Youzhuang Sun, Junhua Zhang, Yongan Zhang
College of Earth Science and Technology, China University of Petroleum, Qingdao 266555, China.
College of Computer Science, China University of Petroleum, Qingdao 266555, China.
ACS Omega. 2023 May 31;8(23):21182-21194. doi: 10.1021/acsomega.3c02217. eCollection 2023 Jun 13.
In oil exploration and development, many reservoir parameters are very essential for reservoir description, especially porosity. The porosity obtained by indoor experiments is reliable, but human and material resources will be greatly invested. Experts have introduced machine learning into the field of porosity prediction but with the shortcomings of traditional machine learning models, such as hyperparameter abuse and poor network structure. In this paper, a meta-heuristic algorithm (Gray Wolf Optimization algorithm) is introduced to optimize the ESN (echo state neural) network for logging porosity prediction. Tent mapping, a nonlinear control parameter strategy, and PSO (particle swarm optimization) thought are introduced to optimize the Gray Wolf Optimization algorithm to improve the global search accuracy and avoid local optimal solutions. The database is constructed by using logging data and porosity values measured in the laboratory. Five logging curves are used as model input parameters, and porosity is used as the model output parameter. At the same time, three other prediction models (BP neural network, least squares support vector machine, and linear regression) are introduced to compare with the optimized models. The research results show that the improved Gray Wolf Optimization algorithm has more advantages than the ordinary Gray Wolf Optimization algorithm in terms of super parameter adjustment. The IGWO-ESN neural network is better than all machine learning models mentioned in this paper (GWO-ESN, ESN, BP neural network, least squares support vector machine, and linear regression) in terms of porosity prediction accuracy.
在石油勘探与开发中，许多储层参数对于储层描述至关重要，尤其是孔隙度。通过室内实验获得的孔隙度是可靠的，但会投入大量人力和物力。专家们已将机器学习引入孔隙度预测领域，但传统机器学习模型存在诸如超参数滥用和网络结构不佳等缺点。本文引入一种元启发式算法（灰狼优化算法）来优化回声状态神经网络（ESN）以进行测井孔隙度预测。引入帐篷映射、一种非线性控制参数策略以及粒子群优化（PSO）思想来优化灰狼优化算法，以提高全局搜索精度并避免局部最优解。利用测井数据和实验室测量的孔隙度值构建数据库。将五条测井曲线用作模型输入参数，孔隙度用作模型输出参数。同时，引入另外三种预测模型（BP神经网络、最小二乘支持向量机和线性回归）与优化后的模型进行比较。研究结果表明，改进后的灰狼优化算法在超参数调整方面比普通灰狼优化算法具有更多优势。在孔隙度预测精度方面，改进的灰狼优化算法-回声状态神经网络（IGWO-ESN）神经网络优于本文提及的所有机器学习模型（GWO-ESN、ESN、BP神经网络、最小二乘支持向量机和线性回归）。
