Feasibility of a novel predictive technique based on artificial neural network optimized with particle swarm optimization estimating pullout bearing capacity of helical piles

This study aimed to assess particle swarm optimization (PSO) enhanced with an artificial neural network (ANN) for the prediction of the Pul (pullout resistance of helical piles in pure cohesionless soils). To make data sets of training and testing as to the expanded predictive models, 36 laboratory experiments were performed. The database involved 27 experiments for the training data sets (e.g., 80% of the whole database) and 9 experiments for the testing data sets (e.g., a range of 20% of the whole database). In addition, variables of the ANN algorithm (e.g., neurons in each hidden layer) and PSO algorithm, such as population size, were optimized utilizing a series of trial-and-error processes. The input parameters that were used in the analysis include density, embedment ratio, shaft base diameter, and shaft diameter, where the output was taken and the laboratory Pul determined. The selection of these parameters is because the Pul is affected by the geologic conditions, helical pile’s configuration, and penetration depth. After performing the sensitivity analysis, the optimized architecture, 4 × 8 × 1 is specified for the structure of ANN. As a result, both models, ANN and PSO–ANN, presented excellent prediction performance. Note that the PSO–ANN method can provide a more accurate network outputs in predicting measured values compared to the conventional ANN model. Based on R2, RMSE and VAF values of, 0.999, 0.0350 and 99.9978, as well as, 0.999, 0.0379 and 99.998, were determined for the normalized training and testing data sets in the optimized PSO–ANN network, respectively. However, in the ANN model with four neurons in each hidden layer, the R2 as well as RMSE for the non-normalized training and testing data sets were (0.99985 and 7.99007) and (0.99990 and 11.97427), respectively, which confirms the superiority of the proposed PSO–ANN model in predicting the Pul.

[1]  Mehdi Raftari,et al.  Settlement of shallow foundations near reinforced slopes , 2013 .

[2]  Hoang Nguyen,et al.  A new soft computing model for estimating and controlling blast-produced ground vibration based on Hierarchical K-means clustering and Cubist algorithms , 2019, Appl. Soft Comput..

[3]  Adil Baykasoglu,et al.  Prediction of compressive and tensile strength of Gaziantep basalts via neural networks and gene expression programming , 2009, Neural Computing and Applications.

[4]  Arash Karimipour,et al.  Develop the nano scale method of lattice Boltzmann to predict the fluid flow and heat transfer of air in the inclined lid driven cavity with a large heat source inside, Two case studies: Pure natural convection & mixed convection , 2018, Physica A: Statistical Mechanics and its Applications.

[5]  Hossein Moayedi,et al.  An artificial neural network approach for under-reamed piles subjected to uplift forces in dry sand , 2017, Neural Computing and Applications.

[6]  Wei Gao,et al.  An independent set degree condition for fractional critical deleted graphs , 2019, Discrete & Continuous Dynamical Systems - S.

[7]  Slawomir Koziel,et al.  Fast tolerance-aware design optimization of miniaturized microstrip couplers using variable-fidelity EM simulations and response features , 2019, Engineering Computations.

[8]  Giovanni Spagnoli.  Some considerations regarding the use of helical piles as foundation for offshore structures , 2013, Soil Mechanics and Foundation Engineering.

[9]  Zaher Mundher Yaseen,et al.  Shear strength prediction of steel fiber reinforced concrete beam using hybrid intelligence models: A new approach , 2018, Engineering Structures.

[10]  Sumi Siddiqua,et al.  Strength measurement and textural characteristics of tropical residual soil stabilised with liquid polymer , 2016 .

[11]  Aminaton Marto,et al.  Foundation size effect on modulus of subgrade reaction on sandy soils , 2012 .

[12]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[13]  Loke Kok Foong,et al.  Optimizing ANN models with PSO for predicting short building seismic response , 2019, Engineering with Computers.

[14]  Biswajeet Pradhan,et al.  Modification of landslide susceptibility mapping using optimized PSO-ANN technique , 2018, Engineering with Computers.

[15]  Nguyen Ngoc Son,et al.  Parameter identification using adaptive differential evolution algorithm applied to robust control of uncertain nonlinear systems , 2018, Appl. Soft Comput..

[16]  Hamid Nikraz,et al.  Predicting pile dynamic capacity via application of an evolutionary algorithm , 2014 .

[17]  J. Jiao,et al.  Confined groundwater zone and slope instability in weathered igneous rocks in Hong Kong , 2005 .

[18]  T. N. Singh,et al.  Developing novel models using neural networks and fuzzy systems for the prediction of strength of rocks from key geomechanical properties , 2017 .

[19]  Hossein Moayedi,et al.  Artificial intelligence design charts for predicting friction capacity of driven pile in clay , 2018, Neural Computing and Applications.

[20]  Arash Karimipour,et al.  The investigation of thermal radiation and free convection heat transfer mechanisms of nanofluid inside a shallow cavity by lattice Boltzmann method , 2018, Physica A: Statistical Mechanics and its Applications.

[21]  Witold Pedrycz,et al.  Application of Particle Swarm Optimization to Create Multiple-Choice Tests , 2018, J. Inf. Sci. Eng..

[22]  Hoang Nguyen,et al.  A comparative study of artificial neural networks in predicting blast-induced air-blast overpressure at Deo Nai open-pit coal mine, Vietnam , 2018, Neural Computing and Applications.

[24]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[25]  Arivalagan Pugazhendhi,et al.  Pectin extraction from Helianthus annuus (sunflower) heads using RSM and ANN modelling by a genetic algorithm approach. , 2019, International journal of biological macromolecules.

[26]  Wei Gao,et al.  Nano properties analysis via fourth multiplicative ABC indicator calculating , 2017, Arabian Journal of Chemistry.

[27]  Ali Nazari,et al.  Prediction compressive strength of Portland cement-based geopolymers by artificial neural networks , 2012, Neural Computing and Applications.

[28]  Amir Hossein Gandomi,et al.  A new multi-gene genetic programming approach to non-linear system modeling. Part II: geotechnical and earthquake engineering problems , 2011, Neural Computing and Applications.

[29]  Hossein Moayedi,et al.  Developing hybrid artificial neural network model for predicting uplift resistance of screw piles , 2017, Arabian Journal of Geosciences.

[30]  D. Dimitrov,et al.  Tight independent set neighborhood union condition for fractional critical deleted graphs and ID deleted graphs , 2019, Discrete & Continuous Dynamical Systems - S.

[31]  Ahmad Safuan A. Rashid,et al.  A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: theory and applications , 2019, Neural Computing and Applications.

[32]  Hossein Moayedi,et al.  Modelling and optimization of ultimate bearing capacity of strip footing near a slope by soft computing methods , 2018, Appl. Soft Comput..

[33]  Nhat-Duc Hoang,et al.  Prediction of soil compression coefficient for urban housing project using novel integration machine learning approach of swarm intelligence and Multi-layer Perceptron Neural Network , 2018, Adv. Eng. Informatics.

[34]  Ramli Nazir,et al.  Performance of single vertical helical anchor embedded in dry sand , 2014 .

[35]  Danial Jahed Armaghani,et al.  Experimental and intelligent techniques to estimate bearing capacity of cohesive soft soils reinforced with soil-cement columns , 2018, Measurement.

[36]  Hossein Moayedi,et al.  Optimization of Shear Behavior of Reinforcement through the Reinforced Slope , 2010 .

[37]  Arash Karimipour,et al.  Develop the lattice Boltzmann method to simulate the slip velocity and temperature domain of buoyancy forces of FMWCNT nanoparticles in water through a micro flow imposed to the specified heat flux , 2018, Physica A: Statistical Mechanics and its Applications.

[38]  Hoang Nguyen,et al.  Prediction of Blast-induced Air Over-pressure in Open-Pit Mine: Assessment of Different Artificial Intelligence Techniques , 2019, Natural Resources Research.

[39]  Charles M. Bachmann,et al.  Neural Networks and Their Applications , 1994 .

[40]  Muhammad Kamran Siddiqui,et al.  Study of biological networks using graph theory , 2017, Saudi journal of biological sciences.

[41]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[42]  Wei Gao,et al.  The feasibility of genetic programming and ANFIS in prediction energetic performance of a building integrated photovoltaic thermal (BIPVT) system , 2019 .

[43]  Wei Gao,et al.  Partial multi-dividing ontology learning algorithm , 2018, Inf. Sci..

[44]  Jinpeng Xu,et al.  A numerical simulation of impact of groundwater seepage on temperature distribution in karst collapse pillar , 2016, Arabian Journal of Geosciences.

[45]  Arash Karimipour,et al.  Electro- and thermophysical properties of water-based nanofluids containing copper ferrite nanoparticles coated with silica: Experimental data, modeling through enhanced ANN and curve fitting , 2018, International Journal of Heat and Mass Transfer.

[46]  H. Moayedi,et al.  Applicability of a CPT-Based Neural Network Solution in Predicting Load-Settlement Responses of Bored Pile , 2018, International Journal of Geomechanics.