BMS Vibration Analytics Using ML Condition Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building management systems (BMS) rely on manual initiation and rule-based approaches for analyzing vibration data, lacking the use of large amounts of historical data to fine-tune advanced models for assessing equipment performance, which limits their ability to detect issues efficiently and effectively manage maintenance.
Innovation Solution
Implementing an automated analytics application within the BMS that receives vibration datasets, assembles feature vectors, and applies machine learning models to generate condition scores for equipment components, enabling automatic scheduling of maintenance and adjustment of setpoints based on these scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual initiation and rule-based approaches are used for analyzing vibration data, then the system operation is simple to implement, but the detection precision and ability to assess equipment performance are insufficient
Solution Approach 1:
The patent replaces manual rule-based analysis with automated machine learning models that process vibration data. The system uses trained models to automatically assess equipment condition, substituting human expert analysis with computational algorithms that provide more precise and consistent detection without requiring manual intervention.
Solution Approach 2:
The system enables self-service through automated analytics that independently evaluate equipment health without human intervention. The machine learning models automatically process vibration datasets, generate condition assessments, and trigger maintenance workflows, allowing the system to serve itself in detecting and responding to equipment issues.
2Productivity
If advanced machine learning models are implemented for vibration data analysis, then the equipment performance assessment capability is improved, but the computational resources and processing time are increased
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models offline with historical vibration data before deployment. This allows the models to be ready for immediate use without requiring extensive processing time during actual equipment monitoring, enabling fast real-time assessments while maintaining high accuracy through prior computational preparation.
3Reliability
If historical vibration data is used to fine-tune machine learning models, then the condition assessment accuracy is improved, but the data storage requirements and processing complexity are increased
Solution Approach 1:
The system extracts only the essential features and patterns from historical vibration data that are most relevant for condition assessment. Rather than processing entire raw datasets, the machine learning models learn to extract key diagnostic features, reducing data processing complexity while maintaining high reliability in condition assessments.
Data Source
AI summary
A method performed by a Building Management System (BMS) includes receiving a vibration dataset associated with a machine controlled by the BMS. The vibration dataset includes machine metadata, machine operating conditions, and one or more time waveforms. The method further includes assembling a feature vector comprising one or more features of the vibration dataset for input to a machine learning model. The machine learning model is associated with a component of the machine. The method further includes applying the feature vector to the machine learning model in order to generate a condition score for the component. The method further includes scheduling a maintenance event for the machine or changing a setpoint associated with the machine depending on the condition score.