Diagnostics in building automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building automation systems face challenges in accurately diagnosing performance issues across multiple buildings, as existing methods often fail to integrate building management data with enterprise-level data, leading to incomplete fault detection and inefficient resource allocation.
Innovation Solution
The implementation of unsupervised machine learning and clustering techniques that combine building automation data with enterprise data to identify performance deficiencies, allowing for proactive diagnosis and optimization of building systems, thereby reducing operational expenses and improving resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If building automation systems analyze only building management data separately for each building, then the analysis is simple and isolated, but the diagnostic accuracy is incomplete and cannot identify cross-building patterns
Solution Approach 1:
The patent combines building management data with enterprise data from multiple buildings into a unified analysis framework. This merging allows the system to identify cross-building patterns and performance issues that would be invisible when analyzing buildings in isolation, thereby improving diagnostic accuracy without requiring complex separate analyses for each building
Solution Approach 2:
The system creates a universal analysis platform that handles both building-specific operational data and enterprise-wide metadata. This multi-functional approach enables the same system to perform both localized building diagnostics and enterprise-wide pattern recognition, eliminating the need for separate specialized systems
2Reliability
If building automation systems integrate multiple data sources including enterprise data, then the diagnostic capability improves, but the data processing complexity increases
Solution Approach 1:
The patent segments the data processing into distinct modules: building management data collection, enterprise data collection, data integration, analysis engine, and reporting. This segmentation allows each module to handle specific tasks independently, making the overall complex system manageable and maintainable while achieving reliable fault detection through comprehensive data analysis
3Productivity
If clustering techniques are applied to multiple building data sets, then common performance issues can be identified, but the computational requirements increase
Solution Approach 1:
The system applies clustering techniques selectively to identify the most significant performance patterns across buildings rather than performing exhaustive analysis on all possible data combinations. This partial action approach achieves sufficient resource allocation efficiency improvements without the prohibitive computational cost of complete exhaustive analysis
Data Source
Figure 1
Figure 2~4
Figure 5~6A
AI summary
Using data from various sources, clustering (52) or other unsupervised learning determines a relationship of the data to performance. Meta data or business data different than building automation data is used to diagnose building automation. Relationships of building automation to the meta or business data are determined with clustering (52) or other case-based reasoning. For multiple building situations, clustering (52) with or without the meta data identifies poor performing buildings, equipment, automation control, or enterprise function.