Driving Sustainability Through Application of Deep-Learning-Based Flare Smoke Detection, Alerting and Control
Digitalization, Sustainability
A significant component in winning the energy transition challenge comes down to managing and reducing the emissions from manufacturing activities of the energy-intensive industries. In most of the facilities in oil & gas production, refining and petrochemical industries, flare is used to burn off waste gases, and typically a manual work process is adopted to ensure complete and smokeless combustion. The work process requires the facility operators to monitor camera feed that shows real-time status of flare operations and make control changes on the DCS to optimize combustion ensuring smokeless flaring.
To automate this manual work process and further enhance operator efficiency and environmental performance in flare operations, we present in this work an end-to-end flare smoke detection, alerting and DCS control solution that leverages existing flare CCTV cameras used at many facilities. The core of this solution is a deep-learning computer vision model that we have developed leveraging an extensive and diverse data set and the model has shown fit-for-use performance in wide-ranging conditions.
We will present results of this application implemented in the plant to further demonstrate the end-to-end solution and its positive impact on sustainable operations.
Facilitator: Adi Punuru, ExxonMobil Technology and Engineering Company
Speaker:
Ye Hu, ExxonMobil Technology and Engineering Company
Speakers
Session Start End
-
Topic
Immersive Learning: the Potential of AI for Training and Business Applications
Digitalization
Facilitator: Tim Chappell, Exxon Mobil Corporation
Speakers:
Rajan Puri, PBF Energy
Keith Hoffman, Exxon Mobil Corporation
Speakers
Session Start End
-
Topic
Digital Twins: Demystifying Asset and Visual Twins - Insights into Digital Twins, Keys to Their Successful Creation and Value
Digitalization
In the context of a refinery, petrochemical or chemical facility, Digital Twins can be used to model and simulate the structure and behavior of equipment, systems, and processes. This session will decompose and demystify the ‘Asset’ and ‘Visual’ virtual representations and their association with one another as Digital Twins. Supported by key use cases that are commonly faced by every operating facility along with actual achieved benefits.
Participants will:
- Gain a basic practical understanding Digital Twins in their primary forms,
- Secure guidance as to the accepted prerequisites, methods, and required level of effort to craft and deploy Digital Twins,
- Learn about Digital Twin sustainment challenges and mitigation strategies, and
- The achievable benefits to be realized from Digital Twin initiatives supported by actual use case experiences.
Facilitator: Bruce Taylor, Digital Transformation SME, FurtherTec
Speakers:
Bruce Taylor, Digital Transformation SME, FurtherTec
Adam Williams, Motiva Enterprises LLC
Speakers
Session Start End
-
Topic
The Digital Reality Ecosystem: How ExxonMobil is Moving to a Visual Way of Working through Open Asset Digital Twins
Digitalization
The industrial sector is going through digital transformation. ExxonMobil's Digital Reality Ecosystem, aka the Industrial Metaverse holds huge benefits with its ability to visualize their sites and offer seamless immersive and connected experiences across their fleet of assets. As this is an emerging technology space, there are diverse sets technologies that will need to be curated as the Industrial Metaverse is still in infancy stage. This session will explore existing and potential industrial use cases of the metaverse, augmented/mixed reality to illustrate the various functions, applications, and benefits of the technology. Participants will:
- Gain an understanding of how ExxonMobil is moving to a visual way of working utilizing innovations and new technologies
- Learn about the components of the ecosystem
- Appreciate the value of data interoperability
Facilitator:
Adi Punuru, ExxonMobil Technology and Engineering Company
Speakers:
Athicha 'M' Dhanormchitphong, ExxonMobil Global Services Company
Kyle Daughtry, ExxonMobil Global Services Company
Session Start End
-
Topic
Data Driven Open Loop Models for Plantwide Optimization
Digitalization
This session explores the issue of making data driven open loop models for a complete plant. This involves many independent and dependent variables and the task is to find meaningful and reproducible relationships between them. This webinar will help anyone involved in the task in the refinery, petrochemicals, or any continuous processing unit.
Facilitator: Atique Malik, AIControl LLC
Speakers:
Adi Punuru, ExxonMobil Research & Engineering Co.
Rajan Rathinasabapathy, Phillips 66
Vikram Gokhale, Chevron U.S.A.
Stephen Dzuik, Aspen Tech
Aaron Durke, Imubit
Yangdong Pan, Delek US
Alex Kalafatis, Aspen Tech
Speakers
Session Start End
-
Topic
Oilfield Production Additives Impact on Unconventional Crudes
Crude
Many refiners are processing larger volumes of attractively priced unconventional crudes produced from fracking operations. Contain polymers and other additives that upstream processors are often used to enhance oil recovery or address hydraulic limitations in their operations. These additives can disrupt refining unit operations such as Crude Desalters or restrict the ability of the refiner to meet key product specifications such as JFTOT or NACE Spindle Corrosion test.
Facilitator: Sam Lordo, Becht
Speakers:
Bob Falkiner, Becht
Wesley Teasdale, Halliburton Multi-Chem
Speakers
Session Start End
-
Topic
Testing and Modelling Crude Oil Compatibility
Crude
Processing crudes from different sources leaves the possibility of blending incompatible mixtures. Compatibility models uses correlations to estimate the potential to create incompatible mixtures. Understanding the potential for compatibility effects without physically testing the crude provides the ability to choose the crude mix and purchase it while the market factors are favorable and the ability to safely purchase distressed cargos. The paper will discuss the basis of model correlations and the application to actual blends.
Facilitator: Sam Lordo, Becht
Speaker: Scott Sayles, Becht
Speakers
Session Start End
-
Topic
Best Practices & Technologies for Processing a Variable Crude Diet
Crude, Coking
Successfully processing a changing crude diet can be a challenge from the tank farm through distillation. Upsets and performance reductions lead to processing cost penalties downstream, loss of production, and environmental impacts through greater emissions and brine water quality issues. Optimizing the design, operational parameters and chemical injection schema from crude receipts through the hot train can minimize these cost penalties and ensure performance is maintained.
Facilitators:
Greg Cantley, Marathon
Jeff Zurlo, Veolia
Speaker: Sylvain Fontaine, Veolia
Session Start End
-
Challenges Solved Through Digitalization – Industrial Pump Monitoring and Machine Optimization
Digitalization
This presentation will focus on industrial pump monitoring and machine optimization and showcasing IoT’s revolutionary impact on our industry. We will explore solving real problems through digitalization and the seamless connectivity of objects, illustrating how data-driven insights and automation are transforming the way we manage our facilities and improve our daily experiences. Speaker will also talk about the benefits, and challenges, and inspire you with the potential of a connected world.
Facilitator: Bruce Taylor, Furthertec
Speaker: Rudy Alexander, Breadware
Speakers
Session Start End
-
Topic