A System-Level Failure Propagation Detectability Using ANFIS for an Aircraft Electrical Power System

Abstract

The Electrical Power System (EPS) in an aircraft is designed to interact extensively with other systems. With a growing trend towards more electric aircraft, the complexity of interactions between the EPS and other systems has grown. This has resulted in an increased necessity of implementing health monitoring methods like diagnosis and prognosis of the EPS at the systems level. This paper focuses on developing a diagnostic algorithm for the EPS to detect and isolate faults and their root causes that occur at the Line Replaceable Units (LRUs) connecting with aircraft systems like the engine and the fuel system. This paper aims to achieve this in two steps: (i) developing an EPS digital twin and presenting the simulation results for both healthy and fault scenarios, (ii) developing an Adaptive Neuro-Fuzzy Inference System (ANFIS) monitor to detect faults in the EPS. The results from the ANFIS monitor are processed in two methods: (i) a crisp boundary approach, and (ii) a fuzzy boundary approach. The former approach has a poor misclassification rate; hence the latter method is chosen to combine with causal reasoning for isolating root causes of these interacting faults. The results from both these methods are presented through examples in this paper.

A Generalised Methodology for the Diagnosis of Aircraft Systems

“…In this work, three aircraft systems shown in the schematic diagram of FAVER (right side of fig 3) are examined: the engine, the ECS, and the fuel system. Previously, a simulation model of the EPS (Electrical Power System) was developed, with an Adaptive Neuro-Fuzzy Inference System (ANFIS) being implemented for its diagnosis [17]. It fits into the current framework but will not be replicated here.…”

“…The hot air then expands across the turbine blades (stations 4-5) and then passes through the core nozzle (stations 7-9). The cold bypassed air passes through a similar nozzle (stations [17][18][19] and mixes with the core flow to produce the thrust that moves the aircraft forward [18]. Bleed air is extracted from the compressor (station 3) based on demand, and supplied to the ECS and for anti-icing and deicing.…”

Fault Detection and Isolation of Landing Gear Retraction/ Extension Hydraulic System Based on BG and GARRs

“…Taking the research object as an example, in the study of fault diagnosis of other complex nonlinear systems such as aircraft hydraulic systems, Jianhua Zhao [12] et al created the drop shock friction equation for the failure mode of single-degree-of-freedom bearing systems, providing a theoretical basis for fault prevention and diagnosis of Magnetic-liquid double suspension bearings (MLDSB). Cordelia Mattuvarkuzhali Ezhilarasu [13] et al created an electrical power system (EPS) diagnostic algorithm to detect and isolate line replaceable units (LRU) problems and their primary causes. Kenan Shen [14] et al suggested a new one-dimensional multichannel convolutional neural network (1DMCCNN) for diagnosing failure scenarios to improve aviation hydraulic system reliability and safety.…”

Vehicular Sensor Network and Data Analytics for a Health and Usage Management System

“…Group D comprises model agnostic techniques suitable for aggregated analysis such as deep neural networks (DNN) [ 24 ], support vector machines (SVM) [ 25 ], hidden Markov models [ 26 ], and k-nearest neighbour classification [ 27 ]. Lastly, Group F include hybrid techniques that combine several model-based and/or data-driven approaches to compensate for the drawbacks in individual approaches, such as adaptive neuro-fuzzy inference systems (ANFIS) [ 28 ].…”