Tuning model structures of dynamic systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual setup of model structures for dynamic systems, such as HVAC systems, is costly and affects overall profits due to inadequate documentation and human behavior complexities, making it difficult to accurately model variables like energy consumption and state variables.
Innovation Solution
Tuning model structures remotely by monitoring dynamic systems to identify and update candidate model structures, focusing on minimizing error rates and optimizing parameters for system supervisory control, which includes predicting variables and determining optimal setpoints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual setup of model structures is performed, then model accuracy can be achieved, but deployment and maintenance costs increase significantly
Solution Approach 1:
The system automatically tunes model structures by evaluating multiple candidate models against measured data, selecting the best-performing model without manual intervention. This self-service approach eliminates the need for expensive manual setup while maintaining model accuracy through automated performance-based selection.
Solution Approach 2:
The system changes the parameter of model structure selection by evaluating multiple candidate models with different structures and selecting the one with the best performance metric. This parameter change approach allows automated optimization of model accuracy while reducing deployment costs.
2Measurement precision
If manual setup of model structures is performed, then model accuracy can be achieved, but maintenance costs increase
Solution Approach 1:
The system performs automated model structure tuning and can re-evaluate candidate models as new data becomes available, maintaining model accuracy without requiring manual maintenance intervention. This self-service mechanism reduces maintenance costs while preserving measurement precision.
3Ease of manufacture
If remote monitoring and automated tuning is implemented, then deployment and maintenance costs are reduced, but system complexity increases
Solution Approach 1:
The system creates multiple candidate model structures (copies of the modeling framework with different parameters) and evaluates them automatically. This copying approach allows automated selection of the best model structure, reducing deployment and maintenance costs while the complexity is managed through systematic evaluation of predefined candidates.
4Measurement precision
If multiple candidate model structures are evaluated, then the best model can be selected for optimization, but computational resources and time are consumed
Solution Approach 1:
The system evaluates multiple candidate model structures beyond what a single manual model would provide, performing partial evaluations of each candidate against the measured data. This partial action approach allows the system to identify the best model structure efficiently, achieving high selection accuracy while managing computational time by not requiring exhaustive analysis of every possible model variant.
Data Source
AI summary
Tuning model structures of dynamic systems are described herein. One method for tuning model structures of a dynamic system includes predicting a variable for each of a number of models associated with a number of model structures of a dynamic system, calculating a rate of error of the predicted variable for each of the number of models compared to an observed variable, determining a best model structure among the number of model structures based on the calculated rate of error, and creating a revised model structure using the best model structure to tune the number of model structures of the dynamic system.