Development of computational vision methodologies for monitoring cuttings in the drilling fluid treatment system

The objective of this work was to apply artificial intelligence techniques, such as computational vision, image processing, and machine learning, to develop a software for performing the analysis and monitoring of cuttings in vibrating screens to detect flow variations and possible instabilities during the drilling process. An experimental unit was built to emulate the flow of cuttings in the sieves, where three different vibration intensities were applied to the apparatus to allow for three distinct flow speeds. Flowing experiments using quartz, marble, granite, and actual gravel fragments were recorded in videos and used by the computational vision software developed on the Matlab © platform. Videos were processed by the proposed algorithm using different image processing and machine learning techniques. The 2D Discrete Fourier Transform associated with the convolution theorem was the segmentation technique used to detect the rocks in the frames. The estimation of the solids’ velocity was performed with the detectors of correspondence points in sequential frames of the video using the MATLAB ’ s functions “MSER”, “Harris”, and “SURF”. The MATLAB ’s function "regionprops" was also used to estimate the area of the sieve filled with rocks as well as some geometric parameters of them, such as size, circularity, roundness, and eccentricity. The results showed that the proposed computational vision software could perform reliable estimates of the reported features for a range of rock types. Besides, in most cases, it was possible to estimate the area of the sieve filled with rocks and their velocities across the sieve with average errors of less than 10%. Results also suggested that it could be possible to implement a real-time monitoring system for vibrating sieves in drilling operations using the software developed in this work.