Geng Shaoyang, Zhai Shuo, Ye Jianwen, Gao Yajie, Luo Hao, Li Chengyong, Liu Xianshan, Liu Shudong
Chengdu University of Technology, College of Energy, Chengdu, 610059, China.
Sinopec Southwest Oil and Gas Company, Chengdu, 611930, China.
Sci Rep. 2024 Sep 16;14(1):21640. doi: 10.1038/s41598-024-72499-5.
Accurately predicting the deviation factor (Z-factor) of natural gas is crucial for the estimation of natural gas reserves, evaluation of gas reservoir recovery, and assessment of natural gas transport in pipelines. Traditional machine learning algorithms, such as Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Artificial Neural Network (ANN) and Bidirectional Long Short-Term Memory Neural Networks (BiLSTM), often lack accuracy and robustness in various situations due to their inability to generalize across different gas components and temperature-pressure conditions. To address this limitation, we propose a novel and efficient machine learning framework for predicting natural gas Z-factor. Our approach first utilizes a signal decomposition algorithm like Variational Mode Decomposition (VMD), Empirical Fourier Decomposition (EFD) and Ensemble Empirical Mode Decomposition (EEMD) to decouple the Z-factor into multiple components. Subsequently, traditional machine learning algorithms is employed to predict each decomposed Z-factor component, where combination of SVM and VMD achieved the best performance. Decoupling the Z-factors firstly and then predicting the decoupled components can significantly improve prediction accuracy of all traditional machine learning algorithms. We thoroughly evaluate the impact of the decoupling method and the number of decomposed components on the model's performance. Compared to traditional machine learning models without decomposition, our framework achieves an average correlation coefficient exceeding 0.99 and an average mean absolute percentage error below 0.83% on 10 datasets with different natural gas components, high temperatures, and pressures. These results indicate that hybrid model effectively learns the patterns of Z-factor variations and can be applied to the prediction of natural gas Z-factors under various conditions. This study significantly advances methodologies for predicting natural gas properties, offering a unified and robust solution for precise estimations, thereby benefiting the natural gas industry in resource estimation and reservoir management.
准确预测天然气的偏差因子（Z 因子）对于天然气储量估算、气藏采收率评估以及管道天然气输送评估至关重要。传统机器学习算法，如支持向量机（SVM）、极端梯度提升（XGBoost）、轻量级梯度提升机（LightGBM）、人工神经网络（ANN）和双向长短期记忆神经网络（BiLSTM），由于无法在不同气体成分和温度 - 压力条件下进行泛化，在各种情况下往往缺乏准确性和鲁棒性。为解决这一局限性，我们提出了一种新颖且高效的用于预测天然气 Z 因子的机器学习框架。我们的方法首先利用诸如变分模态分解（VMD）、经验傅里叶分解（EFD）和集合经验模态分解（EEMD）等信号分解算法将 Z 因子解耦为多个分量。随后，采用传统机器学习算法预测每个解耦后的 Z 因子分量，其中 SVM 和 VMD 的组合表现最佳。首先对 Z 因子进行解耦，然后预测解耦后的分量，可以显著提高所有传统机器学习算法的预测准确性。我们全面评估了解耦方法和分解分量数量对模型性能的影响。与未进行分解的传统机器学习模型相比，我们的框架在 10 个具有不同天然气成分、高温和高压的数据集上实现了平均相关系数超过 0.99，平均平均绝对百分比误差低于 0.83%。这些结果表明，混合模型有效地学习了 Z 因子变化的模式，可应用于各种条件下天然气 Z 因子的预测。本研究显著推进了预测天然气性质的方法，为精确估计提供了统一且稳健的解决方案，从而使天然气行业在资源估计和油藏管理方面受益。
