Time-Correlated Reliability Streams for Building AI Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building data collected by equipment is often unreliable due to temporal faults, configuration issues, measurement uncertainty, and improper commissioning, which hinders the performance of artificial intelligence systems in building management.
Innovation Solution
A building system that generates time-correlated data streams and reliability data streams, including virtual streams, to improve data quality by filtering out unreliable data and providing network traffic analysis for enhanced data reliability, and identifies performance issues through entity relationships and exercises within the building management system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If building equipment collects and transmits data continuously, then data availability for AI systems is improved, but data reliability deteriorates due to temporal faults, configuration issues, and network traffic variations
Solution Approach 1:
The patent introduces a data quality assessment system that acts as an intermediary between building equipment and AI systems. This intermediary evaluates data reliability by analyzing multiple factors including network traffic conditions, equipment operational state, and data consistency metrics, then filters or flags data accordingly before transmission to AI systems, thus resolving the contradiction between continuous data availability and data reliability
Solution Approach 2:
The system implements feedback mechanisms where data quality metrics are continuously monitored and used to adjust data collection and transmission strategies. When reliability thresholds are not met, the system provides feedback to equipment to pause data transmission or to the AI system to request additional verification data, thereby maintaining both availability and reliability through dynamic adjustment
2Productivity
If building systems perform comprehensive data collection from multiple sources, then AI system performance is improved, but system complexity increases due to data integration and reliability assessment requirements
Solution Approach 1:
The patent segments the data quality assessment process into distinct modular components: network traffic analysis modules, equipment state monitoring modules, data consistency validation modules, and reliability scoring modules. Each module handles a specific aspect of data quality assessment independently, making the overall complex system manageable and maintainable while still providing comprehensive data evaluation for AI systems
Data Source
AI summary
A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, generate a time correlated data stream for a data point, and generate a time correlated reliability data stream for the data point. The building device data includes a plurality of data samples of the data point. The time correlated data stream includes values of the plurality of data samples of the data point. The time correlated reliability data stream includes a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.