A PSO-ANN Intelligent Hybrid Model to Predict the Compressive Strength of Limestone Fillers Roller Compacted Concrete (RCC) to Build Dams

The compressive strength of the roller-compacted concrete (RCC) is an essential indicator of quality when designing dams. RCC is optimized in most cases through experimental studies conducted vigorously. This study aims at developing a smart system to predict the compressive strength of the limestone fillers RCC that is used to build dams. The prediction is made base on the following parameters: the maximum diameter of the aggregates, the compactness of the granular mixture, the rates of both cement and limestone fillers, water/cement ratio and the RCC age. The cement strength is taken in to consideration using a corrective equation. Two metaheuristic systems are developed: artificial neural networks (ANN), and a hybrid system consisting of an ANN optimized by a particle swarm optimization (PSO) algorithm. An experimental database is built containing 500 vectors taken from RCC formulations given by lab activity reports about 04 dam projects. The best results were achieved through the PSO-ANN hybrid system. This prediction system is validated by an experimental study conducted on 20 RCC formulations, and a comparison was made with the Laboratoire Central des Ponts et Chaussees (LCPC) method. The prediction resulting from the PSO-ANN system is of a good accuracy level with a correlation factor R2 = 0.85 and a low root mean squared error of 1.45. Finally, a user interface based on the model developed is created.

[1]  Contribution des réseaux de neurones artificiels (RNA) à la caractérisation des pollutions de sol. Exemples des pollutions en hydrocarbures aromatiques polycycliques (HAP) , 2002 .

[2]  E. Rahmani,et al.  A comprehensive investigation into the effect of water to cement ratios and cement contents on the physical and mechanical properties of Roller Compacted Concrete Pavement (RCCP) , 2020 .

[3]  Redouane Rebouh,et al.  A practical hybrid NNGA system for predicting the compressive strength of concrete containing natural pozzolan using an evolutionary structure , 2017 .

[4]  Erick Ringot,et al.  Efficiency of mineral admixtures in mortars: Quantification of the physical and chemical effects of fine admixtures in relation with compressive strength , 2006 .

[5]  Kasthurirangan Gopalakrishnan,et al.  3 – Particle Swarm Optimization in Civil Infrastructure Systems: State-of-the-Art Review , 2013 .

[6]  Danial Jahed Armaghani,et al.  Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks , 2015 .

[7]  J. A. Ware,et al.  Using neural networks to predict workability of concrete incorporating metakaolin and fly ash , 2003 .

[8]  Amir Tavana Amlashi,et al.  Soft computing based formulations for slump, compressive strength, and elastic modulus of bentonite plastic concrete , 2019, Journal of Cleaner Production.

[10]  Karim Moussaceb,et al.  Comparison of artificial neural network (ANN) and response surface methodology (RSM) prediction in compressive strength of recycled concrete aggregates , 2019, Construction and Building Materials.

[11]  Yaqi Suo,et al.  Experimental Study on Hysteretic Behavior of Double-Plate Reinforced Overlapped K-Joints , 2020, Advances in Civil Engineering.

[12]  David P. Thambiratnam,et al.  Damage detection in steel-concrete composite bridge using vibration characteristics and artificial neural network , 2020 .

[13]  F. Larrard.  Concrete Mixture Proportioning: A Scientific Approach , 1999 .

[14]  Jinlong Liu,et al.  Experimental study on real-time control of roller compacted concrete dam compaction quality using unit compaction energy indices , 2015 .

[15]  Serhan Ozdemir,et al.  The use of GA-ANNs in the modelling of compressive strength of cement mortar , 2003 .

[16]  Mahamad Nabab Alam,et al.  A comparative study of metaheuristic optimization approaches for directional overcurrent relays coordination , 2015 .

[17]  M. Chekired,et al.  An intelligent hybrid system for predicting the tortuosity of the pore system of fly ash concrete , 2019, Construction and Building Materials.

[19]  Gokhan Calis,et al.  Investigation of roller compacted concrete: Literature review , 2019, Challenge Journal of Concrete Research Letters.

[20]  Akbar Maleki,et al.  Optimal operation of a grid-connected fuel cell based combined heat and power systems using particle swarm optimisation for residential sector , 2019, International Journal of Ambient Energy.

[21]  I. Yaman,et al.  The effects of compaction methods and mix parameters on the properties of roller compacted concrete mixtures , 2019, Construction and Building Materials.

[22]  K. F. Portella,et al.  Expounding structures of roller compacted concrete dam specimens by means of hard conventional X-ray inspection , 2019, Heliyon.

[23]  Milica Đurić-Jovičić,et al.  Artificial intelligence for assisting diagnostics and assessment of Parkinson’s disease—A review , 2019, Clinical Neurology and Neurosurgery.

[24]  Andy Fourie,et al.  Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill , 2018 .

[25]  Thierry Sedran,et al.  Le logiciel BétonlabPro 3 , 2007 .

[26]  Baroghel-Bouny,et al.  Effet des additions minerales sur les proprietes d'usage des betons - Plan d'experience et analyse statistique , 2000 .

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

[28]  Mohammad Ebdali,et al.  A comparative study of various hybrid neural networks and regression analysis to predict unconfined compressive strength of travertine , 2020, Innovative Infrastructure Solutions.

[29]  M. Sharbatdar,et al.  The effect of water-to-cement ratio on the fracture behaviors and ductility of Roller Compacted Concrete Pavement (RCCP) , 2020 .

[30]  Joong-Hoon Kim,et al.  Learned Prediction of Compressive Strength of GGBFS Concrete Using Hybrid Artificial Neural Network Models , 2019, Materials.

[31]  P. Chindaprasirt,et al.  Case investigation on application of steel fibers in roller compacted concrete pavement in Thailand , 2019 .

[32]  Stefan Larsson,et al.  An artificial neural network based model to predict spatial soil type distribution using piezocone penetration test data (CPTu) , 2018, Bulletin of Engineering Geology and the Environment.

[33]  Jie Yuan,et al.  Predicting the Compressive Strength of Desert Sand Concrete Using ANN: PSO and Its Application in Tunnel , 2020 .

[34]  Mahesh B. Patil,et al.  Water distribution system design using multi-objective particle swarm optimisation , 2019, Sādhanā.

[35]  H. Houari,et al.  Lightweight concrete with Algerian limestone dust: Part I: Study on 30% replacement to normal aggregate at early age , 2013 .

[36]  Jiazheng Li,et al.  Effect of large broken stone content on properties of roller compacted concrete based on fractal theory , 2020 .

[37]  S. Hong,et al.  Relationship between compressive and tensile strengths of roller-compacted concrete , 2018, Journal of Traffic and Transportation Engineering (English Edition).

[38]  Takafumi Noguchi,et al.  Modeling of hydration reactions using neural networks to predict the average properties of cement paste , 2005 .

[39]  Mohammed Ali Jallal,et al.  A novel deep neural network based on randomly occurring distributed delayed PSO algorithm for monitoring the energy produced by four dual-axis solar trackers , 2020 .

[40]  Nazmul Siddique,et al.  Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing , 2013 .

[41]  M. Abd Elaziz,et al.  Modeling of solar energy systems using artificial neural network: A comprehensive review , 2019, Solar Energy.

[42]  Mustapha Zdiri,et al.  Theoretical and experimental study of roller-compacted concrete strength , 2008 .

[43]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[44]  I-Cheng Yeh,et al.  Exploring Concrete Slump Model Using Artificial Neural Networks , 2006 .

[45]  Bassam A. Tayeh,et al.  Mechanical and durability properties of ground calcium carbonate-added roller-compacted concrete for pavement , 2020, Journal of Materials Research and Technology.