Predictive Fault Diagnostics for Connected Building Equipment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems (BMS) face challenges in accurately predicting and diagnosing faults in equipment, leading to potential equipment failures and increased maintenance costs, as existing methods rely on rule-based systems that are cumbersome and inefficient in adapting to changing conditions.
Innovation Solution
Implementing a predictive diagnostics system that uses supervised and unsupervised machine learning techniques to analyze temporal data from connected equipment, generating a probability distribution to separate normal and faulty conditions, and creating a fault prediction model to anticipate and diagnose potential faults, enabling proactive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If rule-based systems are used for fault detection and diagnostics, then the system structure is simple and easy to implement, but the system is cumbersome and inefficient in adapting to changing conditions
Solution Approach 1:
The patent replaces traditional rule-based mechanical diagnostic systems with machine learning-based predictive diagnostics. The system uses supervised and unsupervised learning algorithms to automatically adapt to changing equipment conditions without requiring manual rule updates, thereby improving adaptability while managing complexity through automated model training and inference mechanisms.
Solution Approach 2:
The system dynamically adjusts diagnostic parameters and thresholds based on learned patterns from operational data. By continuously updating probability distributions and fault boundaries through machine learning, the system adapts to changing conditions without requiring complex manual reconfiguration, resolving the contradiction between adaptability and system complexity.
2Measurement precision
If traditional fault detection methods are used, then the implementation is straightforward, but the prediction accuracy and diagnostic capability are insufficient
Solution Approach 1:
The patent replaces traditional threshold-based and rule-based diagnostic methods with machine learning models that analyze temporal data patterns. The supervised learning component generates accurate fault predictions by learning from labeled historical data, while unsupervised learning identifies novel fault patterns, significantly improving diagnostic precision despite increased computational complexity.
Solution Approach 2:
The system performs preliminary fault prediction by analyzing temporal trends and probability distributions before actual faults occur. By continuously monitoring and updating fault probabilities based on current operational data, the system achieves high prediction accuracy by detecting early signs of degradation before failure, resolving the trade-off between precision and complexity.
3Reliability
If machine learning techniques are implemented for predictive diagnostics, then fault prediction accuracy improves, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent segments the diagnostic system into distinct functional modules: data collection from connected equipment, supervised learning for known fault patterns, unsupervised learning for anomaly detection, probability distribution generation, and fault prediction. This modular architecture improves reliability through specialized processing while managing computational complexity by distributing tasks across separate computational components.
Solution Approach 2:
The system replaces complex manual diagnostic procedures with automated machine learning pipelines that process temporal data efficiently. By using probabilistic models and pattern recognition algorithms, the system achieves high equipment reliability through automated, consistent analysis without requiring proportionally increased computational resources, as the learning models are trained once and then execute efficiently during operation.
Data Source
AI summary
A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.