ParaDC: Parallel-learning-based dynamometer cards augmentation with diffusion models in sucker rod pump systems

Abstract

The accurate fault diagnosis of sucker rod pump systems (SRPs) is crucial for the sustainable development of oil & gas. Currently, dynamometer cards (DCs) are widely employed to evaluate the working condition of SRPs, framing fault diagnosis as a pattern recognition problem. While significant attention has been dedicated to enhancing the performance of diagnostic algorithms, the critical role of high-quality DC datasets in improving diagnostic accuracy has been comparatively underexplored. To address issues of incomplete and imbalanced data distribution in existing DC datasets, this paper introduces ParaDC, a novel data augmentation mechanism grounded in parallel learning, to facilitate the transition of DCs from “small data” to “big data” and ultimately realize “deep intelligence”. Under this mechanism, wave equations representing the behavior of SRPs are first utilized to construct the customized “small” DC datasets. Diffusion models are then incorporated to augment the “big” DC datasets and enhance data diversity. Additionally, iterative training combined with human feedback is introduced to optimize and improve the quality of generated DCs, accelerating the pathway towards “deep intelligence”. To further validate the feasibility and effectiveness of ParaDC, extensive computational experiments are conducted to demonstrate its outstanding generative performance. Finally, the potential of intelligent diagnostic systems, supported by digital workers, is discussed in the context of Industry 5.0, which is believed to be indispensable in the future industrial diagnostic paradigm.