Transformer DGA Rate-of-Change Alarms With Adaptive Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transformer fault detection methods using dissolved gas analysis (DGA) often result in false positive alarms due to fixed alarm thresholds that do not account for transformer-specific conditions, leading to unnecessary maintenance and operational disruptions.
Innovation Solution
Implementing adaptive alarm thresholds for dissolved gas concentrations and their rate of change (ROC) based on a sliding time window, which adjusts dynamically using statistical analysis of recent data to minimize false alarms and improve anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed alarm thresholds are used for dissolved gas concentration, then the alarm system is simple to implement, but false positive alarms increase due to inability to account for transformer-specific conditions
Solution Approach 1:
The patent implements dynamic alarm thresholds that adapt over time based on the transformer's operational history and environmental conditions. The system continuously updates thresholds using a sliding time window approach, transforming static thresholds into dynamic, adaptive values that reduce false positives while maintaining detection accuracy.
Solution Approach 2:
The system performs self-adjustment by automatically learning the transformer's baseline behavior and adapting thresholds without requiring manual intervention. The adaptive threshold mechanism uses historical data to self-calibrate, eliminating the need for expert knowledge in threshold setting while improving reliability.
2Reliability
If adaptive alarm thresholds based on sliding time window are implemented, then false positive alarms are reduced, but computational expense increases
Solution Approach 1:
The system applies adaptive thresholding selectively rather than uniformly across all parameters and time periods. By using a sliding time window that focuses computational resources on recent, relevant data while gradually fading older data, the system achieves high alarm accuracy with reduced computational burden compared to processing entire historical datasets.
Solution Approach 2:
The patent changes the temporal parameter of threshold adaptation by introducing a sliding time window mechanism. This transforms the computational approach from static single-point thresholds to dynamic time-dependent thresholds, improving accuracy while managing computational expense through controlled temporal sampling and data retention.
3Adaptability or versatility
If manual threshold setting is required for each transformer, then thresholds can be customized, but the process becomes time-consuming and requires expert knowledge
Solution Approach 1:
The system automatically adapts to each transformer's specific conditions through self-learning mechanisms. By continuously monitoring dissolved gas concentrations and environmental parameters, the system autonomously generates customized thresholds for each transformer without requiring manual configuration, expert knowledge, or time-consuming setup procedures.
Solution Approach 2:
The system performs preliminary adaptation during an initial learning period, establishing baseline thresholds before full operational use. This preliminary action allows the system to pre-customize thresholds for each transformer during commissioning or early operation, eliminating the need for ongoing manual adjustment while maintaining transformer-specific adaptability.
Data Source
AI summary
A method for using adaptive alarm thresholds for rate of change in dissolved gas concentrations for power transformer fault detection may include receiving first dissolved gas data of a power transformer; determining a first rate of change (ROC) of a first gas concentration of the first dissolved gas data; generating, based on the first ROC, a first adaptive alarm threshold for ROC with which to detect a fault in the power transformer; receiving second dissolved gas data of the power transformer; determining a second ROC of a second gas concentration of the second dissolved gas data; comparing the second gas concentration to a static gas concentration threshold; comparing, based on the comparison of the second gas concentration to the static gas concentration threshold, the second ROC to the first adaptive alarm threshold for ROC; detecting the fault based the comparisons; and generating an alert indicative of the fault.