Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost

Li, Sibo; Qin, Jingkun; He, M.; Paoli, Roberto

doi:10.3390/aerospace7040036

Cited by 38 publications

(23 citation statements)

References 30 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, with the enhancement of computers' processing capability, the big data technology is developing rapidly and has been widely used in many branches of science and technology. Machine learning (ML) methods such as eXtreme gradient boosting (Xgboost), 38 support vector machine (SVM), 39 random forest, 40 and artificial neural network (ANN) 41‐46 have been increasingly used in the field of chemical engineering. It was around since the 1940s, 47 but it was not until the last two decades that the ANN was applied to engineering (e.g., the filtered drag development using ANN 32,41,46 ).…”

Section: Introductionmentioning

confidence: 99%

Data‐driven modeling of mesoscale solids stress closures for filtered two‐fluid model in gas–particle flows

2021

View full text Add to dashboard Cite

This study performs data‐driven modeling of mesoscale solids stress closures for filtered two‐fluid model (fTFM) in gas–particle flows via an artificial neural network (ANN) based machine learning method. The data used for developing the ANN‐based predictive data‐driven modeling framework is systematically filtered from fine‐grid simulations. The loss function optimization result reveals that coupling two loss functions promotes more accurate predictions of the mesoscale solids stresses than using a single loss function. Further comprehensive assessments of closure markers demonstrate a systematic dependence of the mesoscale solids stresses on the filtered particle velocity and its gradient as additional anisotropic markers, instead of using the conventional isotropic filtered rate of solid phase deformation as a closure marker. An optimal three‐marker mesoscale closure is thus proposed. Comparative analysis of the conventional filtered model and present three‐marker model shows that the data‐driven model can substantially enhance the prediction accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Data‐driven modeling of mesoscale solids stress closures for filtered two‐fluid model in gas–particle flows

2021

View full text Add to dashboard Cite

show abstract

“…XGBoost uses a gradient descent algorithm, minimizing loss when adding new models. The models in XGBoost are decision trees that are generated and added sequentially [44]. A detailed explanation of the computations can be found in the study by Chen and Guestrin [45].…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

A Comprehensive Study of Machine Learning Methods on Diabetic Retinopathy Classification

Gürcan¹,

Beyca²,

Doğan³

2021

IJCIS

View full text Add to dashboard Cite

Diabetes is one of the emerging threats to public health all over the world. According to projections by the World Health Organization, diabetes will be the seventh foremost cause of death in 2030 (WHO, Diabetes, 2020. https://www.afro.who.int/healthtopics/diabetes). Diabetic retinopathy (DR) results from long-lasting diabetes and is the fifth leading cause of visual impairment, worldwide. Early diagnosis and treatment processes are critical to overcoming this disease. The diagnostic procedure is challenging, especially in low-resource settings, or time-consuming, depending on the ophthalmologist's experience. Recently, automated systems now address DR classification tasks. This study proposes an automated DR classification system based on preprocessing, feature extraction, and classification steps using deep convolutional neural network (CNN) and machine learning methods. Features are extracted from a pretrained model by the transfer learning approach. DR images are classified by several machine learning methods. XGBoost outperforms other methods. Dimensionality reduction algorithms are applied to obtain a lowerdimensional representation of extracted features. The proposed model is trained and evaluated on a publicly available dataset. Grid search and calibration are used in the analysis. This study provides researchers with performance comparisons of different machine learning methods. The proposed model offers a robust solution for detecting DR with a small number of images. We used a transfer learning approach, which differs from other studies in the literature, during the feature extraction. It provides a data-driven, cost-effective solution, which includes comprehensive preprocessing and fine-tuning processes.

show abstract

“…Based on the training data, ML models are capable of addressing strong nonlinearity with the aid of constructing black-box input-output mapping [23]. Due to the complex interaction of multiple flight conditions, the mapping relationship between the input flight conditions and the output aircraft icing severity features is likely to be strongly nonlinear [24]; thus, ML has been implemented in several applications in aircraft icing to predict ice shape [25], icing area, maximum ice thickness, icing severity level [24,26] and the effect of ice on the aircraft aerodynamic performance [27]. The details will be given in Section 4.…”

Section: Introductionmentioning

confidence: 99%

Aircraft Icing Severity Evaluation

Paoli

2022

Encyclopedia

Self Cite

View full text Add to dashboard Cite

Aircraft icing refers to the ice buildup on the surface of an aircraft flying in icing conditions. The ice accretion on the aircraft alters the original aerodynamic configuration and degrades the aerodynamic performances and may lead to unsafe flight conditions. Evaluating the flow structure, icing mechanism and consequences is of great importance to the development of an anti/deicing technique. Studies have shown computational fluid dynamics (CFD) and machine learning (ML) to be effective in predicting the ice shape and icing severity under different flight conditions. CFD solves a set of partial differential equations to obtain the air flow fields, water droplets trajectories and ice shape. ML is a branch of artificial intelligence and, based on the data, the self-improved computer algorithms can be effective in finding the nonlinear mapping relationship between the input flight conditions and the output aircraft icing severity features.

show abstract

Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost

Cited by 38 publications

References 30 publications

Data‐driven modeling of mesoscale solids stress closures for filtered two‐fluid model in gas–particle flows

Data‐driven modeling of mesoscale solids stress closures for filtered two‐fluid model in gas–particle flows

A Comprehensive Study of Machine Learning Methods on Diabetic Retinopathy Classification

Aircraft Icing Severity Evaluation

Contact Info

Product

Resources

About