Systems and methods for steady state detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building management systems (BMS) face challenges in reliably detecting steady states for equipment operations involving multiple variables, which is essential for accurate performance analysis and prediction, due to the need for parameter tuning and high operational costs in industries like HVAC.
Innovation Solution
A BMS with a predictive diagnostics system that recursively updates mean and variance of monitored variables to identify steady or transient states, using a combination of slope and second derivative analysis to adjust equipment operations and construct predictive models for performance prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional steady state detection methods are applied to multiple variables, then detection capability is improved, but system complexity and parameter tuning requirements increase
Solution Approach 1:
The patent segments the steady state detection process into three independent statistical tests: (1) mean stability test using recursive mean calculation and threshold comparison, (2) variance stability test using recursive variance calculation and threshold comparison, and (3) autocorrelation test using lagged product calculation. Each test operates independently on the time series data, avoiding the need for complex multi-parameter tuning while maintaining detection accuracy for multiple variables simultaneously.
2Measurement precision
If traditional steady state detection methods are applied to multiple variables, then detection capability is improved, but operational cost increases
Solution Approach 1:
The patent implements self-service through fully automated steady state detection that requires no operational supervision. The system recursively calculates statistical parameters (mean, variance, autocorrelation) and automatically compares them against thresholds to determine steady state conditions. This eliminates the need for manual parameter tuning and operational intervention, making the system cost-effective for industries like HVAC with minimal operational supervision.
3Measurement precision
If parameter tuning is performed to improve detection accuracy, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent changes the approach from tuning detection parameters to using fixed statistical thresholds. Instead of requiring users to tune sensitivity parameters, the system uses predetermined thresholds for mean change (e.g., 0.1% of range), variance change (e.g., 10% of range), and autocorrelation values. This maintains high detection accuracy while eliminating the operational burden of parameter tuning.
Data Source
AI summary
A method includes receiving samples of one or more monitored variables relating to building equipment, updating a statistical metric of the samples, determining whether the building equipment is operating in a steady state or operating in a transient state using the statistical metric of the samples, and adjusting an operation that uses the samples as an input based on whether the building equipment is operating in the steady state or operating in the transient state.