Gray relational clustering model for intelligent guided monitoring horizontal wells

Abstract

When drilling CBM horizontal wells, in order to improve the drilling rate of coal seams, real-time monitoring the lithology encountered underground must be performed. There are a large number of real-time logging data and historical data during the drilling process. Through data mining methods, the relationship between the changes of the underground lithology and the logging data can be found. Therefore, an improved gray clustering algorithm combined with the principle of mechanical specific energy is proposed to form a set of gray clustering model that can realize intelligent guided monitoring horizontal wells. By introducing correlation degree analysis method, this model optimizes the original gray fixed weight clustering monitoring model, establishing a horizontal well-oriented gray-related clustering model. In addition, the concept of decision rough set is used to replace the subjective given clustering threshold for the cluster threshold problem to achieve rapidly monitoring the CBM horizontal well drilling process. Through field data optimization analysis, the results show that the improved gray correlation clustering model can quickly and accurately identify lithology through real-time logging data.