A new development of ANFIS-GMDH optimized by PSO to predict pile bearing capacity based on experimental datasets

作     者：Harandizadeh, Hooman Jahed Armaghani, Danial Khari, Mahdy 

作者机构：Shahid Bahonar Univ Kerman Fac Engn Dept Civil Engn Pajoohesh SqPOB 76169133 Kerman Iran Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Islamic Azad Univ East Tehran Branch Dept Civil Engn Tehran Iran 

出 版 物：《ENGINEERING WITH COMPUTERS》 (计算机在工程中的应用)

年 卷 期：2021年第37卷第1期

页      面：685-700页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Ultimate pile bearing capacity Deep foundation ANFIS– GMDH– PSO model PSO Algorithm FPNN– GMDH model GMDH network 

摘      要：Prediction of ultimate pile bearing capacity with the aid of field experimental results through artificial intelligence (AI) techniques is one of the most significant and complicated problem in pile analysis and design. The aim of this research is to develop a new AI predictive models for predicting pile bearing capacity. The first predictive model was developed based on the combination of adaptive neuro-fuzzy inference system (ANFIS) and group method of data handling (GMDH) structure optimized by particle swarm optimization (PSO) algorithm called as ANFIS-GMDH-PSO model;the second model introduced as fuzzy polynomial neural network type group method of data handling (FPNN-GMDH) model. A database consists of different piles property and soil characteristics, collected from literature including CPT and pile loading test results which applied for training and testing process of developed models. Also a common artificial neural network (ANN) model was applied as a reference model for comparing and verifying among hybrid developed models for prediction. The modelling results indicated that improved ANFIS-GMDH model achieved relatively higher performance compared to ANN and FPNN-GMDH models in terms of accuracy and reliability level based on standard statistical performance indices such as coefficient of correlation (R), mean square error, root mean square error and error standard deviation values.