Locating Faults in Thyristor-Based LCC-HVDC Transmission Lines Using Single End Measurements and Boosting Ensemble

Most of the fault location methods in high voltage direct current (HVDC) transmission lines usemethods which require signals from both ends. It will be difficult to estimate fault location if the signal recorded is not correct due to communication problems.Hence a robust method is required which can locate fault with minimum error. In this work, faults are located using boosting ensembles in HVDC transmission lines based on single terminal direct current (DC) signals. The signals are processed to obtain input features that vary with the fault distance. These input features are obtained by taking maximum of half cycle current signals after fault and minimum of half cycle voltage signals after fault from the root mean square of DC signals. The input features are input to a boosting ensemble for estimating the location of fault. Boosting ensemble method attempts to correct the errors from the previous models and find outputs by combining all models. The boosting ensemble method has been also compared with the decision tree method and thebagging-based ensemble method. Fault locations are estimated using three methods and compared to obtain an optimal method. The boosting ensemble method has better performance than all the other methods in locating the faults. It also validated varying fault resistance, smoothing reactors, boundary faults, pole to ground faults and pole to pole faults. The advantage of the method is that no communication link is needed. Another advantage is that it allowsreach setting up to 99.9% and does not exhibitthe problem of over-fitting. Another advantage is that the percentage error in locating faults is within 1% and has a low realization cost. The proposed method can be implemented in HVDC transmission lines effectively as an alternative to overcome the drawbacks of traveling wave methods.

Intelligent Fault Diagnosis Framework for Modular Multilevel Converters in HVDC Transmission

Open circuit failure mode in insulated-gate bipolar transistors (IGBT) is one of the most common faults in modular multilevel converters (MMCs). Several techniques for MMC fault diagnosis based on threshold parameters have been proposed, but very few studies have considered artificial intelligence (AI) techniques. Using thresholds has the difficulty of selecting suitable threshold values for different operating conditions. In addition, very little attention has been paid to the importance of developing fast and accurate techniques for the real-life application of open-circuit failures of IGBT fault diagnosis. To achieve high classification accuracy and reduced computation time, a fault diagnosis framework with a combination of the AC-side three-phase current, and the upper and lower bridges’ currents of the MMCs to automatically classify health conditions of MMCs is proposed. In this framework, the principal component analysis (PCA) is used for feature extraction. Then, two classification algorithms—multiclass support vector machine (SVM) based on error-correcting output codes (ECOC) and multinomial logistic regression (MLR)—are used for classification. The effectiveness of the proposed framework is validated by a two-terminal simulation model of the MMC-high-voltage direct current (HVDC) transmission power system using PSCAD/EMTDC software. The simulation results demonstrate that the proposed framework is highly effective in diagnosing the health conditions of MMCs compared to recently published results.