Open-Circuit Fault Detection and Classification of Modular Multilevel Converters in High Voltage Direct Current Systems (MMC-HVDC) with Long Short-Term Memory (LSTM) Method.

Qinghua Wang,Hosameldin O A Ahmed,Mohamed Darwish,Asoke K Nandi,Yuexiao Yu

doi:10.3390/s21124159

Abstract

Fault detection and classification are two of the challenging tasks in Modular Multilevel Converters in High Voltage Direct Current (MMC-HVDC) systems. To directly classify the raw sensor data without certain feature extraction and classifier design, a long short-term memory (LSTM) neural network is proposed and used for seven states of the MMC-HVDC transmission power system simulated by Power Systems Computer Aided Design/Electromagnetic Transients including DC (PSCAD/EMTDC). It is observed that the LSTM method can detect faults with 100% accuracy and classify different faults as well as provide promising fault classification performance. Compared with a bidirectional LSTM (BiLSTM), the LSTM can get similar classification accuracy, requiring less training time and testing time. Compared with Convolutional Neural Networks (CNN) and AutoEncoder-based deep neural networks (AE-based DNN), the LSTM method can get better classification accuracy around the middle of the testing data proportion, but it needs more training time.

Highlights

Modular multilevel converters (MMCs) have been widely applied due to their advantages of modularity, extensibility, high-quality output, and high efficiency [1,2,3]
Our research group proposed Convolutional Neural Networks (CNN), AutoEncoder-based deep neural network (AE-based DNN), and SoftMax classifier for MMC [33], the results showed that these deep learning methods have good potential
This paper presented an long short-term memory (LSTM) deep learning method for fault de

Summary

Introduction

Modular multilevel converters (MMCs) have been widely applied due to their advantages of modularity, extensibility, high-quality output, and high efficiency [1,2,3]. An MMC is formed by cascading multiple sub-modules (SMs) with the same structure. In a high voltage direct current (HVDC) transmission power system, the numbers of SMs are always up to several hundreds or thousands, which may induce some faults of SMs more likely to arise under complex and harsh conditions. The most application of SM circuits is the half-bridge circuit topology (HB-SM), which consists of two wire-bound insulated gate bipolar transistor (IGBT) modules along with their corresponding antiparallel diodes and a capacitor [4,5]. The main disadvantage in HB-SM is that it cannot provide blocking against DC fault. IGBT damage is the most common cause of sub-module failure [6], generally due to short-circuit faults or open-circuit faults [7]

Objectives

Results

Conclusion