In recent years, companies have employed numerous methods to lower expenses and enhance system efficiency in the oilfield. Energy consumption has constituted a significant portion of these expenses. This paper introduces a normalized consumption factor to effectively evaluate energy consumption in the oilfield. Statistical analysis has been conducted on nearly 45,000 wells from six fields in China. Critical factors such as lifting method, daily production, pump depth, gas–oil ratio (GOR), and well deviation angle were evaluated individually. Results revealed that higher production could lead to lower normalized consumption for beam pumps, progressive cavity pumps, and electric submersible pump systems, thus enhancing system efficiency. Additionally, a higher GOR might result in lower normalized consumption for the beam pump system, while the deviation angle of the well showed negligible impact on the normalized consumption factor. This manuscript offers a method to assess the impacts of artificial lift methods on production and discusses suggestions for reducing consumption associated with each lifting method in the oilfield.

Conventional gas well classification methods cannot provide effective support for gas well routine management, and suffer from poor timeliness. In order to guide the on-site operation in liquid loading gas wells and improve the timeliness of gas well classification, this paper proposes a production data-driven gas well classification method based on the LDA-DA (Linear Discriminant Analysis–Discriminant Analysis) combination model. In this method, considering the requirements of routine management, gas wells are evaluated from two aspects: liquid drainage capacity (LDC) and liquid production intensity (LPI), and are classified into six types. Domain knowledge is used to perform the feature engineering on the on-site production data, and five features are set up to quantitatively evaluate the gas well and to create classification samples. On this basis, in order to specify the optimal data processing flow to establish the gas well classification map, four linear dimensionality reduction techniques, LDA, PCA, LPP, and ICA, are used to reduce the dimensionality of original classification samples, and then, four classical classification algorithms, NB, DA, KNN, and SVM, are trained and evaluated on the low-dimensional samples, respectively. The results show that the LDA space achieves the optimal sample separation and is chosen as the decision space for gas well classification. The DA algorithm obtains the top performance, i.e., the highest Average Macro F1-score of 95.619%, in the chosen decision space, and is employed to determine the classification boundaries in the decision space. At this point, the LDA-DA combination model for sample data processing is developed. Based on this model, gas well classification maps can be established by data mining, and the rapid evaluation and diagnosis of gas wells can be achieved. This method realizes instant and efficient production data-driven gas well classification, and can provide timely decision-making support for gas well routine management. It introduces new ideas for performing gas well classification, expanding the content and scope of the classification work, and presenting valuable insights for further research in this field.

Summary: The petroleum industry relies heavily on electric submersible pump (ESP) systems, which can cause substantial economic losses if malfunctioning. However, over half of these malfunctions are due to submersible electric motor (SEM) failures. To address this issue, motor current signature analysis (MCSA) is used in this work to monitor the condition of the SEM. This allows for further fault diagnosis of the ESP system, ensuring that malfunctions are detected and addressed promptly. In this study, a portable high-speed electrical signal acquisition tool was used to capture the current signal at a 10-KHz rate to monitor the SEM condition. Afterward, the fast Fourier transform (FFT) method was used to transform time-domain data into the frequency domain for spectrum analysis. Next, the motor rotational speed, which is critical for identifying fault characteristics, was obtained from the current spectrum based on the deep learning method, and the fault components were extracted from the spectrum to indicate various faults. Finally, maintenance decisions were made based on the detected failure characteristics to prevent further damage and improve system reliability. Fusing MCSA with deep learning techniques significantly improved fault diagnosis accuracy compared with MCSA alone, demonstrating the robustness and effectiveness of the proposed method.