NEWS ARTICLE
学术动态：A Sensor-Aware Decoupled Learning Framework for Robust Multi-Scale Time-Series Forecasting in Oil Production Syste.
论文标题：A Sensor-Aware Decoupled Learning Framework for Robust Multi-Scale Time-Series Forecasting in Oil Production Systems
发布日期：2026-05-24
作者：Guojian Cheng, Wenhan Zhang, Zhonghui Jin, Lei Cai
DOI：10.3390/s26113332
论文摘要：Accurate forecasting of oil well production via field monitoring systems is significantly restricted by a structural conflict in modeling, where temporal dependency learning and nonlinear feature representation are closely coupled. Such coupling forces a trade-off between capturing long-term temporal dependencies and retaining sensitivity to short-term sensor fluctuations, while amplified local sensitivity easily increases noise interference and weakens model robustness under complex non-stationary sensor dynamics. To solve this problem, this study proposes a novel sensor-driven hybrid framework named Temporal Augmented Residual Network (TAR-Net), which adopts a decoupled paradigm to separate global temporal modeling and local fluctuation compensation explicitly. A multi-scale dilated Temporal Convolutional Network (TCN) extracts long-range temporal patterns from multi-source sensor data, and a LightGBM-based residual module conducts targeted error correction. Meanwhile, multi-scale temporal features and adaptive multi-fidelity Bayesian optimization are applied to enhance model adaptability. Validated on real sensor data from the Volve oilfield, TAR-Net surpasses 13 benchmark models with an R2 of 0.9832 and a MAPE of 7.8%. Residual and trajectory analyses verify its balance between global trend consistency and local fluctuation sensitivity. This framework offers a robust sensor-aware solution for complex multi-scale temporal modeling in industrial production systems.
元数据：Crossref 收录的 MDPI Sensors 论文。 DOI: 10.3390/s26113332. Vol. 26, Issue 11. Authors: Guojian Cheng, Wenhan Zhang, Zhonghui Jin, Lei Cai.
开放许可：https://creativecommons.org/licenses/by/4.0/
原文链接：https://doi.org/10.3390/s26113332
PDF 链接：https://www.mdpi.com/1424-8220/26/11/3332/pdf