Nghiên cứu này để xuất sử dụng mạng nơ-ron nhân tạo, nhằm dự báo tốc độ cơ học khoan từ tài liệu khoan thực tế. Bộ số liệu bao gồm 900 mẫu thu được từ các giếng khoan tại mỏ Nam Rồng Đồi Mồi, chứa 6 thông số đầu vào là các thông số chế độ khoan: tải trọng lên choòng (WOB), trọng lượng riêng dung dịch khoan (MW), tốc độ quay choòng (RPM), áp suất tại vòi phun (SPP), lưu lượng dung dịch khoan (FR), mô men quay choòng (TQ). | Journal of Mining and Earth Sciences Vol. 62 Issue 3a 2021 37 - 47 37 Use of Artificial Neural Networks in predicting rate of penetration and optimization weight on bit for several wells in Nam Rong - Doi Moi field Vietnam Hung Tien Nguyen 1 Duong Hong Vu 1 Vinh The Nguyen 1 Doan Thi Tram 1 Pham Van Trung 2 1 Faculty of Oil and Gas Hanoi University of Mining and Geology Vietnam 2 Project block 01 amp 02 PVEP Vietnam ARTICLE INFO ABSTRACT Article history Obtaining the maximum Rate of Penetration ROP by optimization of Received 07th Feb. 2021 drilling parameters is the aim of every drilling engineer. This helps to save Accepted 16th May 2021 time reduces cost and minimizes drilling problems. Since ROP depends on Available online 10th July 2021 a lot of parameters it is very difficult to predict it correctly. Therefore it Keywords is necessary and important to investigate a solution for predicting ROP Artificial Neural Network with high accuracy in order to determine the suitable drilling parameters. Nam Rong - Doi Moi field. In this study a new approach using Artificial Neural Network ANN has been proposed to predict ROP from real - time drilling data of several wells Optimization drilling in Nam Rong - Doi Moi field with more than 900 datasets included parameters important parameters such as weight on bit WOB weight of mud MW Rate of Penetration rotary speed RPM stand pipe pressure SPP flow rate FR torque TQ . In the process of training the network algorithms and the number of neurons in the hidden layer were varied to find the optimal model. The ANN model shows high accuracy when comparing to actual ROP therefore it can be recommended as an effective and suitable method to predict ROP of other wells in research area. Besides base on the proposed ANN model authors carried out experiments and determine the optimal weight on bit value for the drilling interval from 1800 to 2300 m of wells in in Nam Rong Doi Moi field. Copyright 2021 Hanoi University of Mining and .
