Automatic Feature Learning-Based Fault Detection and Classification in Power Transmission Lines Using Deep Transfer Model
This paper proposes an efficient, fast and low-resource based deep learning model for fault detection and classification in electrical power transmission lines. The proposed model automatically extracts features from input signals to decide the state of power transmission lines, hence eradicating the complex need of manually crafting features for fault classification algorithms. The proposed method uses a pre-trained deep learning model as a starting point, then retrains the adapted weight in transfer arrangement for fault classifier applications. This strategy expedites the training process and reduces the need of exhaustive dataset requirement. The model is thoroughly tested for wide range of performance tests such as fault locations, distances, resistance, inception point and signal noise etc. The proposed model is compared with state-of-the-art existing deep learning methods and has proven to be resilient, faster and generic more generalized