Search

Abstract The coalcrete, a new supporting material produced by jet grouting (JG) technique was firstly studied for improving soft coal mass to support roadways in Guobei coal mine, China. Young's modulus is an essential indicator to evaluate the deformation-resisting ability of coalcretes. In this study, for determining Young's modulus of coalcretes efficiently, an intelligent technique was proposed using the support vector machine (SVM) and beetle antennae search (BAS). The hyper-parameters of SVM were firstly tuned by BAS, and then the SVM-BAS model with optimum hyper-parameters was employed to model the non-linear relationship between the inputs (coal content, water content, cement content, and curing time) and output (Young's modulus). By combining these variables, 360 coalcrete samples in total were prepared and tested for establishing the dataset. The results show that BAS is more reliable and efficient than the trial–and–error tuning method. Moreover, by comparison with other baseline models such as back-propagation neural network (BPNN), logistic regression (LR) and multiple linear regression (MLR), the optimized SVM-BAS model is more reliable, accurate and less time consuming for predicting Young's modulus of coalcretes. Besides, by conducting sensitivity analysis (SA), the importance of different input variables was determined. This pioneering work provides guidelines for predicting Young's modulus of coalcretes and designing proper JG parameters in engineering applications. Highlights • The jet grouting technique was firstly utilized in underground coal mine for generating coalcrete to reinforce the roadway stability • A total of 360 specimens were tested to determine the deformation-resisting ability of coalcrete. • A support vector machine model was proposed for predicting Young's modulus of coalcrete. • The hyperparameters of support vector machine were tuned by beetle antennae search algorithm. [ABSTRACT FROM AUTHOR]

Summary: This investigation studied the coalcrete, a new supporting material produced by jet grouting (JG) for supporting surrounding coal seams. For support design, the unconfined compressive strength (UCS) of the coalcrete is an essential parameter to evaluate the jet grouting effect in coal mines. In this study, an intelligent technique was proposed for predicting the UCS of the coalcrete by combining back propagation neural network (BPNN) and beetle antennae search (BAS). The architecture of BPNN was first tuned by BAS, and then, the optimized BPNN‐BAS model was subsequently used for nonlinear relationship modeling. Several crucial influencing variables including water‐cement ratio, coal‐grout ratio, and curing time were selected as the inputs. By combining these variables, 360 coalcrete samples were prepared in a controlled laboratory environment and tested for establishing the dataset. The results demonstrate that BAS can tune the BPNN architecture more efficiently compared with random selection. Moreover, in comparison with multiple regression (MLR) and logistic regression (LR), and support vector machine (SVM), the optimized BPNN‐BAS model is more reliable and accurate for predicting coalcrete strength. Sensitivity analysis (SA) was used to obtain the variable importance, and the results demonstrate that curing time affects the UCS of the coalcrete most strongly, followed by water‐cement ratio and coal‐grout ratio. The success of this study provides an accurate and brief approach to coalcrete strength prediction. [ABSTRACT FROM AUTHOR]