Cold Storage Monitoring With Self-Learned Fault Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for automated remote health monitoring of cold storage devices like refrigerators and freezers to detect abnormalities early, as malfunctions can be critical in settings such as medical research labs, where a lack of real-time monitoring can lead to significant losses.
Innovation Solution
A monitoring system that tracks temperature and electrical current consumption, learns normal operating behavior, and sends alerts when abnormal conditions are detected by analyzing feature vectors and calculating alarm thresholds based on operational state changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated remote health monitoring is implemented, then early detection of abnormalities is improved, but device complexity increases
Solution Approach 1:
The monitoring system performs self-learning by automatically accumulating feature vectors during a learning period and generating alarm thresholds without requiring manual intervention. The system serves itself by autonomously adapting to the cold storage device's normal operating patterns and establishing baseline behavior, eliminating the need for manual threshold configuration while improving early detection capability
Solution Approach 2:
The system continuously monitors electrical current and temperature, compares real-time measurements against learned thresholds, and provides feedback through alarm notifications when abnormalities are detected. This closed-loop feedback mechanism enables automatic adjustment and improvement of monitoring accuracy over time while maintaining system reliability
2Measurement precision
If continuous monitoring and learning process is performed, then detection accuracy is improved, but energy consumption increases
Solution Approach 1:
The system implements periodic monitoring by accumulating feature vectors at discrete time points during the learning period and performing threshold generation at intervals rather than continuously. The monitoring process periodically compares current operating parameters against established thresholds, reducing computational load and energy consumption while maintaining detection accuracy through strategic sampling of operational data
3Reliability
If alarm threshold is generated from learning statistics, then false alarm reduction is improved, but monitoring time is increased
Solution Approach 1:
The system performs preliminary learning during an initial period to accumulate feature vectors and establish alarm thresholds before normal monitoring begins. By preparing the baseline behavior patterns and thresholds in advance, the system enables rapid deployment of accurate monitoring without requiring extended learning periods during operational use, thus reducing false alarms while minimizing time loss
Data Source
AI summary
A monitoring system for a cold storage device such as a vapor compression refrigerator or freezer. The monitoring system learns operating characteristics of the cold storage device and issues alarm notifications when abnormal behavior is detected. Such a system can be used as an “early warning system” to flag when a cold storage device is not operating properly. Such a system could be particularly valuable in applications that make mission-critical use of cold storage devices, e.g., biomedical or pharmaceutical research labs, blood or tissue banks, grocery stores, restaurants, and the like.