School of Engineering Science
Predictive maintenance is one of the major thrust areas for many global manufacturing companies. Artificial intelligence, big data analytics and industrial internet of things (IoT) have already shown great potential in the area of maintenance. However, as more companies adopt these technologies, several key challenges have emerged hindering the progress towards complete digitalization of maintenance operations.
The aim of this project is to develop an Integrated Manufacturing Analytics Platform (IMAP) that combines core Industry 4.0 technologies of industrial IoT, digital twins and analytics to realize the full potential of predictive maintenance and pave the way towards prescriptive maintenance.
The core idea of IMAP is to supplement and validate data from existing IoT infrastructure with simulated data from lean digital twins, preprocess and integrate these multiple sources of data into the CMMS, and use machine learning, analytics and optimization techniques to monitor the health of equipment, thereby predicting the need for maintenance in advance, generating automated maintenance actions and corresponding maintenance work orders.
The project is expected to bring the following targeted improvements to production and maintenance KPIs:
Industry-wide studies have shown that predictive maintenance can increase equipment uptime and availability by 10-20%, reduce the time required to plan maintenance by 20-50%, and reduce overall maintenance costs by up to 25%.