摘要
In order to alleviate noise pollution and improve the sustainability of airport operation,it is of great significance to develop an effective method to predict airport aviation noise. A three-layer neural network is constructed to gain computational simplicity and execution economy. With the preferred node number and transfer functions obtained in comparative tests,the constructed network is further optimized through the genetic algorithm for performance improvements in prediction. Results show that the proposed model in this paper is superior in accuracy and stability for airport aviation noise prediction,contributing to the assessment of future environmental impact and further improvement of operational sustainability for civil airports.
探索一种有效的机场航空噪声预测方法对减轻机场噪声污染和提升机场运营的可持续性具有重要意义。为简便、经济地解决机场航空噪声预测问题,本文采用三层神经网络技术进行建模;基于对比试验中获得的最佳神经元个数和不同层间的传递函数,使用遗传算法对所构建的网络进行优化,以进一步提升网络预测性能。结果表明,本文提出的方法在机场航空噪声预测方面表现出了更高的精确度和稳定性,研究结果有利于评估未来机场航空器运行的环境影响,进而提高机场运营的可持续性。
基金
supported by the National Natural Science Foundation of China(No. 61671237)
the Foundation of State Key Laboratory of Air Traffic Management System and Technology(No. SKLATM202003)
the Fundamental Research Funds for Graduates of Nanjing University of Aeronautics and Astronautics (No. kfjj20200735)
