Data-driven energy management architecture for more-electric aircrafts

Abstract

This paper proposes an attack-resilient ANFIS-DBN based energy management architecture for a hybrid emergency power system of More-Electric Aircrafts (MEAs). Our proposed architecture develops a Deep Belief Network (DBN) stacked Adaptive Neuro-Fuzzy Interference System (ANFIS)-based method to evaluate the integrity of the power output of the fuel-cell in the fuel-cell based hybrid auxiliary power unit (APU), which is vulnerable to the cyber-attacks and critical for the effective energy management and emergency control. Our ANFIS-DBN-based method achieves the integrity evaluation by leveraging the real-time measures on the State of Charge (SOC) of the battery, power output of the ultra-capacitor and the load profile. In our simulation, we evaluate the performance of our proposed ANFIS-DBN-based method to support the integrity of the Energy Management Strategies (EMSs) used in hybrid emergency power system for more-electric aircrafts by using MATLAB/Simulink. Our simulation results illustrate the effectiveness of our proposed method in effectively evaluating the integrity of critical data and achieving resilient control.