plants. The study utilizes theoretical analysis, a comparative studyof international practices, and methods for evaluating the effectiveness of machine learning, deep learning, andsignal processing algorithms in predicting equipment failures. The results demonstrate that AI-based PdM systemscan significantly reduce unexpected downtime, optimize maintenance costs, and extend equipment servicelife. Using international experience as examples, the PdM methods of leading companies, such as Rolls-Royce, Caterpillar, ThyssenKrupp, and SKF, are analyzed and their results are presented. The key stages,technical requirements, and cost effectiveness of implementing AI-based PdM systems are substantiated.
AI, PdM, predictive maintenance, equipment condition, failure prediction, remaining service life, vibration analysis, anomaly detection, machine learning, deep learning, signal processing, IoT, real-time monitoring, Industry 4.0.
Metadata derekkózi: jurnal OAI-PMH arxivi · Sindex tolıq mátindi saqlamaydı, derekkózge silteme beredi.