基于注意力机制的卷积神经网络机械钻速预测方法

传统机器学习方法在进行机械钻速预测时,受复杂特征提取和人为认知局限性的影响,难以满足现场预测精度要求。基于此,提出一种特征提取和回归预测相结合的机械钻速预测方法。首先,采用箱型图和独热编码对钻井实测数据进行预处理,清除异常数据并将离散特征连续化。其次,应用卷积神经网络(convolutional neural network, CNN)挖掘数据特征,并在网络中引入通道注意力机制(squeeze-and-excitation network, SENet),实现对CNN特征通道重要性程度的合理分配,建立SE-CNN机械钻速预测模型。最后,将SE-CNN模型与CNN模型进行对比分析,结果表明：SE-CNN模型的拟合优度提高了2.1%,平均绝对误差和均方根误差分别降低了1.1%和1.5%。SE-CNN模型具有较高的预测精度,可以用于现场机械钻速预测,为钻井提速提供科学参考。

Prediction Method for ROP Based on Attention Mechanism of Convolutional Neural Network

Traditional machine learning methods for mechanical ROP prediction are affected by complex feature extraction and imitations of human understanding, which make the prediction accuracy difficult to meet the on-site demand. Based on this, a new ROP prediction method combining feature extraction and regression prediction was proposed. Firstly, data in drilling engineering were pre-processed by box-plot method and one-hot encoding to eliminate abnormal data and to make discrete characteristic continuous. Secondly, convolutional neural network (CNN) was applied to extracting data features, and channel attention mechanism (squeeze-and-excitation network, SENet) was introduced to construct an SE-CNN model, which could adjust the importance of CNN feature channel. Finally, and SE-CNN model was compared with CNN model. The results shows that the goodness of fit of SE-CNN model is increased by 2.1%, the mean absolute error and the root mean squared error are decreased by 1.1% and 1.5%. SE-CNN model has a good prediction accuracy, SE-CNN model can forecast the ROP of drilling field and provides a scientific reference for increasing the ROP during drilling.