Dongying Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dongying Han has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Peiming Shi
Yanshan University
10 shared publications- Peiming Shi
School of Electrical Engineering, Yanshan University, Qinhuangdao, China
6 shared publications Yu Zhang
5 shared publications- Zhizhou Zhu
School of Vehicles and Energy, Yanshan University, Qinhuangdao, Hebei 066004, People’s Republic of China
3 shared publications Bingfan Li
School of Vehicles and Energy, Yanshan University, Qinhuangdao, Hebei 066004, People’s Republic of China
2 shared publicationsHamid Reza Karimi
Department of Mechanical Engineering, Politecnico di Milano, 20156 Milan, Italy
2 shared publications
Latest Publications
- 18 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (13)
Few-shot Working Condition Recognition of Pumping Units based on Physics-Informed Prototype Network
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.
- 18 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (13)
Few-shot Working Condition Recognition of Pumping Units based on Physics-Informed Prototype Network
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.
- 20 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (14)
Research on Few-Shot working condition recognition method for pumping units based on Hierarchical Contrastive Learning and Prototypical Network
As one of the most extensively employed artificial lifting equipment in oilfield development, the pumping unit requires effective working condition recognition to ensure production stability and economic viability in oilfield operations.However, the scarcity of specific fault condition dynamometer cards samples in realworld production environments severely limits the recognition performance of traditional deep learning methods. To overcome this limitation, this paper develops a Hierarchical Contrastive Learning and Prototypical Network Few-Shot Recognition (HC-PFR) method for pumping units. The core of this method lies in integrating instance-level and category-level contrastive learning to significantly enhance feature discriminability through dual-layer feature optimization. Simultaneously, by incorporating a prototypical network learning mechanism, it effectively leverages limited samples to construct category representations, achieving precise few-shot classification. To strengthen the model's generalization capacity under data-scarce conditions, a physics-constrained data augmentation strategy is introduced, ensuring that augmented dynamometer card data retains physical characteristics consistent with real-world working conditions. In multiple N-way K-shot experiments, the proposed method achieved an accuracy of 92% in 5-way 1-shot scenarios and 97.33% in 5-way 5-shot scenarios. Experimental findings indicate that the proposed method successfully mitigates the data scarcity issue encountered in pumping unit working condition recognition, provides technical support for intelligent oilfield production, and offers a novel research direction for few-shot fault diagnosis of pumping units.
- 20 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (14)
Research on Few-Shot working condition recognition method for pumping units based on Hierarchical Contrastive Learning and Prototypical Network
As one of the most extensively employed artificial lifting equipment in oilfield development, the pumping unit requires effective working condition recognition to ensure production stability and economic viability in oilfield operations.However, the scarcity of specific fault condition dynamometer cards samples in realworld production environments severely limits the recognition performance of traditional deep learning methods. To overcome this limitation, this paper develops a Hierarchical Contrastive Learning and Prototypical Network Few-Shot Recognition (HC-PFR) method for pumping units. The core of this method lies in integrating instance-level and category-level contrastive learning to significantly enhance feature discriminability through dual-layer feature optimization. Simultaneously, by incorporating a prototypical network learning mechanism, it effectively leverages limited samples to construct category representations, achieving precise few-shot classification. To strengthen the model's generalization capacity under data-scarce conditions, a physics-constrained data augmentation strategy is introduced, ensuring that augmented dynamometer card data retains physical characteristics consistent with real-world working conditions. In multiple N-way K-shot experiments, the proposed method achieved an accuracy of 92% in 5-way 1-shot scenarios and 97.33% in 5-way 5-shot scenarios. Experimental findings indicate that the proposed method successfully mitigates the data scarcity issue encountered in pumping unit working condition recognition, provides technical support for intelligent oilfield production, and offers a novel research direction for few-shot fault diagnosis of pumping units.
- Open Access
- 1 January 2026
- Published by Wiley in Shock and Vibration
- Vol. 2026 (1)
Multirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50
Bearings are critical components in wind turbines, and their failure detection is vital for maintaining the reliability of these systems. However, traditional fault diagnosis methods often fail to perform adequately under noisy conditions, which are common in real‐world applications. This study introduces a robust multimodal diagnostic method based on convolutional neural network (CNN)–ResNeXt‐50 for rolling bearing fault diagnosis under noisy environments. The method combines the strengths of CNNs and ResNeXt‐50, utilizing two signal transformations—Fast Fourier Transform (FFT) and Synchrosqueezing Transform (SST)—to extract complementary features from vibration signals. The fused features are then used for fault classification, ensuring superior stability, and generalization ability. Experimental results on three publicly available datasets demonstrate that the proposed approach outperforms existing methods, achieving higher accuracy, faster convergence, and better robustness to varying noise levels, making it highly suitable for practical bearing fault diagnosis in noisy industrial environments.
- 1 January 2026
- Published by Wiley in Shock and Vibration
- Vol. 2026 (1)
Open AccessMultirepresentation Signal Preprocessing for Bearing Fault Diagnosis Under Noise Using CNN–ResNeXt‐50
Bearings are critical components in wind turbines, and their failure detection is vital for maintaining the reliability of these systems. However, traditional fault diagnosis methods often fail to perform adequately under noisy conditions, which are common in real‐world applications. This study introduces a robust multimodal diagnostic method based on convolutional neural network (CNN)–ResNeXt‐50 for rolling bearing fault diagnosis under noisy environments. The method combines the strengths of CNNs and ResNeXt‐50, utilizing two signal transformations—Fast Fourier Transform (FFT) and Synchrosqueezing Transform (SST)—to extract complementary features from vibration signals. The fused features are then used for fault classification, ensuring superior stability, and generalization ability. Experimental results on three publicly available datasets demonstrate that the proposed approach outperforms existing methods, achieving higher accuracy, faster convergence, and better robustness to varying noise levels, making it highly suitable for practical bearing fault diagnosis in noisy industrial environments.
- 27 October 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 042201
Research progress and prospects in fault diagnosis of pumping units using dynamometer cards
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.
- 27 October 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 042201
Research progress and prospects in fault diagnosis of pumping units using dynamometer cards
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.
- 26 February 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (3) , 036134
A novel multiple-prototype and domain adversarial network for few-shot cross-domain fault diagnosis
Since deep learning has been introduced into the field of intelligent fault diagnosis it has made significant accomplishments with large amounts of data. However, in practical industrial settings there is a general lack of labeled data and operating conditions are not stable, therefore existing trained models ignore these problems and diagnostic accuracy and generalization are severely degraded. Therefore, this study proposes a multiple-prototype, domain adversarial network for fault diagnosis of rotating machinery, especially bearings, to address the issues of domain distribution shift and a shortage of labeled samples from the target domain. Firstly, the proposed method adopts a residual network with 12 layers (ResNet12) as the encoder to extract distinct features from the target domain and source domain data. Then, a domain-invariant representation module, using the domain adversarial method, is introduced to bridge the discrepancy between a source and target pair domain. Furthermore, a class typicality weight module is designed to calculate weights by constructing multiple prototypes of the source and target domains to improve the generalization of the model. Extensive experiments are executed on two datasets with variable working conditions to test and verify the feasibility and superiority of the proposed method.
- 26 February 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (3) , 036134
A novel multiple-prototype and domain adversarial network for few-shot cross-domain fault diagnosis
Since deep learning has been introduced into the field of intelligent fault diagnosis it has made significant accomplishments with large amounts of data. However, in practical industrial settings there is a general lack of labeled data and operating conditions are not stable, therefore existing trained models ignore these problems and diagnostic accuracy and generalization are severely degraded. Therefore, this study proposes a multiple-prototype, domain adversarial network for fault diagnosis of rotating machinery, especially bearings, to address the issues of domain distribution shift and a shortage of labeled samples from the target domain. Firstly, the proposed method adopts a residual network with 12 layers (ResNet12) as the encoder to extract distinct features from the target domain and source domain data. Then, a domain-invariant representation module, using the domain adversarial method, is introduced to bridge the discrepancy between a source and target pair domain. Furthermore, a class typicality weight module is designed to calculate weights by constructing multiple prototypes of the source and target domains to improve the generalization of the model. Extensive experiments are executed on two datasets with variable working conditions to test and verify the feasibility and superiority of the proposed method.
- 8 February 2024
- Published by Elsevier in Neural Networks
- Vol. 173, 106167
A universal multi-source domain adaptation method with unsupervised clustering for mechanical fault diagnosis under incomplete data
- 8 February 2024
- Published by Elsevier in Neural Networks
- Vol. 173, 106167
A universal multi-source domain adaptation method with unsupervised clustering for mechanical fault diagnosis under incomplete data
- 21 February 2023
- Published by Elsevier in Neural Networks
- Vol. 162, 69-82
Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis
- 21 February 2023
- Published by Elsevier in Neural Networks
- Vol. 162, 69-82
Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis