AI Asset Grouping for BMS and SCADA Semantic Tagging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building management systems (BMS) and Supervisory Control and Data Acquisition (SCADA) systems face challenges in managing complex environments due to their large size and dynamic changes, requiring labor-intensive manual semantic tagging of assets, which hinders the realization of benefits such as enhanced energy efficiency and prolonged equipment lifespan.
Innovation Solution
A computer tool and method for automated grouping of assets in BMS and SCADA systems using AI algorithms to identify and tag similar equipment based on textual and numerical attributes, simplifying the asset tagging process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual semantic tagging of assets is performed in large-scale BMS and SCADA systems, then asset identification accuracy is improved, but labor time and operational costs increase significantly
Solution Approach 1:
The system enables automated self-tagging of assets by utilizing existing data points and equipment information already present in the BMS/SCADA system. The AI model automatically processes and tags assets without requiring manual human intervention, allowing the system to serve itself in the tagging process.
Solution Approach 2:
The patent replaces the manual mechanical process of semantic tagging with an AI-based automated system. The AI model processes equipment data, identifies patterns, and assigns semantic tags automatically, substituting human labor with intelligent algorithmic processing.
2Quantity of substance
If manual semantic tagging is performed to achieve comprehensive asset coverage, then tagging completeness is improved, but operational costs and resource investment increase
Solution Approach 1:
The automated AI system performs comprehensive asset tagging across the entire BMS/SCADA system without requiring additional human resources. The system independently processes all assets, generating complete tagging coverage while eliminating the need for manual labor costs.
Solution Approach 2:
The patent substitutes expensive manual tagging operations with an automated AI system that processes assets efficiently. This replacement significantly reduces operational costs while maintaining or improving tagging completeness across large-scale systems.
3Adaptability or versatility
If the BMS and SCADA systems are expanded to manage larger facilities, then system functionality is improved, but system complexity and difficulty of control increase
Solution Approach 1:
The AI system automatically manages the complexity of large-scale BMS/SCADA systems by autonomously processing asset data, identifying patterns, and organizing information. This self-service capability allows the system to handle expanded functionality without proportionally increasing operational complexity.
Solution Approach 2:
The patent replaces complex manual system management with automated AI processing. The AI model handles data analysis, asset identification, and tagging operations that would otherwise require sophisticated manual coordination, thereby reducing the perceived complexity for operators.
4Productivity
If AI-based automated asset grouping is implemented, then operational efficiency is improved, but implementation complexity increases
Solution Approach 1:
The AI system is designed to perform multiple functions including asset identification, semantic tagging, grouping, and analysis within a single integrated platform. This multi-functionality consolidates what would otherwise require multiple separate systems, reducing overall implementation complexity while maintaining high operational efficiency.
Solution Approach 2:
The patent introduces an AI model as an intermediary layer between the raw BMS/SCADA data and the asset management interface. This intermediary automatically processes data, generates tags, and organizes assets, simplifying the interaction for end-users while delivering advanced automated capabilities.
Data Source
AI summary
System and method for grouping like equipment in an AIC system. A textual label of the reference equipment is embedded in a first numeral value and textual attributes associated with each point associated with the reference equipment are embedded in a second numerical value. A textual label of at least one candidate equipment is embedded in a third numerical value and textual attributes associated with each point associated with the at least one candidate equipment are embedded in a fourth numerical value. The first and third numerical values are compared to one another to determine if there is a sufficient level of similarity. Responsive to determining there is a sufficient level of similarity between the first and third numerical values, the second and fourth numerical values are compared to one another to determine if there is a sufficient level of similarity. Group the reference equipment with the at least one candidate equipment, responsive to determining a sufficient level of similarity between the third and fourth numerical values.