|
|||||
|
|
| 防波堤的人工神经网络Monte Carlo法可靠性分析 | |
| 引用本文： | 张向东,董胜,张磊,张国伟.防波堤的人工神经网络Monte Carlo法可靠性分析[J].中国海洋大学学报(自然科学版),2012,42(4):82-86. |
| 作者姓名： | 张向东 董胜 张磊 张国伟 |
| 作者单位： | 1. 中国海洋大学工程学院,山东青岛266100;中国人民解放军92304部队,海南三亚572011 2. 中国海洋大学工程学院,山东青岛,266100 3. 中交水运规划设计院有限公司,北京,100007 4. 海洋石油工程(青岛)有限公司,山东青岛,266200 |
| 基金项目： | 国家自然科学基金项目，教育部新世纪优秀人才支持计划项目 |
| 摘 要： | 防波堤建设费用巨大,且一旦遭到破坏,后果甚为严重,因此,如何准确地计算防波堤的可靠性意义重大.随着人工神经网络理论的快速发展,人工神经网络方法在结构可靠性分析中的应用逐渐得到重视.基于神经网络的Monte Carlo法计算直立式防波堤的可靠性,概率意义明确.以秦皇岛典型直立堤为算例,采用基于神经网络的Monte Carlo法对直立式防波堤进行可靠性分析时,将直立堤滑动破坏和倾覆破坏的极限状态方程中的所有参数均作为变量处理,并将计算结果与Monte Carlo模拟的直接抽样法、重要抽样法以及独立变量JC法的计算结果进行对比.结果表明:基于神经网络的Monte Carlo法和Monte Carlo模拟的直接抽样法、重要抽样法计算结果相近,而比独立变量JC法的计算结果略低. |
| 关 键 词： | Monte Carlo模拟 人工神经网络 直立式防波堤 可靠度 波浪力 浮托力 |
Application of Artificial Neural Network-Based Monte Carlo Method in Breakwater Reliability Analysis |
|
| ZHANG Xiang-Dong , DONG Sheng , ZHANG Lei , ZHANG Guo-wei.Application of Artificial Neural Network-Based Monte Carlo Method in Breakwater Reliability Analysis[J].Periodical of Ocean University of China,2012,42(4):82-86. | |
| Authors: | ZHANG Xiang-Dong DONG Sheng ZHANG Lei ZHANG Guo-wei |
| Institution: | 1.College of Engineering,Ocean University of China,Qingdao 266100,China;2.Unit 92304 of the PLA,Hainan 572011,China;3.CCCC Water Transportation Consultants Co Ltd,Beijing 100007,China;4.Offshore Oil Engineering Co Ltd,Qingdao 266520,China) |
| Abstract: | The construction cost of breakwaters is large.Once destroyed,the consequences would be very serious.Therefore,correctly calculating breakwater reliability has great significance.With the rapid development of artificial neural network theory,the application of artificial neural network theory in breakwater reliability is gradually attracting more and more attentions.The probabilistic meaning is definite using the artificial neural network-based Monte Carlo method to calculate the failure probability of the vertical breakwaters.The breakwater in Qinhuangdao is taken as an example to inspect and verify the artificial neural network-based Monte Carlo method.All parameters in the sliding failure limit state function and the overturning limit state function are taken as variables.The failure probability and reliability index are calculated using numerical artificial neural network-based Monte Carlo method.The calculation results are compared with those calculated using variable-independent JC method and Monte Carlo simulation(including direct sampling method and importance sampling method of Monte Carlo simulation).It can be concluded that the reliability indexes calculated using the artificial neural network-based Monte Carlo method are similar to those calculated using the Monte Carlo simulation,but are slightly lower than those calculated using the variable-independent JC method. |
| Keywords: | Monte Carlo simulation artificial neural network vertical breakwaters reliability wave force uplifting pressure |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |