Anomaly Detection in Retail Refrigeration Showcases via Sensor Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Refrigeration showcases in retail stores experience high electric utility costs and service disruptions due to improper usage and equipment failures, necessitating early anomaly detection to reduce losses.
Innovation Solution
A method and system for detecting anomalies in refrigeration showcases by clustering them based on sensor data, building models using multi-variate time series data, and monitoring system status through reconstruction error analysis to identify and alert on failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If anomaly detection is performed on individual showcases without clustering, then detection coverage is achieved, but false positives increase and detection accuracy decreases
Solution Approach 1:
The patent groups multiple showcases into clusters based on their operational characteristics and sensor data patterns. By combining showcases with similar behaviors into clusters, the system performs anomaly detection at the cluster level, which reduces false positives and improves detection accuracy through comparative analysis across similar units.
Solution Approach 2:
The patent segments the overall showcase fleet into distinct clusters based on operational characteristics, sensor configurations, and behavioral patterns. This segmentation allows for more precise anomaly detection by comparing each showcase against its specific cluster peers rather than treating all showcases uniformly.
2Reliability
If comprehensive sensor monitoring is implemented across all showcases, then anomaly detection capability is improved, but system complexity and computational burden increase
Solution Approach 1:
The patent combines sensor data from multiple showcases into cluster-level aggregations, reducing the overall computational burden. By merging data processing at the cluster level rather than individually for each showcase, the system maintains comprehensive monitoring capability while reducing system complexity and computational resources required.
3Reliability
If real-time monitoring of all showcases is performed, then service disruption detection is improved, but energy consumption and computational resources increase
Solution Approach 1:
The patent implements real-time monitoring by clustering showcases and processing their sensor data collectively. This approach maintains the ability to detect service disruptions in real-time while reducing energy consumption and computational resources by avoiding redundant individual processing of each showcase's data stream.
Data Source
AI summary
Systems and methods for detecting anomalies in a plurality of showcases are provided. A system can obtain a corresponding table between each of the plurality of showcases and at least one corresponding sensor. The system obtains information for showcase clustering. The system can include a processor device that can determine at least one cluster of showcases based on the information for showcase clustering and the corresponding table between each of the plurality of showcases and the at least one corresponding sensor. The system can build at least one model for each of the at least one cluster of showcases and detect at least one anomaly based on data from the at least one cluster of showcases and the at least one model.