Prediction Model of Aircraft Icing Based on Deep Neural Network

Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed under different icing conditions.Due to the complexity of the icing process,the rapid assessment of ice shape remains an important challenge.In this paper,an efficient prediction model of aircraft icing is established based on the deep belief network(DBN)and the stacked auto-encoder(SAE),which are all deep neural networks.The detailed network structures are designed and then the networks are trained according to the samples obtained by the icing numerical computation.After that the model is applied on the ice shape evaluation of NACA0012 airfoil.The results show that the model can accurately capture the nonlinear behavior of aircraft icing and thus make an excellent ice shape prediction.The model provides an important tool for aircraft icing analysis.

Scallop ice shape characteristics of swept wing based on large-scale icing wind tunnel experiment

Scallop ice is a special phenomenon that occurs during swept wing aircraft passing through icing clouds.It poses a great challenge for the icing safety assessment that the complex scallop ice shape feature and its mechanism are still unclear.In this work,a large-scale icing wind tunnel experiment of swept wing designed by NACA0012 airfoil is conducted in the Icing Wind Tunnel of China Aerodynamics Research and Development Center.The detailed three-dimensional ice shapes under 0°,15°,30°and 45°swept angles are obtained by laser scanning technology.The experimental results show that with the swept angle increasing from 0°to 45°,the 2D double ice horn structures show certain spanwise variation,and finally transform into complete scallop ice with ice thickness greatly enhanced in the stagnation line region.The empirical mode decomposition of the spanwise ice curve captures the high-frequency fluctuation on the scallop ice caused by the small-scale roughness element,while the trend with low frequency is not obvious.Based on the experimental data,a new complete scallop ice geometric model,named 5Points-5Lines-2Arcs(5P-5L-2A)model,is proposed,which can provide important basis for the quantitative description of complex scallop ice shape.