Building Automation Diagnostics Using Enterprise Data Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building automation systems face challenges in accurately diagnosing issues across multiple buildings due to limited data reflection of problems and the influence of building automation on business operations, leading to inefficient fault detection and maintenance.
Innovation Solution
A method and system utilizing unsupervised machine learning and clustering with enterprise data to identify performance issues in building automation systems, combining operational data from multiple buildings with meta-data to diagnose and predict performance deficiencies, thereby shifting focus from repair to prevention and prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional building automation data collection methods are used, then data from individual buildings can be obtained, but the data does not accurately reflect problems or the influence of building automation on business operations
Solution Approach 1:
The patent combines building automation data with enterprise data from multiple sources including financial systems, human resources, and operational databases. This merging creates a comprehensive dataset that reflects both technical building performance and business impact, enabling more accurate diagnosis by analyzing correlations between automation issues and business outcomes across the enterprise portfolio.
2Adaptability or versatility
If building automation systems operate independently, then each building can be controlled separately, but fault detection and diagnosis efficiency is reduced
Solution Approach 1:
The system creates a multi-functional platform that serves both individual building control needs and enterprise-wide diagnostic functions. The unified data architecture and machine learning models can operate at multiple levels: providing localized building-specific diagnostics while simultaneously identifying patterns across the entire enterprise portfolio, thus achieving both independence and efficiency.
3Ease of repair
If reactive maintenance approaches are used, then immediate repairs can be performed, but operational expenses increase and equipment lifespan is reduced
Solution Approach 1:
The system performs preliminary diagnostic actions by continuously analyzing building automation data in conjunction with enterprise operational data to predict potential failures before they occur. The machine learning models identify patterns and anomalies that indicate impending equipment issues, allowing maintenance teams to perform preventive repairs during scheduled maintenance windows rather than during disruptive breakdowns, thereby reducing operational expenses and extending equipment lifespan.
Data Source
AI summary
Using data from various sources, clustering 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 or other case-based reasoning. For multiple building situations, clustering with or without the meta data identifies poor performing buildings, equipment, automation control, or enterprise function.