Real-Time FPGA-Based Hardware Neural Network for Fault Detection and Isolation in More Electric Aircraft

Qin Liu,Tian Liang,Venkata Dinavahi,Zhen Huang

doi:10.1109/access.2019.2950918

Abstract

More Electric Aircraft (MEA) has a great development prospect in the aviation industry thanks to the progressive power electronics technology and digital systems. Nevertheless, any fault occurring in the power electric system of MEA could be a fatal risk for the safety of the aircraft. To deal with the real-time fault detection and isolation (FDI) on the MEA, we put forward an FPGA-based neural network method which includes two stages: off-line construction using TensorFlow and real-time monitoring on the FPGA. Long Short-Term Memory (LSTM) network is applied because of its capability of learning from the long-term historical information in time series. A comprehensive MEA model based on the Boeing 787 power system created in PSCAD/EMTDC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">®</sup> and a commercial electric aircraft model based on Airbus E-Fan in Simscape are simulated to validate the effectiveness and generality of our proposed method. Adequate contrast experiments are conducted to acquire the most applicable architecture and configurations of the network. The results illustrate that the evaluation of the real-time condition can achieve accuracy over 99.5% within one sampling time on FPGA and reasonable hardware resource utilization.

Highlights

Since human beings fulfilled the dream of flying in the sky, researchers have always endeavored to make aircraft more energy efficient, environmental friendly, reliable and safer as well as less heavy and maintenance cost
In the off-line construction stage, Tensorflow library is applied to build up Long Short-Term Memory (LSTM)-based networks to train a model that is capable of classifying various operating conditions of the More Electric Aircraft (MEA) with respect to 15 features collected in simulation
In this paper, we propose an field-programmable gate array (FPGA)-based neural network method to handle the real-time fault detection and isolation (FDI) on the MEA

Summary

Introduction

Since human beings fulfilled the dream of flying in the sky, researchers have always endeavored to make aircraft more energy efficient, environmental friendly, reliable and safer as well as less heavy and maintenance cost. More Electric Aircraft (MEA) could be a promising answer. The design of conventional aircraft leads to the sacrifice of energy efficiency in balancing various types of energy sources consisting of mechanical, hydraulic, pneumatic, and electrical [1]. MEA, a fly-by-wire (FBW) aircraft, is able to overcome the above problems with advanced power electronics and digital systems. The most recent commercial transport aircraft, such as the Boeing 787 and the Airbus A380, are largely equipped with electrical systems [2].

Methods

Results

Conclusion