According to statistics, an average of about 35 occurrences of aircraft depressurization are happening a year. Sudden depressurization at a high altitude (more than 24 000 feet) is a very dangerous flight emergency, and with incorrect, and most importantly, untimely actions of the aircraft crew, it leads to tragic consequences. Timely, correction and coordinated collaborative actions of aviation specialists in flight emergencies for prevention the catastrophic situation development is the relevant task. The diagrams of cause-and-effect relationships of the aircraft crew actions in the case of depressurization in the form of semantic models are presented. The flowchart of the algorithm of the aircraft crew actions in the case of depressurization if cabin altitude is controllable is designed. The deterministic, stochastic, and non-stochastic operative decision-making models by the crew members in emergency “Depressurization” under certainty, risk, and uncertainty conditions are developed. The deterministic models are built with the help of network planning, stochastic models - based on the expected value criterion with the help of a decision tree, non-stochastic models - based on the Wald, Laplace, Hurwitz, Savage criteria with the help of a decision matrix. The worked-out models can be used in the Intelligent Decision Support System to improve the efficiency of the joint actions of aviation personnel.
In 2021, 44 accidents occurred during commercial passenger and cargo air transportation
(Figure 1) [
In 2019, there were 20 fatal accidents during commercial transportation, resulting in the deaths
of 285 passengers and crew members, and another six people on the ground. Non-commercial
operations have had three fatal accidents and six fatalities this year.
Over the past two years, COVID-19 has significantly decreased global air traffic. Data from the
International Air Transport Association (IATA) shows that total international scheduled passenger
transportation during 11 months of 2021 fell by around 60% compared to the same period in 2019
before the pandemic [
According to the International Civil Aviation Organization (ICAO) [
To increase the level of flight safety, the practical and scientific expediency of studying the problem of interaction of aviation specialists is increasingly being realized. Teamwork research in aviation was first initiated by the USA National Aeronautics and Space Administration (NASA) based on improving the interaction between flight crew members. Over time, this approach was further developed and became one of the most successful tools for preventing human errors [6; 7].
According to the ICAO's modern requirements, for the effectiveness of solutions the use of Collaborative Decision-Making (CDM) models is relevant [8–11].
Nowadays, within the Airport Collaborative Decision-Making (A-CDM) concept, specific solutions are being implemented that can unite the interests of participants (operators of the airport, aircraft, ground handling, air traffic, etc.) in coordinated work. A-CDM concept is based on the principles of transparency and information sharing; it is aimed at enhancement of air traffic and capacity management at airports by decreasing delays, improvement of the predictability of situations, and optimizing the use of resources [8–10].
Moreover, required daily efficiency of operations may be achieved through the mechanism of Flight and Flow Information for a Collaborative Environment (FF-ICE) [11]. FF-ICE concept defines requirements to air navigation information for flight planning, air traffic, flow, and trajectory management; it is a basis of the performance-based Air Navigation System (ANS) [11].
In [12] the issue of synchronizing the technological procedures of the first pilot (named Pilot Flying (PF) – performs the actions of piloting the aircraft) and the second pilot (named Pilot Monitoring (PM) – performs communication functions) during the cross-monitoring in the flight emergency (FE) – a problem with the power supply – is considered.
In [12–15] the research of deterministic, stochastic, non-stochastic, and neural-network modeling, optimization, and intellectualization of CDM by teams of ANS human-operators (pilot – air traffic controller, UAV operator – air traffic controller, pilot – air traffic controller – flight dispatcher, pilot – air traffic controller – engineer, UAV operator – air traffic controller –pilot, etc.) in various FE.
Nevertheless, the problems of operational interaction between ANS human-operators in real time [16; 17] and weak formalization of the CDM process description, which does not allow applying the performance-based approach for its improvement [18], remain unsolved.
The purpose of this work is to build collective models of operative decision-making by the aircraft crew in the case of flight emergency (for example of depressurization if cabin altitude is controllable), which will be used in the Intelligent Decision Support System to improve the efficiency of the collaborative actions of aviation personal.
According to the Civil Aviation Authority of UK statistics, 77 occurrences of aircraft depressurization were happened during 1990-1999. In accordance with Federal Aviation Authority of USA statistics, 355 occurrences of aircraft depressurization happened from 1974 to 1983, an average of about 35 a year. 164 depressurization occurrences were reported to the Transportation Safety Board of Canada during 1985-1999, from 1990 to 1999 Australian Bureau of Air Safety Investigation recorded five depressurization occurrences [19].
Sudden depressurization at a high altitude (more than 24 000 feet) is a very dangerous FE, and with incorrect, and most importantly, untimely actions of the aircraft crew, it leads to tragic consequences. In a matter of seconds, the pressure drops to atmospheric, suffocation sets in, the temperature in the cabin drops to -50 °C, moisture droplets turn into thick fog, visibility in the cabin deteriorates sharply. There are three problems with depressurization:
1. Impact effect, in which aircraft crewmembers and passengers can be injured by the impact of an air jet.
2. A sharp drop in pressure causes the expansion of air in the human body. 3. The onset of hypoxia, i.e. suffocation.
A very unpleasant and dangerous phenomenon during depressurization is the expansion of gas inside the body. This is the effect of an open bottle of mineral water. In human life, nitrogen and oxygen are adsorbed by blood and tissues. If the pressure suddenly decreases, gas bubbles can form in various parts of the body. Formed in cavities where there is no exit (stomach, sinuses, tooth socket) causes severe pain. Gas bubbles can also form in tissues and joints, causing pain.
During rapid depressurization, the air inside the lungs expands and is forced out through the mouth and nose. People can tolerate sudden depressurization without adverse effects as long as the trachea is open. In a calm state, the lung can easily withstand a sudden doubling of its volume. But if the lungs expand too quickly, their lining can rupture, allowing air bubbles to enter the person's blood through damaged blood vessel walls.
Hypoxia is one of the main dangers of cabin depressurization. Consequences for a person: clouding of reason, confusion in thoughts, slowness in assessing the situation and making decisions, dizziness, and, in the extreme case, loss of consciousness. Such symptoms are also noted – rapid breathing, fatigue, headache, sweating, loss of coordination of movements, and blurred vision. The lack of oxygen in the blood causes blue lips and fingers under the nails, as well as tingling, nausea, and a feeling of coldness.
At higher altitudes, the severity of these symptoms increases. If at an altitude of 27 000 feet explosive depressurization causes loss of consciousness in one minute, then at an altitude of 36 000 feet – after 18 seconds.
Diagrams of cause-and-effect relationships for the FE "Depressurization" in the form of semantic models of the P-type and S-type event trees, which are branched, connected, and finite graphs that do not have cycles or loops, have been developed (Figures 4–5).
Technical factors Manufacturing defects of the
pressurization system Despite the fact that aircraft cockpit depressurization is a rare occurrence, and even if it occurs, the probability of a fatal outcome is high. Flying at high altitudes must exclude even the slightest risk of depressurization.
Explosive depressurization is always a random, unexpected phenomenon, but the more monstrous the consequences can be. Therefore, the aircraft crew should always be ready to act in such emergency. Flight safety in this case is ensured by the immediate use of oxygen masks. The emergency descent could be initiated if cabin pressure is out of control at altitudes above 14 000 feet or other operational reasons. Terminated climb and/or preventive normal descent could preclude the necessity of emergency descent.
Following the B737 Quick Reference Handbook (QRH) [20], a flowchart of the algorithm of the crew actions in the case of depressurization if cabin altitude is controllable is built (Figure 6).
Start CABIN ALTITUDE light illuminates Examples of crew actions in the case of depressurization are given in SKYbrary [21].
The concerted technology of work performance by the Pilot Flying (PF) and Pilot Monitoring (PM) in FE “Depressurization” if cabin altitude is controllable following QRH B737 is submitted in Table 1.
ai a1
ti, sec. 1
Total
b14 b15 1 1 34 Based on the experts’ opinion the deterministic model of work performance by the aircraft crew in emergency “Depressurization” if cabin altitude is controllable in the form of the network graph is designed (Figure 7).
b1 a1 b2 a2 Pilot Monitoring b3 a3 b4 a4 b5 a5 Pilot Flying a6 b6 b7 b8 b9 b10 b11 b12 b13
b14 b15 15 26
34 t, sec. a7 a8 cabin altitude is controllable The critical way for PF is the operations a1–a8 and for PM is the operations b1–b15 located one after the other without time gaps and overlapping. The critical time tcr of work by the aircraft crew in emergency “Depressurization” if cabin altitude is controllable is 34 sec.
weather conditions. corresponding to the condition (2): Decision-making by the aircraft crew in the FE “Depressurization” about the continuation of the normal operations and proceeding to the destination aerodrome or diverting to the alternate aerodrome is included next stages of the solution: 1 – choosing between an alternate or destination aerodrome for emergency landing; 4
– choosing between alternate aerodrome 1 and alternate aerodrome 2 for emergency landing; 7 , 8 – choosing between Instrument Flight Rules (IFR) and Visual Flight Rules (VFR). The probabilities pj for each outcome Uij were identified: p1=0.2 – bad weather; p2=0.8 – good The optimal solution is based on the expected value criterion (1) and would be that = ( ; { , α, , }) = (∑ =1 + α );
= min{ }, , = 1, ; = 1, . = =1 where
< −1; α – is an additional risk of FE development, in our example α = 0; – is a time of the decision-making stage, in our example = 1; The decision tree in the case of depressurization is presented in Figure 8.
1
Destination aerodrome Alternative aerodrome 2 3 p1=0.2 p2=0.8 p2=0.8 p1=0.2
Static and dynamic factors influencing decision-making by the aircraft crew in the FE “Depressurization” about the continuation of the normal operations and proceeding to the destination aerodrome or diverting to the alternate aerodrome are: 1) • • • • 2)
Internal factors Fi: f1i – the cause of depressurization; f2i – flight-technical characteristics of the aircraft; f3i – equipment of the aircraft; f4i – time of the FE development;
External factors Fe: • f5e – tactic-technical characteristics of the runway; • f6e – the runway surface condition; • f7e – the navigation facility at the aerodrome; • f8e – the lighting system at the aerodrome; • f9e – weather conditions at the aerodrome; • f10e – readiness of emergency office at the aerodrome; • f11e – factors of the commerce (fees at the airport, ground handling agreements, replacement aircraft, etc.).
The matrix of possible results of the crew actions in the case of depressurization if cabin altitude is controllable is given in Table 2. The Wald, Laplace, Hurwitz, Savage criteria will allow finding the optimal solution in FE “Depressurization” in uncertainty conditions.
To solve the task of finding a compromise between the time of decision-making by humanoperators under the influence of various factors in uncertainty conditions and the critical time of FE parry in certainty conditions it is proposed to use Artificial Neural Networks (ANN) with Machine Learning (ML) and analyzing tools of Big Data (BD). To control Artificial Intelligence (AI) solutions by human-operator it is necessary to introduce Hybrid (Combined) Intelligence (HI) Systems that use both human and machine competence [22; 23].
Diagrams of cause-and-effect relationships in the form of semantic models of the P-type and Stype event trees, which are branched, connected, and finite graphs that do not have cycles or loops, have been developed for the FE "Depressurization". A flowchart of the algorithm of the crew actions in the case of depressurization if cabin altitude is controllable in accordance with the QRH B737 is built.
Concerted technology and the network graph of work performance by the Pilot Flying and Pilot Monitoring in FE “Depressurization” if cabin altitude is controllable are submitted. The critical time tcr of work by the aircraft crew in emergency “Depressurization” if cabin altitude is controllable is 34 sec.
An example of risk calculation in the case of aircraft depressurization based on the expected value criterion with the help of the decision tree is given. An optimal solution is landing at the alternate aerodrome 2 in VFR, where Rmin=8 c.u.
Internal and external factors influencing decision-making by the aircraft crew in the FE “Depressurization” about the continuation of the normal operations and proceeding to the destination aerodrome or diverting to the alternate aerodrome are determined: the cause of depressurization; flight-technical characteristics of the aircraft; equipment of the aircraft; tactictechnical characteristics of the runway; the runway surface condition; the navigation facility at the aerodrome; the lighting system at the aerodrome; weather conditions at the aerodrome; readiness of emergency office at the aerodrome; factors of the commerce (fees at the airport, ground handling agreements, replacement aircraft, etc.).
The compromise between the time of decision-making by human-operators under the influence of various factors in uncertainty conditions and the critical time of FE parry in certainty conditions can be found based on the use Artificial Neural Networks (ANN) with Machine Learning (ML) and analyzing tools of Big Data (BD).
According to statistics, an average of about 35 occurrences of aircraft depressurization are happening a year. Sudden depressurization at a high altitude (more than 24 000 feet) is a very dangerous FE, and with incorrect, and most importantly, untimely actions of the aircraft crew, it leads to tragic consequences. Timely, correction and coordinated collaborative actions of aviation specialists in flight emergencies for prevention the catastrophic situation development is the relevant task.
The diagrams of cause-and-effect relationships of the aircraft crew actions in the case of depressurization in the form of semantic models of the P-type and S-type event trees are presented. The flowchart of the algorithm of the crew actions in the case of depressurization if cabin altitude is controllable following the QRH B737 is designed.
The deterministic, stochastic, and non-stochastic operative decision-making models by the crew members in emergency “Depressurization” under certainty, risk, and uncertainty conditions are developed. The deterministic models are built with the help of network planning, stochastic models – based on the expected value criterion with the help of a decision tree, non-stochastic models – based on the Wald, Laplace, Hurwitz, Savage criteria with the help of a decision matrix.
The direction of further research is to design the individual and collective deterministic, stochastic, and non-stochastic operative decision-making models by different aviation personnel in FE that can use in the composition of Intelligent Decision Support System. In the future, to solve the task of finding a compromise between the time of decision-making by human-operators under the influence of various factors in uncertainty conditions and critical time of FE parry in certainty conditions it is proposed to use Artificial Neural Networks (ANN) with Machine Learning (ML) and analyzing tools of Big Data (BD). Next research requires developing a methodology for the cooperation of Human Intelligence and Artificial Intelligence (creation of Hybrid Intelligence) to improve the efficiency of interaction between the Artificial Intelligence Systems and ANS human-operators (aircraft crew, UAV operator, air traffic controller, flight dispatcher, ground operator, engineer, etc.). [8] A-CDM Concept of Operations, Australia, Airservices Australia, 2014. URL: https://www.airservicesaustralia.com/noc/cdm/docs/CDM_Concept_of_Operations_Airport _v1.5.pdf [9] Airport CDM Implementation: Manual, EUROCONTROL, Brussels, Belgium, 2017. URL: https://www.eurocontrol.int/sites/default/files/publication/files/airport-cdm-manual2017.PDF [10] Airport-Collaborative Decision Making: IATA Recommendations, IATA, Montreal, Canada, 2018. URL: https://www.iata.org/ contentassets/5c1a116a6120415f87f3dadfa38859d2/iata-acdm-recommendations-v1.pdf [11] D.Liang, K.Cropf, R.Sherwin, G.Porter, S.Masarky, F.Sutton, Operational evaluation of FFICE/R2, Proceedings of the IEEE 2019 Integrated Communications, Navigation and Surveillance Conference (ICNS-2019), Herndon, VA, USA, April 9-11, 2019, pp. 649–658.
DOI: 10.1109/ICNSURV.2019.8735320 [12] T.Shmelova, Yu.Sikirda, N.Rizun, A.-B.M.Salem, Yu.Kovalyov (Eds.), Socio-technical decision support in air navigation system: Emerging research and opportunities, IGI Global Publ., Hershey, USA, 2018. DOI:10.4018 / 978-1-5225-3108-1 [13] Т.Shmelova, Yu.Sikirda, М.Yatsko, М.Kasatkin, Collective models of the aviation humanoperators in emergency for Intelligent Decision Support System, CEUR Workshop Proceedings, vol-3156, Proceedings of the 3rd International Workshop on Intelligent Information Technologies & Systems of Information Security (IntelITSIS-2022), Khmelnytskyi, Ukraine, March 23-25, 2022, pp. 160–174. URL: http://ceur-ws.org/ Vol-3156/paper10.pdf [14] T.Shmelova, A.Chialastri, Yu.Sikirda, М.Yatsko, Decision making models by the pilot in flight emergency “Engine failure during take-off”, CEUR Workshop Proceedings, vol-3101, Proceedings of the 2nd International Workshop on Computational & Information Technologies for Risk-Informed Systems (CITRisk 2021) co-located with XXI International Conference on Information Technologies in Education and Management (ITEM 2021), Kherson, Ukraine, September 16–17, 2021, pp. 347–365. URL: http://ceur-ws.org/ Vol-3101/Paper26.pdf [15] Т.Shmelova, М.Yatsko, Yu.Sikirda, Collaborative-factor models of decision making by operators of the Air Navigation System in conflict or emergency situations, Communications in Computer and Information Science (CCIS), vol. 1635, ICTERI 2021 Workshop Proceedings: ITER, MROL, RMSEBT, TheRMIT, UNLP 2021, Kherson, Kherson State University, September 28 – October 2, 2021, pp. 391–409. URL: https://link.springer.com/ chapter/10.1007/978-3-031-14841-5_26 [16] Global Air Navigation Plan 2016-2030, Doc. 9750, 5th ed., ICAO, Montreal, Canada, 2016. [17] L.Ren, M.Castillo-Effen, Air Traffic Management (ATM) operations: A review, report number 017GRC0222, GE Global Research, Niskayuna, New York, United States, 2017 [18] Global Performance of the Air Navigation System (Doc. 9883), ICAO Workshop on the Application and Development of the Vol. III of the CAR, Virtual Meeting, September, 15-17, 2020. URL: https://www.icao.int/SAM/Documents/2020RLA06901-ANPVOLIII/1_2_Doc.%209883%20GPM.pdf [19] S.R.Mohler, Quick response by pilots remains key to surviving cabin decompression, Human
Factors and Aviation Medicine, FSF, 47, 1, 2020 [20] B737 Flight Crew Operations Manual (FCOM): Quick Reference Handbook (QRH), Boeing
Company, Chicago, USA, 2018. URL: http://www.737ng.co.uk/737NG%20POH.pdf [21] Loss of cabin pressurization, SKYbrary, 2022. URL: https://skybrary.aero/articles/losscabin-pressurisation [22] B.Alharbi, M.Prince, A hybrid artificial intelligence approach to predict flight delay, International Journal of Engineering Research and Technology, 13, 4, 2020, pp. 814-822.
DOI: 10.37624/IJERT/13.4.2020.814-822 [23] Artificial Intelligence Roadmap: A human-centric approach to AI in aviation, European Union Aviation Safety Agency, Cologne, Germany, 2020. URL: chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/viewer.html?pdfurl=https%3A%2F %2Fww w.easa.europa.eu%2Fsites%2Fdefault%2Ffiles%2Fdfu%2FEASA-AI-Roadmapv1.0.pdf&clen=4347516&chunk=true