Systems and methods for determining operational relationships in building automation and control networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional building control software faces challenges in efficiently analyzing data from diverse building automation and control networks, requiring manual mapping and expert intervention, which is time-consuming, expensive, and inaccurate, limiting energy efficiency improvements.
Innovation Solution
Machine learning techniques using statistical models and neural networks to automatically predict labels for equipment types, point types, and operational relationships within building control networks, reducing the need for manual mapping and enhancing energy efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual mapping and expert intervention are used to analyze building control network data, then accuracy can be maintained, but deployment time and costs increase significantly
Solution Approach 1:
The system performs automatic equipment identification and relationship determination using machine learning models that analyze time series data from building control networks. The statistical models autonomously classify equipment types and operational relationships without requiring manual expert intervention, enabling the system to serve itself in the data analysis process.
Solution Approach 2:
The patent replaces manual expert analysis with automated computational methods. Machine learning models and statistical algorithms substitute for human experts in analyzing building control network data, identifying equipment types, and determining operational relationships, thereby eliminating the need for manual mapping while maintaining or improving accuracy.
2Measurement precision
If manual mapping and expert intervention are used to analyze building control network data, then accuracy can be maintained, but costs increase significantly
Solution Approach 1:
The system performs automatic equipment identification and relationship determination using machine learning models that analyze time series data from building control networks. The statistical models autonomously classify equipment types and operational relationships without requiring manual expert intervention, enabling the system to serve itself in the data analysis process.
Solution Approach 2:
The patent replaces manual expert analysis with automated computational methods. Machine learning models and statistical algorithms substitute for human experts in analyzing building control network data, identifying equipment types, and determining operational relationships, thereby eliminating the need for manual mapping while maintaining or improving accuracy.
3Productivity
If automated machine learning methods are used to predict equipment labels, then deployment time and costs are reduced, but system complexity increases
Solution Approach 1:
The system performs preliminary training of statistical models using historical building control network data before deployment. The models are pre-trained to recognize patterns in time series data associated with different equipment types and operational relationships, so that during actual deployment, the pre-trained models can quickly and accurately classify new equipment without requiring complex real-time analysis.
4Ease of operation
If conventional building control software is used, then manual control is maintained, but energy efficiency improvements are limited
Solution Approach 1:
The system uses determined operational relationships between equipment to enable automated control strategies. By understanding how equipment interacts and depends on each other, the system can implement feedback-based control that optimizes energy efficiency while maintaining operational effectiveness, moving beyond simple manual control to intelligent automated management.
Data Source
AI summary
Techniques for determining point type, equipment type, equipment instance, and equipment relationship for different points associated with pieces of equipment located at a building is described. The techniques may include obtaining data corresponding to point(s) associated with one or more pieces of equipment located at a building controlled by a building control network, and using the data and statistical model(s) to determine point type(s), equipment type(s), and/or equipment instance(s) for the point(s). The techniques may include determining operational relationships between different pieces of equipment located at the building.