New criterion for rock joints based on three-dimensional roughness parameters

The shear behavior of rock joints is important in solving practical problems of rock mechanics. Three group rock joints with different morphologies are made by cement mortar material and a series of CNL(constant normal loading) shear tests are performed. The influences of the applied normal stress and joint morphology to its shear strength are analyzed. According to the experimental results, the peak dilatancy angle of rock joint decreases with increasing normal stress, but increases with increasing roughness. The shear strength increases with the increasing normal stress and the roughness of rock joint. It is observed that the modes of failure of asperities are tensile, pure shear, or a combination of both. It is suggested that the three-dimensional roughness parameters and the tensile strength are the appropriate parameter for describing the shear strength criterion. A new peak shear criterion is proposed which can be used to predict peak shear strength of rock joints. All the used parameters can be easily obtained by performing tests.

Prediction of product roughness,profile,and roundness using machine learning techniques for a hard turning process

High product quality is one of key demands of customers in the field of manufacturing such as computer numerical control(CNC)machining.Quality monitoring and prediction is of great importance to assure high-quality or zero defect production.In this work,we consider roughness parameter Ra,profile deviation Pt and roundness deviation RONt of the machined products by a lathe.Intrinsically,these three parameters are much related to the machine spindle parameters of preload,temperature,and rotations per minute(RPMs),while in this paper,spindle vibration and cutting force are taken as inputs and used to predict the three quality parameters.Power spectral density(PSD)based feature extraction,the method to generate compact and well-correlated features,is proposed in details in this paper.Using the efficient features,neural network based machine learning technique turns out to be able to result in high prediction accuracy with R2 score of 0.92 for roughness,0.86 for profile,and 0.95 for roundness.