Airline Operations Research Articles

Multiclass Multiple-Instance Learning for Predicting Precursors to Aviation Safety Events

In recent years, there has been a rapid growth in applying machine learning techniques that leverage aviation data collected from commercial airline operations to improve safety. Anomaly detection and predictive maintenance have been the main targets for machine learning applications. However, this paper focuses on the identification of precursors, which is a relatively newer application. Precursors are events correlated with adverse events that happen before the adverse event itself. Therefore, precursor mining provides many benefits, including the identification of factors relevant to the occurrence of an adverse event and their signatures, which can be tracked throughout a flight to alert the operators of the potential for an adverse event in the future. This work proposes using the multiple-instance learning framework, a weakly supervised learning task, combined with a carefully designed binary classifier leveraging a Multi-Head Convolutional Neural Network–Recurrent Neural Network (MHCNN-RNN) architecture. Multiclass classifiers are then created and compared, enabling the prediction of different adverse events for any given flight by combining binary classifiers, and by modifying the MHCNN-RNN to handle multiple outputs. Results obtained showed that the multiple binary classifiers perform better and are able to accurately forecast high-speed and high-path-angle events during the approach phase. Multiple binary classifiers are also capable of determining the aircraft parameters that are correlated to these events. The identified parameters can be considered precursors to the events and may be studied/tracked further to prevent these events in the future.

Hierarchical integrated machine learning model for predicting flight departure delays and duration in series

Flight delays may propagate through the entire aviation network and are becoming an important research topic. This paper proposes a novel hierarchical integrated machine learning model for predicting flight departure delays and duration in series rather than in parallel to avoid ambiguity in decision making. The paper analyses the proposed model using various machine learning algorithms in combination with different sampling techniques. The highly noisy, unbalanced, dispersed, and skewed historical high dimensional data provided by an international airline operating in Hong Kong was used to demonstrate the practical application of the model. The result shows that for a 4-h forecast horizon, a constructive neural network machine learning algorithm with the Synthetic Minority Over Sampling Technique-Tomek Links (SMOTETomek) sampling technique was able to achieve better average balanced recall accuracies of 65.5%, 61.5%, 59% for classifying delay status and predicting delay duration at thresholds of 60 min and 30 min, respectively. Similarly, for minority labels, the precision-recall and area under the curve showed that the proposed model achieved better results of 32.44% and 35.14% compared to the parallel model of 26.43% and 21.02% for thresholds of 60 min and 30 min, respectively. The effect of different sampling techniques, sampling approaches, and estimation mechanisms on prediction performance is also studied.

Two-Phase Heuristic Algorithm for Integrated Airline Fleet Assignment and Routing Problem

High profitability and high costs have stiffened competition in the airline industry. The main purpose of the study is to propose a computationally efficient algorithm for integrated fleet assignments and aircraft routing problems for a real-case hub and spoke airline planning problem. The economic concerns of airline operations have led to the need for minimising costs and increasing the ability to meet rising demands. Since fleets are the most limited and valuable assets of airline carriers, the allocation of aircraft to scheduled flights directly affects profitability/market share. The airline fleet assignment problem (AFAP) addresses the assignment of aircraft, each with a different capacity, capability, availability, and requirement, to a given flight schedule. This study proposes a mathematical model and heuristic method for solving a real-life airline fleet assignment and aircraft routing problem. We generate a set of problem instances based on real data and conduct a computational experiment to assess the performance of the proposed algorithm. The numerical study and experimental results indicate that the heuristic algorithm provides optimal solutions for the integrated fleet assignment and aircraft routing problem. Furthermore, a computational study reveals that compared with the heuristic method, solving the mathematical model takes significantly longer to execute.

Estimating fuel-efficiency while accounting for dynamic fleet management: Testing the effects of fuel price signals and fleet rollover

Fuel efficiency has become one of the most important policy goals for airline operations management. This study develops an econometric model to estimate airlines’ fuel burn determinants, aiming to test the hypothesis of fuel price signals on carriers’ incentives for energy-saving efforts. We propose a novel high-dimensional sparse IV-LASSO method to account for airline dynamic fleet management. Our model also provides controls for thousands of nuisance factors related to route direction, airway congestion, and aircraft model specificities, allowing for flexible time-varying unobserved effects of flight stages. The results show that energy intensity reduction induced by price increases was observed 3–4 years earlier, possibly due to fleet rollover and fleet modernization. Furthermore, although new competition may create incentives for improved fuel management to control costs, our results suggest that the overall effect of market deconcentration is unclear and may produce the unintended consequence of worse performance, as measured in some key fuel efficiency dimensions.

Developing prescriptive maintenance strategies in the aviation industry based on a discrete-event simulation framework for post-prognostics decision making

The aviation industry is facing an ever-increasing competition to lower its operating cost. Simultaneously, new factors, such as sustainability and customer experience, become more important to differentiate from competitors. As aircraft maintenance contributes about 20% to the overall cost of airline operations and can significantly influence other objectives of an airline as well, maintenance providers are required to constantly lower their cost share and contribute to a more reliable and sustainable aircraft operation. Subsequently, new condition-monitoring technologies have emerged that are expected to improve maintenance operations by reducing cost and increasing the aircraft’s availability. As many of these technologies are still in their technological infancy, it is necessary to determine the expected benefit for the airline operations with the given technological maturity and to develop suitable maintenance strategies that incorporate the newly gained insights. With this paper, a discrete-event simulation framework is developed that uses established parameters to describe a condition-monitoring technology’s performance and subsequently develops a suitable prescriptive maintenance strategy. Therefore, it enables the adjustment of the optimization goal for the developed strategy to incorporate performance features beyond the frequently used financial indicators. The developed capabilities will be demonstrated for the tire pressure measurement task of an Airbus A320.

Estimating runway veer-off risk using a Bayesian network with flight data

Risk assessments in airline operations are mostly qualitative, despite abundant data from programmes such as flight data monitoring (FDM) and flight operations quality assurance (FOQA). In this paper, features relating to runway excursion causal factors are extracted from flight data from over 310,448 flights from Airbus A320 series aircraft flown on a European network. The data is combined with meteorological data to provide additional features.Bayesian networks are then learnt from the feature set, and two network learning algorithms are compared, Bayesian Search and Greedy Thick Thinning (GTT). Cross-validation of the resulting networks shows both algorithms produce similarly performing networks, and a subjective analysis concludes that the GTT algorithm is marginally preferred.The resulting networks produce relative probabilities, which airlines can use to quantitatively assess runway veer-off risk under different scenarios, such as different meteorological conditions and unstable approaches.This paper's main finding is that by utilising existing data sources, such as FDM and weather databases, airlines can create and use Bayesian networks alongside their existing qualitative risk assessment methods to provide quantitative risk assessment and understand the effect of different conditions on those risks. This is not possible with current methods in use by airlines.The method described can be extended to other operational safety risks, such as runway overrun.

Airline unit load device dispatch and scale in short-term operations involving skypooling – A new sharing economy in airline industry

The skypooling is a free platform for the sharing of unit load devices (ULD), which contributes a new sharing economy by allowing airlines to exchange ULDs and coordinate ULD delivery services. The akypooling aids airlines to match their requirements for the two ULD sharing operations. However, such matching is not always successful. The matching success rate naturally affects skypooling performance and generates a gap between the expected and available numbers of ULDs for the two ULD sharing operations. We design two achievement rates for ULD sharing operations, which represent the likelihood of meeting ULD dispatch requirements in actual operations, as well as devising. We develop a novel ULD sharing model and a solution algorithm to handle the problem. The model is developed by combining the network technique utilized in Operations Research with the binomial distribution utilized in Statistics. The solution algorithm comprises a three-stage iterative evolutionary process. We obtain that the carrier decrease the number of ULDs utilized each week by 7% by the two ULD sharing operations. Different instances exemplifying optimistic, normal, and pessimistic situations are examined to understand the ultimate implications and applications of the new technique for airline operations.

Passengers’ perception of safety and its relationship with demographics, service quality, satisfaction and loyalty in airlines sector - A case study of Vietnam to Australia route

Our understanding of airline passengers' perception of safety and its association with their satisfaction and airline service quality measures is limited in the literature. This study aims to conduct a systematic examination of airline passengers’ perception of safety and its association with demographics attributes, service quality measures, overall satisfaction and loyalty by using Vietnam to Australia route as a case study.We conducted a questionnaire survey of 436 respondents travelling on a full-service airline flying from Vietnam to Australia. Only 53.4% of respondents feel safe while travelling in the airline while 28.9% feel neutral safe and 17.7% feel unsafe. We found that the four service quality measures of SERVQUAL model (Tangibles, Reliability, Assurance and Empathy) and airline specific measures (Flight Experience, Ground Service, Airline Employees and Flight Schedule) had significant effects on the passengers' perception of safety. Also, respondents' differences in educational qualification, frequency of travel, ticket types and the membership of frequent flyer program (FFP) had a significant effect on their perception of safety. Likewise, passengers’ overall satisfaction and loyalty to the airline also had a significant effect on the perception of safety. No effects on the perception of safety were found for differences in gender, age, nationality, income and purpose of travel.Although all airlines flying in and out of Australia must meet Australia's Safety Management System regulations and requirements, our findings emphasize the importance of understanding the relationship between passengers' perception of safety and their satisfaction. There is an opportunity for the airline operator to secure a lead in the market share of air travel by improving service quality measures that can influence passengers' perception of safety.

DEVELOPMENT AND ANALYSIS OF 2D FLIGHT PLANNING SEARCH ENGINE CONSIDERING FUSION OF SWIM DATA

Flight planning is one of the essential factors of the airline operation. The selection of routes will determine the economic value of the flight. However, some conditions may prevent the flight to use the most optimum route due to airspace restriction or weather condition. The research aims to develop a search engine program that uses dynamic flight parameters that considers fusion of System Wide Information Management (SWIM) data including weather data and NOTAM to produce the most optimum route in 2D flight planning. The Dijkstra’s pathfinding is implemented in Python programming language to produce the flight plan. The navigation data used is enroute airway in Indonesian FIR regions. The scenario used is a flight from Jakarta to Makassar with duration of 2 hours flight with considering the effect of restricted airspace and weather blockage during in-flight. The study also uses the optimum route produced by the algorithm to be compared with the possible alternate routes to define how optimum the route is. Adding a restricted airspace parameter will result in a new optimum flight plan that able avoids the airspace and the most minimum distance. The effect of external wind parameter could influence the optimum route which may vary depends on the speed of the wind.

Preface

The Proceedings of the 4th International Conference on Aeronautical, Aerospace and Mechanical Engineering (AAME 2021) contain the scholarly papers presented during a virtual conference on 26-28 February, 2021. The designated physical conference venue was Sanya, China. The AAME series of conferences have been held in different parts of the world for the last three years already. This year (2021), due to COVID-19 restrictions, the conference was held online.The AAME 20201 conference has attracted more than 30 participants from renowned universities in Australia, Japan, Singapore, Russia, Egypt, South Africa, Malaysia and China. Together with the assistance of the International Technical Committee, which is formed by members from universities and research organisations around the world, the conference attracted many submissions of high quality papers. The papers accepted in these proceedings have passed the vigorous review process and amended to the satisfaction of reviewers. The online conference serves to provide the opportunity for the audience to raise critiques and comments on the presentations. It is on this basis that these proceedings are good references to future research investigations and publications.The proceedings have Six sections. Each section has 5 to 8 papers related to a topic. Section 1 and 2 (Mechanical Design and Manufacturing Technology) has 10 papers in total on machine tools, special products 3D printing and new processes. Study of materials properties is essential to develop efficient machining and formation processes for cost effective manufacturing. The 10 papers cover broad industrial level research to improve effectiveness and efficiency of manufacturing.Section 3 (Power Machinery and Engineering) has 6 papers focusing on mechanical power applications. The broad application areas in machinery and its design are highlighted in the short conference version of the papers. Authors have applied relevant computational and experimental analysis techniques demonstrating close relationship between theory and practice.Section 4 (Modern Electronics and Information Engineering) has 6 papers related to more fundamental treatment of aerodynamics, acoustics, heating and cooling phenomena. These studies have many immediately viable industry applications in aircraft electronics, satellite operations, noise control and so on. The papers have presented valuable experimental data supporting future electronic and information engineering in aeronautics and astronautics scientific fields.Section 5 (Supersonic Flow and Fluid Mechanics) has 5 papers on mechanics and properties of polymer materials and their applications to space vehicles, aircraft structures, high flow environment. Computational approaches such as computational fluid dynamics, finite element analysis, large body simulation are used to analyse some of the most complex microstructures in the materials thereby contributing to knowledge in the fields of liquid and applied mechanics.Section 6 (Aerospace Science and Transportation Engineering) has 8 papers closely related to aircraft design, airline operations, flight control. These researches have advanced understanding of their respective engineering disciplines and in many respects, fill the gap of understanding of the aerospace systems so as to improve their reliability and quality.The variety of research topics presented in the AAME 2021 conference and novelty exhibited in the papers published in these proceedings once again demonstrated the value of the online conference enabling researchers of different nationalities and different engineering fields to participate in a live research conversation. I would like to thank the conference committee, the conference secretariat, keynote speakers and all participants for their hard work making the AAME 2021 conference a success as well as publishing a valuable knowledge literature contributing to state-of-the-art developments in aeronautical, aerospace and mechanical engineering.John P.T. MoProfessor of Manufacturing EngineeringBSc(Engg), MSc(Engg), PhD(Loughborough), FIEAust CPEng NER APEC Engineer IntPE(Aus),CEng, FIMechE, MHKIE, MFIESchool of EngineeringRMIT UniversityEmail: john.mo@rmit.edu.auMarch 2021, Melbourne, AustraliaList of Conference Committees are available in this pdf.

The best practice of marketing strategies for the Malaysian business event industry from experts' perspective

PurposeThis paper aims to explore the best practices in marketing strategies for the Malaysian business event industry.Design/methodology/approachA qualitative methodology was adopted to collect primary data from semi-structured interviews. The informants included ten experts from the Malaysian business event industry. The data collected were then grouped using the ATLAS.ti (v.8) software for thematic analysis. A trustworthiness assessment was applied to increase the credibility and ensure the rigour of the qualitative findings.FindingsThe qualitative results revealed the following final themes: event marketing, the marketing plan, the 7 Ps of the marketing mix, strength, weaknesses, opportunities and threats (SWOT) analysis and traditional and digital marketing. Interestingly, three inductive themes were also emerged as follows: relationship marketing, unique selling points (USPs) and key opinion leaders.Research limitations/implicationsThis study looked at Malaysian business events and focused only on findings from the industry expert's perspective. In the future, further investigation may concentrate on other business event industry players such as destination marketing companies, airline operators, travel intermediaries, clients, suppliers, universities and the government.Practical implicationsThe findings offer a holistic approach to increase Malaysia's competitiveness among other primary business event host destinations in the Asian-Pacific, improve its worldwide and Asian-Pacific rankings and better position the country as a preferred business event destination during the coronavirus disease 2019 (COVID-19) pandemic.Originality/valueThis is the first such study to date, which has never been explored in qualitative academic research. This study has substantial implications for various business event industry stakeholders in Malaysia.

Concept and Economic Evaluation of Prescriptive Maintenance Strategies for an Automated Condition Monitoring System

In order to reduce operating costs and increase the operational stability, the aviation industry is continuously introducing digital technologies to automate the state detection of their assets and derive maintenance decisions. Thus, many industry efforts and research activities have focused on an early state fault detection and the prediction of system failures. Since research has mainly been limited to the calculation of remaining useful lifetimes (RUL) and has neglected the impact on surrounding processes, changes on the objectives of the involved stakeholders, resulting from these technologies, have hardly been addressed in existing work. However, to comprehensibly evaluate the potential of a fault diagnosis and failure prognosis system, including its effects on adjacent maintenance processes, the condition monitoring system’s maturity level needs to be taken into account, expressed for example through the technology’s automation degree or the prognostic horizon (PH) for reliable failure projections. In this paper, we present key features of an automatic condition monitoring architecture for the example of a Tire Pressure Indication System (TPIS). Furthermore, we develop a prescriptive maintenance strategy by modeling the involved stakeholders of aircraft and line maintenance operations with their functional dependencies. Subsequently, we estimate the expected implications for a small aircraft fleet with the introduction of such a monitoring system with various levels of technological maturity. Additionally, we calculate the maintenance cost savings potential for different measurement strategies and compare these results to the current state-of-the-art maintenance approach. To estimate the effects of implementing an automated condition monitoring system, we use a discrete-event, agentbased simulation setup with an exemplary flight schedule and a simulated time span of 30 calendar days. The obtained results allow a comprehensive estimation of the maintenance related implications on airline operation and provide key aspects in the development of an airline’s prescriptive maintenance strategy.

Relationships Under Stress: Relational Outsourcing in the U.S. Airline Industry After the 2008 Financial Crisis

This paper studies how firms restructure their relational contracts in the face of permanent shocks to the value of their relationships. In the context of the U.S. airline industry, we argue that major carriers enter self-enforcing agreements with their outsourced regional partners because a key aspect of airline operations—the exchange of landing slots under adverse weather—is formally noncontractible. We show empirically that major and regional airlines did not terminate their relational contracts after the 2008 crisis but rather, restructured the scope of such contracts in a way that restored their credibility. In particular, we show that a major airline was less likely to continue outsourcing a route to a regional partner after the 2008 crisis the lower the present discounted value of their preexisting relationship and hence, the larger the negative effect of the crisis on the relational contract’s “self-enforcing range.” This paper was accepted by Joshua Gans, business strategy.

Artificial Intelligence in travel

Over the past four decades Operations Research (OR) has played a key role in solving complex problems in airline planning and operations. Over the past decade Artificial Intelligence (AI) has seen a rapid growth in adoption across a range of industry verticals such as automotive, telecommunications, aerospace, and health care. It has been acknowledged that while adoption of AI in the travel industry has been slow, the potential incremental value is high. This paper discusses the role of AI and a range of applications in travel to support revenue growth and customer satisfaction.

EXPLORING QUALITY DETERMINANTS IN AIRLINE SERVICES: A STUDY OF CUSTOMER EXPERIENCE IN VIETNAM

The increasing prices of oil, rank as one of the main threats to airlines. Generally, all airlines will adjust their prices to deal with oil price variations, and this often impacts customer service satisfaction. However, there tends to be gapin research exploring the relationship between the changing oil prices and its impact on customer satisfaction in the airline sector. This research gap widens particularly in the context of an airline operating in the developing country context. This study therefore explores the relationship between oil prices, perceived service quality, customer loyalty and customer satisfaction for a Vietnamese airline. The study reports the findings from a survey of 235 passengers of Vietnam airlines and explores the relationships between prices, service quality, service satisfaction and loyalty. Our findings indicate that increasing oil prices do affect the customer satisfaction negatively however customer loyalty largely remains unaffected.

Evaluation and mitigation analysis of carbon footprint for an airline operator: Case of Nepal airlines corporation

This paper deals with evaluation and analysis of carbon footprint of an airline operator, Nepal Airlines Corporation (NAC) by using its actual flight and maintenance data from 2016 to 2019. NAC is a multi-fleet operator, of both turboprop and turbofan aircrafts. Carbon footprint in terms of Carbon Dioxide (CO2) emission has been calculated for NAC’s airline operations per individual aircraft, fleet-type and operating sector (i.e., international and domestic), and total ground handling operations. In each of the study years, contribution to NAC’s total CO2 production from its domestic fleet was found out to be very small (below 6% of yearly total), even though its fleet number outnumbered that of international fleet. This indicates better optimization opportunities for international-sector (turbofan) aircrafts than domestic-sector (turboprop) aircrafts. Reductions in fuel on-board as per prescribed levels, better airport slot management and selection of long-haul flight destinations have been identified as potential mitigation strategies for CO2 emission from international sector. Smaller aircrafts operating in domestic sectors are more prone to variations in occupancy rate and as such, NAC could focus on optimizing its commercial strategy to improve its CO2/passenger rate in domestic sector.

Impact of Covid-19 Pandemic on Air Transport: Overview and Implications

The current situation of the COVID-19 pandemic has led to multiple changes in the international market as well as in the lifestyle of people worldwide. The transport sector has undoubtedly been one of the most affected sectors due to restrictions imposed by the governments across the world to protect the health of their citizens, particularly the restrictions imposed on the operation of airlines. On the other hand, the reduction in travel by means of transport has contributed in part to the improvement in the environmental conditions on account of reduction in the levels of CO2 emissions and pollution. The present paper discusses the major consequences of the COVID-19 pandemic on the aviation industry. The data and critical observations presented in this paper were collected from the detailed studies published on this crucial topic and thus provide a broad overview to the reader.

Formal modelling and verification of a multi-agent negotiation approach for airline operations control

This paper proposes and evaluates a new airline disruption management strategy using multi-agent system modelling, simulation, and verification. This new strategy is based on a multi-agent negotiation protocol and is compared with three airline strategies based on established industry practices. The application concerns Airline Operations Control whose core functionality is disruption management. To evaluate the new strategy, a rule-based multi-agent system model of the AOC and crew processes has been developed. This model is used to assess the effects of multi-agent negotiation on airline performance in the context of a challenging disruption scenario. For the specific scenario considered, the multi-agent negotiation strategy outperforms the established strategies when the agents involved in the negotiation are experts. Another important contribution is that the paper presents a logic-based ontology used for formal modelling and analysis of AOC workflows.

Airline ground operations: Optimal schedule recovery with uncertain arrival times

Airline operations are subject to a number of stochastic influences which result into variable ground and block times for same flights on different days. Our research explores how airline operations control centers may benefit from an integrated decision support system for schedule recovery during aircraft ground operations. In this paper, we study the sensitivity of an optimal set of schedule recovery options towards uncertain arrival times. The calculation of recovery options is based upon an integrated and iterative scheduling and optimization algorithm, which incorporates uncertainties for arrival flights as a function of a given look-ahead time. Potential recovery options include stand re-allocation, quick-turnaround, quick passenger transfer, waiting for transfer passengers, cancellation of passenger or crew connections, and arrival prioritization. Within a case study setting at Frankfurt Airport, 20 aircraft turnarounds are analysed during a morning peak with their respective estimated arrival times (including potential arrival delays). The analysis of simulation results reveals an almost identical set of selected recovery options under high uncertainty circumstances and from post-operational point-of-view, which indicates high solution stability.

Airline Disruption Management: A Review of Models and Solution Methods

The normal operation of aircraft and flights can be affected by various unpredictable factors, such as severe weather, airport closure, and corrective maintenance, leading to disruption of the planned schedule. When a disruption occurs, the airline operation control center performs various operations to reassign resources (e.g., flights, aircraft, and crews) and redistribute passengers to restore the schedule while minimizing costs. We introduce different sources of disruption and corresponding operations. Then, basic models and recently proposed extensions for aircraft recovery, crew recovery, and integrated recovery are reviewed, with the aim of providing models and methods for different disruption scenarios in the practical implementation of airlines. In addition, we provide suggestions for future research directions in these topics.