ABSTRACT
Understanding the precursors leading to rock fracture is crucial for ensuring safety in mining and geotechnical engineering projects. To effectively discern these precursors, a collaborative monitoring approach that integrates multiple sources of information is imperative. This paper considered a rock multi-parameter monitoring loading system, incorporating infrared radiation and acoustic emission monitoring technologies to simultaneously track the rock fracture process. The study delves into the spatiotemporal evolution patterns of infrared radiation and acoustic emission in rock under loading. Utilizing stress, cumulative acoustic emission count, and average infrared radiation temperature (AIRT), the paper establishes a comprehensive evaluation model termed "acoustic-thermal-stress" fusion information, employing principal component analysis (PCA). The research reveals that the sensitivity to rock sample damage response follows the sequence of cumulative acoustic emission count, AIRT, and stress. Furthermore, a novel method for identifying rock fracture precursors is proposed, based on the first derivative of the comprehensive evaluation model. This method addresses the limitations of single physical field information, enhancing the robustness of monitoring data. It determines the average stress level of fracture precursors to be 0.77σmax. Subsequently, the study defines the probability function of rock damage during loading and fracture, enabling the realization of probability-based warnings for rock fracture. This approach introduces a new perspective on rock fracture prediction, significantly contributing to safety monitoring and warning systems in mine safety and geotechnical engineering. The findings of this research hold paramount engineering significance, offering valuable insights for enhancing safety measures in such projects.
ABSTRACT
Construction industry is indirectly the largest source of CO2 emissions in the atmosphere, due to the use of cement in concrete. These emissions can be reduced by using industrial waste materials in place of cement. Self-Compacting Concrete (SCC) is a promising material to enhance the use of industrial wastes in concrete. However, there are very few methods available for accurate prediction of its strength, therefore, reliable models for estimating 28-day Compressive Strength (C-S) of SCC are developed in current study by using three Machine Learning (ML) algorithms including Multi Expression Programming (MEP), Extreme Gradient Boosting (XGB), and Random Forest (RF). The ML models were meticulously developed using a dataset of 231 points collected from internationally published literature considering seven most influential parameters including cement content, quantities of fly ash and silica fume, water content, coarse aggregate, fine aggregate, and superplasticizer dosage to predict C-S. The developed models were evaluated using different statistical errors including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2) etc. The results showed that the XGB model outperformed the MEP and RF model in terms of accuracy with a correlation R2 = 0.998 compared to 0.923 for MEP and 0.986 for RF. Similar trend was observed for other error metrices. Thus, XGB is the most accurate model for estimating C-S of SCC. However, it is pertinent to mention here that it does not give its output in the form of an empirical equation like MEP model. The construction of these empirical models will help to efficiently estimate C-S of SCC for practical purposes.
