基于蝙蝠算法优化模糊神经网络的耙吸挖泥船耙头吸入密度研究  

Research on Optimization of Rake Head Density of Suction Hopper Dredger Based on BA and FNN

作　　者：郝光杰 俞孟蕻[1] 苏贞[1] HAO Guangjie;YU Menghong;SU Zhen(School of Electronic and Information,Jiangsu University of Science and Technology,Zhenjiang 212003)

机构地区：[1]江苏科技大学电子信息学院,镇江212003

出　　处：《计算机与数字工程》2022年第2期436-441,共6页Computer & Digital Engineering

基　　金：中国交通建设股份有限公司科技研发项目“生态智能疏浚技术创新体系构建及关键技术研究与应用”(编号:2035151801)资助。

摘　　要：耙吸挖泥船的耙头产量主要取决于耙头的吸入密度,准确的吸入密度预测对提高耙吸挖泥船疏浚产量具有重要的意义。针对目前对吸入密度预测方法存在精度低、实时效果性差的缺点,提出了一种蝙蝠算法与模糊神经网络相结合的预测方法。通过实测施工数据,构建BA-FNN预测模型。实验表明:BA-FNN预测精度高且稳定性能好,能够为耙头产量预测以及指导施工提供科学有效的参考依据。The output of drag head of drag suction dredger mainly depends on the suction density of drag head. Accurate prediction of suction density is of great significance to improve the dredging output of drag suction dredger. In view of the shortcomings of low accuracy and poor real-time effect of current prediction methods for inhalation density,a prediction method combining bat algorithm and fuzzy neural network is proposed. Based on the measured construction data,the BA-FNN rake head prediction model is constructed. The results show that BA-FNN has high prediction accuracy and good stability,which can provide scientific and effective reference for production prediction and construction guidance.

关 键 词：耙吸挖泥船 耙头模型 吸入密度预测 蝙蝠算法(BA) 模糊神经网络(FNN) 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]