Systems and methods for automated system identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building control systems require significant human intervention and expertise for system identification, which is necessary for accurate predictive modeling and optimal operation of building equipment.
Innovation Solution
A controller that automates system identification by generating predictive models to predict system dynamics based on environmental inputs, optimizing cost functions for building equipment operation, and updating models in response to prediction error metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If automated system identification is implemented, then the need for human intervention is reduced, but the complexity of the control system increases
Solution Approach 1:
The system performs self-identification by automatically generating predictive models of building equipment dynamics using operational data without requiring external expert intervention. The controller autonomously collects data, identifies model parameters, and updates models as conditions change, enabling the system to serve itself in the model generation process.
Solution Approach 2:
The system changes parameters by automatically adjusting model parameters based on operational data analysis. The predictive models have parameters that are dynamically updated through the identification process, allowing the system to adapt to changing building conditions without manual reconfiguration by experts.
2Measurement precision
If predictive models are continuously updated, then the accuracy of system predictions is improved, but the computational resources required increase
Solution Approach 1:
The system implements dynamic model updating where the frequency and extent of model updates adapt to changing conditions. Models are updated when significant changes in building dynamics are detected, rather than continuously, allowing the system to maintain accuracy while reducing unnecessary computational effort during stable operating conditions.
Solution Approach 2:
The system uses feedback from prediction errors and residual analysis to determine when model updates are necessary. By monitoring the accuracy of predictions and triggering updates only when performance degrades below thresholds, the system maintains high accuracy while minimizing computational resource consumption.
3Loss of information
If detailed system modeling is performed, then the understanding of building dynamics is improved, but the time required for system identification increases
Solution Approach 1:
The system segments the building into separate thermal zones and models each zone independently with its own predictive model. This segmentation allows parallel processing of multiple zones, reducing overall identification time while maintaining detailed dynamics for each individual zone. The modular approach enables simultaneous model generation for different building areas.
Data Source
AI summary
A controller for performing automated system identification. The controller includes processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations including generating a predictive model to predict system dynamics of a space of a building based on environmental condition inputs and including performing an optimization of a cost function of operating building equipment over a time duration to determine a setpoint for the building equipment. The optimization is performed based on the predictive model. The operations include operating the building equipment based on the setpoint to affect a variable state or condition of the space and include monitoring prediction error metrics over time. The operations include, in response to detecting one of the prediction error metrics exceeds a threshold value, updating the predictive model.