About this Virtual Instructor Led Training (VILT)

Working in a refinery is not without its hazards. Safety, environmental impacts, process efficiencies, and condition-based monitoring are some of the critical areas that can be addressed using analytical workflows. In addition, an intelligent refinery is home to thousands of sensors generating a plethora of data. This 4 half-day Virtual Instructor-Led Training (VILT) course discusses Asset Performance Analytics (APA) in a Refinery. It addresses the fundamental business problems to yield a Smart Digital Twin, providing an end-to-end centralized perspective of all critical operations. Effective data gathering and automated data preparation workflows enable key stakeholders to maximize profits and ensure the safety of all personnel in a refinery. This VILT course will also discuss APA workflows to optimize performance and predict disruptive events, identifying potential failures and degradation of critical assets such as pipelines, turbines, compressors, and pumps. In addition, this VILT course will examine siloed operations to optimize processes, provide health and safety analytical workflows and maximize cost savings by improving quality and reducing poor maintenance scheduling — all with Machine Learning and Deep Learning techniques. In addition, it explores video-based analytics and asset efficiency improvements with condition-based monitoring workflows. Course Highlights: Day 1 (Session 1) opens the critical conversation of applying data-driven analytical workflows downstream. For example, what are the standard soft computing modeling techniques in Asset Performance Analytics, Condition Based Monitoring, Digital Twins, asset lifecycles, and Smart Refineries? Day 1 sheds light on data-driven approaches and helps participants decide when and how to get the most out of a digital transformation in Oil & Gas assets. The VILT course will explore supervised and unsupervised algorithms and identify repeatable and scalable predictive analytical workflows to address typical refinery business problems. Day 2 (Session 2) gets into the details and builds on the topics introduced on Day 1. Participants will go through an anonymized case study in each area: Asset Performance Analytics, Digital Twins, and Smart Refinery. They will focus on data preparation workflows to cleanse and quality control data prior to hybrid modeling, operationalizing a model in the context of first principles. Days 3 and 4 (Sessions 3 & 4) will draw upon the advanced Machine Learning data-driven methodologies covering historical static data and real-time data, edge computing, and event stream processing using Digital Signal Processing algorithms. In addition, participants will then develop a suite of data-driven workflows to build a repeatable and scalable template for a Smart Refinery and Digital Twin case study based on the Machine Learning workflows discussed on Day 1 and Day 2 (Sessions 1 & 2).