Adaptive Filter Bank Thermal Model for Diagnostic Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing thermal systems face challenges in accurately characterizing heat transfer without commissioning information, leading to inefficiencies and wasteful energy use due to unknown or unreliable zone geometry and thermal mass data.
Innovation Solution
An adaptive filter bank is implemented to characterize heat transfer by generating thermal coefficients from passive observations of environmental conditions and device data, minimizing estimation errors and detecting diagnostic events indicative of anomalous operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If thermal models use passive observations to characterize heat transfer without commissioning information, then ease of operation is improved, but measurement precision deteriorates due to unknown or unreliable zone geometry and thermal mass data
Solution Approach 1:
The thermal model performs self-characterization by automatically extracting heat transfer parameters from passive observations of temperature and power consumption data. The system serves itself by learning zone geometry and thermal mass characteristics without requiring external commissioning information or manual input, thereby maintaining ease of operation while improving measurement precision through adaptive filtering algorithms.
Solution Approach 2:
The system implements feedback mechanisms where the thermal model continuously refines its heat transfer characterization by comparing predicted temperature profiles with actual observations. This iterative feedback process allows the model to correct estimation errors and improve measurement precision over time while continuing to operate without commissioning information.
2Device complexity
If thermal models operate without commissioning information, then device complexity is reduced, but reliability deteriorates due to errors in heat transfer characterization
Solution Approach 1:
The thermal model achieves self-characterization by automatically extracting reliable heat transfer parameters from operational data. This self-service capability maintains low device complexity by eliminating the need for complex commissioning procedures while improving reliability through adaptive filtering and continuous validation of thermal coefficients against observed temperature behavior.
Solution Approach 2:
The system replaces traditional mechanical commissioning procedures with computational methods. Instead of requiring physical measurements and manual configuration during installation, the system uses algorithms to substitute and extract thermal characteristics from operational data, thereby reducing device complexity while enhancing reliability through data-driven characterization.
3Ease of manufacture
If thermal models use passive observations to extract heat transfer data, then ease of manufacture is improved, but loss of information increases due to unknown or unreliable zone geometry and thermal mass data
Solution Approach 1:
The thermal model performs self-characterization by automatically extracting heat transfer parameters from passive observations of temperature and power consumption data. The system serves itself by learning zone geometry and thermal mass characteristics without requiring external commissioning information or manual input, thereby maintaining ease of operation while improving measurement precision through adaptive filtering algorithms.
Solution Approach 2:
The system implements feedback mechanisms where the thermal model continuously refines its heat transfer characterization by comparing predicted temperature profiles with actual observations. This iterative feedback process allows the model to correct estimation errors and improve measurement precision over time while continuing to operate without commissioning information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments of the disclosure provide a thermal model based on an adaptive filter bank for characterizing heat transfer of a volume of a thermal system. In one embodiment, the adaptive filter bank is used for diagnostics that provides information related to the condition of a thermal system. The diagnostics are based on an analysis of heat transfer characteristics of a dynamic representation of the thermal system. In accordance with the embodiments, thermal coefficients are generated based on an adaptive filter bank. One or more filters are applied to the thermal coefficients based on a sampling rate and one or more estimate thermal coefficient thresholds are generated based on the sampling rate. It is determined whether at least one of the thermal coefficients that is filtered satisfies at least one of the estimated thermal coefficient thresholds. Thereupon, alert information indicative of a diagnostic event is provided based on the determination.