Deep learning-driven interval uncertainty propagation for aeronautical structures

Interval Uncertainty Propagation(IUP)holds significant importance in quantifying uncertainties in structural outputs when confronted with interval input parameters.In the aviation field,the precise determination of probability models for input parameters of aeronautical structures entails substantial costs in both time and finances.As an alternative,the use of interval variables to describe input parameter uncertainty becomes a pragmatic approach.The complex task of solving the IUP for aeronautical structures,particularly in scenarios marked by pronounced nonlinearity and multiple outputs,necessitates innovative methodologies.This study introduces an efficient deep learning-driven approach to address the challenges associated with IUP.The proposed approach combines the Deep Neural Network(DNN)with intelligent optimization algorithms for dealing with the IUP in aeronautical structures.An inventive extremal value-oriented weighting technique is presented,assigning varying weights to different training samples within the loss function,thereby enhancing the computational accuracy of the DNN in predicting extremal values of structural outputs.Moreover,an adaptive framework is established to strategically balance the global exploration and local exploitation capabilities of the DNN,resulting in a predictive model that is both robust and accurate.To illustrate the effectiveness of the developed approach,various applications are explored,including a high-dimensional numerical example and two aeronautical structures.The obtained results highlight the high computational accuracy and efficiency achieved by the proposed approach,showcasing its potential for addressing complex IUP challenges in aeronautical engineering.

AEROELASTIC TAILORING OF AERONAUTICAL COMPOSITE WING STRUCTURES

This paper deals with the aeroelastic tailoring of aeronautical composite wing surfaces. The objective function is structural weight. Multi constraints, such as displacements, flutter speed and gauge requirements, are taken into consideration. Finite element method is used to the static analysis. Natural vibration modes are obtained by the spectral transformation Lanczos method. Subsonic doublet lattice method is used to obtain the unsteady aerodynamics.The critical flutter speed is generated by V-g method.The optimal problem is solved by the feasible direction method.The thickness of the composite wing skin is simulated by bicubic polynomials, whose coefficients combined with the cross-sectional areas or thicknesses of other finite elements are the design variables. The scale of the problem is reduced by variable linkage. Derivative analysis is performed analytically.Two composite wing boxes and a swept-back composite wing are optimized at the end of the paper.

Development Trend of NC Machining Accuracy Control Technology for Aeronautical Structural Parts

High-performance five-axis computer numerical control machine tools are widely used in the processing of Aeronautical Structural parts. With the increase of service life, the precision of CNC machine tools equipped by aeronautical manufacturing enterprises is declining day by day, while the new generation of aircraft structural parts are developing towards integration, large-scale, complexity, thin-walled and lightweight. It is very easy to produce dimension overshoot and surface quality defects due to unstable processing technology. The machining accuracy of aircraft structural parts is also affected by complex factors such as cutting load, cutting stability, tool error, workpiece deformation, fixture deformation, etc. Because of the complexity of structure and characteristics of Aeronautical Structural parts, the consistency and stability of cutting process are poor. It is easy to cause machining accuracy problems due to tool wear, breakage and cutting chatter. Relevant scholars have carried out a lot of basic research on NC machining accuracy control and achieved fruitful results, but the research on NC machining accuracy control of Aeronautical structural parts is still less. This paper elaborates from three aspects: error modeling method of NC machine tools, error compensation method, prediction and control of machining accuracy, and combines the characteristics of Aeronautical Structural parts, the development trend and demand of NC machining accuracy control technology are put forward.