Building Sensor Classification Using Time-Series and Metadata
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building automation systems face challenges in efficiently managing and monitoring sensors due to the lack of standardization in sensor classification, with different manufacturers and installers using varying classification schemes, leading to inconsistent labeling and difficulty in determining the actual data provided by sensors.
Innovation Solution
The system employs time-series classification and meta data classification techniques to rapidly identify and standardize sensors by analyzing statistical factors and meta information, such as labels and associated equipment, allowing for accurate classification and labeling of sensors across different systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple classification schemes are used by different manufacturers and installers, then device compatibility and manufacturer flexibility are improved, but classification consistency and system management efficiency deteriorate
Solution Approach 1:
The patent introduces a standardized classification schema as an intermediary layer between diverse sensor manufacturers and the building automation system. This schema acts as a common language that translates various manufacturer-specific classifications into unified categories, enabling consistent identification and management of sensors without sacrificing manufacturer flexibility or device compatibility
Solution Approach 2:
The patent creates a universal classification framework that can accommodate multiple types of sensors from different manufacturers under a single standardized system. This universal schema enables the system to handle diverse sensor classifications (temperature, humidity, occupancy, etc.) consistently across the entire building automation ecosystem
2Difficulty of detecting and measuring
If sensors are labeled with various identifiers, then device identification capability is improved, but ease of monitoring and management deteriorates
Solution Approach 1:
The patent segments the complex sensor identification process into two distinct layers: a standardized classification layer for consistent categorization (temperature, humidity, occupancy) and a device-specific identifier layer for unique identification. This segmentation allows the system to maintain detailed device identification capabilities while presenting unified, easy-to-manage classification information to operators
Solution Approach 2:
The patent adds a classification dimension to the existing device identifier dimension. Instead of relying solely on complex device IDs, the system introduces a new classification category dimension that groups sensors by their functional type, making monitoring and management easier while preserving the ability to identify individual devices through their original identifiers
3Device complexity
If no classification is applied to sensors, then system complexity is reduced, but system management and control efficiency deteriorates
Solution Approach 1:
The patent applies preliminary classification action during the sensor installation and onboarding process. By automatically assigning standardized classification categories to sensors at the time of system integration, the classification work is performed in advance, eliminating the need for complex manual classification later and enabling efficient system management from the outset
Solution Approach 2:
The system implements self-service classification by automatically categorizing sensors based on their inherent properties and data characteristics. The classification process occurs autonomously without requiring manual intervention, reducing system complexity while improving management efficiency through automated, consistent categorization of all sensors in the building automation system
Data Source
AI summary
A building automation space facility or building automation facility comprising systems and methods for classifying and standardizing sensors and sensor data using time-series data and/or meta data, such as data and meta information available in a control network or hardware is disclosed. The disclosed system and methods provide techniques to rapidly identify and classify sensors using analysis of time-series data (e.g., data collected from a sensor such as by polling the sensor every second, minute, hour, day, month, and so on) and/or meta data (e.g., label names, group names, associated equipment, and so on) from these sensors and associated control systems. In this manner, the disclosed techniques greatly improve the extent to which a building automation facility or system monitors, manages, and reports on various elements within a building or group of buildings.