Research progress and prospects in fault diagnosis of pumping units using dynamometer cards

Abstract Pumping units are critical equipment in oilfield operations, handling over 80% of global oil extraction. However, frequent failures under sustained high-load conditions significantly impact production efficiency and cause substantial economic losses, making reliable fault diagnosis essential for operational stability. This paper presents a comprehensive systematic review of pumping unit fault diagnosis research based on dynamometer cards, analyzing technological developments and identifying future research directions. Through extensive literature analysis covering publications from 2011–2024, we systematically examine five primary feature extraction methodologies: Freeman chain code, Fourier descriptors, gray-level co-occurrence matrices, moment eigenvectors, and curve moments. Each method’s computational complexity, noise sensitivity, and practical applicability are critically evaluated. We comprehensively analyze the evolution from classical machine learning approaches (support vector machine, BP neural network) to advanced deep learning architectures (generative adversarial network, convolutional neural network), comparing their diagnostic accuracy, computational requirements, and industrial suitability. Our analysis reveals that while traditional methods offer interpretability and computational efficiency suitable for small datasets, deep learning approaches demonstrate superior feature extraction capabilities and diagnostic accuracy for complex fault scenarios. However, significant challenges remain, including limited labeled datasets, cross-domain generalizability, and real-time processing requirements. Based on these findings, we identify five critical future research directions: optimization of feature extraction methods through automated design, deep integration of multi-source heterogeneous data, development of cross-condition adaptive models, exploration of advanced architectures (YOLOv8, Vision Transformer), and implementation of digital twin-based diagnostic frameworks. This comprehensive review provides researchers and practitioners with a systematic understanding of current technologies and a roadmap for advancing intelligent fault diagnosis systems in oilfield operations.