Search

In this study, a database developed from existing literature about permeability of cracked rock was established. The performance of Support Vector Machine (SVM) combined with optimisation algorithms: Genetic Algorithm (GA) and Particle Swarm Optimisation Algorithm (PSO) in predicting the permeability of cracked rock masses (CRM) is evaluated. Also, the sensitivity analysis of the influence factors to the permeability of CRM is conducted. The results indicate that the hybrid GA–SVM and hybrid PSO–SVM models can accurately predict the permeability of CRM in terms of the statistical performance criteria: Coefficient of Determination R2, Regression Coefficient R and Mean Residual Error (MSE); Additionally, optimisation algorithms: PSO and GA can improve significantly the predictive performance of the SVM model. Based on the sensitivity analysis, crack angle is the most important factor to change the permeability of CRM, followed by confining pressure. [ABSTRACT FROM AUTHOR]

In this paper, the permeability and porosity of self-prepared artificial columnar jointed rock masses (CJRM) with different columnar dip angles under different pore pressures during cyclic loading-unloading of confining pressure were measured. The experimental results indicate that the gas permeability of the artificial CJRM gradually decreases with the rise of pore pressure due to the existence of Klinkenberg effect, and Klinkenberg effect gradually decreases with the rise of columnar dip angle. The existence of it improves significantly the intrinsic permeability. Besides, the intrinsic permeability and porosity of artificial CJRM are more sensitive to the first loading than that of the intact cement mortar specimen. The permanent deformation of pores in the specimens mainly appears in the first cycle, and the subsequent cycles have smaller effects on the intrinsic permeability and porosity. The permanent deformation results in the intrinsic permeability, and porosity in the loading process is always higher than those in the unloading process. The intrinsic permeability gradually increases with the growth of columnar dip angle, exhibiting obvious permeability anisotropy. Under high confining pressure, the permeability anisotropy of artificial CJRM is less than that under low confining pressure. Meanwhile, under the same confining pressure, during the repeated loading-unloading cycles, the permeability anisotropy decreases gradually. The existence of a representative element volume (REV) for CJRM is verified; thus, the equivalent continuum media model can be utilized to analyse the seepage characteristics of CJRM. [ABSTRACT FROM AUTHOR]

The selection of printing parameters for 3D printing can dramatically affect the dynamic performance of components such as polymer spur gears. In this paper, the performance of 3D printed gears has been optimised using a machine learning process. A genetic algorithm (GA)–based artificial neural network (ANN) multi-parameter regression model was created. There were four print parameters considered in 3D printing process, i.e. printing temperature, printing speed, printing bed temperature and infill percentage. The parameter setting was generated by the Sobol sequence. Moreover, sensitivity analysis was carried out in this paper, and leave-one cross validation was applied to the genetic algorithm-based ANN which showed a relatively accurate performance in predictions and performance optimisation of 3D printed gears. Wear performance of 3D printed gears increased by 3 times after optimised parameter setting was applied during their manufacture. [ABSTRACT FROM AUTHOR]

Columnar jointed rock masses (CJRM) as a type of jointed rock masses with the distinct structure are widely distributed in nature and have received considerable attention during the last few decades. In this paper, an approach, which is a combination of experiment and graphing method, is proposed to verify the existence of a representative elementary volume (REV) of CJRM during cyclic loading and unloading of confining pressure based on physical model permeability experiments. According to the experiment results, mathematical models for calculating permeability tensor of CJRM were established, and the major principal permeability component (PPC), the minor PPC, and the principal permeability angle (PPA) of CJRM during cyclic loading and unloading of confining pressure are calculated. It was concluded that the existence of a REV of CJRM during cyclic loading and unloading of confining pressure can be verified easily by using the proposed method. During cyclic loading and unloading of confining pressure, a REV does not always exist, especially at high confining pressure. The impacts of confining pressure on the major PPC, the minor PPC, and the PPA are large in the first cyclic loading phase. [ABSTRACT FROM AUTHOR]