Clear Air Turbulence Avoidance Strategy via Genetic Algorithm & Neural Network Methods

• Main Authors: Hao-Fan Huang, 黃皓汎
• Other Authors: Tung Wan
• Format: Others
• Language: en_US
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/54893682778818764720

碩士 === 淡江大學 === 航空太空工程學系 === 90 === In modern airline’s operation, clear air turbulence (CAT) remains one of the most influential factors in flight safety and flight quality consideration. In this research we use Matlab to create 3-D turbulence based on the real turbulence profiles, and prediction parameters (indices) T1, T2 and T3. The T1 factor is to define the turbulence intensity, the T2 and T3 factors are the response of aircraft in linear acceleration and three angular accelerations. Finally we use the genetic algorithm and combining the genetic algorithm (GA) and annealed neural network (ANN) methods to search the optimum escape trajectory. Results show moderate success that the computational time was shortened by 25% and with the same quality of solutions. It is hoped that the concepts and techniques implemented in this work could be used in future airborne Doppler radar research and flight simulation practice. In this work we first simulate turbulence/gust like three-dimensional wind profiles. The method is to use the Matlab tool and directly combine more then fifty trigonometric function waves. Comparing with real wind velocity profiles, the simulated wind show similar fluctuating behavior and can be used in our flight simulation. Secondly, to quantify the severity of CAT phenomenon, a set of prediction parameters（T1, T2, T3）have been proposed, T1 is three-dimensional turbulence acceleration, T2 is aircraft response in linear translation, and T3 is aircraft response in angular motion. These simulated T values show excellent agreement with real turbulence/gust T values. Thirdly, the classical rigid body, mass/mass distribution fixed flight dynamics equations are solved by standard 4th order Runge-Kutta method. To achieve an optimum flight trajectory in order to avoid the severity of CAT, two methods are employed as the steering tools, namely, the genetic algorithm and the genetic algorithm plus annealed neural network modification method. In our work the real-value GA approach is chosen due to its computation efficiency and similarity it the natural world. Our GA process is implemented as follow: both of T1+ T2+ T3, and T1+ T2+ T3+root mean squares of three Euler angles are assigned as the objective functions. And in the last, to further improve the computation efficiency of our work, the neural network method is added to our GA scheme. The model we selected is annealed neural network. It is relatively new and gives accurate data in a less timely fashion. Results show that this combination of GA and annealed neural network do improve the computation efficiency by 25%. When the CAT avoidance strategy is implemented and optimum flight trajectory achieved, it is obvious that direction attitude angles are also kept minimum. Thus represent a high degree of ride comfort and flight quality. It is hoped that the concepts proposed in this work will improve future passenger flight safety, and we no longer need to worry about clear air turbulence influence in our journey.