Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill

New paper published on Construction and Building Materials

Paper Title: Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill

Authors: Chong-chong Qi, Andy Fourie, Qiu-song Chen

Abstract: Cemented paste backfill (CPB) has been widely used to prevent and mitigate hazards produced during the excavation of underground stopes. In practice, the strength of CPB is often an essential parameter for successful stope design. We propose an intelligent technique in this study for predicting the unconfined compressive strength (UCS) of CPB. This intelligent technique is a combination of the artificial neural network (ANN) and particle swarm optimization (PSO). The ANN was used for non-linear relationships modelling and PSO was used for the ANN architecture-tuning. Inputs of the ANN were selected to be the tailings type, the cement-tailings ratio, the solids content, and the curing time. A total of 396 CPB specimens under different combination of influencing variables were tested for the preparation of the dataset. The results showed that PSO was efficient for the ANN architecture-tuning. Also, comparison of the predicted UCS values with experimental values showed that the optimum ANN model was very accurate at predicting CPB strength.

Keywords: Cemented paste backfill; Artificial neural network; Particle swarm optimization; Unconfined compressive strength

Comments from reviews:

Reviewer 1: This study investigates the predictability of the unconfined compressive strength (UCS) of cemented paste backfill (CPB) using a new technique named as PSO-ANN method. Four different parameters (tailings type, the cement-tailings ratio, the solids content and the curing time) were selected for the extensive testing program and proposed model. This study has novelty and contributes to mining industry or operators to reliably estimate the UCS of CPB samples. The topic of the manuscript is suitable for the Construction and Building Materials. The reviewer suggests some minor revisions to improve paper quality before it can be accepted for publication.

Reviewer 2: Modelling of UCS value of CPB specimens was undertaken using an intelligent technique based on the ANN and PSO.
The reported results show that PSO has impressive efficiency in the ANN architecture-tuning.
Further details about the adopted procedure, mainly about the fitness function of the PSO algorithm, would be highly profitable.
As trivial modifications, the acronyms in highlights should be defined and the role of Appendix (recalled at lines 67 and 72) should be clarified.

Graphic Abstract:

Full paper can be obtained through Email.