In this study, two novel hybrid intelligent models were developed to evaluate the short-term rockburst using the random forest (RF) method and two meta-heuristic algorithms, whale optimization algorithm (WOA) and coati optimization algorithm (COA), for hyperparameter tuning. Real-time predictive models of this phenomenon were created using a database comprising 93 case histories, taking into account various microseismic parameters. The results indicated that the WOA achieved the highest overall performance in hyperparameter tuning for the RF model, outperforming the COA. RF-WOA model accurately predicted the occurrence of this phenomenon with an accuracy of 0.944. Additionally, for this model, precision, recall and F1-score were obtained as 0.950, 0.944 and 0.943, respectively, indicating that the proposed model is robust in predicting damage severity of rockburst in deep underground projects. Subsequently, the Shapley additive explanations (SHAP) method was employed to interpret and explain the prediction process and assess the influence of input features based on RF-WOA model. The results showed that three parameters including cumulative seismic energy, cumulative microseismic events, and cumulative apparent volume have the greatest impact on the occurrence of rockburst events. This study provides an interpretable and transparent resource for accurately predicting rockburst events in real time. It can facilitate estimating project costs, selecting a suitable support system, and identifying essential ways to limit the danger of rockburst.
Assessing the stability of pillars in underground mines (especially in deep underground mines) is a critical concern during both the design and the operational phases of a project. This study mainly focuses on developing two practical models to predict pillar stability status. For this purpose, two robust models were developed using a database including 236 case histories from seven underground hard rock mines, based on gene expression programming (GEP) and decision tree‐support vector machine (DT‐SVM) hybrid algorithms. The performance of the developed models was evaluated based on four common statistical criteria (sensitivity, specificity, Matthews correlation coefficient, and accuracy), receiver operating characteristic (ROC) curve, and testing data sets. The results showed that the GEP and DT‐SVM models performed exceptionally well in assessing pillar stability, showing a high level of accuracy. The DT‐SVM model, in particular, outperformed the GEP model (accuracy of 0.914, sensitivity of 0.842, specificity of 0.929, Matthews correlation coefficient of 0.767, and area under the ROC of 0.897 for the test data set). Furthermore, upon comparing the developed models with the previous ones, it was revealed that both models can effectively determine the condition of pillar stability with low uncertainty and acceptable accuracy. This suggests that these models could serve as dependable tools for project managers, aiding in the evaluation of pillar stability during the design and operational phases of mining projects, despite the inherent challenges in this domain.
1 December 2023 in Proceedings of the Institution of Civil Engineers - Geotechnical Engineering
Squeezing is a well-known geotechnical phenomenon in the excavation of underground spaces, especially tunnels. Squeezing occurs under different geotechnical conditions in weak rock masses. A study was carried out to develop a mathematical and practical model to predict squeezing so that risk mitigation measures can be taken if necessary. A mathematical model based on a gene expression programming algorithm was developed using a database of 115 squeezing case histories. Four model performance evaluation criteria – specificity, sensitivity, accuracy and Matthew's correlation coefficient – and the receiver operating characteristic curve were then assessed based on a testing dataset. The accuracy of the model was also compared with that of previously developed models. Found to be able to determine squeezing with acceptable accuracy, the model was then used to investigate squeezing-prone areas in the Beheshtabad water-conveyance tunnel in Iran.
28 July 2021 in Bulletin of Engineering Geology and the Environment
Cutting tool wear constitutes one of the principal parameters in the processing cost of building stone. The life index of the cutting tool is obtained by evaluating the wear of diamond segments in the processing plants and examining the main parameters thereof. The purpose of this study is to determine the life index of the diamond cutting tool by considering the physico-mechanical properties of marble stones and the operational parameter of cutting speed. To this end, a dataset was provided by collecting the data from eight building stone processing plants in the provinces of Tehran, Isfahan, and Yazd of Iran. In this regard, the number of square metres of building stone that every diamond cutting tool can cut during its lifetime is defined as the cutting tool life index (TLI). After collecting the required data, SPSS software was employed for statistical analysis. The results revealed that the Brazilian tensile strength is the main parameter that affects the cutting tool life index. Linear and non-linear regression analyses were then considered for the development of predictive models for the TLI based on the Brazilian tensile strength. The performance of the developed models was subsequently examined by using three different criteria: the coefficient of determination, the variance accounted for, and the root-mean-square error. The results of this study show that the non-linear predictive model of the TLI presents a very good performance, and thus, the diamond cutting tool life index can be obtained for marble stones by considering the model developed herein.