System and method for controlling operation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional HVAC systems fail to provide optimal thermal comfort for occupants due to rudimentary communication methods, leading to inefficient energy consumption and discomfort, as they rely on manual adjustments of temperature set-points and lack personalized comfort models that account for individual preferences and environmental conditions.
Innovation Solution
A system that uses a personalized thermal comfort model, combining biometric data and environmental data to automatically adjust temperature set-points and latent heat transfer, leveraging a hybrid approach with labeled data from both the individual and historical users to reduce the need for extensive user feedback and improve model accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual adjustment of temperature set-points is implemented, then occupants can indicate desired thermal comfort levels, but constant manual readjustment is not practical and distracts occupants from productivity
Solution Approach 1:
The system enables self-service by automatically adjusting temperature set-points based on occupancy detection and thermal comfort models. The HVAC system monitors environmental conditions and occupant presence, then autonomously modifies temperature settings without requiring manual intervention, thereby eliminating distraction while maintaining comfort.
Solution Approach 2:
The system implements feedback loops where thermal comfort models continuously evaluate environmental conditions and occupancy data, then feed this information back to automatically adjust HVAC operations. This closed-loop control ensures thermal comfort is maintained adaptively without manual input from occupants.
2Measurement precision
If conventional thermal comfort models are used, then a sign of needed correction can be determined, but over-correction frequently occurs resulting in unnecessarily high temperature set-points
Solution Approach 1:
The system changes key parameters including latent heat transfer amounts and temperature set-points based on dynamic occupancy conditions and thermal comfort model outputs. By adjusting multiple parameters simultaneously rather than relying solely on temperature changes, the system achieves more precise and nuanced thermal comfort control.
Solution Approach 2:
The system transitions from static temperature set-points to dynamic adjustment where temperature and latent heat transfer are continuously modified based on real-time occupancy detection and environmental monitoring. This dynamic approach prevents over-correction by adapting to actual conditions rather than applying fixed corrections.
3Measurement precision
If HVAC sensors are located at the HVAC device intake, then air temperature can be measured, but the sensed temperature is different from that experienced by occupants due to temperature gradients
Solution Approach 1:
The system applies local quality by using thermal comfort models that account for spatial temperature variations and radiant heat effects at the occupant level rather than relying on a single centralized sensor reading. The model calculates equivalent temperature at occupant locations based on HVAC sensor data and environmental conditions.
Solution Approach 2:
The thermal comfort model acts as an intermediary that translates HVAC sensor measurements into estimates of occupant-experienced temperature. The model bridges the gap between centralized sensor data and distributed occupant comfort by incorporating radiant heat, air movement, and spatial gradient effects.
4Measurement precision
If personalized thermal comfort models are created using only individual labeled data, then model accuracy can be improved, but extensive user feedback is required increasing system complexity
Solution Approach 1:
The system merges individual labeled data with unlabeled environmental and occupancy data to create personalized thermal comfort models. By combining multiple data sources including sensor measurements, occupancy detection, and environmental monitoring, the system achieves high model accuracy without requiring extensive manual user feedback.
Solution Approach 2:
The system performs preliminary actions by collecting and processing unlabeled environmental and occupancy data in advance to pre-train thermal comfort models. This preliminary data preparation reduces the subsequent need for extensive labeled user feedback while still achieving personalized accuracy.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Systems and methods for controlling an operation of devices for an occupant. A processor to iteratively train a personalized thermal comfort model (PTCM) during an initialization period. Receive a sequence of unlabeled real-time data. A transmitter requests the occupant to label an instance of unlabeled data, when there is a disagreement between the labels of stored historical labeled data (LD) similar to received unlabeled data and a predicted label on the new unlabeled data that exceeds a threshold. The processor, in response to receiving the labeled data, trains the PTCM using different weights of the personalized LD than to the historical LD. Retrains PTCM using the historical database and the updated personalized database. A controller controls the set of devices based on the retrained PTCM.