A Novel Deep Offline-to-Online Transfer Learning Framework for Pipeline Leakage Detection With Small Samples
Chuang Wang, Zidong Wang, Weibo Liu, Yuxuan Shen, Hongli Dong
Abstract
In this article, a two-stage deep offline-to-online transfer learning framework (DOTLF) is proposed for long-distance pipeline leakage detection (PLD). At the offline training stage, a feature transfer-based long short-term memory network with regularization information (TL-LSTM-Ri) is developed where a maximum mean discrepancy regularization term is employed to extract domain-invariant features and an adjacent-bias-corrected regularization term is introduced to extract early fault features from pipeline samples under different scenarios. At the online detection stage, the trained TL-LSTM-Ri is employed for motion prediction, so as to monitor the operating condition of the pipeline in real time. To demonstrate its application potential, the DOTLF is successfully applied to handle the PLD problem on the long-distance oil–gas pipeline data. Experimental results demonstrate the effectiveness of the proposed DOTLF for real-time PLD under real-world scenarios.