Self-Learning Thermal Modeling for HVAC Energy and Comfort Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current thermal management systems in buildings lack the ability to learn heat transfer characteristics and occupant comfort preferences autonomously, leading to inefficient energy consumption and comfort control.
Innovation Solution
A processor-implemented method and system that utilizes thermal models to estimate energy consumption and temperature by learning from weather estimations and thermal device properties, allowing for autonomous control of HVAC systems to minimize energy usage while maintaining occupant comfort without requiring commissioning information or extensive occupant interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If traditional thermal management systems are used, then basic temperature control is achieved, but energy consumption is high and comfort control is inefficient
Solution Approach 1:
The thermal management system performs self-learning of heat transfer characteristics and occupant comfort preferences through automated data collection and analysis from thermal sensors and weather data, without requiring manual commissioning or extensive occupant interaction. The system autonomously builds and updates thermal models to optimize energy consumption while maintaining comfort.
Solution Approach 2:
The system continuously collects feedback from thermal sensors measuring temperature, humidity, and occupancy, combined with weather data, to dynamically adjust HVAC operations. This closed-loop feedback mechanism enables the system to learn from actual thermal responses and occupant behavior patterns, progressively improving energy efficiency and comfort control.
2Measurement precision
If commissioning information and extensive occupant interaction are required, then accurate thermal modeling is achieved, but system complexity and implementation difficulty increase
Solution Approach 1:
The system eliminates the need for manual commissioning by automatically learning thermal characteristics through sensor data and weather information. It performs self-calibration by analyzing thermal responses to HVAC operations and environmental conditions, building accurate thermal models without human intervention or complex setup procedures.
Solution Approach 2:
The system uses weather data as an intermediary to infer external thermal influences on the building envelope, eliminating the need for direct measurement of all heat transfer paths. This intermediary data source simplifies the modeling process while maintaining accuracy by providing contextual information about environmental conditions.
Data Source
AI summary
A system for comfort based management of thermal systems, including residential and commercial buildings with active cooling and/or heating, is described. The system can operate without commissioning information, and with minimal occupant interactions, and can learn heat transfer and thermal comfort characteristics of the thermal systems so as to control the temperature thereof while minimizing energy consumption and maintaining comfort. A thermal model represents thermal behavior of a volume in a thermal system, characterizing heat transfer and estimating energy consumption and temperature. A comfort model represents thermal comfort in a volume of a thermal system, estimating an effective temperature at which an occupant is unlikely to object. A comfort agent interacts with thermal models to estimate physically-realizable discrete temperature states with associated transition values, constrained by comfort model estimates, to identify an optimal path and define control temperatures for volumes in a thermal system, facilitating optimal start and temperature control.