To improve the electric submersible pump (ESP) system’s anomaly monitoring performance, this article proposes a novel approach known as the dual spatio-temporal contrastive learning network with adaptive threshold generation (DSTCL-ATG). Unlike previous ESP process modeling methods, this study comprehensively considers the spatio-temporal coupling characteristics of ESP data and incorporates Crossformer into the dual-path contrastive learning (DCL) architecture to provide superior normal ESP process modeling. Furthermore, we design an ATG approach based on a random forest regressor that is aimed at successfully mitigating frequent false alarms resulting from fluctuations in ESP status. The algorithm is evaluated using data from four faulty wells in real oilfield scenarios, demonstrating its effectiveness and superiority through extensive comparative experiments against state-of-the-art methodologies.
This paper addresses the challenges of fault diagnosis in gas turbines (GTs) utilized in oil and gas pipeline systems by proposing a novel multiparameter analysis framework that integrates dynamic, quantile-based Statistical Process Control (SPC) with prior domain knowledge. The proposed approach initially employs a dynamic quantile SPC model to establish adaptive control limits, effectively handling the non-stationarity and non-normality of gas turbine operational data. By analyzing parameter variations under typical operating conditions and incorporating expert insights, a multiparameter fault analysis matrix and corresponding weighting factors are constructed to facilitate fault diagnosis with prior knowledge. Furthermore, a fault probability model based on parameter change rates and weighting factors is developed to quantify the likelihood of different fault modes. An operating condition clustering and correction mechanism enables the dynamic adjustment of control limits, thereby preventing misdiagnoses caused by varying operational states. The validity of the proposed method is demonstrated using real data from a domestic pipeline gas turbine, validated by real domestic pipeline GT data, outperforming existing models, with a fault accuracy up to 10%. The approach efficiently estimates fault probabilities and accurately detects both sudden and gradual faults, significantly enhancing intelligent fault diagnosis capabilities for gas turbines.