Statistical summary of key features.

To ensure the safe operation of oil and gas pipeline systems in complex environments, accurately predicting the corrosion rate of natural gas well pipes is of paramount importance. Given the widespread challenge of pipe corrosion in the oil and gas industry, we propose a transfer learning model based on a CNN-LSTM-Transformer architecture with a staged fine-tuning strategy for corrosion rate prediction under small-sample conditions. The model integrates Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Transformer modules. CNN is employed to extract local features from corrosion data. LSTM captures the temporal dependencies within the data, and the Transformer module applies multi-head attention to recalibrate features, effectively addressing long-range dependencies. To enhance the model’s adaptability, the CNN-LSTM-Transformer model is initially trained on a source domain and then progressively fine-tuned on a target domain to facilitate knowledge transfer. Experimental results demonstrate that, after staged fine-tuning, the CNN-LSTM-Transformer model achieves an MAE of 0.021, RMSE of 0.031, and an R² of 0.909, outperforming other transfer learning approaches by a substantial margin.

为保障复杂环境下油气管道系统的安全运行，精准预测天然气井管的腐蚀速率至关重要。鉴于管道腐蚀是油气行业普遍面临的难题，本文针对小样本条件下的腐蚀速率预测任务，提出一种基于CNN-LSTM-Transformer架构、并采用分阶段微调策略的迁移学习模型。该模型整合了卷积神经网络（Convolutional Neural Networks，简称CNN）、长短期记忆网络（Long Short-Term Memory networks，简称LSTM）以及Transformer模块：其中卷积神经网络（CNN）用于提取腐蚀数据的局部特征，长短期记忆网络（LSTM）用于捕捉数据内的时序依赖关系，Transformer模块则通过多头注意力机制对特征进行重校准，有效解决长距离依赖问题。为提升模型的适配能力，该CNN-LSTM-Transformer模型首先在源域完成预训练，随后在目标域上逐步微调以实现知识迁移。实验结果表明，经分阶段微调后，该模型的平均绝对误差（Mean Absolute Error，简称MAE）为0.021、均方根误差（Root Mean Squared Error，简称RMSE）为0.031、决定系数（Coefficient of Determination，简称R²）为0.909，其性能大幅优于其他迁移学习方法。