Instrument Reliability using Predictive Analytics (IRIS)

The purpose of this research is to introduce IRIS, an Integrated Asset Analytics solution designed to offer real-time comprehensive insights and efficient workflow management for over 10,000 monitored devices, including sensors, valves, systems, and tanks since 2021. The motivation behind IRIS stems from the pressing need to address issues such as scattered data across multiple databases, leading to siloed information and a lack of visibility on critical equipment. By leveraging predictive analytics, IRIS aims to enhance maintenance planning, reduce operational and capital expenses, ensure compliance with safety standards for critical equipment, and minimize process safety incidents. The integrated approach facilitates data-driven decision-making, ultimately improving plant reliability and reducing unplanned downtime. This paper discusses the development and implementation of IRIS as an in-house cloud-based solution, highlighting its potential impact on instrument reliability and overall asset management. It provides valuable insights into the benefits and values of analytics, along with a brief module description and challenges during implementation. Through the use of predictive analytics, failure rate analysis, and early anomaly detection, IRIS aims to shift from a time-based to a predictive mindset culture, optimizing maintenance costs and avoiding deferment or shutdown. The implementation of IRIS offers significant benefits to complex operations, fleets, or networks of assets in the industry, including reductions in unplanned downtime, maintenance costs, and safety incidents, while also increasing asset availability and production productivity. In summary, IRIS presents a comprehensive solution to address challenges such as scattered data, lack of insights, and the growing need for integrated asset analytics in the industry.