Novel robust Elman neural network-based predictive models for bubble point oil formation volume factor and solution gas–oil ratio using experimental data

作     者：Kohzadvand, Kamyab Mahmoudi Kouhi, Maryam Ghasemi, Mehdi Shafiei, Ali 

作者机构：Tehran Iran Petroleum Engineering Program School of Mining and Geosciences Nazarbayev University Astana010000 Kazakhstan 

出 版 物：《Neural Computing and Applications》 (Neural Comput. Appl.)

年 卷 期：2024年第36卷第23期

页      面：14503-14526页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The financial support received from Nazarbayev University through a Collaborative Research Proposal (grant# 091019CRP2103) is acknowledged and highly appreciated. The authors would like to thank anonymous reviewers for their critical yet fair and constructive comments  which helped the authors to improve the quality of the manuscript 

主　　题：Mean square error 

摘      要：Bubble point oil formation volume factor (Bob) and solution gas–oil ratio (Rs) are two crucial PVT parameters used for modeling and volumetric calculations in petroleum industry. They are usually determined in laboratory or estimated using empirical correlations. Experimental methods are time-consuming and expensive where empirical correlations have limitations. Artificial intelligence can be sued overcome these limitations to develop more accurate, robust, and quick predictive tools. In this paper, we used three artificial neural network algorithms to develop intelligent models to predict Bob and Rest using 465 experimental data. Application of the Elman neural network (ENN) for this purpose is being reported for the first time. A variety of input parameters were selected based on a sensitivity analysis which include reservoir temperature (T), oil API gravity (°API), bubble point pressure (Pb), gas-specific gravity (γg), and Rs was used to predict the Bob. T, °API, Pb, γg, and Bob was used to predict the Rs. The ENN model was found superior to the other developed smart models and the empirical correlations with coefficient of determination (R2) of 0.993, root mean square error (RMSE) of 0.0093, and average absolute percent relative error (AAPRE) of 0.93% for the Bob and 0.999, 0.016, and 6.72% for the Rs, respectively. The ENN network has fewer adjustable parameters and provides faster training capabilities using fewer neurons and hidden layers compared to other ANN algorithms. The developed smart predictive tools can be safely used instead of laboratory methods and empirical correlations for a much wider ranges of input parameters and with higher accuracy and confidence. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.