Overview

​​Dynamic Risk Analyzer (DRA) is an autonomous early warning software which is quick to implement, almost like a plug and play system. It provides valuable additional time for operators to identify deviations of individual parameters to troubleshoot potential problems before alarms are triggered. For more complex systems, enhanced monitoring could be achieved via Fault Tree Analysis (FTA). In FTA, process knowledge can be used to provide the relationship among individual tags, to show how these parameters interlink and affect a process plant, much like a Fault Tree normally developed during incident investigation or root cause analysis.

However, instead of being used for post incident investigation it becomes a predictive, pre-incident early warning tool. With the online Fault Tree Analysis, we draw down the experience, tacit knowledge and lessons learnt from previous incident investigations, as well as theoretical knowledge of the process. Years of experience and knowledge are captured, and visualized for enhancement of existing predictive monitoring system. Operations team performing daily monitoring are able to see the potential issues developing from the early stages or the root causes, before they escalate into more concerning issues. Operators are able to visualize the potential faults that could occur, identify the triggered root causes, and are advised with possible prescriptive actions. Thus assessment of the impact of an anomaly and corrective actions could be done more quickly.

Speakers

Azura Othman, Group Technical Solutions, Petronas

Azura has been with PETRONAS for 20 years. Currently with Group Technical Solutions performing feasibility studies or front end engineering for new and existing plant modifications. Additionally her work in Process Technology involves optimization initiatives at the refineries and deployment of digital predictive monitoring tool across the group, including refinery, petrochemical and LNG assets. Prior to GTS she was in Technical Services, Projects and Production Department in the Refinery and Aromatics plant in Kerteh.

Ankur Pariyani, Chief Innovation Officer, Near-Miss Management

 Ankur is Co-Founder and Chief Innovation Officer of Near-Miss Management. He specialises in early risk detection of industrial plants for their improved safety and reliability, using autonomous AI methods. His pioneering work has led to several patents and publications in high-impact journals and industry media. He holds PhD and MS degrees in Chemical Engineering from the University of Pennsylvania and a BTech from the Indian Institute of Technology in Guwahati. He is a recipient of 2017 AIChE ‘35 Under 35’ Award.

The material presented in this webinar has not been peer-reviewed. Any opinions are the presenters' own and do not necessarily represent those of IChemE or the Computer Aided Process Engineering Special Interest Group. The information is given in good faith but without any liability on the part of IChemE.

Webinar recording