Affiliations: [a] School of Computer Science, Southwest Petroleum University, Chengdu, Sichuan, China | [b] Lab of Machine Learning, Southwest Petroleum University, Chengdu, Sichuan, China | [c] Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, Sichuan, China | [d] Petroleum Engineering School, Southwest Petroleum University, Chengdu, Sichuan, China | [e] Oil and Gas Field Development Department, Geological Exploration and Development Research Institute, Chengdu, Sichuan, China
Correspondence:
[*]
Corresponding author: Fan Min, School of Computer Science, Southwest Petroleum University, Chengdu, Sichuan 610500, China. E-mail: [email protected].
Abstract: Effective identification of anomalous data from production time series in the oilfield affects future analysis and forecasting. Such time series is often characterized by irregular time intervals due to uneven manual sampling, and missing values caused by incomplete measurements. Therefore, the identification task becomes more challenging. In this paper, an Attention-Embedded Time-Aware Imputation Network (ATIN) with two sub-networks is proposed for this task. First, Time-Aware Imputation LSTM (TI-LSTM) is designed for modeling irregular time intervals and incomplete measurements. It decays the long-term memory component as the producing well conditions may be varied during the water cut stage. Second, Attention-Embedding LSTM (ATEM) is designed to improve the effectiveness of anomaly detection. It focuses on the correlation between the last and historical measurements in a given sequence. Comparison experiments with several state-of-the-art methods, including mTAN, GRU-D, T-LSTM, ATTAIN, and BRITS are conducted. Results show that the proposed ATIN performs better in accuracy, F1-score, and area under curve (AUC).
Keywords: Attention mechanism, missing value, production data, time series
