Bryan Chao

VP of International Commercialization

Oiler.ai

United States of America

Bryan Chao leads international commercialization at Oiler.ai, a company building AI-powered optical gas imaging systems for methane leak detection, quantification, and flare monitoring. He works across field validation, partner enablement, and product positioning—bridging plant operations, measurement science, and deployable monitoring workflows. Prior to Oiler.ai, Bryan spent ~10 years in business development and operations for technology startups, supporting commercialization, corporate strategy, and investment/M&A work. He has helped scale multiple ventures in fintech from early stage to global growth and has contributed to numerous venture and M&A transactions. Bryan earned his MBA at MIT focusing on energy and applied machine learning, and undergrad from the University of Pennsylvania in EE and Finance. 

Participates in

TECHNICAL PROGRAMME | Energy Technologies

GHG Emissions (Scope 1&2) Abatement (CO2, Methane) - Detection; CO2 Capture; CCUS; DAC; Carbon Products
Forum 20 | Hall 10 - Technical Programme 4
13
October
10:00 11:30
UTC+3
 During the extraction of oil and natural gas, a large amount of excess flammable gas, the majority of which is methane, is often produced. From the perspectives of safety, environmental protection and economy, the excess gas needs to be burned. In today's petroleum industry, with increasingly strict environmental protection regulations introduced by countries around the world and the rising demand from flare users for remote and non-contact monitoring of combustion exhaust gas emissions, the monitoring methods of flare systems urgently need to transform from traditional contact measurements to visual and intelligent monitoring. China's "Atmospheric Pollution Prevention and Control Law" clearly stipulates that oil and gas companies must install flare systems to treat associated gas in order to reduce its pollution to the environment. The United States Environmental Protection Agency (EPA) stipulates that the combustion efficiency of the torch must reach over 98% to ensure that the associated gas can be fully burned and reduce the emission of harmful gases. Regular monitoring and analysis of the efficiency of torches is an urgent need in the industry at present. This research aims to develop a non-contact system based on infrared imaging and visual recognition. By remotely monitoring the torch combustion and combining the characteristics of the flame and the emitted gas, it realizes the refined calculation of indicators such as the torch combustion efficiency. Specifically, in this study, through a specially designed optical system and detector, the spectral images of infrared radiation from different substances generated during the torch combustion process were captured and relevant indicators such as the flame combustion coefficient were calculated and transformed. The significance of this research lies in that the downstream system can further expand and integrate the automatic control module for the combustion-supporting agent. By real-time analysis of the flame combustion efficiency and the proportion of escaping gas, the injection amount of combustion-supporting air or steam can be fed back and adjusted to achieve dynamic closed-loop control of flame stability and combustion efficiency. It can not only enhance the combustion efficiency of torches and thus environmental compliance, but also provide a new path for green refining and chemical industry as well as intelligent emission management.