Medium-Voltage Switchgear Thermal Fault Detection With Autoencoders
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Monitoring medium voltage switchgear or control gear using infrared thermographic cameras requires continuous human attention to detect temperature anomalies, which is impractical.
Innovation Solution
Employing an autoencoder neural network to analyze infrared images from within the switchgear or control gear, comparing them with synthetic images to detect faults by measuring distance metrics, such as root mean squared error, and generating alarms when deviations exceed thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If an infrared camera is used to monitor medium voltage switchgear, then temperature anomalies can be detected, but continuous human monitoring is required which is impractical
Solution Approach 1:
The system enables self-service monitoring by implementing an autoencoder neural network that automatically analyzes infrared images and detects temperature anomalies without requiring human intervention. The autoencoder is trained on normal thermal patterns and autonomously identifies deviations, making the monitoring system self-sufficient and eliminating the need for continuous human attention.
Solution Approach 2:
The patent replaces the mechanical system of human visual inspection with an automated image processing system based on neural networks. The autoencoder processes infrared images algorithmically, substituting human cognitive functions with computational algorithms that can continuously analyze thermal data without fatigue or distraction.
2Extent of automation
If traditional image analysis methods are used, then fault detection is possible, but automated analysis algorithms are complex to implement
Solution Approach 1:
The autoencoder employs a copying mechanism where the neural network learns to reproduce normal thermal patterns from training data. During operation, it attempts to copy or reconstruct the input infrared image, and the reconstruction error automatically indicates anomalies. This copying approach simplifies the detection logic compared to traditional methods that require explicit rule-based definitions of various fault conditions.
Solution Approach 2:
The patent transforms the fault detection problem from analyzing multiple complex parameters into a single parameter comparison: the reconstruction error of the autoencoder. By changing the detection parameter from multiple thermal features to a single error metric, the system achieves high automation with reduced algorithmic complexity.
3Measurement precision
If manual inspection of infrared images is performed, then temperature anomalies can be identified, but it is not practical for continuous monitoring
Solution Approach 1:
The automated autoencoder system enables continuous analysis of infrared images without interruption, maintaining constant monitoring of thermal conditions. Unlike manual inspection which must be periodic due to human limitations, the neural network can process images continuously, ensuring no anomaly goes undetected and eliminating gaps in monitoring coverage.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Automatically and efficiently identifies faults in current-carrying parts of switchgear or control gear, reducing the need for continuous human monitoring and improving fault detection accuracy using only healthy image data for training.
Implementation Method 1
an infrared camera... configured to acquire an infrared image
Data Source
AI summary
A medium voltage switchgear or controlgear monitoring system includes: an infrared camera; and a processing unit. The infrared camera is mounted within a medium voltage switchgear or controlgear. The infrared camera is configured to acquires an infrared image including image data of two or three current carrying parts of the switchgear or control gear. The two or three current carrying parts are the same current carry part of two or three equivalent systems within the switchgear or controlgear. The infrared camera provides the infrared image to the processing unit. The processing unit determines that the two or three current carrying parts are operating correctly or that one of the two or three current carrying parts has a fault. The determination includes analysis of the infrared image by an autoencoder implemented by the processing unit.