MPC Operator Support for Irregular Condition Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Model predictive controllers (MPC) in industrial process control systems often require complex configuration and can malfunction during upset conditions, leading to operator uncertainty and loss of confidence, as they are configured as complex 'black box' technologies that do not react as expected in real-life operating conditions.
Innovation Solution
A method and apparatus for real-time model predictive control operator support using function blocks that detect irregular operating conditions in controlled and manipulated variables, analyze case-specific conditions, and provide recommendations to operators for correcting issues, thereby enhancing operator understanding and decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If MPC controllers are configured as complex black box technology, then adaptability and control capability are improved, but operator understanding and confidence deteriorate
Solution Approach 1:
The patent introduces an intermediary system that sits between the MPC controller and the operator. This intermediary translates the complex internal states and decisions of the black box controller into comprehensible explanations for operators, maintaining the advanced control capability while restoring operator understanding through intermediate interpretation layers
Solution Approach 2:
The patent creates a virtual copy or representation of the MPC controller's internal reasoning process. By replicating and exposing the decision-making logic in an interpretable form, operators can understand the controller's behavior without needing to comprehend the full complexity of the original black box system
2Adaptability or versatility
If MPC controllers are configured as complex black box technology, then control adaptability is improved, but reliability during upset conditions deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors operator interactions and system performance during upset conditions. This feedback loop allows the explanatory system to adapt its explanations and the controller to adjust its behavior based on operator confidence and actual performance outcomes, improving reliability iteratively
Solution Approach 2:
The patent provides operators with preliminary understanding and explanations of the MPC controller's behavior before upset conditions occur. By pre-explaining normal operating patterns and potential responses, operators are better prepared to handle upset conditions confidently, improving system reliability when critical situations arise
3Ease of operation
If MPC applications are disabled during upset conditions, then operator confidence is improved, but productivity deteriorates
Solution Approach 1:
The patent enables the MPC controller to serve itself by providing self-explanations of its actions and decisions. This self-service capability allows the controller to maintain operation during upset conditions while simultaneously building operator confidence through transparent communication, eliminating the need to disable the controller
4Manufacturing precision
If detailed analysis of operating conditions is performed, then removal accuracy of irregular conditions is improved, but processing time increases
Solution Approach 1:
The patent segments the analysis of operating conditions into distinct categories and priority levels. By dividing the complex analysis task into manageable segments, the system can process critical irregularities quickly while performing more detailed analysis on less urgent conditions, maintaining accuracy without excessive processing time
Data Source
AI summary
A method includes obtaining measurements associated with a plurality of controlled variables (CVs) and a plurality of manipulated variables (MVs). The method also includes detecting an irregular operating condition of a CV or an MV. The method also includes analyzing case specific operating conditions based on the irregular operating condition. The method further includes removing the irregular operating condition based on analyzing the case specific operating conditions.