Occupancy-Learning HVAC and Lighting Control for Low-Setup Buildings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building control systems for lighting, shading, and HVAC are costly due to labor-intensive installation and maintenance, requiring professional setup and configuration, which increases overall ownership costs.
Innovation Solution
A self-learning building management system that uses adaptive algorithms to identify occupancy patterns and behavioral profiles, allowing for simplified installation and maintenance by automatically configuring and controlling lighting, shading, and HVAC systems based on detected human and pet activity, using sensors and smart devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If professional installation and configuration systems are used, then system control functionality is improved, but installation cost and labor time increase significantly
Solution Approach 1:
The system performs self-configuration and self-learning automatically without requiring professional installation. Occupancy sensors and other devices automatically register themselves with the controller, and the system learns occupancy patterns and building characteristics through adaptive algorithms, eliminating the need for technician configuration and testing
Solution Approach 2:
The system uses adaptive algorithms that continuously learn and adjust parameters such as occupancy patterns, behavioral profiles, and spatial relationships. This dynamic parameter adjustment allows the system to improve its control functionality over time while maintaining simple initial installation
2Use of energy by moving object
If adaptive learning algorithms are implemented, then energy savings and comfort are improved, but system complexity and processing requirements increase
Solution Approach 1:
The system performs preliminary learning during the commissioning phase, automatically discovering the building layout, occupancy patterns, and device locations before full operation begins. This preliminary action reduces the complexity of ongoing operations by pre-establishing the foundational data structures and spatial models
Solution Approach 2:
The system continuously monitors occupancy sensor data, HVAC performance, and lighting usage to provide feedback to the adaptive algorithms. This feedback loop enables the system to optimize energy savings while managing complexity through iterative learning rather than requiring complex upfront configuration
Data Source
AI summary
A system for automatic setup and control of Lighting, Heating Ventilation and Air Conditioning systems comprising a set of occupancy detectors and at least one controller where the controller determines various aspects of the building control based on the input of the occupancy detectors.