IIARD International Institute of Academic Research and Development

International Journal of Engineering and Modern Technology (IJEMT )

E-ISSN 2504-8848
P-ISSN 2695-2149
VOL. 9 NO. 2 2023

---

A Bio-Inspired Algorithm for Predicting Equivalent Circulating Density of Drilling Muds for Niger Delta Oilfields

Michael Friday Timothy and Julius U. Akpabio

---

Abstract

Equivalent circulating density (ECD) is a critical parameter in drilling operations that helps to ensure the safety of drilling personnel and equipment. Mud ECD has over time received substantial attention in theoretical analyses, laboratory experiments, field measurements and modelling. This study developed a bio-inspired algorithm based on an artificial neural network to predict mud equivalent circulating density using data obtained from fields in the Niger Delta region of Nigeria. Eleven variables namely: depth, temperature, pore pressure, flow rate, mud weight, average equivalent annular diameter across bottom hole assembly (BHA), average equivalent annular diameter across drill pipe (DP), flow conduit length across BHA, flow conduit length across DP, average annular velocity across BHA and average annular velocity across DP were used as the input parameters to the algorithm. To develop the model, 1011 data points collated from different fields were used to develop the model. To assess the model performance, four statistical error tools namely: the mean square error (MSE), average absolute percentage error (AAPE), root mean square error (RMSE) and determination coefficient (R2) were adopted. The best performing topology for 11 inputs was: 11–3–1. The results indicate that the model developed by this topology had an R2 value of 0.9993 and an MSE of 0.000265, AAPE of 0.337 and RMSE of 0.01628. In order to ascertain the parametric importance of the input variables used, the Garson’s algorithm was utilized. In this regard, six input parameters had significant effects on ECD namely: mud weight (34%), pore pressure (14%), average equivalent annular diameter across drill pipe (9.2%), average equivalent annular diameter across BHA (9%), temperature (8.1%), depth (7.3%) and average annular velocity across drill pipe (7.04%). In addition, the ANN model was presented in an explicit form that makes it easy to be deployed in software applications, someth

---

References:

Abdelgawad, K.Z., Elzenary, M., Elkatatny, S., Mahmoud, M., Abdulraheem, A. and Patil, S.
(2019). New approach to evaluate the equivalent circulating density (ECD) using
artificial intelligence techniques. Journal of Petroleum Exploration and Production
Technology, Volume 9, pp:1569–1578.

Adamson, K., Birch, G., Gao, E., Hand, S., Macdonald, C., Mack, D. and Quadri, A. (1998)
High Pressure, High temperature well construction. Oilfield Review, pp. 36 – 49.

Adesina, F.A.S., Abiodun, A., Anthony, A. and Olugbenga, F. (2015) Modelling the Effect of
Temperature on Environmentally Safe Oil Based Drilling Mud using Artificial
Neural Network Algorithm. Petroleum and Coal Journal, Volume 57, Number 1, pp.
60-70

DOWNLOAD PDF

---

Back