Predictive Equipment Control Using Abnormality Simulation Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for controlling equipment in plants rely on worker experience and intuition to adjust control parameters, lacking a systematic approach to prevent abnormal states, and existing predictive models do not effectively simulate future equipment states to guide proactive control measures.
Innovation Solution
A control support apparatus that estimates equipment abnormalities using measurement data, simulates future states for candidate control methods, and selects the most effective control method to maintain a normal operational state, incorporating an equipment abnormality estimation section, simulation section, and control instruction section to instruct the equipment control apparatus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If workers use experience and intuition to adjust control parameters, then flexibility in handling equipment issues is improved, but reliability of preventing abnormal states deteriorates
Solution Approach 1:
The system performs preliminary simulation of future equipment states before actual control actions are taken. By evaluating multiple candidate control methods through simulation in advance, the system identifies the most effective control approach to prevent abnormal states, thereby improving reliability while maintaining flexibility through systematic evaluation rather than random trial and error.
Solution Approach 2:
The system implements feedback by continuously monitoring equipment state, estimating abnormalities, and using this information to generate and evaluate candidate control methods. The simulation results feed back into the control decision-making process, allowing the system to adaptively select control strategies that prevent abnormal states while maintaining operational flexibility.
2Measurement precision
If predictive models are used to estimate equipment state, then ability to forecast abnormalities is improved, but ability to guide proactive control measures deteriorates
Solution Approach 1:
The system segments the control decision-making process into distinct steps: generating multiple candidate control methods, simulating future states for each candidate, evaluating simulation results, and selecting the optimal control method. This segmentation transforms the complex task of proactive control guidance into manageable steps, making it easier to operate while maintaining high forecasting accuracy.
Solution Approach 2:
The system changes control parameters by evaluating multiple candidate control methods with different parameter settings. By simulating future equipment states under different control parameter configurations, the system identifies the optimal parameters that prevent abnormal states, thereby improving control guidance capability while maintaining forecasting accuracy.
3Measurement precision
If multiple candidate control methods are simulated, then accuracy of selecting optimal control method is improved, but time required for control decision deteriorates
Solution Approach 1:
The system applies partial action by simulating and evaluating only the necessary number of candidate control methods required to achieve optimal selection accuracy. Rather than exhaustively evaluating all possible control methods, the system identifies and evaluates a sufficient subset that provides the needed level of accuracy, thereby reducing decision time while maintaining selection quality.
4Reliability
If simulation of future equipment states is performed, then ability to prevent abnormal states is improved, but complexity of control system deteriorates
Solution Approach 1:
The system introduces a simulation module as an intermediary between equipment state monitoring and control decision-making. This intermediary component evaluates future states for multiple candidate control methods, enabling abnormality prevention through systematic simulation while managing complexity by modularizing the control system architecture. The simulation module acts as a mediator that processes state information and generates control recommendations without requiring complex direct control logic.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a control support apparatus, comprising: an equipment abnormality estimation section for estimating an abnormality of equipment based on measurement data by measuring the equipment; a simulation section for simulating a future state of the equipment when controlling the equipment by each of a plurality of candidate control methods according to an abnormality estimation result of the equipment; and a simulation abnormality estimation section for estimating a future abnormality of the equipment based on a future state of the equipment for each of the plurality of candidate control methods.