An Advanced Probabilistic Neural Network for the Design of Breakwater Armor Blocks

作     者：Dookie KIM Dong Hyawn KIM Seongkyu CHANG Gil Lim YOON 

作者机构：Department of Civil and Environmental EngineeringKunsan National UniversityKunsanJeonbukKorea Department of Ocean System EngineeringKunsan National UniversityKunsanJeonbukKorea Coastal Engineering Research DepartmentKORDIAnsanGyeonggiKorea 

出 版 物：《China Ocean Engineering》 (中国海洋工程（英文版）)

年 卷 期：2007年第21卷第4期

页      面：597-610页

核心收录：

学科分类：081505[工学-港口、海岸及近海工程] 08[工学] 0815[工学-水利工程] 0824[工学-船舶与海洋工程] 0814[工学-土木工程] 082401[工学-船舶与海洋结构物设计制造] 

基　　金：This work was supported by grant PM484400 PM41500 from"High-Tech Port Research Program"founded by Ministry of Maritime Affairs and Fisheries of Korean Government 

主　　题：breakwater armor block stability number multivariate gaussian distribution classigication artificial neural network (ANN) advanced probabilistic neural network (APNN) 

摘      要：In this study, an advanced probabilistic neural network （APNN） method is proposed to reflect the global probability density function （PDF） by summing up the heterogeneous local PDF which is automatically determined in the individual standard deviation of variables. The APNN is applied to predict the stability number of armor blocks of breakwaters using the experimental data of＇ van der Meet, and the estimated results of the APNN are compared with those of an empirical formula and a previous artificial neural network （ANN） model. The APNN shows better results in predicting the stability number of armor bilks of breakwater and it provided the promising probabilistic viewpoints by using the individual standard deviation in a variable.