检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:许诺雅 张敏[1] 张鏖 沈俊 XU Nuoya;ZHANG Min;ZHANG Ao;SHEN Jun(College of Engineering,Ocean University of China,Qingdao 266100,Shandong,China;Institute of Defense Engineering,AMS,PLA,Beijing 100036,China)
机构地区:[1]中国海洋大学工程学院山东省海洋工程重点实验室,山东青岛266100 [2]军事科学院国防工程研究院,北京100036
出 处:《中国海洋平台》2023年第3期42-48,共7页China offshore Platform
基 金:国家自然科学基金面上项目(编号:51879247,52171281);山东省重点研发计划(编号:2020CXGC010702)。
摘 要:提出一种基于NARX(Nonlinear Auto-Regressive Model with Exogenous Inputs)神经网络和谐波探测法的非线性系统传递函数识别方法。该方法可基于实测响应数据,采用NARX神经网络方法对结构响应模型进行训练。在此基础上采用谐波探测法得到系统响应传递函数。选取深海半潜浮式平台及系泊系统为研究对象,计算平台及其系泊系统在不同波浪工况作用下的时域耦合响应,以波高和系泊缆张力时程作为数据集,利用NARX神经网络结合谐波探测法辨识此系泊系统的响应传递函数。采用识别的传递函数预测系泊缆在不同海况下的张力响应,并与数值计算结果进行对比,证明NARX神经网络结合谐波探测法可较好地识别系泊浮体系统的非线性响应传递函数,并能够对系泊系统的张力响应进行准确预测。A transfer function identification method of nonlinear system based on NARX(Nonlinear Auto-Regressive Model with Exogenous Inputs)neural network and harmonic probing is proposed.In this method,the NARX neural network is used to train the structural response model based on the measured response data.On this basis,the harmonic probing method is used to obtain the system response transfer functions.Taken the semi-submersible platform and its mooring system as the object,the time-domain coupling responses of the platform and its mooring system in irregular waves are calculated.Taken the wave height and mooring line tension time history as the data set,the response transfer functions of the mooring system are identified by NARX neural network combined with harmonic probing.The tension responses of the mooring line under different sea conditions are predicted by identified transfer functions.Through comparing the predicted responses with the numerical results,it is proved that NARX neural network combined with harmonic probing can identify the nonlinear response transfer functions of moored floating body system and accurately predict the tension responses of mooring system.
关 键 词:传递函数识别 NARX神经网络 谐波探测 系泊缆 响应预测
分 类 号:P751[交通运输工程—港口、海岸及近海工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222