Drilling performance monitoring and optimization are crucial in increasing the overall NPV of an oil and gas project. Even after rigorous planning, drilling phase of any project can be hindered by unanticipated problems, such as bit balling. The objective of this paper is to implement artificial intelligence technique to develop a smart model for more accurate and robust real-time drilling performance monitoring and optimization. For this purpose, the back propagation, feed forward neural network model was developed to predict rate of penetration (ROP) using different input parameters such as weight on bit, rotations per minute, mud flow (GPM) and differential pressures. The heavy hitter features identification and dimensionality reduction are performed to understand the impacts of each of the drilling parameters on ROP. This will be used to optimize the input parameters for model development and validation and performing the operation optimization when bit is underperforming. The model is first developed based on the drilling experiments performed in the laboratory and then extended to field applications. From both laboratory and field test data provided, we have proved that the data-driven model built using multilayer perceptron technique can be successfully used for drilling performance monitoring and optimization, especially identifying the bit malfunction or failure, i.e., bit balling. We have shown that the ROP has complex relationship with other drilling variables which cannot be captured using conventional statistical approaches or from different empirical models. The data-driven approach combined with statistical regression analysis provides better understanding of relationship between variables and prediction of ROP. Keywords Data-driven technology • Drilling • Drill-bit dysfunction • Drilling performance monitoring Abbreviations AI Artificial intelligence ANN Artificial neural network MLP Multilayer perceptron ROP Rate of penetration (ft/h) WOB Weight on bit (klb) RPM Rotation per minute GPM Gallons per minute DOC Depth of cutting (in) DiffPress Differential pressure (Psi) SPP Standpipe pressure (Psi)

No abstract

In a close game of basketball, victory or defeat can depend on a single shot. Being able to identify the best player and play scenario for a given opponent’s defense can increase the likelihood of victory. Progress in technology has resulted in an increase in the popularity of sports analytics over the last two decades, where data can be used by teams and individuals to their advantage. A popular data analytic technique in sports is deep learning. Deep learning is a branch of machine learning that finds patterns within big data and can predict future decisions. The process relies on a raw dataset for training purposes. It can be utilized in sports by using deep learning to read the data and provide a better understanding of where players can be the most successful. In this study the data used were on division I women’s basketball games of a private university in a conference featuring top 25 teams. Deep learning was applied to optimize the best offensive play in a game scenario for a given set of features. The system is used to predict the play that would lead to the highest probability of a made shot.

No abstract

With increasing technological development and wide accessibility of online video content, there has been a corresponding increase in the production and integration of online screencast tutorials in higher education courses. Screencast tutorials are being used to provide and to support instruction at all grade levels (K-12 and college) in online and blended learning environments; we specifically focus on engineering in our study. The predominant use of online videos by engineering students has been to seek out specific course related tutorial videos to support their learning or to supplement content in traditional teaching courses. However, the characteristics of an effective screencast tutorial for teaching purposes are not well-defined (i.e., is it enough to work an example problem step-by-step in a 5 to 15-minute video or record an entire classroom session on a tablet PC?). In this paper, the survey results of engineering and student instructor perceptions of use and characteristics of online engineering video tutorials are presented. Based on survey results, students are most likely to utilize online video tutorials to complete homework assignments and prepare for exams. Students and instructors consider organization (as characterized by step-by-step, clear, concise) to be the most valued characteristic of quality engineering video tutorials. In addition, specific recommendations are provided, which individual instructors can implement to create effective engineering video tutorials.