Digital twin to serve as reference design for modular reactor

The U.S. Department of Energy has announced awards to two teams of industry experts to develop tools to transform the operations and maintenance of advanced nuclear reactors through the use of Artificial Intelligence-enabled digital twins using the GE Hitachi (GEH) BWRX-300 small modular reactor as a reference design.

GE Research and MIT have been awarded grants through the U.S. Department of Energy (DOE) Advanced Research Projects Agency-Energy (ARPA-E) Generating Electricity Managed by Intelligent Nuclear Assets (GEMINA) program to lead the project teams that will develop digital twin technology for advanced nuclear reactors utilizing artificial intelligence and advanced modeling controls.

The GE Research-led team consisting of Exelon Generation, Oak Ridge National Laboratory (ORNL), the University of Tennessee-Knoxville and GEH will build a digital twin of BWRX-300 critical components and utilize artificial intelligence predictive technologies to make risk informed decisions. Exelon, which operates the largest U.S. fleet of nuclear power plants, will provide historical data based on significant experience to inform the model and targets which are aimed at reducing the operating and maintenance costs of advanced reactors.

The MIT-led team consisting of GE Research and GEH will advance and demonstrate new predictive maintenance approaches and model-based fault system detection techniques. The digital twins will address mechanical and thermal fatigue failure modes which drive operations and maintenance activities.

Abhinav Saxena, a Senior AI Scientist at GE Research and project leader on the AI-enabled predictive maintenance digital twins project, says GE has developed and deployed well over 1.2 million digital twins within an array of products and services that span the aviation, transportation and energy sectors, including in nuclear energy. He says the team is excited to expand its application in the nuclear energy sector through both projects.

Saxena noted that GE already has been piloting its Humble AI technology with wind turbines in the field and gas turbine combustion, which have both resulted in higher efficiency and energy output.  The goal is to bring those same benefits, along with reduced operational and maintenance costs and more plant automation, to the nuclear sector. The Digital Twin and Humble AI technologies developed under this program will have similar impact in the nuclear sector, moving maintenance activities from time based to condition-based maintenance and paving the path towards autonomous operations.

The BWRX-300 is a 300 MWe water-cooled, natural circulation SMR with passive safety systems that leverages the design and licensing basis of GEH’s U.S. NRC-certified ESBWR. Through dramatic design simplification, GEH projects the BWRX-300 will require significantly less capital cost per MW when compared to other water-cooled SMR designs or existing large nuclear reactor designs.

By leveraging the existing ESBWR design certification, utilizing licensed and proven nuclear fuel designs, incorporating proven components and supply chains and implementing simplification innovations the BWRX-300 can, GEH believes, become cost-competitive with power generation from combined cycle gas plants and renewable energy platforms. As the tenth evolution of GE’s first Boiling Water Reactor (BWR) design, GEH’s BWRX-300 represents the simplest, yet most innovative BWR design since GE began commercializing nuclear reactors in 1955.