The shear mechanical behavior is regarded as an essential factor affecting the stability of the surrounding rocks in underground engineering. The shear strength and failure mechanisms of layered rock are significantly affected by the foliation angles. Direct shear tests were conducted on cubic slate samples with foliation angles of 0 degrees, 30 degrees, 45 degrees, 60 degrees, and 90 degrees. The effect of foliation angles on failure patterns, acoustic emission (AE) characteristics, and shear strength parameters was analyzed. Based on AE characteristics, the slate failure process could be divided into four stages: quiet period, step-like increasing period, dramatic increasing period, and remission period. A new empirical expression of cohesion for layered rock was proposed, which was compared with linear and sinusoidal cohesion expressions based on the results made by this paper and previous experiments. The comparative analysis demonstrated that the new expression has better prediction ability than other expressions. The proposed empirical equation was used for direct shear simulations with the combined finite-discrete element method (FDEM), and it was found to align well with the experimental results. Considering both computational efficiency and accuracy, it was recommended to use a shear rate of 0.01 m/s for FDEM to carry out direct shear simulations. To balance the relationship between the number of elements and the simulation results in the direct shear simulations, the recommended element size is 1 mm. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).
Accurate prediction of soil settlements induced by open caisson construction in sand is essential for safe and reliable delivery of critical underground urban infrastructure. This paper presents a novel prescriptive design approach using a neural network (NN) constrained by empirical relationships, referred to as an 'empiricism-constrained neural network'. The proposed approach is benchmarked using a traditional closed-form empirical expression. Both methods are calibrated using experimental data from reduced-scale laboratory testing for the prediction of surface and subsurface settlement trough shape and magnitude. The outcomes demonstrate that while both methods accurately capture the primary effect of caisson depth on surface and subsurface soil settlements, the NN approach exhibits superior prediction accuracy. These methods are developed in a form amenable for routine design use in industry and have the potential for broader applicability in other design scenarios, such as building damage assessment and risk-assessment exercises.