کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Differential Protection for Power Transformers Using Tree-based Pipeline Optimization Tool

نویسندگان :

Reza Afsharisefat¹ Mohsen Jannati² Mohamad Reza Shams³

1- دانشگاه اصفهان 2- دانشگاه اصفهان 3- دانشگاه اصفهان

کلمات کلیدی :

Differential Protection،Power Transformer،Inrush Current،Internal Fault،Machine Learning،Tree-based Pipeline Optimization

چکیده :

Accurate differentiation between inrush current and internal faults is crucial for power transformer differential protection. During transformer energization and inrush current generation, transformer differential protection may misinterpret inrush current as an internal fault, leading to a trip command being issued to the breakers. This study proposes an innovative machine learning-based approach named the Tree-based Pipeline Optimization Tool (TPOT) to enhance the F-score and efficiency of inrush current detection in relation to internal faults in power transformers. TPOT performs in-depth data analysis and extracts significant features that influence the distinction between inrush current and transformer internal faults. As a model optimizer, TPOT fine-tunes models by adjusting parameters and structures. Consequently, this approach enables differentiation between inrush current and internal faults in power transformers with high F-score and continuous improvements in detection capability. Simulation results on a real 160 MVA, 230/63 kV transformer in the MATLAB and Python software environments demonstrate the effectiveness of the proposed protection scheme in classifying transformer inrush current from internal faults with an F1-score of 92%.