An End-to-end Transient Recognition Method for VSC-HVDC Based on Deep Belief Network

Abstract

Lightning is one of the most common transient interferences on overhead transmission lines of high-voltage direct current (HVDC) systems. Accurate and effective recognition of faults and disturbances caused by lightning strokes is crucial in transient protections such as traveling wave protection. Traditional recognition methods which adopt feature extraction and classification models rely heavily on the performance of signal processing and practical operation experiences. Misjudgments occur due to the poor generalization performance of recognition models. To improve the recognition rates and reliability of transient protection, this paper proposes a transient recognition method based on the deep belief network. The normalized line-mode components of transient currents on HVDC transmission lines are analyzed by a deep belief network which is properly designed. The feature learning process of the deep belief network can discover the inherent characteristics and improve recognition accuracy. Simulations are carried out to verify the effectiveness of the proposed method. Results demonstrate that the proposed method performs well in various scenarios and shows higher potential in practical applications than traditional machine learning based ones. Index Terms-Deep belief network, transient recognition, machine learning, voltage source converter based high-voltage direct current (VSC-HVDC).

Pilot facial feature recognition and fatigue classification method under high exposure environment

“…𝑥 𝑖 ̂= 𝐹 −1 {|𝐹 𝑚 (𝑢, 𝑣)|∠𝜙 𝑖 (𝑢, 𝑣)} (10) where the different faces𝑥 𝑖 , the𝐹 𝑚 is the amplitude frequency characteristic of the face, and𝜑 𝑖 is the phase frequency characteristic of the face. From equation (10), it can be seen that the amplitudefrequency characteristics of the face after normalization of illumination are consistent with the amplitude-frequency characteristics of the sample mean of the training set, so that the normalization of illumination of the face can be achieved while preserving the invariance of the phase frequency characteristics and thus ensuring the distinguishability of the face.…”

“…One normalizes the illumination conditions in the image and homogenizes the illumination in the image by weakening the differences. Such as histogram equalization [9] Gamma correction [10] DCT (Discrete Cosine Transform) [11] etc. Another method is the direct elimination of the illumination part of the image to remove the image caused by light recognition, such as Rstinex algorithm [12] The Rstinex algorithm, frequency-domain light normalization, and single-scale SSR and multi-scale MSR algorithms are generated according to the scale.…”

Energy Efficiency Evaluation of HVDC Converter Station Based on Deep Neural Network Model

“…2) Determine the network architecture of RBF [11]. This paper sets the number of input and output layer nodes according to the specific problem.…”

Fault Diagnosis Method for MMC-HVDC Based on Bi-GRU Neural Network

“…The fault diagnosis based on AI algorithm is fast and accurate and meets the requirements of power grid protection [17]. Luo Guomin et al [18] propose a transient identification method based on a deep belief network. This method trains the network with the normalized line mode component of transient currents and identifies faults and lightning disturbances with an accuracy of 96.4%.…”