A Framework for IoT-Based Monitoring and Diagnosis of Manufacturing Systems

Abstract

IoT systems have gained increasing attentions in research community and industry. Tens of billions of devices are now connected to the Internet and quintillion bytes of data are generated from sensing devices every day. One of the important applications of IoT systems in industry is monitoring, fault detection, and diagnosis of manufacturing systems (MFDM). However, current practices in the development of such systems are individualized with each company developing their own solutions. To address this issue, we propose a SaaS-centered framework for manufacturing system health management. The configurability and easy evolution of SaaS can facilitate reuse and sharing of data, processes, and technologies. Besides the general framework, we also look into the technologies that are important for the framework. The literature in time series data storage and the techniques for mining correlated data are reviewed and the gaps are identified. To bridge the gap, we discuss some potential methods for resolving the problems. We also consider how to incorporate the potential techniques into our framework for effective fault detection and diagnosis.