3. Electronic Theses and Dissertations (ETDs) - All submissions
Permanent URI for this communityhttps://wiredspace.wits.ac.za/handle/10539/45
Browse
3 results
Search Results
Item Rock failure prediction under true triaxial loading: evaluation of statistical techniques and machine learning based techniques(2019) Sambo, AneleUnderstanding the stress changes within the vicinity of an excavation is critical in mining environments and should be accounted for by rock engineers. These changes in stresses have a substantial influence on the strength and deformational properties of rocks and can result to instabilities and rock failure. Rock failure is considered as one of the phenomenon having dire consequences to mining operations. Due to the repercussion of rock failure, rocks are subjected to laboratory testing with the aim of determining the stresses that are likely to result to failure as well as measuring the rock strength. Normally, conventional testing is conducted which focuses on the major and minor principal stress. With further studies, the influence of the intermediate stress was appreciated therefore introducing true triaxial testing which is also used today. These tests are the bases of several failure criterions including Hoek-Brown failure criterion, Mogi 1971 etc. The results retrieved from laboratories are analysed with the aim of determining stresses resulting to rock failure, rock strength as well as rock mass parameters which are normally used in numerical modelling. It has been tradition to use least square regression as a modelling technique. This technique is easy to implement and interpret, however it is a non-robust technique and thus causes inaccuracies when predicting rock failure. The inaccuracies caused by poor modelling have greater harm than what is expected. Poor modelling in rock engineering can result to the application of inappropriate numerical models, poor support design, rock failure, fatalities and many more. Hence this research focuses on evaluating different modelling techniques. It outlines the capabilities and limitations as well as factors affecting the predictive performance of each technique. True triaxial data of 11 rocks retrieved from scientific journals and books was used. The data included all three principal stresses (major, intermediate and minor) as well as the strength of each rock. In rock failure prediction, a failure criterion is normally chosen. For this research, Mogi’s 3D failure criterion utilizing all three principal stresses was used. The laboratory data was modelled using each modelling technique. The four modelling techniques were divided into two groups’ i.e. statistical techniques (least square regression and quantile regression) and machine learning based techniques (logistic regression and k-nearest neighbour). The statistical techniques made use of regression lines as failure envelopes hence they were strongly affected by indecisive points i.e. points plotting directly on the regression line and can neither be classified as stable nor failing. This had an effect on the performance and accuracy of the model. Furthermore, the least square regression was influenced by outliers as expected. On the other hand, the machine learning based techniques showed a very good predictive performance but were also affected by data pre-processing parameters. Logistic regression was influenced by the cutoff value and the pre-processing stages where the author had to decide on the variables to use since some of the variables were statistically non-significant. K-nearest neighbour was limited by the k-value (neighbourhood values) and the split (ratio between trained dataset and tested dataset). These parameters had an influence on the predictive performance of the models. The performance of the four techniques were evaluated using different measuring techniques including the coefficient of determination (R2) for statistical techniques, Receiver Operating Characteristic (ROC) curve for logistic regression and the confusion matrix for all four techniques. Research showed that R² is influenced by outliers and the x-axis range and does not give a true reflection of the model’s performance. Confusion matrix however is not influenced by any factors hence the accuracies of the models were based on this parameter. K-nearest neighbour had the highest rock failure prediction accuracy followed by logistic regression, then least square regression and lastly quantile regression. Furthermore, the machine learning based techniques were good at identifying and classifying points resulting in failure as they had high sensitivity values while statistical techniques had high specificity meaning they were perfect at predicting stable points. In overall, it was a challenge implementing and interpreting machine learning based models however the rock failure prediction accuracy was higher compared to that of statistical techniques.Item Failure criteria and acoustic emission as applied to composite materials(1992) Campbell, IThis project involves the comparison of different failure criteria with experimental results for fibre composite materials, and investigates the usefulness of acoustic emission in composite testing. Three sets of specimens were tested to failure in tension. The specimens had various ply orientations and were tested using acoustic emission to determine ply failures. Carbon and glass fibre reinforced epoxy pre-impregnated specimens were used. The testing machine was an ESH testing machine, and a physical Acoustics corporation computer and data acquisition unit were used to record data from a piezo-electric sensor. Suitable failure criteria should be chosen on the basis of ply orientation and material type (eg fibre stiffness), a combination of criteria being used if necessary. Acoustic emission was successfully used to detect ply failure in multi-layered laminates.Item Investigations into the mechanism of fracture onset and growth in layered rock using physical and numerical modelling(2015) Dede, TufanOne of the major impediments in the field of numerical modelling in rock mechanics is limited knowledge of the mechanisms of fracture and failure of brittle rock. One important tool for improving the understanding of rock behaviour is the use of laboratory experiments under controlled conditions. The Displacement Discontinuity Method, capable of fracture growth simulation (DIGS), has been used to model fracturing in samples under punch loading. A Finite Difference Method, capable of plastic deformations due to its explicit time marching scheme (FLAC), has also been used to model the punch tests. By comparing numerical simulations with results from laboratory experiments of punch tests, it has been possible to define the basic failure mechanism for pillar foundation failure. Two different test set-ups were used namely, steel jacketed axisymmetric punch tests and long strip punch tests in the triaxial cell which is built for these specific tests. The layered structure of the test specimens and in the test procedure had significant effects on the fracture pattern as well as the failure load. When the layer is near to the punch area, then both the layer and the layer conditions had a strong effect on the failure load. When the layer was frictionless, the failure stress dropped by about 20 percent. The same result occurred in both the axisymmetry and strip loading tests. When shear fractures intersect a layer with either low or high friction it terminates. This is not the case for the tensile fractures, which can pass through the layer media. However, it is important to note that the tensile fractures which originate from near the cone area can not pass through the layers. They stop at the interface.