Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ2A Unified and Interpretable Benchmark of Classification Models for DGA-Based Power Transformer Fault Diagnosis
Doğan, Kıvanç; Ertarğın, Merve; Çalışkan, Abuzer; Bakay, Ayşenur
Power transformers are among the most critical components of electric power transmission and distribution systems, and unexpected failures can lead to substantial economic losses and prolonged power outages. Dissolved Gas Analysis (DGA) is the most widely used diagnostic technique for transformer fault diagnosis and involves interpreting gases dissolved in insulating oil. However, conventional interpretation methods, such as the Rogers ratio, the Doernenburg ratio, the IEC 60599 ratio method, and the Duval Triangle, rely heavily on expert knowledge, may produce inconsistent diagnoses for the same oil sample, and may fail to provide a diagnosis in certain cases. In this study, 12 classification models were evaluated using the publicly available Power Transformers Fault Detection and Diagnosis (FDD) and Remaining Useful Life (RUL) dataset and a unified evaluation protocol. Model performance was assessed using Accuracy, Balanced Accuracy, and Macro-F1 score, while model interpretability was investigated through Shapley Additive Explanations (SHAP) analysis. The results showed that ensemble tree-based methods achieved the best overall performance. LightGBM and Random Forest both attained an Accuracy of 0.969 and a Macro-F1 score of 0.924, while LightGBM further achieved the highest Balanced Accuracy of 0.940. XGBoost exhibited the most stable performance under cross-validation. SHAP analysis revealed that engineered relative concentration features, particularly the CO/H2 ratio and the combined gas ratio, were among the most influential features for fault classification. These findings demonstrate that, for datasets of this scale, ensemble tree-based models combined with well-designed features provide strong and interpretable performance for imbalanced DGA-based fault diagnosis, highlighting the effectiveness of feature-based ensemble learning for small- to medium-sized datasets.
- MakaleYalnız künye2019Scopus SJRQ2Design and development of travelling-wave-frequency-based transmission line fault locator using TMS320 DSP
Arkan, Müslüm; Akmaz, Düzgün; Mamiş, Mehmet S.; Tağluk, Mehmet Emin
The authors use a TMS320 digital signal processor (TMS320-DSP) to determine fault instants and estimate their location in real time in a laboratory environment. The fault instant is determined via examining the instantaneous differential changes in the line currents. After the fault is detected, the fault location is determined by processing the time-domain transient current waves. First, the travelling-wave frequency is determined by application of the fast Fourier transform to the positive-sequence-component line current after the fault, and subsequently, the fault location is estimated by utilising this frequency. The alternative transients programme (ATP)–electromagnetic transient programme is used to simulate the line currents and create short-circuit fault conditions. Furthermore, LabVIEW software and a National Instruments data acquisition board are used to transform the line currents obtained through the ATP programme into analogue signals. The TMS320-DSP determines the fault in real time and estimates the fault location using the completed software and analogue input signals. Their results indicate that the prototype device designed with the use of the TMS320-DSP is suitable for real-time fault detection.
AtıfScopus16WoS16OpenAlex16
İncele - MakaleYalnız künye2013Scopus SJRQ2Fault diagnosis system for series compensated transmission line based on wavelet transform and adaptive neuro-fuzzy inference system
Eristi, Huseyin
This paper proposes a new fault diagnosis approach based on combined wavelet transform and adaptive neuro-fuzzy inference system for fault section identification, classification and location in a series compensated transmission line. It performs an effective feature extraction approach based on norm entropy in order to obtain the features represented main frequency, harmonic and transient characteristics of the fault signals. The proposed method uses the samples of fault voltages and currents for one cycle duration from the inception of fault. The feasibility of the proposed method has been tested on a 400 kV, 300 km series compensated transmission line for all the ten types of faults using MATLAB/Simulink for a large data set of 23,436 fault cases comprising of all the 10 types of faults. Fault signals varying with fault resistance, fault inception angle, fault distance, load angle, percentage compensation level and source impedance are applied to the proposed algorithm. The results also indicate that the proposed method is robust to wide variation in system conditions and has higher fault diagnosis accuracy with regard to the other approaches in the literature for this problem. (C) 2012 Elsevier Ltd. All rights reserved.
AtıfWoS82OpenAlex101İncele