Air Transport Safety Research Articles

A Review of Aircraft Engine Fault Prediction and Performance Optimization Based on Deep Learning

This paper is aimed at presenting a systematic review of the recent studies on the use of deep learning techniques in aircraft engine health management for fault detection and performance enhancement. This comes in the light of increased growth in the air transport industry, the efficiency of aircraft engines and the efficiency of their maintenance have emerged as key issues in the safety and efficiency of air transport. This paper also identifies some of the key issues emerging from this area such as the data issues and the need to develop very accurate models for faulting and performance enhancement. Some of the most advanced techniques, namely the Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs) are discussed as potential solutions to these challenges. The theoretical descriptions of the working principles, as well as the strengths and weaknesses of the methods in question with regard to the problems of aircraft engine health management, are elaborated. Furthermore, this paper introduces the application of Reinforcement Learning as a new technique in the area of optimal control of engine parameters with the hope of improving the dependability and maintainability of aircraft engines and in the process of achieving sustainable growth in the aviation industry. The issues on model interpretability, model generalization and model deployment are also discussed and research guidelines for the future work in this field are also outlined. In this paper, the state of the art and the importance of deep learning as well as the applications of deep learning in aircraft engine health management are discussed based on the literature and case studies.

Vortex safety when flying at an assigned flight level

Air traffic intensity between countries and within individual countries is increasing year by year. As a rule, airways follow the same routes. As a result, so-called “roads in the sky” are formed. And where there are roads, there are bumps by the time, in the form of CAT, updraughts and downdraughts and increased turbulence. Horizontal and vertical separation plays an important role in ensuring flight safety on route. Currently, a variety of regulatory documents, defining safe separation at the flight level, has been adopted. Thus, provided there is turbulence in the vortex wake, longitudinal separation is based on the arrangement of aircraft types by three categories according to their maximum certified take-off weight. Since November 2011, the Western standard of vertical separation RVSM (Reduced Vertical Separation Minimum) has been introduced in Russia. Vertical separation is the distance between the vertical flight levels on route. Previously, this distance amounted to 600 m (2000 ft), but due to the increasing intensity of air traffic, it was decided to reduce the vertical separation to 300 m (1000 ft). Hence, at the most common flight level, the vertical separation is 300 m. The question arises if this separation ensures the safety of air transportation? The fact is that the altitude of the flight level does not necessarily coincide with the actual aircraft height. Aircraft altimeters are, inherently, calibrated barometers, that calculate the altitude by the difference in pressure on the ground and in the air. To calculate the height above ground, it would be necessary to constantly input atmospheric pressure data to altimeters at each waypoint and take into consideration the waypoint altitude above the sea level. Consequently, it is customary to use standard pressure. If the same pressure values are set on the altimeter on all aircraft, then, altitude readings on the instrument at an assigned point of airspace will be similar. Therefore, from a certain moment during the climb (transition level) to a certain moment during the descent (transition level), the aircraft height is calculated according to the standard pressure. The value of the standard pressure (QNE) is the same all over the world and amounts to 760 mmHg (1013.2 hectopascals). Thus, the flight on route is controlled by an altimeter, a barometric altimeter, which is comprised into the integrated flight and navigation system. An analysis of the instrument accuracy shows that when atmospheric pressure drops, altimeter readings may differ from true reading by ±100 m. It is known that a trailing vortex forms behind a flying plane. By the time, the trailing vortex descends and may be found at another flight level. May this cause air bump at the flight level? To answer this question, the A-380 aircraft was chosen as the object of research. This is one of the largest aircraft in the world. Therefore, the study of a trailing vortex behind the A-380 at the flight level, as the most dangerous in terms of the impact of its trailing vortex on other aircraft, will allow us to understand how safe and reasonable the accepted vertical and horizontal separation is. For the study, the special computational software system, based on the discrete vortex method, was used. This complex has passed the evaluation test and the state registration.

An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation

AbstractFour‐dimensional trajectory prediction is a crucial component of air traffic management, and its accuracy is closely related to the efficiency and safety of air transportation. Although long short‐term memory (LSTM) or its variants have been widely used in recent studies, they may produce unacceptable results in long‐term prediction due to the iterative output that accumulates error. To address this issue, a transformer‐based long‐term trajectory prediction model is proposed here, which utilizes the self‐attention mechanism to extract time series features from historical trajectory data. For long‐term prediction scenarios, we a trajectory stabilization module is introduced to ensure the stationarity of the time series for better predictability. Additionally, the transformer output strategy is improved to generate the prediction sequence by a single step instead of serial dynamic decoding, thus effectively enhancing the precision and inference speed. The proposed model is validated using real data obtained from China's Southwest Air Traffic Management Bureau. The experimental results demonstrate that this model outperforms the benchmark model. Further ablation experiments and visualizations are performed to analyze the impact of trajectory stabilization and one‐step inference strategy.

ANALYSIS OF CORRECTIVE MAINTENANCE MONITOR CCA TOOL DVOR SELEX TYPE-1150A

In the aviation industry, navigation has a crucial role in supporting the smooth running of flight routes to maintain the safety and security of air transportation. Perum LPPNPI Pekanbaru branch provides communication, Navigation, Surveillance, and Data Processing facilities to ensure flight safety, regularity, and comfort. One of the navigation facilities available at Perum LPPNPI Pekanbaru branch is the Doppler VHF-Omnidirectional Range (DVOR), an air navigation system control tool that can guide aircraft to land precisely at the destination airport by providing information in the form of azimuth or artificial bearing. This research aimed to analyze the care and maintenance system for DVOR equipment, and identify several potential problems that have arisen during the operation of DVOR equipment at Perum LPPNPI Pekanbaru branch. In this research, evaluations and observations were carried out to assess the level of DVOR maintenance in accordance with Advisory Circular CASR Part 171-12. This research focused on evaluating Corrective Maintenance Monitor (CMM) analysis on DVOR Selex Type-1150A equipment at Perum LPPNPI Pekanbaru Branch. DVOR is a critical air navigation system that requires effective corrective maintenance. The method used in the research is procedural analysis of equipment maintenance as in research conducted by Widasari Mutiara, this research also focused on CMM evaluation, identification of potential problems, and performance analysis to improve maintenance efficiency. Research adopted a qualitative research method with a descriptive approach, because the data collected is textual in nature. This research method involved CMM system inspection, equipment maintenance analysis, and interviews with engineering personnel. The research results provide insights for improving corrective maintenance procedures, and increasing the availability and reliability of the DVOR system. The implications of these findings support safe and reliable flight operations at Perum LPPNPI Pekanbaru Branch.

Green approach to alternative fuel for jet fuel quality issues in the perspective of decarbonization

The policy of decarbonization in the aviation industry is currently being implemented in most of the developed and developing countries throughout the world with some of the global systems being launched to encourage the use of renewable fuels rather than raw materials. However, while the prospect of electrification seems inevitable for the automotive industry, a fundamentally new aircraft is still yet to be introduced. To ensure the safety of air transportation, every new component is to undergo a vast variety of tests to verify that the properties of such component are in accordance with the set standards; even after the approval is received the component is subject to further studies to meet more stringent quality requirements. The objective of this study is to analyze the current fuel quality issues and the related impact on an increase in the share of biofuels in total jet fuel consumption. The study also shows the change in fundamental properties resulting by the increased percentage of renewable fuels in the composition and presents information on two groups of potential problems, namely problems, that may occur due to the fuel group composition changes, and problems related to technologies involved in raw materials processing.

Assessing economic performance and aviation accidents using zero-inflated and over-dispersed panel data models

This paper explores the link between air transport safety and profitability. Traditionally, the empirical literature has used Poisson regression models to estimate the expected number of accidents given the profitability of the airline. However, there are two major deficiencies in this analysis related to the statistical properties of the data. First, the equi-dispersion assumed in Poisson models hardly holds in the airline data. Second, accidents are rare cases, so the data has an excess of zeros. In this paper, we propose the use of a zero-inflated negative binomial model to deal with these shortcomings. Our results show several interesting facts. On the one hand, they show that airlines with higher levels of profitability are less likely to have an accident. On the other hand, when an accident occurs, there is a higher expected number of accidents in airlines with higher profitability. Finally, the severity of an accident has an inverse relationship with profitability.

Flight Technology Evaluation Based on Flight Parameters

Based on the flight safety, this paper develops a flight technology evaluation method based on the gradient boosting decision tree ( GBDT ) model by collecting and analyzing flight data. This method comprehensively considers flight parameters and provides a more accurate pilot flight technology assessment tool through the analysis of flight records. It is expected to improve the training plan and enhance the technical level of pilots to further improve the safety and sustainable development of air transportation. By introducing the deep learning network structure optimization evaluation method, the flight safety is further enhanced.

Developing conceptual model for safety risk management in aviation as building capacity and resilience strategy

Purpose This study aims to develop an inclusive, multidisciplinary, flexible and organizationally adaptable safety risk management framework, including diversity management, that will be implemented to ensure safety is and remains at the desired level. If the number of incidents and potential incidents that could lead to accidents and their impact rates are to be reduced operationally and administratively, aviation safety risks and sources of risk must be better understood, sources of risk identified, and the safety risk management framework designed in an organization-specific and organization-wide sustainable way. At this point, it is necessary to draw the conceptual framework well and to define the boundaries of the concepts well. In this study, a framework model that can be adapted to the organization is proposed to optimize the management of risks and provide both efficient and effective resource allocation and organizational structure design in its operations and management functions. Design/methodology/approach The qualitative research method – triple techniques – was deemed appropriate for this study, which aims to identify, examine, interpret and develop the situations of safety management models. In this context, document analysis, business process modeling technique and Delphi techniques from qualitative research methods were used via integration as the methodology of this research. Findings To manage dynamic civil aviation management activities and business processes effectively and efficiently, the risk management process is the building block of the “Proposed Process Model” that supports the decision-making processes of aviation organizations and managers. This “Framework Conceptual Model” building block also helps build capacity and resilience by enabling continuous development, organizational learning, and flexible structuring. Research limitations/implications This research is limited to air transportation and aviation safety management issues. This research is limited specifically to a safety-based risk management framework for the aviation industry. This research may have social implications as source saving, optimum resource use and capacity building will make a contribution to society and add value besides operational and practical implementation. Social implications This research may contribute to more safe operations and functions in the aviation industry. Originality/value Management and academia may gain considerable support from this research to manage their safety risks via a corporate-tailored risk management framework, both improving resilience and developing corporate capacity. With this model presented, decision-makers will have a guiding structure that can optimally manage the main risk types that may be encountered in the safety risk in the fields of suppliers, manufacturers, demand changes, logistics, information management, environmental, legal and regulatory. Existing studies in the literature are generally in the form of algorithms and cannot be used as a decision-making support tool. This model aims to fill the gap in the literature. In addition, added value may be created by applying this model to optimum management safety risks in the real aviation industry and its related sectors.

Safety of helicopter transport in patients with acute coronary syndrome.

ST-elevation myocardial infarction (STEMI) systems of care have reduced inter-hospital transfer times and facilitated timely reperfusion goals. Helicopters may be an option when land transportation is not feasible; however, the safety of air transport in patients with acute coronary syndrome (ACS) is a factor to consider. The aim of this study was to evaluate the safety of helicopter transport for patients with ACS. Prospective, observational, and descriptive study including patients diagnosed with ACS within the STEMI network of a metropolitan city transferred by helicopter to a large cardiovascular center to undergo percutaneous coronary intervention. The primary outcome of the study was the incidence of air-travel-related complications defined as IV dislodgement, hypoxia, arrhythmia, angina, anxiety, bleeding, and hypothermia. Secondary outcomes included the individual components of the primary outcome. A total of 106 patients were included in the study; the mean age was 54 years and 84.9% were male. The most frequent diagnosis was STEMI after successful fibrinolysis (51.8%), followed by STEMI with failed fibrinolysis (23.7%) and non-reperfused STEMI (9.4%). Five patients (4.7%) developed at least one complication: IV dislodgement (1.8%) and hypoxemia (1.8%) in two patients and an episode of angina during flight (0.9%). A flight altitude of > 10,000 ft was not associated with complications. The results of this study suggest that helicopter transportation is safe in patients undergoing acute coronary syndrome, despite the altitude of a metropolitan area.

Integrated safety for sea and air transportation during the COVID-19 pandemic

Climate change and COVID-19 have disrupted food supply chains and exacerbated food security challenges (Rasul, 2021). The safety of sea and air transportation in food delivery is also a disruption that impacts logistics in the food value chain (Singh et al., 2021). Integration of sea and air transportation safety during the COVID-19 pandemic, with a focus on the impact of climate change on food supplies and the rapid spread of viruses through air travel, is essential to ensure that food distribution is not disrupted. The research investigates the response of countries and major international organizations such as the World Health Organization (WHO), the International Maritime Organization (IMO), and the International Civil Aviation Organization (ICAO). The methodology used in the study was a systematic literature review (SLR) by identifying 875 journals in the first stage. Then, through strict screening, 50 articles were selected and further analyzed. Covering continents, specific countries, and important ports, the research uses quantitative databases such as the Scopus journal index. The study results reveal the long-term impact of the COVID-19 pandemic on the aviation and maritime sectors and its influence on global passenger and goods transportation. SLR’s findings also bring together insights from diverse research on safety integration across different modes of transportation during the pandemic. Research provides recommendations — climate-related changes for safe transportation, applicable in normal and pandemic circumstances. In conclusion, this article comprehensively explains maintaining a safe and efficient transportation network amidst complex challenges.

Глобальні економічні тренди авіаційних пасажирських перевезень

The relevance of the chosen issue is due to the fact that the rapid development of large-scale processes of transport globalization has led, on the one hand, to another restructuring of the aviation sector of national economies, but on the other hand, to the emergence of significant global risks (COVID-19, terrorism, territorial seizures, increased competition among major aviation companies, unprecedented consequences of air pollution, etc.). These and some other preconditions (including the rise in fuel prices) have contributed to the bankruptcy of individual airlines, both among large companies and those with only 3-4 aircraft at their disposal. In today's conditions, the positioning of the world's leading airlines within the three dominant aviation alliances, Sky Team, Star Alliance, and One World, has become increasingly important. The author has demonstrated that they have divided the global aviation space into three unequal parts and have taken dominant positions in world. The article substantiates the phenomenon of the rapid development of aviation transport leaders, particularly passenger airlines: American Airlines (USA), Delta Airlines (USA), Ryanair Group (Ireland), United Airlines (USA), Southwest Airlines (USA), Lufthansa Group (Germany). The article examines the systemic nature and features of the development of budget airlines (low-cost carriers), as well as leading Chinese and Arab airlines. The leading role and development prospects of aviation infrastructure (including global airports) in improving the quality, safety, reliability, and efficiency of passenger air transport are substantiated. The central role of airlines in organizing the tourism business and forming on this basis new forms of economic activity is determined. A graphic model of the development of air passenger transport for the period 2020–2040 has been developed. The important role of global and national institutions in regulating air transport (harmonization of the regulatory framework, networking of aviation space, global hybridization of transportation, etc.) is emphasized.

РАЗРАБОТКА МЕТОДИКИ ИДЕНТИФИКАЦИИ И РАЗРЕШЕНИЯ КОНФЛИКТНЫХ СИТУАЦИЙ ПРИ ОПЕРАТИВНОМ ПЛАНИРОВАНИИ ЧЕТЫРЕХМЕРНОЙ ТРАЕКТОРИИ ПОЛЕТА

Conflict detection and resolution is one of the key tasks in ensuring the safety and efficiency of air transport. In Trajectory Based Operation (TBO), aircraft are given greater flexibility in planning trajectories along the route and greater responsibility for self-separation from each other, so the pilot will need assistance to safely and efficiently perform the task of decentralized conflict resolution during the en-route flight. In this work, we develop a method for identifying and resolving conflict situations in cruising phase based on four-dimensional grid nodes (4D-grid) and the A-star shortest path search algorithm (A* for short) to form an optimal four-dimensional trajectory (4D-trajectory) bypass all airspace obstacles. This new approach helps to avoid false warnings about potential conflicts due to the ability to early detect them and accurately determine the distance from aircraft to areas of dangerous proximity (prohibited zones (PZ), zones of bad weather, other aircraft) and then autonomously form a time-spatial trajectory to bypass them. In order to demonstrate the effectiveness of the proposed method, we conduct three experiments in different airspace conditions (with and without the areas of dangerous proximity). The results of the experiments prove that potential dangerous proximities of aircraft in flight are effectively identified and resolved using the proposed methodology.

ОБНАРУЖЕНИЕ И ДЕМОДУЛЯЦИЯ СИГНАЛОВ С КОЭФФИЦИЕНТАМИ МОДУЛЯЦИИ БОЛЕЕ ЕДИНИЦЫ В ЗАДАЧАХ РАДИОМОНИТОРИНГА АВИАЦИОННЫХ ЛИНИЙ СВЯЗИ

Communication between an aircraft and ground services is the main means of organizing air traffic control and providing the safety and regularity of air transportation. In order to maintain the operability of radio communication channels is to perform radio monitoring. This article considers a radio monitoring algorithm. It makes possible to classify amplitude-modulated signals by modulation depth, to show the possibility of detection of overmodulated oscillations and to restore the initial information message with sufficient accuracy for its perception.

Оценка информационно-управляющего поля кабины пилотов с использованием нейронных сетей и методов

<p>The paper deals with the methodology of estimating the cockpit information and control field using indicators of oculomotor activity and a probabilistic neural network, which is used to calculate the final estimate of the considered display version. This methodology was tested on the universal prototyping bench basis with the participation of pilots. The using of this methodology contributes to the rapid and qualitative ergonomic assessment of the cockpit information and control field, which in turn increases the efficiency of human-machine interaction and, as a consequence, the safety of air transportation.</p>

A multi-objective memetic algorithm with adaptive local search for airspace complexity mitigation

Airspace complexity is a paramount safety metric to measure the difficulty and effort required to safely manage air traffic. The continuing growth in air traffic demand results in increasing airspace complexity and unprecedented safety concerns. Most existing methods treat the minimization of airspace complexity as the sole objective, ignoring the path deviation cost induced by the re-scheduled aircraft. In this paper, regarding reduction of airspace complexity and path deviation cost as two conflicting objectives, a multi-objective airspace complexity mitigation model is proposed to simultaneously ensure the safety and efficiency of air transport by optimizing flight trajectories. To effectively solve this multi-objective and non-linear optimization problem, a novel Memetic Algorithm with Adaptive Local Search (called MA-ALS) is developed. Specifically, we design a new crossover and three new local search operators under the flight trajectory representation. MA-ALS conducts exploration by crossover, and exploitation by a hill-climbing local search process. Moreover, we proposed an adaptive local search selection mechanism which facilitates the dynamic collaboration of different local search operators during evolution. A comprehensive comparison with the most recently developed algorithms on Chinese air traffic dataset is conducted. The Pareto front generated by the proposed algorithm dominates that of the compared baselines. Moreover, compared with a real flight schedule, the flight plan obtained by the proposed algorithm can significantly reduce the airspace complexity.

IDENTIFICATION OF THREATS AND RISK ASSESSMENT IN AIR TRANSPORT WITH THE USE OF SELECTED MODELS AND METHODS

Air transportation is one of the safest means of transport, but carrying out activities in the areaof aviation incident analysis still remains necessary. Proper assessment and analyses of incidentsmust be based on identification of hazards in the area. Safety hazards can occur in the airspace, onthe airport premises, and in the area of aircraft ground handling. The development of unmannedaircraft is also associated with the emergence of further safety hazards. Therefore, it is of greatimportance that available methods and tools be used to assess risks in each area. To this end, thereare a lot of available quantitative and qualitative methods for analysing air transport incidents. Animportant aspect is the analysis of aviation incidents, which can contribute to proactive measuresaimed at improving air transport safety. The paper presents selected aviation incident analysismethods and risk assessment tools.

Securing air transportation safety through identifying pilot's risky VFR flying behaviours: An EEG-based neurophysiological modelling using machine learning algorithms

Most general aviation accidents result from pilot errors while flying under visual flight rules (VFR), many of which are linked to situation awareness prone to meteorological and situational effects. This study reveals the impacts of weather and flight route factors contributing to unsafe flight behaviours on pilots’ performance (flight operation & neurophysiology). Importantly, another purpose is to identify risky flight behaviours by executing EEG-based neurophysiological modelling for securing air transportation safety. A two-by-two (adverse/clear weather; experienced/inexperienced flight route) within-subject experiment was conducted. Inexperienced flight routes have an explicit impact on contributing to unsafe flight operations except during departure and descent. However, the neurophysiological activity in power spectrum density and cooperative correlation showed that meteorology deterioration may require more mental efforts and have an implicit impact on maintaining safe flight awareness, making it challenging to correct risky flight operations due to mental resource exhaustion possibly. For the pilot's risky behaviour identification, neurophysiological modelling using EEG data was established, and a leave-one-subject-out cross-validation was used to evaluate the modelling feasibility, with the highest accuracy of 80.8%. This work could serve as the foundation for developing a real-time risky flight behaviour prediction modelling that could support safety-enhancing air transportation via artificial intelligence.

Air Traffic Safety Assurance Based on Flight Plan Risk Assessment and Early Warning

This article presents a novel risk assessment method for aircraft flight plans in a four-dimensional trajectory-based operation background. With the increasing air transport volume and airspace demand and during the allocation and modification of flight plans, safety should also be considered in addition to economic benefits and competitiveness. By employing the time geography concept, this article first quantifies the space-time accessibility and estimates the visiting probability of aircraft in the four-dimensional trajectory-based operation context. On this basis, this article studies the method and process to evaluate the conflict risk between one flight plan and a special airspace, the weather-influenced airspace, and another flight plan. This article also proposes the conflict risk alerting strategy. The achievements of the study are expected to provide assistance for air traffic controllers in strategic conflict avoidance and are of great significance in assuring air transport safety.

Holistic Approach to Ensuring Safety and Cybersecurity in the Use of Intelligent Technologies in Air Transport

The article is devoted to the study and analysis of the problems associated with the use of intelligent technologies in air transport security and cybersecurity issues. Possible dangers that may arise when using autonomous systems, including autonomous aircraft, are considered. The technical measures that can be taken to prevent these dangers, including the development of new methods of cybersecurity and protection against hacker attacks, are analyzed. The problem of ensuring security in air transport associated with the introduction of new technologies and automated systems is investigated. The risks associated with this process are described, such as possible aircraft accidents, data storage problems, and passenger safety issues. Technical measures that can be taken to ensure safety in air transport, including the development of new technologies and diagnostic methods that can detect possible problems before they become serious, are considered. Practical solutions to these problems are proposed, including the development of new security and cybersecurity systems that can be used in air transport. The technical measures that can be taken to ensure the safety and efficiency of the use of intelligent technologies in air transport are described. It is established that the developed simulation model can serve as an effective tool for managing the processes of aircraft ground handling at the airport, as well as allow predicting the results of such processes and developing algorithms for the rational allocation of resources, considering the functioning of the system in different modes. To ensure the efficient functioning of the aircraft ground handling system, it is proposed to implement technical measures to improve cybersecurity and ensure the system's resilience to possible cyberattacks.

Air transport safety in UAV operational conditions

The article presents the possibilities of using unmanned aerial vehicles in air transport. The use of UAVs in the airspace has become widespread, despite many implemented legal regulations, there are many incidents that threaten not only aircraft during the flight, but also the airport infrastructure. The potential threats and the chances of implementing remedial measures were analyzed. An attempt to evaluate the possibility of maintaining aviation safety at an appropriate level in the conditions of UAV operational conditions has been done. The main research problem was defined as follows: How would implementing unmanned aerial vehicles into the air transport system influence the acceptable level of safety? The article uses theoretical methods such as: system analysis, analysis and synthesis in the field of literature, analogy, comparative method. In terms of empirical methods, an original diagnostic survey was carried out, based on a selected group of people related to the explored topic. In addition, the observation method was used by the feedbacks and observations of the group of air traffic controllers from civil airports (located in Poland). The article describes the current transformation of air transport, taking into account the planned modernizations. It presents the PansaUTM system as one of the countermeasures, monitoring and securing the movement in the airspace. Furthermore, the transponder issue was raised in relation to the enhancement of the UAV identification system, with a detailed explanation of the importance of the TCAS (Traffic Collision Avoidance System). Referring to the prospects for the development of air transport, the latest design concepts for cargo drones were presented. The issue of full transport autonomy of UAVs was analyzed based on the requirements of legal regulations. The comparison of benefits and threats in conjunction with the conducted empirical methods allowed for the development of conclusions confirming the research hypothesis and indicating the possibility of using remedial measures in the process of UAV evolution.