A Distributed Modeling Framework for Monitoring Big Data in Plant-Wide Processes

With the growing complexity of the modern process industry, the era of big data has arrived, particularly for the large scale plant-wide processes. The size of data can range from terabyte to petabyte in the plant-wide process even for a single dataset. This big size of data poses great challenges not only for information capture, data management and storage, but also more important, to efficiently interpret the information hidden within those data. In this paper, a big data oriented distributed modeling framework is developed for plant-wide process monitoring. Based on this framework, the whole plant-wide process is decomposed into different blocks, and statistical data models are constructed inside those blocks. For online monitoring, results obtained from different blocks are integrated through the decision fusion algorithm. A detailed case study is carried out for performance evaluation of the plant-wide monitoring method. Research challenges and perspectives are also discussed and highlighted for future work.