Search

Evaluation of earthquake-induced liquefaction potential is crucial in the design phase of construction projects. Although several machine learning models achieve good prediction accuracy on their particular datasets, they may not perform well in other liquefaction datasets. To address this issue, we proposed a novel hybrid classifier ensemble to improve generalizability by combining the predictions of seven base classifiers using the weighted voting method. The applied base classifiers include back propagation neural network, support vector machine, decision tree, k-nearest neighbours, logistic regression, multiple linear regression and naïve Bayes. The hyperparameters and weights of the base classifiers were tuned using the genetic algorithm. To verify the robustness of the classifier ensemble, its performance was tested on three datasets collected from previous published researches. The results show that the proposed classifier ensemble outperforms the base classifiers in terms of a variety of performance metrics including accuracy, Kappa, precision, recall, F1 score, AUC and ROC on the three datasets. In addition, the importance of influencing variables was achieved by the classifier ensemble on the three datasets to facilitate the future data collecting work. This robust ensemble method can be extended to solve other classification problems in civil engineering. [ABSTRACT FROM AUTHOR]

Summary: Rockbust is a violent expulsion of rock due to the extreme release of strain energy stored in surrounding rock mass, leading to considerable damages to underground strucures and equipment, and threatening workers' safety. As the operational depth of engineering projects increases, a larger number of factors influence the mechanism of rockburst. Therefore, accurate classification of rockburst intensity cannot be achieved based on conventional criteria. It is urgent to develop new models with high accuracy and ease to implement in practice. This study proposed an ensemble machine learning method by aggregating seven individual classifiers including back propagation neural network, support vector machine, decision tree, k‐nearest neighbours, logistic regression, multiple linear regression and Naïve Bayes. In addition, we proposed nine data imputation methods to replace the missing values in the compiled database including 188 rockburst instances. Five‐fold cross validation and the beetle antennae search algorithm are used to tune hyperparameters and voting weights of the individual classifiers. The results show that the rockburst classification accuracy obtained by the classifier ensemble has increased by 15.4% compared with the best individual classifier on the test set. The predictor importance obtained by the classifier ensemble shows that the elastic energy index is the most sensitive input variable for rockburst intensity classification. This robust ensemble method can be extended to solve other classification problems in underground engineering projects. [ABSTRACT FROM AUTHOR]

Cemented paste backfill (CPB) is an eco-friendly composite containing mine waste or tailings and has been widely used as construction materials in underground stopes. In the field, the uniaxial compressive strength (UCS) of CPB is critical as it is closely related to the stability of stopes. Predicting the UCS of CPB using traditional mathematical models is far from being satisfactory due to the highly nonlinear relationships between the UCS and a large number of influencing variables. To solve this problem, this study uses a support vector machine (SVM) to predict the UCS of CPB. The hyperparameters of the SVM model are tuned using the beetle antennae search (BAS) algorithm; then, the model is called BSVM. The BSVM is then trained on a dataset collected from the experimental results. To explain the importance of each input variable on the UCS of CPB, the variable importance is obtained using a sensitivity study with the BSVM as the objective function. The results show that the proposed BSVM has high prediction accuracy on the test set with a high correlation coefficient (0.97) and low root-mean-square error (0.27 MPa). The proposed model can guide the design of CPB during mining. [ABSTRACT FROM AUTHOR]

Coal-grout composites were fabricated in this study using the jet grouting (JG) technique to enhance coal mass in underground conditions. To evaluate the mechanical properties of the created coal-grout composite, its unconfined compressive strength (UCS) needed to be tested. A mathematical model is required to elucidate the unknown nonlinear relationship between the UCS and the influencing variables. In this study, six computational intelligence techniques using machine learning (ML) algorithms were used to develop the mathematical models, which includes back-propagation neural network (BPNN), random forest (RF), decision tree (DT), support vector machine (SVM), k-nearest neighbors (KNN), and logistic regression (LR). In addition, the hyper-parameters in these typical algorithms (e.g., the hidden layers in BPNN, the gamma in SVM, and the number of neighbor samples in KNN) were tuned by the recently developed beetle antennae search algorithm (BAS). To prepare the dataset for these ML models, three types of cementitious grout and three types of chemical grout were mixed with coal powders extracted from the Guobei coalmine, Anhui Province, China to create coal-grout composites. In total, 405 coal-grout specimens in total were extracted and tested. Several variables such as grout types, coal-grout ratio, and curing time were chosen as input parameters, while UCS was the output of these models. The results show that coal-chemical grout composites had higher strength in the short-term, while the coal-cementitious grout composites could achieve stable and high strength in the long term. BPNN, DT, and SVM outperform the others in terms of predicting the UCS of the coal-grout composites. The outstanding performance of the optimum ML algorithms for strength prediction facilitates JG parameter design in practice and could be the benchmark for the wider application of ML methods in JG engineering for coal improvement. [ABSTRACT FROM AUTHOR]

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]