Comparative study of advanced computational techniques for estimating the compressive strength of UHPC

Abstract

The effect of raw materials on the compressive strength of concrete is a complex process, especially in the case of ultra-high-performance concrete (UHPC), where a higher number of inter-dependent parameters are involved in the strength development. In this era of digitalization, advanced machine learning methods are used to predict the material's mechanical characteristics because of their superior performance compared to conventional and nonlinear statistical regression models. Thus, the goal of the current study is to estimate the compressive strength of UHPC from the designed raw materials using advanced machine learning techniques. The compressive strength of UHPC is predicted from the 14 input parameters, i.e., cement, fly ash, slag, silica fume, nano-silica, limestone powder, sand, coarse aggregate, quartz powder, water, superplasticizer, PE fiber, steel fiber, and curing time. A total of eight machine learning models were compared that include multi-layer perceptron neural network (MLPNN), MLPNN Bootstrap aggregating (MLPNN-BA), MLPNN adaptive boosting (MLPNN-AB), Gradient boosting (GB), Decision tree (DT), DT Bootstrap aggregating (DT-BA), DT adaptive boosting (DT-AB) and Random Forest (RNF). The validation and performance evaluation of the above models were checked by using K-fold cross-validation, mean absolute error (MAE), root mean square error (RSME), coefficient of determination (R2), relative root mean square error (RRMSE), performance index (PI), and Nash Sutcliffe efficiency (NSE). The optimal model was selected based on the results of all statistical checks. It was found the ensembled machine learning models especially decision tree-based models outperform the neural network-based models with higher accuracy and low error. Thus, the recommended machine learning model is random forest having superior prediction capacity followed by DT Bootstrap aggregating and DT adaptive boosting.

Use of Artificial Intelligence for Predicting Parameters of Sustainable Concrete and Raw Ingredient Effects and Interactions

“…There are some new prediction approaches [ 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 ], such as adaptive neuro-fuzzy inference system (ANFIS), deep learning (DL), marine predators algorithm (MPA), pure random orthogonal search (PROS), artificial neural networks (ANNs), genetic algorithm (GA), and particle swarm optimization (PSO) method, etc. These approaches can better reveal the strength of structures in a more unbiased way, which should be studied in the future.…”

Flexural Strength Prediction of Steel Fiber-Reinforced Concrete Using Artificial Intelligence

“…Several studies have attempted to predict concrete strength characteristics [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ]. Machine learning methods are employed to forecast concrete strength [ 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 ] and the durability of concrete [ 50 , 51 , 52 ]. Bagging regression (BR) and gradient boosting (GB) models based on a variation of the bootstrap aggregation decision tree (DT) method have been shown in several studies to outperform other stand-alone ML models in terms of concrete strength prediction accuracy [ 53 , 54 , 55 , 56 ].…”

Compressive Strength Estimation of Steel-Fiber-Reinforced Concrete and Raw Material Interactions Using Advanced Algorithms

“…Steel, artificial, and natural fibers are incorporated into concrete to enhance the mechanical properties and resistance against cracks of cementitious concrete composites [ 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. Different studies have been conducted on models for regular concrete mechanical properties depending on a wide database [ 16 ], although there are additional predicting parameters such as fiber type, aspect ratio, and volumetric content for SFRC compared to normal concrete. However, the development of appropriate predictive models is still new.…”

“…Subsequently, the scuffling of conventional nonlinear and linear regression models is used to determine the compressive strength of SFRC. ML techniques may assist in resolving the issue of difficulty for the strength prediction of SFRC [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. Although multiple experimental studies have been conducted for this purpose, as reported in the literature, the prediction of SFRC properties having different mix design components is still quite hard.…”