Evaluation of the Effects of Geomechanical Parameters on Drilling Rate Using MLP-PSO Algorithm
محل انتشار: دومین کنفرانس ملی ژئومکانیک نفت
سال انتشار: 1395
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 458
فایل این مقاله در 10 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
این مقاله در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
NPGC02_093
تاریخ نمایه سازی: 10 تیر 1396
چکیده مقاله:
An important issue in the industry of oil and gas reservoir drilling is to predict the rate of penetration (ROP). Prior to the construction of drilling rate prediction model, it is necessary to perceive how controllable and uncontrollable parameters affect the rate of penetration. Prediction of drilling rate leads to selecting optimum value of controllable parameters and it will lead to the reduction of drilling costs. Numerous efforts have been made to predict the rate of penetration; however, geomechanical parameters are not included. In this paper, in order to find out the effect of evaluating geomechanical parameters on estimation of drilling rate, two groups of estimator models were constructed using Multi-Layer Perceptron (MLP) neural network combined with Particle Swarm Optimization (PSO) algorithm on the data of a well from the Karanj Oil Field. In the model of the first group, only mud logging data were considered as input data. In the model of the second group, in addition to mud logging data, geomechanical characteristics entered for ROP prediction. Results showed that inclusion of geomechanical properties improves the accuracy of estimation significantly. To validate the constructed models, the commonly used model, i.e. Bourgoyne and Young (BY) model, was applied to estimate drilling rate. Results proved that constructed model of the second group is superior to Bourgoyne and Young model. In addition, they indicate the considerable effect of geomechanical parameters on drilling rate.
کلیدواژه ها:
Drilling rate prediction ، Geomechanical parameters ، Neural network ، Bourgoyne and Young drilling rate model
نویسندگان
Mohammad Anemangely
Ph.D candidate at Shahrood University of Technology
Ahmad Ramezanzadeh
Assistant professor at Shahrood University of Technology