Extracting Unmeasured Parameters Based on Quick Access Recorder Data Using Parameter-Estimation Method

Sembiring, Javensius; Drees, Ludwig; Holzapfel, Florian

doi:10.2514/6.2013-4848

Cited by 8 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, scholars use QAR data to conduct research primarily in the following domains: Mathematical analysis and processing methods to estimate data parameters that are not directly recorded in QAR data (Sembiring et al , 2013; Sembiring et al , 2018), determination of energy dissipation rate (EDR) through wind component of QAR data and pollutant emissions during flight (Kim et al , 2022; Huang et al , 2019; Pan et al , 2021), identification of normal and abnormal flights during operation (Li et al , 2011), identification of anomalous in-flight data (Chen et al , 2022; Jesse et al , 2008), consideration of the tradeoff between accuracy and complexity in Engine Health Management (Ren et al , 2022), resolution of the similarity issue in QAR data (Feng et al , 2012), diagnosis of aircraft exceedance event (Gao et al , 2014) and enhancement of maintenance fault diagnosis and prevention efficiency (Yang and Dong, 2012; Yang and Meng, 2012). Diverse data analysis systems are developed to explore operational risks, evaluate and assess pilot flight technology, identify technical training problems, optimize training processes, enhance flight training quality, monitor flight quality, engine status and elevate the underutilized QAR data rate (Haverdings and Chan, 2010; Sun, 2003; Li, 2010).…”

Section: Introductionmentioning

confidence: 99%

Risk assessment method for controlled flight into terrain of airlines based on QAR data

Guo

Sun

et al. 2023

AEAT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to assess the risk of controlled flight into terrain (CFIT) for airlines and to develop a practical method for evaluating and predicting CFIT risk to ensure safe and efficient airline operations. Design/methodology/approach In accordance with the monitoring project specification issued by the Flight Standards Department of the Civil Aviation Administration of China (CAAC), a preliminary draft of evaluation indicators for CFIT risk was developed based on the literature review and semi-structured interviews. Fifteen aviation experts were then selected and invited to participate in a Delphi method to revise the draft. Analytic hierarchy process (AHP) and entropy weight method were used to determine the combined weight of the indicators. The variable fuzzy set model and quick access recorder (QAR) data were applied to evaluate the CFIT risk of an airline from 2007 to 2018, and the classification results were compared with actual operational data. Findings The research findings reveal that the six most significant monitoring items affecting CFIT risk are incorrect configuration settings during landing, loss of altitude during climbing, ground proximity warning, G/S deviation, flap extension delay during landing and incorrect takeoff configuration. The CFIT risk of airlines has shown an increasing trend since 2015. The values in 2010, 2017 and 2018 were greater than 2 and less than 2.5, indicating that the CFIT risk is at Level 2, close to Level 3, and the risk is low but approaching medium. Practical implications Using the combination weight determined by AHP and entropy weight method to rank the weight of 15 monitoring items, airlines can take necessary measures (simulator training, knowledge training) to reduce the occurrence of monitoring items with high weight to reduce CFIT risk. This risk assessment method can quantitatively evaluate the CFIT risk of airlines and provide theoretical guidance and technical support for airlines to formulate safety management measures and flight training programs, enabling the interconnection between QAR data and flight quality. Originality/value The proposed method in this study differs from traditional approaches by offering a quantitative assessment of CFIT risk for airlines and enabling the interconnection between QAR data and flight quality.

show abstract

Section: Introductionmentioning

confidence: 99%

Risk assessment method for controlled flight into terrain of airlines based on QAR data

Guo

Sun

et al. 2023

AEAT

View full text Add to dashboard Cite

show abstract

“…Although the concept of integrating scientific knowledge and machine learning models has only become a popular topic of scientific research in the last few years, there is already extensive literature on this topic [22][23][24]. In the last decade, there has been an increase in utilizing operational flight data, namely Quick Access Recorder (QAR) or Flight Data Recorder (FDR) [25] for many applications such as performance monitoring, anomaly detection, or weather forecasting [26][27][28][29]. These data consist of historical logs of all parameters that can be measured or observed through on-board sensors and systems.…”

Section: Introductionmentioning

confidence: 99%

Physics Guided Deep Learning for Data-Driven Aircraft Fuel Consumption Modeling

Uzun

Demirezen²,

Tsourdos

2021

Aerospace

View full text Add to dashboard Cite

This paper presents a physics-guided deep neural network framework to estimate fuel consumption of an aircraft. The framework aims to improve data-driven models’ consistency in flight regimes that are not covered by data. In particular, we guide the neural network with the equations that represent fuel flow dynamics. In addition to the empirical error, we embed this physical knowledge as several extra loss terms. Results show that our proposed model accomplishes correct predictions on the labeled test set, as well as assuring physical consistency in unseen flight regimes. The results indicate that our model, while being applicable to the aircraft’s complete flight envelope, yields lower fuel consumption error measures compared to the model-based approaches and other supervised learning techniques utilizing the same training data sets. In addition, our deep learning model produces fuel consumption trends similar to the BADA4 aircraft performance model, which is widely utilized in real-world operations, in unseen and untrained flight regimes. In contrast, the other supervised learning techniques fail to produce meaningful results. Overall, the proposed methodology enhances the explainability of data-driven models without deteriorating accuracy.

show abstract

“…Therefore, they are not suitable to quantify the operational risk for a specific airline or airport. Instead, wind estimated from operational flight data in the onboard Quick Access Recorder (QAR) [ 6 , 7 ], as a sufficient wind database, allows us to analyze the specific statistical characteristics of the real wind conditions.…”

Section: Introductionmentioning

confidence: 99%

Modeling of Stochastic Wind Based on Operational Flight Data Using Karhunen–Loève Expansion Method

Wang

Beller

Czado

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Wind has a significant influence on the operational flight safety. To quantify the influence of the wind characteristics, a wind series generator is required in simulations. This paper presents a method to model the stochastic wind based on operational flight data using the Karhunen–Loève expansion. The proposed wind model allows us to generate new realizations of wind series, which follow the original statistical characteristics. To improve the accuracy of this wind model, a vine copula is used in this paper to capture the high dimensional dependence among the random variables in the expansions. Besides, the proposed stochastic model based on the Karhunen–Loève expansion is compared with the well-known von Karman turbulence model based on the spectral representation in this paper. Modeling results of turbulence data validate that the Karhunen–Loève expansion and the spectral representation coincide in the stationary process. Furthermore, construction results of the non-stationary wind process from operational flights show that the generated wind series have a good match in the statistical characteristics with the raw data. The proposed stochastic wind model allows us to integrate the new wind series into the Monte Carlo Simulation for quantitative assessments.

show abstract

Extracting Unmeasured Parameters Based on Quick Access Recorder Data Using Parameter-Estimation Method

Cited by 8 publications

References 2 publications

Risk assessment method for controlled flight into terrain of airlines based on QAR data

Risk assessment method for controlled flight into terrain of airlines based on QAR data

Physics Guided Deep Learning for Data-Driven Aircraft Fuel Consumption Modeling

Modeling of Stochastic Wind Based on Operational Flight Data Using Karhunen–Loève Expansion Method

Contact Info

Product

Resources

About