Few-shot Working Condition Recognition of Pumping Units based on Physics-Informed Prototype Network
- 18 June 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (13)
Abstract
In the context of intelligent oilfield operation and maintenance, the accurate recognition of pumping unit working conditions is crucial for ensuring production safety and efficiency. However, practical scenarios face challenges such as scarce labeled samples, imbalanced fault categories, and limited computational resources on edge devices, which constrain the application of deep learning methods.To address this, this paper proposes a lightweight working condition diagnosis method that integrates physical prior knowledge and few-shot learning-the Physics-Informed Prototypical Network (PIPK). This method builds a few-shot classification framework based on the prototypical network and embeds, as hard constraints into the feature learning process, the Gibbs one-dimensional wave equation describing the dynamic behavior of the sucker rod system and the mechanical model of polished rod load, thereby enhancing the model's physical consistency and generalization capability. To further meet the requirements for edge deployment, an improved knowledge distillation architecture is designed to transfer knowledge from the complex teacher model containing physical information to a lightweight MobileNetV2 student network.Experiments on a real indicator diagram dataset show that PIPK achieves an average accuracy of 95.07% and an F1 score of 94.46% using only 5 support samples per class, significantly outperforming existing few-shot learning methods.Keywords
Funding Information
- Yanshan University Basic Innovation Research Cultivation Project (2024LGQL001)
- Science Research Project of Hebei Province Higher Education (CXZX2025024)
- Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts (IDICP-KF-2024-10)
This publication has 33 references indexed in Scilit:
- Knowledge-data synergy enabling zero-shot composite fault diagnosis in sucker-rod pumping systemsEngineering Applications of Artificial Intelligence, 2025
- Multi-label learning for fault diagnosis of pumping units with one positive labelApplied Soft Computing, 2025
- ParaDC: Parallel-learning-based dynamometer cards augmentation with diffusion models in sucker rod pump systemsNeurocomputing, 2024
- A gradual self distillation network with adaptive channel attention for facial expression recognitionApplied Soft Computing, 2024
- Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samplesKnowledge-Based Systems, 2024
- A novel contrastive adversarial network for minor-class data augmentation: Applications to pipeline fault diagnosisKnowledge-Based Systems, 2023
- Attention-based deep meta-transfer learning for few-shot fine-grained fault diagnosisKnowledge-Based Systems, 2023
- An evolutional deep learning method based on multi-feature fusion for fault diagnosis in sucker rod pumping systemAlexandria Engineering Journal, 2022
- Data Augmentation Method Based on Improved Generative Adversarial Network for the Sucker Rod Pump SystemInternational Journal of Control, Automation, and Systems, 2022
- A physics-informed deep learning approach for bearing fault detectionEngineering Applications of Artificial Intelligence, 2021