Recognition method of voltage sag causes based on Bi‐LSTM

Abstract

In recent years, the power quality problem has become more complicated in power grids because of the extensive usage of power electronics and multisource multitransformation features. The method, based on physical characteristics such as time domain, frequency domain and transform domain, is facing challenges in terms of adaptability, algorithm efficiency and accuracy for the recognition of complex disturbance recognition. The bidirectional long short-term memory network is an algorithm in deep learning. It is based on data for characterization learning, which can effectively overcome the problem of information loss and generalization ability of physical methods. Moreover, it has the characteristics of memory, which can simultaneously consider historical information and future information and can better learn data features with time series characteristics. Aiming at the transient voltage sag time series data, this paper proposes a recognition method of the voltage sag causes based on the bidirectional long short-term memory network's extraction eigenvalue, the full-connection layer's high-dimensional feature extraction and the Softmax network layer's classification. The experiment uses simulation data and measured data to prove that the model has good recognition ability and good antinoise performance in the recognition of voltage sag causes and can be reliably applied in practical engineering.

A systematic review of real-time detection and classification of power quality disturbances

“…For instance, some studies use threephase classifications of sags [140,158], which are strongly related to the type of faults that cause the voltage sags. Another aspect analyzed in this category is the classification of sags according to the root causes [133,147,149,150,180], e.g., faults, the starting of induction motors and heavy loads, and transformer energizing. The characterization of voltage sags, i.e., the quantification of the parameters such as duration, magnitude, starting and ending phase angle, etc., is also performed in some studies [132,173,174].…”

“…For instance, reference [81] presents a categorization according to different causes, namely, fault, self-extinguishing fault, line energizing, non-fault interruption, and transformer energizing. Similarly, voltage sags are usually classified according to the main underlying causes, i.e., faults, motor starting, and transformer energizing [175][176][177][178][179][180].…”

“…Convolutional Neural Networks (CNN) have been widely used in multiple PQDs and voltage sag classification [103,111,116,119,121,125,130,131,158,164,167,171,179,183]. Other deep learning models have been particularly used in the classification of voltage sags according to the root causes, e.g., deep feedforward ANNs [124], Long Short-Term Memory (LSTM) [129,159,180] (2023) 8:3 [165,175], and independently recurrent neural networks [182].…”

Unbalanced Voltage Sag Dataset Enhancement Based on Improved Balancing Generative Adversarial Network

“…The other type is to use a deep learning algorithm, based on data‐driven, using an end‐to‐end training method to optimize network parameters to complete the automatic extraction of sag features. Such as deep belief network [8], convolutional neural network [9,10], long short‐term memory network [11] and so on. Reference [12] realizes the high‐precision identification of sag signals based on the fusion of convolutional neural network and deep belief network.…”

A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances

“…CNNs are applied for the classification of PQ disturbances as in [27][28][29][30][31], voltage dip classification [5], recognition of voltage dip causes [32], and prediction of harmonics [33][34][35]. LSTM is applied to classification of events [36,37], recognition of voltage dip causes [38], voltage dip classification [39], and harmonic prediction [33]. GANs are applied to the classification of PQ events [40].…”