Industrial Plant Command Recommendation Using Historic-State Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Operating an industrial plant is a complex task, especially in critical situations, where well-trained operators often struggle to make effective operational commands without adequate recommendations.
Innovation Solution
A computer-implemented method that recommends operational commands by comparing the current plant state to historic states, running simulations based on variations of historic operational commands, and determining the quality value of each simulation to suggest the best course of action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple simulations are run to evaluate different operational commands, then the reliability of the recommendation is improved, but the time required to generate a recommendation increases
Solution Approach 1:
The system pre-calculates and stores quality values for different operational commands in a lookup table during normal operation. When an alarm occurs, the system immediately queries this pre-computed data rather than running full simulations, dramatically reducing response time while maintaining recommendation quality through the use of pre-evaluated options.
Solution Approach 2:
The system implements a hierarchical approach where full simulations are used to generate and validate the lookup table offline, then this pre-computed knowledge is nested within the real-time decision support system. This nested structure allows complex simulations to inform simple, fast queries during critical alarm situations.
2Measurement precision
If a simulation model is used to evaluate operational commands, then the accuracy of the recommendation is improved, but the computational complexity increases
Solution Approach 1:
The simulation model is executed in advance during system initialization or offline periods to pre-compute quality values for various operational commands. These pre-computed results are stored in a lookup table, eliminating the need to run complex simulations during real-time alarm handling while preserving the accuracy benefits of simulation-based evaluation.
Solution Approach 2:
Instead of running the full simulation model during alarm response, the system creates and uses a simplified copy of the simulation results in the form of a lookup table. This copy contains pre-evaluated quality values that can be quickly queried without invoking the complex computational machinery of the original simulation model.
Data Source
AI summary
A method for recommending an operational command includes receiving an alarm from a sensor and/or an operator; obtaining the current state of the plant that includes a current process value and/or operational command; comparing the current state to a list of historic states, each comprising a plurality of historic process values and/or historic operational commands; when the current state matches a subset of at least one of the historic states, starting a simulation and running a plurality of simulations, each based on a variation of at least one of the historic operational commands; determining, for each simulation of the plurality of simulations, a quality value, based on at least one quality criterion; and recommending the variation of the operational command that resulted in the simulation with the highest quality value.