(259c) Revisiting Fault Detection and Diagnosis in the Era of Big Data and Machine Learning

Several techniques for fault detection and diagnosis (FDD) in chemical process industry have been explored over the last three decades. However, assumptions made while developing these techniques regarding data availability and computational power have to be revisited, given the explosion of IOT and big data, and availability of advanced programming and computational platforms. As a result, it might be worthwhile exploring enhancements to existing techniques to solve more meaningful problems, and posing newer problems that the current generation of technologies will allow us to solve. This talk will focus on these aspects from a FDD perspective and will also include case studies from industrial implementations of some of these ideas.