Virtual plant operator

A virtual plant operator system for use in an industrial plant, the plant operator system comprising:

• a data aggregator configured to monitor operating data within the industrial plant, the operating data including at least one of extrapolated operating data from an extrapolated scenario, operator actions performed in the industrial plant, and trip data, the data aggregator is configured to send the operating data from a future destabilized scenario based on the extrapolated operating data as a current state;
• an operator assistant configured to receive the current state, the operator assistant comprising:
• a digital twin of the industrial plant configured to simulate plant operations in the industrial plant based on the current state,
• an artificial intelligence engine having at least one machine-learned model, the machine-learned model configured to process the simulated plant operations based on the current state to determine a recommendation output, wherein the recommendation output comprises one or more stabilizing actions to plant operations in the industrial plant in the future destabilized scenario and a predicted degree of shutdown for each of the stabilizing actions.

A method of operating an industrial plant, the method comprising:

• monitoring operating data within the industrial plant;
• sending a current state based on the operating data to an operator assistant of a virtual plant operator system;
• identifying a destabilized scenario within the industrial plant via the operator assistant;
• updating a digital twin of the operator assistant based on the current state to simulate plant operations in the industrial plant based thereon;
• processing the current state within an artificial intelligence engine of the operator assistant, wherein processing comprises:
• evaluating an initial degree of shutdown based on standard operating conditions criteria to analyze an initial state of the digital twin;
• executing at least one of a stabilizing action and a disrupting action to modify one or more operating variables within the digital twin;
• evaluating a subsequent degree of shutdown based on the standard operating conditions criteria to analyze a post-action state of the digital twin;
• comparing the subsequent degree of shutdown to the initial degree of shutdown to determine a change in degree of shutdown within the digital twin;
• and
• obtaining a composite action reward based on at least the change of degree of shutdown within the digital twin, the composite action reward configured to reward the machine-learned model for reducing the subsequent degree of shutdown relative to the initial degree of shutdown;
• recommending one or more stabilizing actions based on the composite action reward to perform in the industrial plant;
• and
• providing a predicted degree of shutdown for each stabilizing action.