Artificial intelligence-driven predictive maintenance in IoT systems
Raghdah Adnan Abdulrazzq, Nisreen Mustafa Sajid, Md. Kamrul Hasan
Abstract
The study looks at the application of AI-driven predictive maintenance in IoT systems. Predictive device failure, efficient reduction in system downtime, reduced maintenance costs, and overall efficiency in connected devices will be enabled through machine learning and deep learning algorithms. The AI models developed within this research were able to provide a prediction accuracy of 92%, while the traditional methods of maintenance were far behind at 78%. It resulted in a 35% reduction in system downtime and a 28% decrease in maintenance costs while reducing the error rate to 8%. The above results bring out the potential of AI-based solutions for real-time predictive maintenance over complex IoT networks. It concludes by indicating some further research vectors, such as the refinement of the model and the extension of AI-driven predictive maintenance for broader applications in IoT, such as smart cities and healthcare systems.