基于物理模型驱动的机器学习方法预测超临界二氧化碳管道最大泄漏速率

A physical model driven machine learning for predicting maximum leakage rate in supercritical CO_(2) release

碳捕集与封存(CCS)项目中涉及的大规模CO_(2)适合采用超临界管道输送。然而超临界CO_(2)管道泄漏过程伴随着复杂相变,因此对其最大泄漏速率进行准确预测是目前的研究难点。鉴于传统物理模型方法存在建模复杂、假设过多、计算耗时等缺点,研究提出通过机器学习方法预测超临界CO_(2)管道最大泄漏速率,分别采用粒子群算法优化的支持向量机(PSO-SVM)和简化处理的卷积神经网络(CNN)对等熵阻塞泄漏模型所生成的泄漏特征数据进行学习,并测试了机器学习模型的预测准确率和泛化能力。研究结果表明:①物理模型、PSO-SVM、CNN的预测结果与实验数据的平均误差为28.82%;②两种机器学习模型预测精度相差不大,CNN的训练时间远短于PSO-SVM,但PSO-SVM的泛化能力强于CNN,因此,SVM适用于小样本数据精确预测,而CNN更适用于对大数据的学习和预测。本研究成果为超临界CO_(2)管道最大泄漏速率预测提供了一种高效的新方法。

Supercritical CO_(2)pipelines are suitable to transport the large-scale CO_(2)involved in Carbon capture and storage projects.The leakage process of supercritical CO_(2)pipelines is accompanied by complex phase changes. Therefore, it is difficult to predict the maximum leakage rate accurately at present. In view of the shortcomings of traditional physical model methods such as complex modeling, too many assumptions and time-consuming calculations, a way of predicting the maximum leakage rate of supercritical CO_(2)pipelines by machine learning method was proposed. It used to simply convolutional neural networks(CNN) and support vector machine improved by particle swarm optimization(PSO-SVM) respectively to study the leakage feature data generated by the isentropic choked flow leakage model. The prediction accuracy and generalization ability of the trained machine learning model were tested. The results show that: First, the average error between experimental data and prediction results of physical model, PSO-SVM, CNN is 28.82%. Second, the prediction accuracy of the two machine learning models shows little difference, the training time of CNN is much shorter than that of PSO-SVM, but the generalization ability of PSOSVM is stronger than that of CNN. Therefore, SVM is suitable for accurate prediction of small sample data, while CNN is more suitable for learning and prediction of large sample data. This study provides a new efficient method for predicting the maximum leakage rate of supercritical CO_(2)pipelines.