Abstract: Through the use of edge AI, this abstract explores the world of predictive maintenance for industrial devices. In order to predict future equipment faults, the method combines the seamless integration of sensor-generated data, preprocessing methods, and localised AI models. This methodology enables enterprises to proactively manage maintenance needs, minimising unplanned downtime and optimising resource allocation. It does this by leveraging real-time data analytics at the edge.Sensor raw data is systematically collected, and to get actionable insights, the data is put through noise reduction and feature extraction pre processing phases. These understandings serve as the cornerstone for AI models that have been painstakingly trained on past data to identify patterns suggestive of upcoming failures. This predictive capacity makes it easier to create real-time alerts that inform maintenance teams of potential problems before they happen.
Cite:
Akash T.Koli,Deepali V.Nangare,Akanksha I.Shitole, Mahesh R.Mule,Rajveer K.Shastri, "PREDICTIVE MAINTENANCE OF INDUSTRIAL MACHINE USING EDGE AI", IJIREEICE International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, vol. 12, no. 1, 2024, Crossref https://doi.org/10.17148/IJIREEICE.2024.122.
Copyright Form