A Novel Deep Learning-Based Diagnosis Method Applied to Power Quality Disturbances

Abstract

Monitoring electrical power quality has become a priority in the industrial sector background: avoiding unwanted effects that affect the whole performance at industrial facilities is an aim. The lack of commercial equipment capable of detecting them is a proven fact. Studies and research related to these types of grid behaviors are still a subject for which contributions are required. Although research has been conducted for disturbance detection, most methodologies consider only a few standardized disturbance combinations. This paper proposes an innovative deep learning-based diagnosis method to be applied on power quality disturbances, and it is based on three stages. Firstly, a domain fusion approach is considered in a feature extraction stage to characterize the electrical power grid. Secondly, an adaptive pattern characterization is carried out by considering a stacked autoencoder. Finally, a neural network structure is applied to identify disturbances. The proposed approach relies on the training and validation of the diagnosis system with synthetic data: single, double and triple disturbances combinations and different noise levels, also validated with available experimental measurements provided by IEEE 1159.2 Working Group. The proposed method achieves nearly a 100% hit rate allowing a far more practical application due to its capability of pattern characterization.

Advances in Power Quality Analysis Techniques for Electrical Machines and Drives: A Review

“…Recently, due to the difficulty for detecting various and more complex disturbances that may appear in the electrical network, techniques with the ability to handle and process large volumes of data and find relations among the types of disturbances have been considered. For instance, classical machine learning techniques like support vector machines (SVM) [97][98][99], artificial neural networks (ANN) [85,[100][101][102], deep learning (DL) [103,104], and other machine-learning techniques. Notwithstanding, several studies identify a combination of power disturbances described in the standards [105].…”

“…The approach classifies multiple power disturbances in two main classes, reaching accurate results for simulated data. In [104], a novel method based on deep learning is proposed for identifying and classifying PQDs in three main stages: feature extraction from the power system, adaptive pattern recognition by means of AE, and, finally, disturbances classification by NN. Continuing with datadriven strategies, the SVM are becoming important approaches for characterizing multiple patterns that would help to give support to the classification taks.…”

Overview of Signal Processing and Machine Learning for Smart Grid Condition Monitoring

“…Indeed, the automatic features extraction and the high pattern recognition capability of these approaches pave the way for an extensive use for power system issue prediction, detection and estimation. Hence, the last years have witnessed a big interest of researchers in the field of power system monitoring for deep learning as a medium for power quality enhancement and disturbancesmitigation [145,[186][187][188][189][190]. Hence, in [191], an unsupervised deep learning technique has been investigated for load profile management and classification.…”

Identification of Even-Order Harmonics Injected by Semiconverter into the AC Grid

“…Finally, the third issue is the appearance of even-order harmonics in half-controlled rectifiers, which can result in asymmetry of the AC voltage (e.g., DC magnetic bias phenomenon in AC transformers) [6]. Furthermore, issues regarding PQ require careful study and monitoring of the impact of each disturbance type produced by PE converters [7]. Most DC loads are connected to the power grid using some type of PE converter.…”