Assessing the compressive strength of eco-friendly concrete made with rice husk ash: A hybrid artificial intelligence-aided technique

Abstract

Providing an eco-friendly replacement for cement in cementitious materials mitigates not only its consumption but also the environmental effects such as extraction of natural resources and greenhouse gas emissions resulting from its production. In light of this, the utilization of rice husk as a by-product of rice fields in the form of rice husk ash (RHA) as a partial substitute for cement, in addition to solving the problem of its disposal due to its silica content and high pozzolanic reaction, has been considered in the construction of sustainable concretes. This study seeks to move from the traditional laboratory-based methods for the examination of compressive strength (fc′) of concretes containing RHA towards artificial intelligence-based techniques by developing a novel hybrid model by integrating biogeography-based optimization (BBO) technique with artificial neural network (ANN). Besides, the performance of the hybrid ANN-BBO model was assessed with the single ANN model. To this end, the models were developed on an extensive dataset including 1276 data records collected from the literature. The efficiency of the models was evaluated by performance criteria and error histogram, and also cross-validation was utilized to avoid overfitting problems and generalize the models. Results demonstrated that the hybrid ANN-BBO model outperformed the single ANN model with high accuracy and minimum error values. Error histograms revealed that over 90 % of errors in the ANN-BBO model occurred in the range (−4 MPa, 4 MPa], while this range for the ANN model fell within (−6 MPa, 6 MPa]. Analyzing the influence of input parameters showed that more than 70 % of the contribution rate in the fc′ of RHA concrete belonged to four influential parameters of specimen age, cement, rice husk ash, and water, respectively. Eventually, to validate the proposed ANN-BBO model, a comparison was made with recent studies, in which the performance criteria revealed that the proposed model based on a more extensive dataset outperformed the models in previous studies.