Adaptive Building Equipment Model Update via Autocorrelation Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing equipment models used to predict the performance of building equipment often lose accuracy over time, leading to suboptimal model-based control methodologies due to the difficulty in identifying when the model no longer accurately represents the equipment.
Innovation Solution
A system for adaptively updating predictive models by collecting and comparing operating data across different time periods, using statistical hypothesis testing to determine if the model has changed, and updating the model coefficients accordingly to maintain accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If equipment models are used to predict performance over extended periods, then productivity is improved through continuous operation, but measurement precision deteriorates as the model loses accuracy over time
Solution Approach 1:
The patent implements dynamic model updating by continuously comparing model predictions with actual equipment performance data. When the deviation exceeds a threshold, the model is automatically retrained with new data, making the system adaptive to changing equipment conditions over time while maintaining continuous operation
Solution Approach 2:
The system establishes a feedback loop where actual performance measurements are continuously fed back to validate model predictions. This feedback mechanism triggers model updates when accuracy degrades, ensuring the model remains precise without requiring continuous manual intervention
2Measurement precision
If model coefficients are frequently updated to maintain accuracy, then measurement precision is improved, but device complexity increases due to additional monitoring and updating mechanisms
Solution Approach 1:
The system performs self-diagnosis by automatically detecting when model accuracy degrades through performance comparison. It autonomously triggers model updates without external intervention, reducing the need for complex monitoring infrastructure while maintaining high accuracy
Solution Approach 2:
The patent changes the state of the model from static to dynamic by implementing conditional updates based on performance thresholds. The model coefficients are updated only when necessary, controlled by parameters such as accuracy thresholds and data recency, simplifying the overall system architecture
3Measurement precision
If statistical hypothesis testing is implemented to detect model changes, then measurement precision is improved through accurate change detection, but device complexity increases due to the testing framework
Solution Approach 1:
The patent extracts only the essential elements of statistical hypothesis testing needed for model validation. It implements a simplified testing framework that focuses specifically on detecting model drift without the full complexity of comprehensive statistical analysis, maintaining accuracy while reducing burden
Data Source
AI summary
A system for generating and using a predictive model to control building equipment includes building equipment operable to affect one or more variables in a building and an operating data aggregator that collects a set of operating data for the building equipment. The system includes an autocorrelation corrector that removes an autocorrelated model error from the set of operating data by determining a residual error representing a difference between an actual output of the building equipment and an output predicted by the predictive model, using the residual error to calculate an autocorrelation for the model error, and transforming the set of operating data using the autocorrelation. The system includes a model generator module that generates a set of model coefficients for the predictive model using the transformed set of operating data and a controller that controls the building equipment by executing a model-based control strategy that uses the predictive model.