Aircraft Fuel System Research Articles

Intelligent Multi-Fault Diagnosis for a Simplified Aircraft Fuel System

Machine learning (ML) techniques are increasingly used to diagnose faults in aerospace applications, but diagnosing multiple faults in aircraft fuel systems (AFSs) remains challenging due to complex component interactions. This paper evaluates the accuracy and introduces an innovative approach to quantify and compare the interpretability of four ML classification methods—artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs), and logistic regressions (LRs)—for diagnosing fault combinations present in AFSs. While the ANN achieved the highest diagnostic accuracy at 90%, surpassing other methods, its interpretability was limited. By contrast, the decision tree model showed an 82% consistency between global explanations and engineering insights, highlighting its advantage in interpretability despite the lower accuracy. Interpretability was assessed using two widely accepted tools, LIME and SHAP, alongside engineering understanding. These findings underscore a trade-off between prediction accuracy and interpretability, which is critical for trust in ML applications in aerospace. Although an ANN can deliver high diagnostic accuracy, a decision tree offers more transparent results, facilitating better alignment with engineering expectations even at a slight cost to accuracy.

Integration of a Model-Based Systems Engineering Framework with Safety Assessment for Early Design Phases: A Case Study for Hydrogen-Based Aircraft Fuel System Architecting

Integration of a Model-Based Systems Engineering Framework with Safety Assessment for Early Design Phases: A Case Study for Hydrogen-Based Aircraft Fuel System Architecting

Hexagon, Nikon and Airbus Collaborate to Create Lightweight Aircraft Fuel System

Hexagon, Nikon and Airbus Collaborate to Create Lightweight Aircraft Fuel System

How Often Should Microbial Contamination Be Detected in Aircraft Fuel Systems? An Experimental Test of Aluminum Alloy Corrosion Induced by Sulfate-Reducing Bacteria.

Microbial contamination in aircraft fuel-containing systems poses significant threats to flight safety and operational integrity as a result of microbiologically influenced corrosion (MIC). Regular monitoring for microbial contamination in these fuel systems is essential for mitigating MIC risks. However, the frequency of monitoring remains a challenge due to the complex environmental conditions encountered in fuel systems. To investigate the impact of environmental variables such as water content, oxygen levels, and temperature on the MIC of aluminum alloy in aircraft fuel systems, orthogonal experiments with various combinations of these variables were conducted in the presence of sulfate-reducing bacteria. Among these variables, water content in the fuel oil demonstrated the most substantial influence on the corrosion rate of aluminum alloys, surpassing the effects of oxygen and temperature. Notably, the corrosion rate of aluminum alloys was the highest in an environment characterized by a 1:1 water/oil ratio, 0% oxygen, and a temperature of 35 °C. Within this challenging environment, conducive to accelerated corrosion, changes in the corrosion behavior of aluminum alloys over time were analyzed to identify the time point at which MIC intensified. Observations revealed a marked increase in the depth and width of corrosion pits, as well as in the corrosion weight-loss rate, starting from the 7th day. These findings offer valuable insights for determining the optimal frequency of microbial contamination detection in aircraft fuel systems.

Health Management of Aircraft Fuel Systems: A Practical Prognostic Perspective

Aircraft health management, specifically pertaining to fuel systems, is a comprehensive process that is undertaken to ensure the continuous airworthiness of the aircraft over its entire lifespan. The integration of health management into aircraft systems requires a methodical strategy to quantitatively evaluate the possible advantages provided by each specific application. Gaining a thorough comprehension of the advantages linked to integrated health management systems provides useful insights for enhancing the design of these systems and formulating efficient prognostic techniques. The role of prognosis in the field of prognostics and health management (PHM) is essential for improving the dependability of systems. Prognosis involves accurately predicting the remaining useful life (RUL) within the domain of integrated health management. This study improves the precision of prediction results, optimises the derived prerequisites for health management in the specialised field of RUL prediction for aircraft fuel systems, provides a thorough understanding, and advances the grasp of the previously described requirements in a more effective way. Additionally, it presents the most suitable solutions in order to address these demands by utilising prognostic techniques. Furthermore, this study presents an analysis of the proposed hybrid prognostic approach in the setting of controlled laboratory conditions. The applications encompassed in this work consist of three main areas. Firstly, the evaluation of inspection interval modifications is conducted by taking into account load and environmental monitoring data. Secondly, design considerations for damage prognostics are incorporated into the analysis. Lastly, a design modification is presented as an example of how condition-based maintenance (CBM) can be facilitated. A methodology that enables the efficient and well-founded construction of a health management system, specifically designed for aircraft fuel systems, is presented. This methodology, together with its associated outcomes, presents a compelling advantage in terms of lowering life cycle expenses while simultaneously enhancing availability, dependability, and performance.

Study on Hot Weather Operation Flight Test of Civil Aircraft Fuel System

Abstract As one of the important on-board systems of an airplane, the fuel system of a civil aircraft mainly supplies fuel to the engine and APU of the aircraft, and it is necessary to ensure that the pressure and flow rate of the fuel supply meets the needs of the engine and APU under each kind of probable operating conditions. This paper studies the specific requirements of the airworthiness regulations for the fuel system to work under hot climate conditions. At the same time, it explores how to show the compliance of the fuel system with the airworthiness regulations through the flight test method, which covers the determination of the flight test parameters, the control of the hot fuel temperature, the test modification, the implementation of the flight test mission and the analysis of the results. This paper provides a reference for the implementation of the hot weather operation of similar types of aircraft fuel systems.

Optimization of Aircraft Fuel Systems Considering Fluid Dynamics Principles

The fuel system is the lifeline of any aircraft, pivotal for its operation and future advancements. This study delves into aircraft fuel system design methodologies, aiming to streamline development processes. Through optimization and matrix methods like the morphological matrix, Saab Aerospace pioneer’s conceptual designs. These methods automate development and deepen our understanding of how top-level requirements impact engineering details. Quantifying matrices opens doors to design optimization and probabilistic design. Furthermore, a systematic approach to simulation modeling minimizes development time, leveraging parallel development and collaborative engineering. With stakeholder expectations in mind, experience gleaned from projects like the Gripen fuel system shapes an overarching process for future endeavors. This journey promises to reshape aircraft fuel system design, ensuring each drop of fuel propels us towards boundless horizons. Key Words: Aerospace engineering, Fuel system, Optimization techniques, Matrix methods, Simulation models, Conceptual design, System integration, Aircraft performance, Fuel tank configurations, Operational flexibility, Gripen Fuel, DSM- Design Structure Matrix

Design and Build of Electronic-Based Cessna 172 Aircraft Fuel System Simulator

Airplanes need a system that can control the distribution of fuel in each operation so that the resulting fuel supply is stable. Based on the research results of Edgar Dale (1969), 90% of a person has the ability to absorb objects of knowledge by doing.This final project discusses the design and manufacture of a fuel flow simulator for an aircraft fuel system using LED lights as a substitute for fuel. This final project aims to design and create a fuel flow simulator for an aircraft fuel system as an alternative learning medium. There are two methods used in completing this Final Project, namely analytical and experimental methods which consist of several stages including problem identification, data collection, tool design, tool design, and tool testing.The results showed that with the Design and Build of the Electronic-Based Cessna 172 Aircraft Fuel System Simulator, where the value of cadets when learning using simulation tools has increased compared to without using tools. Itcan be concluded that this fuel system simulation tool can scientifically increasethe value and understanding of cadets, especially material about fuel systems.

Intelligent Fault Diagnosis of an Aircraft Fuel System Using Machine Learning—A Literature Review

The fuel system, which aims to provide sufficient fuel to the engine to maintain thrust and power, is one of the most critical systems in the aircraft. However, possible degradation modes, such as leakage and blockage, can lead to component failure, affect performance, and even cause serious accidents. As an advanced maintenance strategy, Condition Based Maintenance (CBM) can provide effective coverage, by combining state-of-the-art sensors with data acquisition and analysis techniques to guide maintenance before the asset’s degradation becomes serious. Artificial Intelligence (AI), particularly machine learning (ML), has proved effective in supporting CBM, for analyzing data and generating predictions regarding the asset’s health condition, thus influencing maintenance plans. However, from an engineering perspective, the output of ML algorithms, usually in the form of data-driven neural networks, has come into question in practice, as it can be non-intuitive and lacks the ability to provide unambiguous engineering signals to maintainers, making it difficult to trust. Engineers are interested in a deterministic decision-making process and how it is being revealed; algorithms should be able to certify and convince engineers to approve recommended actions. Explainable AI (XAI) has emerged as a potential solution, providing some of the logic on how the output is derived from the input given, which may help users understand the diagnostic result of the algorithm. In order to inspire and advise data scientists and engineers who are about to develop and use AI approaches in fuel systems, this paper explores the literature of experiment, simulation, and AI-based diagnostics for the fuel system to make an informed statement as to the progress that has been made in intelligent fault diagnostics for fuel systems, emphasizing the necessity of giving unambiguous engineering signals to maintainers, as well as highlighting potential areas for future research.

Test Procedure for Aircraft Fuel Systems in the Case of a Lightning Strike

Test Procedure for Aircraft Fuel Systems in the Case of a Lightning Strike

Numerical Study on Pipeline Pressure Surge of the Large Aircraft Fuel System

The sudden closure of the refueling valve during the refueling process will cause the water hammer phenomenon in the pipeline of the large aircraft fuel system and produce pressure waves propagating along the pipeline. In serious cases, it will cause severe damage to the pipeline. The pressure surge in the pipeline can be affected by many design factors. In this study, the numerical modeling method of the large aircraft fuel system is studied using the Flowmaster program, and the accuracy of steady and transient state analysis of the simulation method is verified by experimental data. Based on this numerical method, a complete system-level simulation model of the large aircraft fuel system was established. Using this model, the effects of valve closure speed, diameter of the refueling main pipe, and refueling volume flow rate on pipeline pressure surge during the refueling process are investigated. The results indicate that all three factors have a significant impact on the pipeline pressure surge of the fuel system. The effect of the valve closing speed and the pipe diameter on the pressure surge of the pipeline is nonlinear and gradually weakened with the decrease of valve speed and the increase of pipe diameter, while the effect of refueling volume flow rate on the pipeline pressure surge is approximately linear.

Efficiency of Didecyl Dimethyl Ammonium Chloride as a Microbial Corrosion Inhibitor for 7b04 Aluminum Alloy in an Aircraft Fuel System

Efficiency of Didecyl Dimethyl Ammonium Chloride as a Microbial Corrosion Inhibitor for 7b04 Aluminum Alloy in an Aircraft Fuel System

Analysis and Experimental of Valve Closing Characteristics of Aircraft Fuel System

Analysis and Experimental of Valve Closing Characteristics of Aircraft Fuel System

The Research of Aircraft Fuel System Icing Test

When a civil aircraft is flying in high altitude and low temperature environment, once the fuel feed system freezes, the fuel pressure and flow of engine and APU will decrease, resulting in the loss of aircraft power and even the occurrence of flight accidents. In this paper, the icing test platform of aircraft fuel system is set up, the test configuration and measurement system design method are given. By carrying out icing test of a certain type of fuel system, the test results show the safety and rationality of the aircraft fuel system design and test rig design, so as to provide guidance and reference for the implementation of icing test of aircraft fuel system.

Utilization of Low-Potential Energy Through to the Use in Aircraft Fuel System

The article discusses the possibility of improving the main characteristics (efficiency, specific thrust) of a gas turbine engine by using liquefied natural gas (LNG) as fuel. This possibility is considered on the example of using as fuel instead of aviation kerosene on PS-90A and NK-93 engines. The parameters of the engine were determined at various stages in the cruise flight mode when operating on kerosene and LNG. The parameters evaluating the fuel consumption of the engine are calculated and compared for both fuels. The performance characteristics for kerosene and LNG were evaluated in the system of the Tu-330 subsonic transport aircraft. Energy losses during storage of cryogenic fuel on board the aircraft are estimated.

Application Research of Oil Quantity Measurement on Ground Simulation Table of Aircraft Fuel System Based on Computer Test

Application Research of Oil Quantity Measurement on Ground Simulation Table of Aircraft Fuel System Based on Computer Test

Fault Detection for Aircraft Fuel System with Neural Network

The technological advances in the aircraft industry in the last decade have increased the complexity of aircraft systems. This, in turn, makes the fault detection, diagnosis and modification/ repair processes more difficult. The presence of a fault within a system can result in changes to system function, reduce system performance and cause operational downtime. Due to this reason Condition Based Maintenance (CBM) which predicts the state of the component on based upon data gathered is widely used in aircraft MRO industries. CBM uses diagnostics and prognostics models to make decisions on appropriates maintenance actions based upon the remaining used life (RUL) of the components. In this research, we applied a Neural Network model to solve the fault detection problem, and the experimental results demonstrated the neural network model can obtain excellent performance. Fault diagnosis is a more complicated problem, and it requires diagnosing the type of fault. Therefore, fault diagnosis becomes a classification problem. More importantly, the fault state of a fuel system may relate to the previous state of the fuel system. Therefore, a Recurrent Neural Network model could be developed for fault diagnosis.

A Feasibility Study on the Implementation of Visibility Algorithms for Fault Diagnosis in Aircraft Fuel Systems

This paper discusses the applicability of Visibility Algorithms to detect faults in condition monitoring applications. The general purpose of Visibility Algorithms is to transform time series into graphs and study them through the characterization of their associated network. Degradation of a component results in changes to the network. This technique has been applied using a test rig of an aircraft fuel system to show that there is a correlation between the values of key metrics of visibility graphs and the severity of four failure modes. We compare the results of using Horizontal Visibility algorithms against Natural Visibility algorithms. The results also show how the Kullback-Leibler divergence and statistical entropy can be used to produce condition indicators. Experimental results show that there is little dispersion in the values of condition indicators, leading to a low probability of false positives and false negatives.

Comparison of ANFIS and ANN Techniques in the Simulation of a Typical Aircraft Fuel System Health Management

Comparison of ANFIS and ANN Techniques in the Simulation of a Typical Aircraft Fuel System Health Management

기계학습을 활용한 항공기 연료 시스템 무결성 감시

항공기 연료 시스템은 핵심적인 항공기의 전자, 기계적 시스템 중 하나로서 안전한 비행을 위해 연료 시스템의 신뢰성은 무엇보다 중요하지만, 현대의 항공기는 최첨단 기술과 장비의 탑재에도 불구하고 단순 결함 및 조종사 또는 정비사의 부주의만으로도 여전히 많은 사고가 발생하고 있다. 이에, 본 논문에서는 높은 신뢰성이 보장되어야 하는 항공기 연료 시스템의 오류로 인한 사고 발생을 사전에 방지하기 위해 항공기 연료 소모량 예측을 통한 무결성 감시 기법을 제안하였다. 신경망을 기반으로 한 항공기 연료 소모량 예측 알고리즘은 Levenberg Marquardt을 기반으로 학습하였으며, B747 항공기 데이터를 활용한 모의시험을 통해 기존 항공기연료 소모량 모델과 비교 평가하였다. 그 결과, 간섭 노드(속도, 고도)와 무관하게 제안된 잡음 환경의 모의시험에서 예측 시스템은 기존 모델 대비 전 구간에 걸쳐 20~30% 이상 높은 잡음 강인성을 확인할 수 있었다.