AI application from BHGE and C3.ai provides early warning of production downtime and process risk
Unveiled at BHGE's annual digital conference, UNIFY2019, the now generally available application uses deep learning predictive models, natural language processing, and machine vision to continuously aggregate data from plant-wide sensor networks, enterprise systems, maintenance notes, and piping and instrumentation schematics. Using historical and real-time data from entire systems, the BHC3 Reliability machine learning models identify anomalous conditions that lead to equipment failure and process upsets. Application alerts enable proactive action by operators to reduce downtime and lost revenue.
Applicable to operations across all sectors of the energy value chain, BHC3 Reliability's system-of-systems approach scales to any number of assets and processes across offshore and onshore platforms, compressor stations, refineries, and petrochemical plants, reducing downtime and increasing productivity.
The AI-enabled BHC3 Reliability application, powered by the BHC3 AI Suite, draws on BHGE's domain expertise by augmenting application alerts with failure prevention recommendations and prescriptive actions.
"This application is a demonstration of how the BakerHughes C3.ai team is moving with speed to address the need for AI applications that deliver increased productivity, efficiency, and safety for oil and gas businesses," said
Derek Mathieson, chief marketing and technology officer, BHGE. "BHC3 Reliability delivers the system-wide insights from data that are only possible with the use of leading AI and machine learning technology."
"The rapid release of BHC3 Reliability soon after the BHGE and C3.ai joint venture agreement sends a clear signal that BakerHughesC3.ai is a transformative force for the oil and gas industry," said
Ed Abbo, president and CTO, C3.ai. "Through our work together, we are uniquely positioned to deliver significant value to oil and gas companies by quickly deploying domain-specific advanced AI applications for diverse use cases across the energy value chain."