Flight Accidents Research Articles

Prediction of civil aircraft hard landing risk based on GBDT-GS method

Hard landing may cause symptom events such as structural damage to the aircraft, or even cause fatal flight accidents. In view of the lack of physical analysis in the current hard landing risk assessment, in order to effectively implement the hard landing risk identification and grade judgment criteria, so as to improve the quality of pilots' landing operations, a hard landing risk prediction model was constructed based on the gradient boosting decision tree algorithm (GBDT) and grid search (GS) combined with flight state analysis. Firstly, the five flight state parameters closely related to the hard landing were determined by analyzing the aircraft force and constructing the landing flight kinematic equation; then, the flight state data was extracted from the data recorded by the onboard Quick Access Recorder (QAR) to construct a data set, and according to the QAR parameter characteristics, the hard landing risk prediction model was constructed by the GBDT algorithm, and the model parameters were optimized by GS; finally, taking the "Chengdu-Shenyang" route of an airline as an example, 530 QAR data were selected to train and test the model, and the results were compared with those of random forest, logistic multivariate regression, recurrent neural network (RNN) and other algorithms. The results show that the performance of GBDT-GS algorithm in predicting hard landing risk is better than other algorithms, and the prediction accuracy reaches , which 92%，verifies the objective effectiveness of the model.

Shock buffet onset prediction with flow feature-informed neural network

Transonic shock buffet is a significant self-excited shock oscillations and aerodynamic instability phenomenon induced by shock-boundary layer interaction, which limits the flight envelope and even causes flight accidents. The aviation industry has a significant interest in accurately predicting the shock buffet onset boundary, defined by a specific combination of Mach number and angle of attack. While the current methods of steady and unsteady numerical simulation suffer from a contradiction of efficiency and accuracy. In the current paper, a flow feature-informed neural network (FINN) model is constructed to predict the buffet onset boundary over airfoils. Typical features associated with buffet onset are extracted from the steady base flow and subsequently integrated into the hidden layer of the neural network to impose physical constraints. With the test cases of the NACA0012 airfoil at various Mach numbers, the FINN model can accurately predict the damping representing the unsteady instability margin. Compared to the direct mapping input-output neural network (NN) model, the proposed method with shock wave feature-informed has enhanced accuracy, with an average relative error decreased by 70% at extrapolated Mach numbers. This research demonstrates the effectiveness of the FINN model in predicting the buffet onset, which leverages physics features derived from the more economical steady solution far from the onset boundary at a given predicted Mach number.

Research on fatigue detection of flight trainees based on face EMF feature model combination with PSO-CNN algorithm

Even though the capability of aircraft manufacturing has improved, human factors still play a pivotal role in flight accidents. For example, fatigue-related accidents are a common factor in human-led accidents. Hence, pilots’ precise fatigue detections could help increase the flight safety of airplanes. The article suggests a model to recognize fatigue by implementing the convolutional neural network (CNN) by implementing flight trainees' face attributions. First, the flight trainees’ face attributions are derived by a method called the land-air call process when the flight simulation is run. Then, sixty-eight points of face attributions are detected by employing the Dlib package. Fatigue attribution points were derived based on the face attribution points to construct a model called EMF to detect face fatigue. Finally, the proposed PSO-CNN algorithm is implemented to learn and train the dataset, and the network algorithm achieves a recognition ratio of 93.9% on the test set, which can efficiently pinpoint the flight trainees’ fatigue level. Also, the reliability of the proposed algorithm is validated by comparing two machine learning models.

Research on identification of flight cadets’ cognitive load based on multi-source physiological data and CGAN-DBN model

Modern aircraft cockpit system is highly information-intensive. Pilots often need to receive a large amount of information and make correct judgments and decisions in a short time. However, cognitive load can affect their ability to perceive, judge and make decisions accurately. Furthermore, the excessive cognitive load will induce incorrect operations and even lead to flight accidents. Accordingly, the research on cognitive load is crucial to reduce errors and even accidents caused by human factors. By using physiological acquisition systems such as eye movement, ECG, and respiration, multi-source physiological signals of flight cadets performing different flight tasks during the flight simulation experiment are obtained. Based on the characteristic indexes extracted from multi-source physiological data, the CGAN-DBN model is established by combining the conditional generative adversarial networks (CGAN) model with the deep belief network (DBN) model to identify the flight cadets’ cognitive load. The research results show that the flight cadets’ cognitive load identification based on the CGAN-DBN model established has high accuracy. And it can effectively identify the cognitive load of flight cadets. The research paper has important practical significance to reduce the flight accidents caused by the high cognitive load of pilots.

Wind Shear Response of Aircraft with C* and C*U Controller during Approach

This study investigates the impact of wind shear on the flight dynamics of commercial aircraft where C* and C*U control laws are employed during the approach phase. Given the high incidence of flight accidents during takeoff and landing attributed to wind shear, this research aims to enhance aviation safety by analyzing control law behavior under varying wind shear conditions. A nonlinear flight simulation model was developed, utilizing aerodynamic and engine data from a B737, to explore the aircraft’s response to different wind shear intensities. The simulation analysis was used to compare the response of the aircraft with C* and C*U controllers, respectively, under different wind shear, and to evaluate the effectiveness of its stability enhancement in wind shear. It was found that in most cases, the controller can achieve a good stabilization effect, but in some cases of wind fields, the aircraft suffered more significant oscillation.

Detection method for unrecognized spatial disorientation based on optical flow stimuli.

Flight accidents caused by spatial disorientation (SD) greatly affect flight safety. Few studies have been devoted to the evaluation of SD. 10 pilots and 10 non-pilots were recruited for the experimental induction of SD. Videos for giving optical flow stimuli were played at two different flow speeds to induce SD. Subjective judgment and center of foot pressure (CoP) data were collected from the tests. The data were combined to determine the occurrence of SD and analyze the SD types. The number of self-reported SD events was slightly smaller in the pilots than in the non-pilots. The average upper bound of the confidence interval for the standard deviation of CoP was 0.32 ± 0.09 cm and 0.38 ± 0.12 cm in the pilots and non-pilots, respectively. This indicator was significantly lower in the pilots than in the non-pilots (P= 0.03). The success rate of the experimental induction of unrecognized SD was 26.7% and 45.0% in the pilots and non-pilots, respectively. The method offered a new to analyze unrecognized SD. We could determine the occurrence unrecognized SD. This is an essential means of reducing flight accidents caused by unrecognized SD.

Comparative Study and Airspeed Sensitivity Analysis of Full-Wing Solar-Powered UAVs Using Rigid-Body, Multibody, and Rigid-Flexible Combo Models

Solar-powered UAVs are characterized by large-scale, lightweight, and low airspeed, and changes in airspeed lead to wing deformation or stalling, which can easily induce serious flight accidents. A single dynamic model cannot accurately describe this feature, and this airspeed sensitivity can only be analyzed by integrating rigid-body, multirigid-body, and rigid-flexible combo models. This paper proposes a dynamic analysis method for a mixture of rigid-body, multirigid-body, and rigid-flexible combo models, considering the applicable airspeed ranges, computational costs, and structural deformation assumptions of the three models and comparing the differences of modes and responses at different airspeeds, and quantitatively analyzes the effects of airspeed on the motion, deformation, and coupling. The results show that appropriate increase of airspeed is beneficial to the stability of large-scale lightweight platforms, but when it is increased to more than two times the cruise speed, the structural deformation is coupled with the flight dynamic modes, leading to the deterioration of the overall dynamic response. Finally, a mixture of the three models at different airspeeds is proposed, which is necessary for future ultralarge-scale solar-powered UAVs.

An Anomaly Detection Method for UAV Based on Wavelet Decomposition and Stacked Denoising Autoencoder

The paper proposes an anomaly detection method for UAVs based on wavelet decomposition and stacked denoising autoencoder. This method takes the negative impact of noisy data and the feature extraction capabilities of deep learning models into account. It aims to improve the accuracy of the proposed anomaly detection method with wavelet decomposition and stacked denoising autoencoder methods. Anomaly detection based on UAV flight data is an important method of UAV condition monitoring and potential abnormal state mining, which is an important means to reduce the risk of UAV flight accidents. However, the diversity of UAV mission scenarios leads to a complex and harsh environment, so the acquired data are affected by noise, which brings challenges to accurate anomaly detection based on UAV data. Firstly, we use wavelet decomposition to denoise the original data; then, we used the stacked denoising autoencoder to achieve feature extraction. Finally, the softmax classifier is used to realize the anomaly detection of UAV. The experimental results demonstrate that the proposed method still has good performance in the case of noisy data. Specifically, the Accuracy reaches 97.53%, the Precision is 97.50%, the Recall is 91.81%, and the F1-score is 94.57%. Furthermore, the proposed method outperforms the four comparison models with more outstanding performance. Therefore, it has significant potential in reducing UAV flight accidents and enhancing operational safety.

Instability Feature Extraction Method of Compressor Based on Sample Autocorrelation Function

The stability of aero-engine compressor is related to flight safety. Severe instability may lead to engine surge, parking or mechanical damage and even cause flight accidents. Aiming at this problem, a compressor instability feature extraction method based on sample autocorrelation function is proposed, and an autocorrelation analysis model of fluctuating pressure is established. The model is verified and analyzed by using the flight test data of an engine, which shows the feasibility of this method. It can provide technical support for real-time monitoring and quantitative evaluation of aero-engine compressor stability and improve safe flight efficiency.

The effects of social media usage on vicarious traumatization and the mediation role of recommendation systems usage and peer communication in China after the aircraft flight accident

ABSTRACT Background: Previous research has indicated that continuous exposure to disaster-related information through social media can lead to vicarious trauma. However, scholars have recognized the need for further in-depth research into the underlying mechanisms influencing this relationship. Objective: The purpose of this study is to investigate the impact mechanism of social media usage on vicarious traumatization in users and analyze the roles of recommendation systems and peer communication. Methods: This study was conducted with college students in China, focusing on the context of the MU5735 aircraft flight accident in China in which 123 passengers and 9 crew members died. Data were collected through an online questionnaire. The partial least square structural equation modelling (PLS-SEM) method was used to test the data and model. Results: This study obtained valid responses from 1317 participants. The study findings revealed a significant positive correlation between social media usage(β = 0.180，P < .001), recommendation systems usage (β = 0.172, P < .001), peer communication (β = 0.303, P < .001), and the development of vicarious traumatization. Recommendation systems usage (specific indirect effect = 0.063, P < .001) and peer communication (specific indirect effect = 0.138, P < .001) mediated the relationship between social media use and vicarious trauma. Additionally, the impact of peer communication on vicarious trauma was found to be higher compared to the effects of continuous social media use and recommendation system use. Conclusion: The study found that the use of social media to obtain information about accidents, the frequent pushing of accident information by recommender systems, and the frequent discussion of accidents among peers during unexpected accidents contribute to vicarious traumatization. The study suggests that users’ reduced retrieval of accident information via social media, as well as reduced peer-to-peer discussions about accidents, and social media platforms’ adjustment of recommender system algorithm rules to reduce accident information pushes, may help reduce the likelihood of users experiencing vicarious traumatization.

Improvement of Data Operations Management using CMMI and DMBOK in Soekarno-Hatta Meteorology Station

Soekarno-Hatta Meteorology Station is a Technical Implementation Unit within Badan Meteorologi, Klimatologi, dan Geofisika (BMKG). It has the duties to manage, and process data for safety, regulation, and aviation navigation efficiency by distributing the processed data to their stakeholder, such as Air Traffic Service (ATS), flight operators, and pilots. Furthermore, research was also conducted in the station regarding the creation of Aerodrome Climatological Summary (ACS) annually. Loss of flight document data occurred in 2019 due to a ransomware attack, causing the cessation of the data operation process on the flight document. Unfortunately, there is no data recovery resulting in the unavailability of flight document data. This accident is very crucial because flight document data should not be lost within a 30-day timeframe as it is needed in case of any flight accident mechanism. It shows that Data Operations Management needs to be improved to support the business process. This study aims to evaluate the maturity level of data operations management in Soekarno-Hatta Meteorology Station by a conceptual model based on DAMA-DMBOK and the level of maturity is assessed using the Capability Maturity Model Integration (CMMI). The result showed that the average activity reaches level 2. Six activities are at level 1, namely obtaining externally sourced data, plan for data recovery, set database performance service levels, archive, retain, and purge data, support specialized database inventory and track data technology licenses, support data technology usage and issues. The rest of the activities will require action to improve their maturity level as given in the recommendation.

MTL-PIE: A multi-task learning based drone pilot identification and operation evaluation scheme

As one of the most promising industries, consumer-grade Unmanned Aerial Vehicles (UAVs), also known as drones, have changed our lives. Although significant progress in drones has been made, adversary impersonation attacks still pose severe risks to flying drones. In addition, authorized pilot miss-operations also has become a critical factor leading to drone flight accidents. To validate the pilot's legal status and remind the authorized pilot about their miss-operations, we propose a multi-task learning-based drone pilot identification and operation evaluation scheme named MTL-PIE. Specifically, we first present qualitative and quantitative guidelines to evaluate pilot operation proficiency. Then, we design a pilot identification module and an operation evaluation module to resist pilot impersonation attacks and assess pilot operation proficiency, respectively. Finally, we propose a soft-parameter sharing mechanism to transfer knowledge between two modules and a dynamic weight-adjusting algorithm to prevent domain-dominant problems. Numerical results show that MTL-PIE can verify pilot legal status with an accuracy of 95.36% (outperforming our previous work with a margin of 2%-3%) and act as assessors to evaluate pilot operation proficiency with an accuracy of 94.47%. Note that MTL-PIE needs only 35 ms to verify pilot legal status and assess pilot operation proficiency; it has great potential to reduce drone flight accidents.

A novel framework based on two-stage multi-view feature optimization and improved support vector data description for aeroengine bearing early fault detection

Early fault detection is crucial to avoid catastrophic flight accidents caused by unplanned downtime of equipment. Aimed at the shortcomings of feature selection and early fault detection, this paper proposes a method combining two-stage multi-view feature optimization and improved support vector data description for aeroengine bearing early fault detection. First, a comprehensive evaluation index is constructed via combining monotonicity, correlation, robustness index and entropy weight method to be used for initial screening sensitive degradation features from multi-view candidate degradation feature. After that, the hierarchical clustering algorithm and local preserving projection algorithm is introduced to realize sensitive degradation features clustering and dimensionality reduction. On this basis, the Euclidean distance sample reduction and the sparrow search algorithm is utilized to complete the training sample selection and model parameter optimization of different clusters and further use the verification samples to filter the optimal features and model. Finally, based on the optimal degradation features and models, a fusion performance degradation index is built to achieve intelligent detection of early fault. Comparisons with some existing fault detection methods, the proposed method improves degradation trend sensibility and demonstrates potential of good early fault detection engineering applications.

A Real-Time Measurement Model of Attention-Allocation Level and Its Application in Simulated SPO Task

Most human-caused flight accidents can be attributed to a pilot’s attention deficit and monitoring errors. Accordingly, pilots’ attention allocation is strongly related to their task performance. This study is aimed at analyzing pilots’ fixation characteristics and attention-allocation levels. First, we proposed a model for measuring attention-allocation level based on the salience, effort, expectancy, and value (SEEV) model. Second, a low-fidelity single-pilot operation (SPO) cockpit environment was constructed, and 20 pilots were recruited for an experiment to compare their fixation characteristics between SPO and double-pilot operation (DPO) scenarios. The results showed slight differences in the attention levels allocated by SPO and DPO pilots under a scenario of one-engine failure. It concluded that Human-centered flight deck design can enhance a pilot’s attention allocation level. These findings can be used to optimize future flight deck designing and flight training for improving pilot’s task performance.

Aviation Safety Risk Analysis Based on Bayesian Network Modeling

The occurrence of serious flight accidents not only brings huge economic losses to airlines but also poses a great threat to passengers' lives. The occurrence of serious flight accidents will not only bring great economic losses to airlines but also cause great threats to the lives of passengers. Therefore, in this paper, based on the flight records of different flight crews, flight routes, airports, and specific flight conditions, aircraft safety risk analysis is conducted to calculate and evaluate the risk propensity. Firstly, the data are preprocessed, and then the QAR data are clustered to extract the key data items affecting the safe flight of the aircraft; then the data are transformed to the attached data, and a hierarchical clustering model is established based on the K-means clustering algorithm, which classifies the factors affecting the safety quality of the aircraft flight into the three main aspects of environmental factors, crew maneuvering, and aircraft state, and the key parameters are weighted by the Random Forest algorithm. weights of the key parameters. Then, based on the 3 criterion, the outliers exceeding 3 were selected as the dependent variables leading to the occurrence of deviation; based on the three-layer model, a Bayesian neural network model based on the three-layer model, and then determine the Bayesian nodes; finally, calculate the Bayesian node probability, and then provide a reasonable quantitative description of the flight maneuver.

Experimental statistical analysis of radar signals reflected from weather hazards

The nature of the causes of prerequisites for flight accidents due to meteorological conditions has remained unchanged for many years. For the effective operation of aviation, it is necessary to solve the issues of the timely detection of weather hazards and the identification of their intensity. This article discusses the research into the atmospheric reflectivity and turbulence in cumulonimbus clouds using a near-field meteorological radar system. Experimental studies are carried out with the aim of obtaining estimates of statistical characteristics of the reflectivity distribution and turbulence for weather hazards. The methodology for conducting an experimental study to obtain information about the weather hazards (rain shower, thunderstorm and hail), special features of the radar reflectivity propagation and the specific rate of turbulent energy dissipation in the considered conditions for the Tver region is presented. The analysis of the obtained results has been carried out: comparisons of meteorological data derived, using the meteorological radar complex of the near airfield zone (WR BZ), with the reliable sources of meteorological observation data obtained during experimental studies. Studies of horizontal sections and vertical profiles of the weather hazards parameters under consideration, associated with the cumulonimbus area, have been carried out. A data bank has been formed. Histograms of the information parameter distribution have been constructed. The article considers the results of experimental data approximation, using the χ2 criterion for various distribution laws. It is shown that the distributions of reflectivity and turbulence can be described by the generalized Rice’s law. The results obtained can be used to correct the classification criteria of weather hazards to subsequently increase the justification and reliability of the weather hazard classification. The further development of the method to process meteorological information is also of paramount importance to more correctly interpretate experimental data processing results of remote meteorological phenomena sensing.

A clustered borderline synthetic minority over-sampling technique for balancing quick access recorder data

Most of the flight accident data have uneven distribution of categories. When the traditional classifier is applied to this data, it will pay less attention to the minority class data. Synthetic Minority Over-sampling Technique (SMOTE), and its improvements are well-known methods to address this imbalance problem at the data level. However, traditional algorithms still have the problems in blurring the boundary of positive and negative classes and changing the distribution of original data. In order to overcome these problems and accurately predict flight accidents, a new Clustered Biased Borderline SMOTE(CBB-SMOTE) is proposed for Quick Access Recorder (QAR) Go-Around data. It generates more obvious positive and negative class boundaries by using K-means for boundary minority class data and safety minority class data respectively, and maintains the original data distribution to the greatest extent through a biased oversampling method. Experiments were carried out on a group of QAR Go-Around data. The data set is balanced by CBB-SMOTE, SMOTE, Cluster-SMOTE algorithm respectively, and the random forest algorithm is used to predict the new data set. The experimental results show that CBB-SMOTE outperforms the SMOTE in terms of G-means value, Recall and AUC.

Airline Customers Conflict Resolution in The Framework of Legal Protection For Consumers in Indonesia

Aviation related issues include low supervision of airlines in Indonesia, the condition of aircraft that are old and less feasible and high rates of flight accidents. Management negligence and mistakes reach a level that endangers state security. An airline is an organization that provides flight services including cargo to passengers. They provide these services and form cooperation or alliances with other airlines for mutual benefit. However, the relationship between customers and airlines can sometimes lead to ruthless legal battles and violent conflicts. This paper discusses legal protection for airline customers in Indonesia. It seeks to investigate not only the legal arrangments regarding air transportation in Indonesia but mechanism to minimize/prevent disputes between consumers and airlines. Consumer dispute resolution with airlines refers to the Consumer Protection Act and Aviation Law. The research reveals that consumer-airlines conflicts can be resolved outside of the court through several dispute resolution models, including Consumer Dispute Settlement Agency, Non-Governmental Consumer Protection Agency, the Directorate of Consumer Protection agreed by the parties, based on Article 1338 of the Civil Code. This paper also show that it is necessary to make a simple dispute resolution system specifically for airline consumers in the form of an airline consumer dispute resolution assembly or a special arbitration agency.

Rating ESG key performance indicators in the airline industry

The environmental, social, and governance (ESG) integration finds itself in a transition with rapid developments worldwide, given that the pandemic incentivized companies and investors to focus on other social and governance measures such as ESG ratings. However, the divergence of ratings from the ESG and a lack of transparency lead the companies to report voluntary indicators without standardization. This study aimed to identify the ESG criteria and the most suitable set of key performance indicators (KPIs) in the airline industry after the impact of COVID-19. Furthermore, the second objective was to determine the appropriate weights and ranking of the identified criteria. The multi-criteria decision-making analytical hierarchical process was applied for this purpose. Additionally, the use of intuitionistic variables delivers a comprehensive model for rating the airlines according to their ESG performance. The most relevant criteria found in the study were critical risk management, greenhouse gas emissions, and systemic risk management. Regarding the KPIs, the top-3 weights were the number of flight accidents, jet fuel consumed and sustainable aviation used, and the number of digital transformation initiatives.

A novel estimation method for weight and center-of-gravity via the aircraft trim data

Aircraft weight and center-of-gravity are significant parameters that affect flight stability and controllability, and unreasonable CG position may cause serious flight accidents. However, there is no airborne sensor can directly measure aircraft weight and center-of-gravity. In view of this, a novel estimation method for weight and center-of-gravity via the aircraft trim data is introduced. Specifically, the trim data calculation process for the aircraft with variable center of mass is given. Then, an inverse interpolation approach based on the binary search algorithm is presented to estimate the aircraft weight and center-of-gravity, and an improved moving average filter is introduced to eliminate the adverse effect on estimation results caused by the high-frequency noise of airborne sensors. Some simulations are given to demonstrate the validity of the proposed estimation method, and it can be drawn from the result that the aircraft longitudinal CG position estimation error is within 0.05 %MAC.