Flight Operations Research Articles

Multimodal Approach for Pilot Mental State Detection Based on EEG.

The safety of flight operations depends on the cognitive abilities of pilots. In recent years, there has been growing concern about potential accidents caused by the declining mental states of pilots. We have developed a novel multimodal approach for mental state detection in pilots using electroencephalography (EEG) signals. Our approach includes an advanced automated preprocessing pipeline to remove artefacts from the EEG data, a feature extraction method based on Riemannian geometry analysis of the cleaned EEG data, and a hybrid ensemble learning technique that combines the results of several machine learning classifiers. The proposed approach provides improved accuracy compared to existing methods, achieving an accuracy of 86% when tested on cleaned EEG data. The EEG dataset was collected from 18 pilots who participated in flight experiments and publicly released at NASA's open portal. This study presents a reliable and efficient solution for detecting mental states in pilots and highlights the potential of EEG signals and ensemble learning algorithms in developing cognitive cockpit systems. The use of an automated preprocessing pipeline, feature extraction method based on Riemannian geometry analysis, and hybrid ensemble learning technique set this work apart from previous efforts in the field and demonstrates the innovative nature of the proposed approach.

Fuel consumption prediction for pre-departure flights using attention-based multi-modal fusion

Improper fuel loading decision results in carrying excessive dead weight during flight operation, which will burden the airline operation cost and cause extra waste emission. Existing works mainly focused on the post-event fuel consumption based on flight trajectory. In this work, a novel deep learning model, called FCPNet, is proposed to achieve the fuel consumption prediction (FCP) before the flight departure. Considering the influential factors for aircraft performance, the multi-modal information sources, including the planned route, weather information, and operation details, are selected as the model input to predict fuel consumption. Correspondingly, three modules are innovatively proposed to learn embedding features from multi-modal inputs. Based on the planned route, the graph convolutional network is proposed to mine the spatial correlations in the non-Eulerian route network. Considering the grid attributes of the weather information, the ConvLSTM is applied to learn abstract representations from both the temporal and spatial dimensions, in which the three-dimensional convolution neural networks are also designed to fine-tune intermediate feature maps. The fully connected layer is also proposed to learn informative features from operation details. Finally, an attention-based fusion network is presented to generate the final embedding by considering the unique contributions of the multi-modality sources, which are further applied to predict flight fuel consumption. A binary encoding representation is proposed to formulate the FCP task as a multi-binary classification problem. The proposed model is validated on a real-world dataset, and the results demonstrate that it outperforms other baselines, i.e., achieving a 6.50% mean absolute percentage error, which can practically support the airline operation and global emission control before flight departure.

A Stealth–Distance Dynamic Weight Deep Q-Network Algorithm for Three-Dimensional Path Planning of Unmanned Aerial Helicopter

Unmanned aerial helicopters (UAHs) have been widely used recently for reconnaissance operations and other risky missions. Meanwhile, the threats to UAHs have been becoming more and more serious, mainly from radar and flights. It is essential for a UAH to select a safe flight path, as well as proper flying attitudes, to evade detection operations, and the stealth abilities of the UAH can be helpful for this. In this paper, a stealth–distance dynamic weight Deep Q-Network (SDDW-DQN) algorithm is proposed for path planning in a UAH. Additionally, the dynamic weight is applied in the reward function, which can reflect the priorities of target distance and stealth in different flight states. For the path-planning simulation, the dynamic model of UAHs and the guidance model of flight are put forward, and the stealth model of UAHs, including the radar cross-section (RCS) and the infrared radiation (IR) intensity of UAHs, is established. The simulation results show that the SDDW-DQN algorithm can be helpful in the evasion by UAHs of radar detection and flight operations, and the dynamic weight can contribute to better path-planning results.

A Review on Weather Impact on Aviation Operations: Visibility, Wind, Precipitation, Icing

Meteorological conditions affect aviation, marine, and land transportation, and play an important role in aviation accidents and operations. Wind (Uh), visibility (Vis), and Precipitation rate and amount (PR and PA) are the most important meteorological parameters that affect the terminal weather and in- flight conditions. Weather is considered a causal factor in about 30% of all US aviation accidents (NASA, 1999). Fatal aviation accidents based on the NTSB data related to ceiling, fog, and wind are estimated at 20%, 14%, and 10%, correspondingly. Knowing weather conditions can help to improve operational planning, including fuel consumption and people safety. Wind shear and gust, and turbulence need to be measured or predicted for the flight route and airport terminal weather. In addition, low Vis and ceiling are the second most important weather events affecting aviation operations. Lastly, precipitation type, rate and amount are the third important group of parameters that severely affect the flight operations such as de-icing. Earlier analysis of these events suggested that the meteorological conditions need to be studied in detail to better predict and monitor weather conditions for operational needs. In this respect, both observations quality and numerical weather predictions model simulations should be improved, and both new technologies and statistical models such as machine learning and artificial intelligence analysis should be developed for the aviation operations.

Optimal Energy Consumption Path Planning for Unmanned Aerial Vehicles Based on Improved Particle Swarm Optimization

In order to enhance the energy efficiency of unmanned aerial vehicles (UAVs) during flight operations in mountainous terrain, this research paper proposes an improved particle swarm optimization (PSO) algorithm-based optimal energy path planning method, which effectively reduces the non-essential energy consumption of UAV during the flight operations through a reasonable path planning method. First, this research designs a 3D path planning method based on the PSO optimization algorithm with the goal of achieving optimal energy consumption during UAV flight operations. Then, to overcome the limitations of the classical PSO algorithm, such as poor global search capability and susceptibility to local optimality, a parameter adaptive method based on deep deterministic policy gradient (DDPG) is introduced. This parameter adaptive method dynamically adjusts the main parameters of the PSO algorithm by monitoring the state of the particle swarm solution set. Finally, the improved PSO algorithm based on parameter adaptive improvement is applied to path planning in mountainous terrain environments, and an optimal energy-consuming path-planning algorithm for UAVs based on the improved PSO algorithm is proposed. Simulation results show that the path-planning algorithm proposed in this research effectively reduces non-essential energy consumption during UAV flight operations, especially in more complex terrain scenarios.

Low concentration of indoxacarb interferes with the growth and development of silkworm by damaging the structure of midgut cells

As an important economic insect, Bombyx mori plays an essential role in the development of the agricultural economy. Indoxacarb, a novel sodium channel blocker insecticide, has been widely used for the control of various pests in agriculture and forestry, and its environmental pollution caused by flight control operations has seriously affected the safe production of sericulture in recent years. However, the lethal toxicity and adverse effects of indoxacarb on silkworm remain largely unknown. In this study, the toxicity of indoxacarb on the 5th instar larvae of silkworm was determined, with an LC50 (72 h) of 2.07 mg/L. Short-term exposure (24 h) to a low concentration of indoxacarb (1/2 LC50) showed significantly reduced body weight and survival rate of silkworm larvae. In addition, indoxacarb also led to decreased cocoon weight and cocoon shell weight, but had no significant effects on pupation, adult eclosion, and oviposition. Histopathological and ultrastructural analysis indicated that indoxacarb could severely damage the structure of the midgut epithelial cells, and lead to physiological impairment of the midgut. A total of 3883 differentially expressed genes (DEGs) were identified by midgut transcriptome sequencing and functionally annotated using GO and KEGG. Furthermore, the transcription level and enzyme activity of the detoxification related genes were determined, and our results suggested that esterases (ESTs) might play a major role in metabolism of indoxacarb in the midgut of B. mori. Future studies to examine the detoxification or biotransformation function of candidate genes will greatly enhance our understanding of indoxacarb metabolism in B. mori. The results of this study provide a theoretical basis for elucidating the mechanism of toxic effects of indoxacarb on silkworm by interfering with the normal physiological functions of the midgut.

The Relationship Between On the Job Training Flight Operation Officer and Job Readiness

On the Job Training Flight Operation Officer Relationship with Job Readiness. In this study there are two variables X (On the Job Training Flight Operation Officer), variable Y (Job Readiness) at PT Citilink Indonesia in Cengkareng City. The purpose of this study is to measure the relationship between, On the Job Training Flight Operation Officer PT Citilink Indonesia in Cengkareng City and job readiness of Indonesia Aviation Academy Banyuwangi (APIB) Cadets. The sampling technique in the study was carried out with the Solving formula with a sample of 38 cadets D-III Aircraft Operations Indonesia Aviation Academy Banyuwangi at PT Citilink Indonesia in Cengkareng City. Data analysis uses the pearson product moment correlation test which is used to test independent variables and dependent variables. Based on the results of data analysis using the pearson product moment method, a value of 0.881 with a significant value of 0.000 is less than 0.05 which means it has a very high and significant relationship between, On the Job Training Flight Operation Officer and job readiness. So, it can be concluded that On the Job Training Flight Operation Officer is very closely and significantly related to job readiness.

Swift Assessment of Flexible Elements of High Speed Flexible Couplings for Aircraft Transmission Systems

The High Speed Flexible Coupling (HSFC) known as Power Take-Off shaft (PTO) is used in combat aircraft for connecting engine gearbox with accessory gearbox to transmit power and to accommodate larger misalignments. The HSFC utilizes series of metallic contoured plates as flexible elements. The development of a HSFC shaft assembly involves high cost and time process. Any failure of the HSFC during flight operation will deprive the secondary power system mainly used for controlling the single engine fighter aircraft. To develop the reliable HSFC with minimum developmental cost and time, an innovative approach termed as Swift Assessment of Flexible Elements (SAFE) for the development of HSFC is evolved. A case study of a typical high speed flexible coupling developed using this approach is presented With the SAFE approach, sufficient level of flexibility in design modification, trim down product development cycle time and cost were realized.

The effect of the eruption of mount Hunga-Tonga on density altitude, air pressure and flight operations in eastern Indonesian

There was an eruption of the Hunga Tonga volcano in the Pacific Ocean on January 15, 2022 and produced the phenomenon of Shock Waves in the atmosphere, in addition to sonic booms, and tsunami waves that spread to various parts of the world. Data from the automated weather observing system (AWOS) in several Airports in Indonesia were analyzed to assess the impact of the eruption of Mount Tonga on the Indonesian atmosphere. There are sudden changes in air pressure (QNH) at locations (Airports) including Sorong, Wamena, Ternate, Sumbawa, Biak, Geser, Lombok, Sabu, and Kupang, with a range between 0.6 to 1.9 Mb. These atmospheric waves propagate at a speed of about 1248 km/hour. This drastic change in air pressure is not followed by a significant change in density altitude which affects the effectiveness of the aircraft’s lift, but a sudden change will cause a change in air pressure (QNH) in the altimeter which can cause a change in aircraft altitude. This sudden change has high probability to result in a plane crash due to a stall or undershoot or collision with aircraft.

KARI and NASA JSC Collaborative Endeavors for Joint Korea Pathfinder Lunar Orbiter Flight Dynamics Operations: Architecture, Challenges, Successes, and Lessons Learned

This paper outlines the collaborative efforts between the Korea Aerospace Research Institute (KARI) and the National Aeronautics and Space Administration (NASA) Johnson Space Center (JSC) for the Flight Dynamics (FD) operation of the Korea Pathfinder Lunar Orbiter (KPLO). From the outset of the KPLO program, the joint KARI KPLO FD team and NASA JSC Flight Operations Directorate (FOD) have devoted significant time and effort towards ensuring the mission’s success. This paper begins by introducing the aims and scope of the collaborative work, followed by a detailed description of the efforts made between the KPLO FD team and JSC FOD. This includes the top-level concept, interface architecture, test results, established operation procedures/timeline, and the summary of the joint rehearsal conducted. Finally, the paper discusses the challenges and lessons learned from this journey, particularly from the practical FD operational perspectives. Thanks to the joint team’s collaborative efforts, KPLO has successfully entered lunar orbit and is performing its mission exceptionally well. The joint experience has fostered mutual trust between KARI and NASA JSC, serving as a foundation for further cooperation and collaboration. The efforts and outcomes described in this work will provide valuable insights to experts worldwide who are willing to foster similar international collaborations in the future.

Analisis Manajemen Parking Stand Terhadap Keselamatan Pergerakan Pesawat Udara Di Bandara Udara Komodo Labuan Bajo

Aviation safety, especially on the air side, is very important, so there is a need for supervision so that it can be maximized in maintaining the smooth running of activities on the apron, this has been regulated in Circular Letter Number 23 of 2011 concerning Improving Operational Safety at the Apron. One of the activities at Apron is the activity carried out by the Apron Movement Control Unit, namely determining the stand packing for the aircraft parking lot. Management Parking Stand which greatly determines safety in flight operations. Komodo Labuan Bajo Airport has 3 parking stands that are used for non-commercial planes such as private planes, private jets, however, all of these three parking stands cannot be used. from the parking stand because the wings between the two aircraft were too close or the sizes of the parking stands between A1, A2, and A3 were different sizes and the three parking stands are still actively used today. This study aims to determine parking stand management applied at Labuan Bajo Airport and parking stand management for the safety of aircraft movements at Komodo Labuan Bajo Airport.This study used a qualitative method with data collection methods in the form of observation, interviews, and documentation. Sources of data in this study were obtained from primary data and secondary data. This research was conducted from May to June 2023 at Labuan Bajo Airport.The results of this study Labuan Bajo Airport have 7 parking stands, of which 2 parking stands are used for garbarata, and 5 parking stands are used for remote and parking stands for charters where not many charter planes enter Labuan Bajo Airport and to maintain flight safety in determine the parking stand The AMC Unit is working according to the SOP that has been set. When there are planes that will be landing at the same time, the AMC Unit will ask the ATC for an estimate of the aircraft, then the AMC Unit will determine the parking stand based on the type of aircraft that will be landing, for parking stands 5 and 6 can be used for Boeing and Airbus aircraft, parking stand 3 is used for ATR type aircraft, and parking stands 6 and 7 can be used for Boeing or Airbus type aircraft.

Variation of Pilots’ Mental Workload Under Emergency Flight Conditions Induced by Different Equipment Failures: A Flight Simulator Study

Pilots’ excessive mental workload could reduce their ability to perform concurrent tasks during emergency flights, which is one of the most critical aviation safety concerns. Several past efforts have attempted to investigate the underlying issues, but all had limited success owing to the challenge of collecting representative data under realistic operating conditions. This study aimed to address this challenge by conducting a flight simulator study involving a comparatively large number of participants, who were pilot cadets with flight experience, and using noninvasive functional near-infrared spectroscopy (fNIRS) to collect the pilots’ brain activity data. Pilots’ subjective ratings and brain activity records were collected over a total of 75 simulated flights under three subtask scenarios comprising different equipment failures. A statistical analysis was carried out on the subjective ratings and on the changes observed in the saturation of the oxyhemoglobin (ΔOxyHb) of individual fNIRS channels. The mental workload of the pilots was classified using a support vector machine hierarchical combination classifier, focusing on the question of whether it is feasible to classify pilots’ mental workload using brain activity signals (i.e., ΔOxyHb). The results suggested that the pilots’ mental workload levels were highly associated with the ΔOxyHb measures as well as with the activities of different brain regions, including the prefrontal-, motor-, and occipital cortex. The findings from this study could provide a reference for optimizing pilot training systems and improving pilot performance during emergency flight operations.

The influence of safety-specific transformational leadership on safety behavior among Chinese airline pilots: The role of harmonious safety passion and organizational identification

Safety is a key consideration in the worldwide civil aviation industry, in which an increasing number of aviation accidents are related to flight crew performance. Based on social exchange theory and social identity theory, the primary objective of this study is to examine the relationships among safety-specific transformational leadership, harmonious safety passion, organizational identification, and safety behavior among Chinese airline pilots. Data was collected from 332 commercial airline pilots from China Eastern Airlines Co., Ltd. using self-report questionnaires. Correlation analysis, mediation analysis and moderated analysis were conducted. The results show that safety-specific transformational leadership has a positive effect on safety behavior and an indirect effect on safety behavior through the influence of harmonious safety passion. Harmonious safety passion acts as a mediating role, whereas organizational identification acts as a moderating role in the relationship between safety-specific transformational leadership and safety behavior. The managerial implications stemming from the findings of this study may promote pilots’ safety behavior, improve airline management and maintain safety of flight operation.

SWOT re-entry: Maneuver strategy and risk computation

The Surface Water & Ocean Topography (SWOT) mission is a joint NASA/CNES mission launched on December 16th, 2022 dedicated to oceanography and continental hydrology. Once the scientific mission is over, SWOT will have to perform a controlled re-entry to comply with the French Space Operation Act (FSOA). Indeed, the launch authorization is subject to the respect of the FSOA, fully applicable since 2020. The main requirement applying to the end-of-life of the satellite consists in limiting the casualty area and then the probability of having a victim on ground under the threshold of 10−4 in case of a natural re-entry. With a mass over two tons and a casualty area of about 47 m2, SWOT cannot comply with this requirement. Thus, the platform has been designed with a specific propulsion system to carry out end-of-life maneuvers leading to an atmospheric re-entry and impact in the South Pacific Ocean Uninhabited Area (SPOUA). CNES is in charge of defining the re-entry maneuvers strategy, performing end-of-life operations and evaluating the risk of casualties in case of failure during nominal strategy. This paper addresses these topics. The computation of the ten maneuvers used to decrease the perigee altitude and finally target the SPOUA is performed using the DOORS tool. Before describing the maneuvers strategy, this paper presents an overview of the current functionalities of this tool, which has been already used during the five ATV missions and ASTRA-1K de-orbit twenty years ago. DOORS is mainly used for mission analysis purposes, but for end-of-life operations it can be activated by the operational Flight Dynamics System (FDS). Finally, the casualty risk estimation relies on the use of two other CNES tools, DEBRISK and ELECTRA, whose methods are presented. The list of surviving fragments has been computed using the new DEBRISK-V3 methodology in case of controlled and uncontrolled re-entry. The risk of human casualty is evaluated using ELECTRA and its Monte Carlo simulations. This tool generates numerous trajectories of the satellite and its fragments with various dispersed variables. The impact locations compared to an up-to-date grid of the World population lead to the probability of victims. The complete risk of SWOT controlled re-entry encompasses both the risk related to a failure during the last re-entry maneuver and the risk associated with the natural re-entry in case a failure occurs before this last burn (during the mission or during the first re-entry maneuvers). Both of them are weighted by their probability of occurrence.

Benchmark Evaluation of Hybrid Fixed-Flapping Wing Aerial Robot With Autopilot Architecture for Autonomous Outdoor Flight Operations

Benchmark Evaluation of Hybrid Fixed-Flapping Wing Aerial Robot With Autopilot Architecture for Autonomous Outdoor Flight Operations

Pilots’ Knowledge-Based Decision-Making Process in Flight Operations in Civil Aviation

Sivil havacılık sektörü özellikle II. Dünya Savaşı sonrasında yaşanan teknolojik gelişmeler ve yapılan yatırımlar sayesinde büyük bir gelişim ve dönüşüm süreci içerisine girmiştir. Küreselleşmeye bağlı olarak gelişen pazar payı ve artan rekabet koşulları nedeniyle geçmişe göre daha ekonomik, daha hızlı, güvenli, tercih edilen bir ulaşım seçeneği haline gelmiştir. Pilotlar uçuş faaliyetlerinin temel aktörüdür ve uçuş operasyonlarının merkezinde yer almaktadır. Çalışmanın amacı, sivil havayolu ulaşımında görevli pilotların bilgiye dayalı kararları nasıl aldıklarının anlaşılmasıdır. Pilotların uçuşun planlanmasından tamamlanmasına kadar geçen tüm aşamalarda ihtiyaç duydukları bilgilere bilişim teknolojileri ve otomasyona dayalı kokpit sistemleri aracılığıyla gerçek zamanlı olarak ulaşabilmesi önemlidir. Bu çalışmada literatür taraması yapılmış, pilotların uçuş operasyonlarında bilgiyi edinme ve kullanımlarına yönelik konular açıklanmıştır.

A Study on the Flight Operations Quality Assurance System for Predictive Safety Management of the Republic of Korea Air Force

A Study on the Flight Operations Quality Assurance System for Predictive Safety Management of the Republic of Korea Air Force

Implementation of “digital twin” technology within the thermo-elastic distortion testing of a precision carbon fiber reflector for the spacecraft antenna subsystem

Mirror antenna subsystems (AS) with the deployable reflectors are important integral parts of the telecommunication spacecraft payloads and provide reception and transmission of the information in a given service area [14]. The reflector design shall provide strength and stiffness, specified radiofrequency (RF) characteristics and antenna pattern boresight error of the AS. Performance compliance shall be approved in the frame of ground experimental testing, and thermo-elastic distortion (TED) testing to assess their effect on the antenna pattern boresight error is the part of the ground testing. This testing is hard to carry out because of the following aspects resulting in lack of the guaranteed achieved criteria to assess the test results: considerable difference of thermal and physics behavior between carbon-fiber-reinforced polymer (CFRP) filler and epoxide component and the steep CFRP anisotropy result in increased variation of the layer strain-stress state and internal stresses which make the design behavior undefined under thermal environment; it is almost impossible in the frame of the testing to implement and maintain the real map of the thermal fields of specified accuracy on the large-sized object due to the fact that the temperature in a giant thermal chamber is extremely varying; in the frame of testing it is possible to carry out few optical measurements for the deformed reflector surface points which are not enough to provide the required level of confidence for geometric parameters variation; the test lasts 50 days and requires cost-intensive chamber exploitation, huge power consumption operating fluid rate (liquid nitrogen), expensive equipment providing thermal modes. Development and implementation of the cutting-edge digital twin technology is the effective method to address TED testing issue. The main idea of the technology is to substitute real object to be tested with digital model verified based their parameter compliance using convergence criteria. The paper presents technology block diagram, convergence criteria and correlation technique of the predicted and measured TED cases. Evaluation data of the deformed reflector effects on AS RF performances are given and demonstrate that performances comply with the specified requirements and qualify successfully the digital twin technology under real testing. The digital twin was successfully implemented in 2019 year in JSC RESHETNEV in the frame of reflector TED testing for RF antenna subsystem with shaped antenna pattern for Express-AMU7 spacecraft, which was launched and accepted for the flight operation in 2021. This is the first time in the Russian space industry tests using the digital twin technology of a domestic reflector for RF space AS with parameters at the imported analogues level have been successfully qualified. The qualification of this technology will ensure the competition of domestic high-tech developments and will solve the problems of import substitution and increase the share of the Russian component in the global space telecommunications market.

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.

Unstable Approach Detection and Analysis Based on Energy Management and a Deep Neural Network

The study of managing risk in aviation is the key to improving flight safety. Compared to the other flight operation phases, the approach and landing phases are more critical and dangerous. This study aims to detect and analyze unstable approaches in Taiwan through historical flight data. In addition to weather factors such as low visibility and crosswinds, human factors also account for a large part of the risk. From the accidents studied in the stochastic report of the Flight Safety Foundation, nearly 70% of the accidents occurred during the approach and landing phases, which were caused by improper control of aircraft energy. Since the information of the flight data recorder (FDR) is regarded as the airline’s confidential information, this study calculates the aircraft’s energy-related metrics and investigates the influence of non-weather-related factors on unstable approaches through a publicly available source, automatic dependent surveillance-broadcast (ADS-B) flight data. To evaluate the influence of weather- and non-weather-related factors, the outliers of each group classified by weather labels are detected and eliminated from the analysis by applying hierarchical density-based spatial clustering of applications with noise (HDBSCAN), which is utilized for detecting abnormal flights that are spatial anomalies. The deep learning method was adopted to detect and predict unstable arrival flights landing at Taipei Songshan Airport. The accuracy of the prediction for the normalized total energy and trajectory deviation of all flights is 85.15% and 82.11%, respectively. The results show that in different kinds of weather conditions, or not considering the weather, the models have similar good performance. The input features were analyzed after the model was obtained, and the flights detected as abnormal are discussed.