Development cost prediction of general aviation aircraft using combined estimation technique

Obtaining accurate development cost estimation results of general aviation aircraft is crucial for companies to adopt the best strategy in the development process.To address this problem,this paper proposes a combination of three commonly used single prediction methods.The optimal weight values of the three single prediction methods are determined by utilizing the shortest ideal point method.Ten cost datasets collected from literature are utilized for fitting and testing the combined prediction method,and the weight coefficients of the three individual prediction methods are calculated as 0.6859,0.0035 and 0.3106,respectively.The results of this study indicate that the developed method has better fitting and estimation accuracy than that of the three individual methods,with average fitting and predicting error values of 2.60%and 6.43%,respectively.Additionally,the cost data of military and civil aircraft development from literature are collected for verification.The results further confirm that the proposed method is not only superior to the single prediction methods in terms of high precision but has wider applications.More importantly,this research can provide important reference for general aviation aircraft companies in term of product cost planning and corporate sales strategies.

Aerodynamic/mechanism optimization of a variable camber Fowler flap for general aviation aircraft

A conventional Fowler flap is designed to improve the take-off and landing performances of an aircraft. Because the flight states of general aviation aircraft vary significantly. A Fowler flap with a double-sliding track has been designed, which is ca- pable of changing airfoil camber while cruising and climbing as well as meeting low-speed performance requirements. The aerodynamic characteristics of the variable camber Fowler flap were studied by computational simulation, and cambering was found to be beneficial for improving the lift-to-drag ratio when the lift coefficient was larger than the critical value, below which decambering was more effective; this critical value differed somewhat under different conditions. Taking the mecha- nism into account, the take-off and landing configurations were optimized on the basis of the GA （W）-1 airfoil with a 30% chord Fowler flap. Compared with reference configuration, the maximum lift coefficient of optimized take-off configuration was increased by 6.6% as well as the stalling angle and the lift-to-drag ratio were increased by 1.3° and 7.58%, respectively. Moreover, the maximum lift coefficient of the optimized landing configuration was increased by 6.3%, and the stalling angle was increased by 1.1°; however, the nose-down pitching moment of both configurations increased. Similar results were at- rained on a general aviation aircraft wing/body combination nism was established in a computer-aided design system, achieved by the double-sliding track. A 3D model of the variable-camber Fowler flap driving mecha- and the results showed that all design configurations could be

ADS-B Anomaly Data Detection Model Based on Deep Learning and Difference of Gaussian Approach

Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for positioning of general aviation aircraft.Aim to acquire the accurate position information of aircraft and detect anomaly data,the ADS-B anomaly data detection model based on deep learning and difference of Gaussian(DoG)approach is proposed.First,according to the characteristic of ADS-B data,the ADS-B position data are transformed into the coordinate system.And the origin of the coordinate system is set up as the take-off point.Then,based on the kinematic principle,the ADS-B anomaly data can be removed.Moreover,the details of the ADS-B position data can be got by the DoG approach.Finally,the long short-term memory(LSTM)neural network is used to optimize the recurrent neural network(RNN)with severe gradient reduction for processing ADS-B data.The position data of ADS-B are reconstructed by the sequence to sequence(seq2seq)model which is composed of LSTM neural network,and the reconstruction error is used to detect the anomalous data.Based on the real flight data of general aviation aircraft,the simulation results show that the anomaly data can be detected effectively by the proposed method of reconstructing ADS-B data with the seq2seq model,and its running time is reduced.Compared with the RNN,the accuracy of anomaly detection is increased by 2.7%.The performance of the proposed model is better than that of the traditional anomaly detection models.