Transformer State Prediction Using Oil Filtering Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for diagnosing transformer states based on dissolved gas analysis are inaccurate and fail to predict future states, leading to unpredictable equipment accidents and significant economic losses.
Innovation Solution
A method and apparatus that utilize different learning models to predict transformer states based on whether oil filtering is performed, using dissolved gas data and transformer state data to determine the current and future states of transformers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single prediction model is used for all transformer conditions, then the device complexity is reduced, but the prediction accuracy deteriorates because the model cannot account for different oil filtering states
Solution Approach 1:
The patent divides the prediction task into separate models based on oil filtering state. One model predicts transformer state when oil filtering is performed, and another model predicts when oil filtering is not performed. This segmentation allows each model to specialize in specific conditions, improving prediction accuracy without requiring a single overly complex model to handle all scenarios.
2Reliability
If oil filtering state is not considered, then the ease of operation is improved, but the prediction reliability deteriorates due to inaccurate state assessment
Solution Approach 1:
The system performs preliminary classification to determine the oil filtering state before selecting the appropriate prediction model. This preliminary action of identifying whether oil filtering has been performed allows the system to choose the correct specialized model, thereby improving prediction reliability while keeping the operational process straightforward through automated model selection.
3Measurement precision
If simple gas concentration analysis is used, then the ease of operation is improved, but the diagnostic precision deteriorates making it difficult to determine transformer state accurately
Solution Approach 1:
The patent transforms the diagnostic approach by changing from simple gas concentration threshold comparison to a machine learning-based prediction system. The system uses dissolved gas concentrations as input parameters but processes them through trained models that consider oil filtering state, thereby improving diagnostic precision while maintaining operational simplicity through automated analysis.
Data Source
AI summary
A method of predicting a transformer state in consideration of whether oil filtering is performed includes receiving, by a transformer state prediction apparatus, transformer data of a transformer, determining, by the transformer state prediction apparatus, whether an oil of the transformer is filtered on the basis of the transformer data, and predicting, by the transformer state prediction apparatus, a state of the transformer on the basis of different prediction models depending on whether the oil is filtered.