The major problems associated with shale formation when it interacted with water based mud are borehole instability. This Wellbore instability may be due to swelling and dispersion of clay present in shale and also leads to other well problems like pipe sticking, hole enlargement, improper rheological & fluid loss control properties, and additional reaming etc. In this research paper an attempt has been made to evaluate the feasibility of synthesized graft copolymer in the formulation of water based mud system for challenging formations. The microwave irradiation technique has been adopted for synthesizing PAA/AMPS-g-Sesbania gum copolymer. Further, it was processed in the formulation of mud system. The remarkable rheological and filtration properties of the mud system have been seen with synthesized additive. The developed mud has possessed strong pseudoplastic behavior which is a desired property of any mud which has been observed from shear rate vs. shear rate curve. In addition, shale stabilization properties were investigated with shale rotability test on the synthesized core sample prepared in the laboratory. Moreover, percentage reduction in permeability (i.e., formation damage effect) has been found lesser in developed copolymer system co paring to conventionally used PHPA system. Hence, the formulated mud system can be used as a potential drilling mud system for drilling any oil wells.

No abstract

No abstract

Stock market movements are affected by numerous factors making it one of the most challenging problems for forecasting. This article attempts to predict the direction of movement of stock and stock indices. The study uses three classifiers - Artificial Neural Network, Random Forest and Support Vector Machine with four different representation of inputs. First representation uses raw data (open, high, low, close and volume), The second uses ten features in the form of technical indicators generated by use of technical analysis. The third and fourth portrayal presents two different ways of converting the indicator data into discrete trend data. Experimental results suggest that for raw data support vector machine provides the best results. For other representations, there is no clear winner regarding models applied, but portrayal of data by the proposed approach gave best overall results for all the models and financial series. Consistency of the results highlight the importance of feature generation and right representation of dataset to machine learning techniques.