Building Data Point Tagging With Feedback-Guided Commissioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The initial commissioning of new buildings and spaces within building management systems is time-intensive and costly, involving significant manual effort and potential for input errors due to the complexity of manually generating digital representations of physical assets and configuring devices.
Innovation Solution
A system utilizing processing circuits with machine learning models to automatically tag and validate data points associated with building entities, such as equipment and spaces, by extracting context data, performing signal analysis, and receiving user feedback to enhance data accuracy and reduce manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual commissioning methods are used to generate digital representations and configure devices, then data accuracy can be ensured through human review, but the process becomes time-intensive and costly
Solution Approach 1:
The system enables automatic self-tagging of data points using machine learning models that analyze context data and operational patterns. The building management system autonomously identifies and tags data points without requiring manual intervention for each data point, while still achieving high accuracy through confidence metrics and selective manual review.
Solution Approach 2:
The system implements a feedback loop where manual review results are used to train and improve the machine learning models. Users can review suggested tags and provide corrections, which are then fed back into the system to enhance future automatic tagging accuracy, progressively reducing the need for manual intervention.
2Productivity
If automatic tagging using machine learning models is implemented, then commissioning time is reduced and productivity increases, but data accuracy may be compromised without manual validation
Solution Approach 1:
The system applies automatic tagging to all data points initially, then selectively applies manual review only to data points with lower confidence metrics. This partial manual validation approach ensures high accuracy for critical data points while maintaining overall productivity gains from automation.
Solution Approach 2:
The system dynamically adjusts the confidence threshold parameter to control the balance between automatic and manual tagging. By changing this parameter, the system can optimize the trade-off between commissioning speed and tagging accuracy based on specific project requirements and data quality characteristics.
3Measurement precision
If comprehensive manual review of all data points is performed, then tagging accuracy is maximized, but the complexity of the commissioning process increases
Solution Approach 1:
The commissioning process is segmented into automated tagging and selective manual review phases. The system automatically tags data points with high confidence metrics without manual intervention, and only routes low-confidence data points to manual review, thereby simplifying the overall process while maintaining accuracy.
Solution Approach 2:
The machine learning model acts as an intermediary between raw data and final tagged output. It pre-processes and suggests tags for all data points, filtering out obvious cases and presenting only ambiguous cases for manual review, thus reducing the complexity of direct human review of all data points.
4Measurement precision
If machine learning models are trained using historical information, then automatic tagging accuracy improves, but the initial setup time and computational resources increase
Solution Approach 1:
The system performs preliminary training of machine learning models using available historical data before the commissioning process begins. This preliminary action establishes a baseline model that can immediately begin automatic tagging, with the understanding that the model will continue to improve as it receives feedback during operation.
Solution Approach 2:
The machine learning model training is an continuous process that operates throughout the commissioning and operational phases. The model continuously learns from new data and feedback, improving accuracy over time without requiring separate training interruptions, thus maintaining continuous useful action in the commissioning process.
Data Source
AI summary
A system for commissioning a model, comprising one or more processing circuits configured to identify a first plurality of data points in the building, automatically tag at least a portion of the first plurality of data points with one or more first tags using context data extracted from and/or associated with the data points, the one or more entities comprising one or more of building equipment, building spaces, people, or events, identify at least one of the first plurality of data points for manual review and generate one or more suggested tags for the at least one data point, receive feedback from the manual review, and receive a second plurality of data points in the building and automatically tag at least a portion of the second plurality of data points with one or more second tags using the feedback from the manual review.