2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS) (2015)
Dec. 11, 2015 to Dec. 13, 2015
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/DSDIS.2015.97
Internet of Things (IoT) has become an important topic in both industry and academia for the recent years as it offers great potentials in numerous real world applications. This paper considers the problem of fault diagnosis and prediction from IoT data collected in the process industry. We propose a solution by making use of IoT enabling technologies offered by SAP. The proposed solution first discovers the causal relationship of the physical devices by analyzing only the device sensor data without the knowledge of the physical manufacturing system. While faults of certain devices can be detected by monitoring the healthy index of these devices in real-time, possible faults of other devices can be predicted based on the causal relationship discovered in the previous step. Such prediction capability enables new breeds of predictive maintenance applications where appropriate actions can be recommended to operators of the manufacturing system in a timely manner. The viability of the proposed solution is confirmed by a real world application of IoT conducted with an industry partner.
Predictive models, Industries, Algorithm design and analysis, Real-time systems, Prediction algorithms, Monitoring, Databases
C. Wang, H. T. Vo and P. Ni, "An IoT Application for Fault Diagnosis and Prediction," 2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS), Sydney, Australia, 2015, pp. 726-731.