Data Analytics, Machine Learning & Artificial Intelligence > Refinery Asset Performance Analytics & Digital Twins – Virtual Instructor Led Training (VILT)
Code Date Venue Early Bird Fee Fee
PE1606 03 - 06 Oct 2022 Virtual Instructor Led Training (VILT) SGD 2,899 SGD 3,099 Remind me of Course Dates
PE1606 03 - 06 Oct 2022 Virtual Instructor Led Training (VILT) USD 2,199 USD 2,399 Remind me of Course Dates

Learn in teams and save more! Enjoy group discounts of up to 50% off normal fees for team based learning. Contact us on info@asiaedge.net to learn more today!

Code

PE1606

Date

03 - 06 Oct 2022

Venue

Virtual Instructor Led Training (VILT)

Early Bird Fee

SGD 2,899

Fee

SGD 3,099

Code

PE1606

Date

03 - 06 Oct 2022

Venue

Virtual Instructor Led Training (VILT)

Early Bird Fee

USD 2,199

Fee

USD 2,399

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).

By the end of this VILT course, participants will be equipped with an understanding of:

  • Fundamental concepts of Machine Learning and Deep Learning for predictive and prescriptive models
  • Machine Learning workflows for data preparation prior to model development
  • The role of performance metrics and Explainable AI (XAI)
  • Refinery case studies with data and Python Notebooks for the practical application of ML/DL
  • Digital Twin Machine Learning workflows: what is a digital twin and how can we implement a digital twin
  • Digitalization techniques for Anomaly Detection to optimize asset performance
  • Downstream Case Studies – The Smart Refinery techniques and business value propositions

This VILT course is designed for engineers, refinery asset managers, data scientists working on condition-based monitoring, asset performance optimization, anomaly detection, and refinery managers who would like to apply data-driven modeling techniques for HSE optimization. It is also intended for managers and supervisors who would like to update their skills on the technology’s current level. Oil & Gas professionals interested in applying machine learning methods for asset performance in their downstream projects and traditional workflows and who have experience using Python in Jupyter Notebooks will find this VILT course beneficial.

  1. Engineers and data scientists in Oil & Gas companies: Operators & service companies
  2. Technical professionals who are involved in downstream Asset Performance Analytics and Digital Twin technologies

The VILT course will be delivered online in 4 half-days consisting of 4 hours per day, with two breaks of 10 minutes per day.

Course Duration: 4 half-day sessions, 4 hours per session (16 hours in total).

Your expert trainer started off his career in the oil & gas industry as a geophysicist, involved in processing and interpreting seismic data. While in the oil & gas industry, he was previously working with PGS, Petroleum Development Oman (PDO), ARCO and BP. He later moved into software development with SAS Institute, Inc. He has been involved in upstream Oil & Gas data driven model building across Exploration and Production for over 10 years. He is currently developing business strategies to establish Analytical Centres of Excellence and data management architectures across the Oil and Gas industry. He holds a Degree in Geology and Mathematics as well as a Master’s Degree Geophysics and Seismology from Durham University, England, UK. He currently holds 2 patents that have been issued out in 15 countries.