Towards a rapid configurable embedded development for manufacturing prognostics: A review and proposed framework

With the fast changing global business landscape, manufacturing companies are facing the increasing challenge to reduce the cost of production, increase equipment utilisation and rapidly provide innovative products in order to compete with low cost economies. One of the methods is zero or near zero down time. Unfortunately, the current research and industrial solutions do not provide a user friendly and rapidly configurable environment to create 'adaptive microprocessor size with supercomputer performance' solution in order to reduce downtime. Most of the current solutions are PC-based with offthe-shelf software tools, which are found to be inadequate for adaptive prognostics near the sensor source using embedded devices. On the other hand, developing a solution for various industrial domains can be too time consuming because the tools and rapid methods for creating adaptive or real time reconfigurable solutions are lacking. A total of 175 papers from 38 refereed journals and international conferences are collated and reviewed. Based on the review, some of the potential industrial needs, research trends and gaps in manufacturing prognostics are discussed. Finally, a research agenda towards a rapid configurable embedded development environment for manufacturing environment is identified.