The joint roughness coefficient (JRC) is a key parameter in the assessment of mechanical properties and the stability of rock masses. This paper presents a novel approach to JRC evaluation using a genetic algorithm-optimized backpropagation (GA-BP) neural network. Conventional JRC evaluations have typically depended on two-dimensional (2D) and three-dimensional (3D) parameter calculation methods, which fail to fully capture the nonlinear relationship between the complex surface morphology of joints and their roughness. Our analysis from shear tests on eight different joint types revealed that the strength and failure characteristics of the joints not only exhibit directional dependence but also positively correlate with surface dip angles, heights, and back slope morphological features. Subsequently, five simple statistical parameters, i.e. average dip angle, median dip angle, average height, height coefficient of variation, and back slope feature value (K), were utilized to quantify these characteristics. For the prediction of JRC, we compiled and analyzed 105 datasets, each containing these five statistical parameters and their corresponding JRC values. A GA-BP neural network model was then constructed using this dataset, with the five morphological characteristic statistics serving as inputs and the JRC values as outputs. A comparative analysis was performed between the GA-BP neural network model, the statistical parameter method, and the fractal parameter method. This analysis confirmed that our proposed method offers higher accuracy in evaluating the roughness coefficient and shear strength of joints. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published 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/).

Understanding the shear mechanical behaviors and instability mechanisms of rock joints under dynamic loading remains a complex challenge. This research conducts a series of direct shear tests on real rock joints subjected to cyclic normal loads to assess the influence of dynamic normal loading amplitude (Fd), dynamic normal loading frequency (fv), initial normal loading (Fs), and the joint roughness coefficient (JRC) on the mechanical properties and instability responses of these joints. The results show that unstable sliding is often accompanied by friction weakening due to dynamic normal loads. A significant negative correlation exists between cyclic normal loads and the normal displacement during the shearing process. Dynamic normal load paths vary the contact states of asperities on the rough joint surfaces, impacting the stick-slip instability mechanism of the joints, which in turn affects both the magnitude and location of the stress drop during the stick-slip events, particularly during the unloading phases. An increasing Fd results in a more stable shearing behavior and a reduction in the amplitude of stick-slip stress drops. The variation in fv influences the amplitude of stress drop for the joints during shear, characterized by an initial decrease (fv = 0.25-2 Hz) before exhibiting an increment (fv = 2-4 Hz). As Fs increases, sudden failures of the interlocked rough surfaces are more prone to occur, thus producing enhanced instability and a more substantial stress drop. Additionally, a larger JRC intensifies the instability of the joints, which would induce a more pronounced decline in the stick-slip stress. The Rate and state friction (RSF) law can provide an effective explanation for the unstable sliding phenomena of joints during the oscillations of normal loads. The findings may provide certain useful references for a deeper comprehension of the sliding behaviors exhibited by rock joints when subjected to cyclic dynamic disturbances. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published 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/).