Occupancy estimation based on multiple sensor inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building control systems face increased complexity and cost due to the inclusion of multiple occupancy sensors with varying degrees of accuracy, necessitating a simplified model that can integrate and weigh estimates from different types of sensors to provide accurate occupancy data for efficient system control.
Innovation Solution
A method and system that monitor occupancy counts from multiple sensors, calculate error parameters, assign weights based on these errors, and use a trained model to determine an estimated occupancy count, which is then used to control Building Management Systems (BMS) components, thereby simplifying the integration of diverse sensor data and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple occupancy sensors are included to improve occupancy estimation accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple occupancy sensors of different types (e.g., CO2 sensors, motion sensors, access control sensors) into a unified occupancy estimation system. The controller integrates data from these diverse sensors and applies weighted averaging to produce a single comprehensive occupancy estimate, thereby improving measurement precision while managing system complexity through consolidation.
Solution Approach 2:
The patent introduces a trained machine learning model as an intermediary that processes raw sensor data and ground truth occupancy information. This model learns optimal weighting schemes and integration strategies, acting as a mediator between multiple sensors and the final occupancy estimate, which simplifies the overall system architecture while maintaining high accuracy.
2Measurement precision
If multiple occupancy sensors with varying accuracies are integrated, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The system employs a self-training mechanism where the machine learning model automatically learns the optimal weighting and integration strategy for multiple sensors using ground truth occupancy data. This self-service approach eliminates the need for manual calibration and configuration by operators, improving ease of operation while maintaining high measurement precision through adaptive sensor fusion.
3Productivity
If occupancy sensors are added to control BMS components, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent creates a universal occupancy estimation module that serves multiple building management functions simultaneously. The same sensor integration and weighted averaging mechanism is used for HVAC control, lighting control, security systems, and energy management, thereby improving overall building productivity while avoiding the complexity of separate systems for each function.
Data Source
AI summary
An occupancy count of the space of a building from each of a plurality of occupancy sensors may be monitored and an error parameter for each of the plurality of occupancy sensors may be identified, each error parameter representative of a difference between the occupancy count of the respective occupancy sensor and a ground truth occupancy count of the space, normalized over a period of time. An assigned weight for each of the plurality of occupancy sensors may be determined based at least in part on the respective error parameter. The estimated occupancy count of the space of the building is determined based at least in part on the occupancy count of each of the plurality of occupancy sensors and the assigned weight of each of the plurality of occupancy sensors. The BMS system is controlled based at least in part on the estimated occupancy count.