Fault Diagnosis for Modular Multilevel Converter (MMC) Based on Deep Learning: An Edge Implementation Using Binary Neural Network

Abstract

Recently deep neural network (DNN) has been proposed for fault diagnosis of modular multilevel converter (MMC). The training of DNN is convenient due to its end-to-end feature, and DNN has a strong learning ability due to its deep structure. However, DNN is hard to be implemented at the edge (i.e., the MMC side) since it involves a large number of floating-point parameters and calculations. This article proposes a methodology to deploy a DNN with fault diagnosis purpose at the edge. First, the floating-point DNN is converted to a binary neural network (BNN) version. BNN not only binarizes the floating-point weights as “1” or “−1” to save the storage footprint but also replaces the floating-point multiply accumulates (MACs) with bitwise operations to reduce the computation complexity. Second, the computation of different BNN layers is distributed to different embedded real-time controllers in MMC, in order to fully use the existing computing resources. With the proposed methodology, a typical DNN, namely, 1-D convolutional neural network (1-D CNN) for open-circuit fault (OCF) diagnosis of MMC, which has 238.93 kB parameter storage footprint and 91 752 floating-point MACs, is replaced by a BNN with only 7.48 kB parameter storage footprint and bitwise operations. A total of 96.87% storage footprint is saved and almost floating-point operations are replaced, and as a tradeoff, the diagnostic accuracy is only reduced by 4.33% compared with the 1-D CNN counterpart. This work shows the huge potential of edge intelligence for fault diagnosis of power electronics.