基于FGSO-BP的飞机大修周期预测方法  

FGSO- BP Based Aircraft Overhaul Makespan Prediction Method

作　　者：符式峰 贾晓亮[1] 安磊 常笑 FU Shi-feng;JIA Xiao-liang;AN Lei;CHANG Xiao(Northwestern Polytechnical University,Xi′an 710000,China;Maintenance Group of Equipment Department of Air Force,Beijing 100000,China)

机构地区：[1]西北工业大学,陕西西安710000 [2]空军装备部装备保障大队,北京100000

出　　处：《航空计算技术》2022年第2期67-71,共5页Aeronautical Computing Technique

基　　金：国家自然科学基金项目资助(52075452)。

摘　　要：准确的飞机大修周期分析和预测,能够为飞机大修过程的任务安排、人员配置、飞机大修过程优化等提供决策支持。针对数据驱动的飞机大修周期预测分析及建模,提出融合模糊萤火虫算法和BP神经网络(FGSO-BP)的飞机大修周期预测方法,通过引入模糊隶属函数,可动态改变萤火虫寻优步长,提高萤火虫算法的性能,进一步利用模糊萤火虫算法优化BP神经网络。使用标准测试函数对所提出的算法进行了仿真对比,结果表明算法可有效提高收敛速度和寻优精度。基于某飞机大修历史数据进行了应用验证,表明了方法在飞机大修周期预测中的有效性。Accurate analysis and prediction for makespan can provide decision support for task arrangement, resource allocation and optimization in aircraft overhaul process.Aiming at data-driven aircraft overhaul makespan prediction analysis and modelling, an aircraft overhaul makespan prediction method based on FGSO-BP is proposed.Firstly, fuzzy membership function is introduced to address the limitation of fixed optimization step of traditional GSO algorithm, which improves the performance of GSO algorithm.Then the Fuzzy Glowworm Swarm Optimization algorithm(FGSO) is used to optimize the BP neural network.And the corresponding simulation results show that the convergence speed of the BP neural network optimized by the proposed FGSO algorithm is accelerated and the optimization accuracy is improved.Finally, the FGSO-BP method is verified on an aircraft overhaul makespan application case with satisfied result.

关 键 词：飞机大修 周期预测 萤火虫算法 模糊隶属函数 BP神经网络 

分 类 号：V267[航空宇航科学与技术—航空宇航制造工程]