Research on early warning model of electric submersible pump wells failure based on the fusion of physical constraints and data-driven approach

Abstract

At present, there are too few characteristic parameters for early identification of electric submersible pump (ESP) wells failures. In addition, existing predictive models rely only on data-driven techniques, which do not provide a comprehensive understanding of the intrinsic mechanisms behind the occurrence of failures. This article presents the development of a health index calculation approach for evaluating the operational status of the ESP wells. The wellbore energy conservation equation and the health index calculation formula were employed to develop a physical constraints (PC) for the loss function in the network model of Long Short-Term Memory (LSTM). This constraint was then utilized to construct the PC-LSTM ESP health warning model. The study examines the health index trends associated with three types of faults: ESP clogging, sand production in oil wells, and reservoir pressure rise. The results indicate that the PC-LSTM network structure exhibits faster convergence during training. In relation to the accuracy of prediction, PC-LSTM demonstrates a notable enhancement. Specifically, when the ESP clogging fault, the traditional LSTM achieves a mean relative error (MRE) of 211.15%, whereas the PC-LSTM achieves a reduced MRE of 12.74%. Similarly, for sand production in oil wells, the traditional LSTM yields an MRE of 19.07%, while the PC-LSTM achieves a reduced MRE of 9.62%. Lastly, in the scenario of reservoir pressure rise, the traditional LSTM exhibits an MRE of 41.07%, whereas the PC-LSTM achieves a reduced MRE of 12.74%. In the meantime, the model demonstrates a high level of accuracy in capturing the pre- and post-trends of the health status of the ESP wells. This improved prediction accuracy and interpretability of the underlying mechanisms serve as valuable tools for analyzing the lift performance of ESP wells and providing early warning signals for potential failures.