Hao Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hao Ren has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Weihua Gui
Central South University
7 shared publications - Chunhua Yang
Central South University
6 shared publications - Xiaojun Liang
Peng Cheng Laboratory, Shenzhen, China
6 shared publications - Yi Chai
Chongqing University
5 shared publications Haojie Ren
4 shared publications- Haojie Ren
State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
4 shared publications
Latest Publications
- 17 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Experimental investigation on straight-fin helical strakes with varying geometric parameters for vortex-induced vibration suppression
- 17 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Experimental investigation on straight-fin helical strakes with varying geometric parameters for vortex-induced vibration suppression
- Open Access
- 12 September 2026
- Published by Elsevier in Journal of Ocean Engineering and Science
Cross-sectional Mechanical Characteristics of Unbonded Flexible Riser Under Axisymmetric Loads Based on a Simplified Finite Element Model
- 12 September 2026
- Published by Elsevier in Journal of Ocean Engineering and Science
Open AccessCross-sectional Mechanical Characteristics of Unbonded Flexible Riser Under Axisymmetric Loads Based on a Simplified Finite Element Model
- 3 August 2026
- Published by Elsevier in Ocean Engineering
- Vol. 365
An efficient three-dimensional ocean wave reconstruction method based on adaptive strip-wise stereo matching
- 3 August 2026
- Published by Elsevier in Ocean Engineering
- Vol. 365
An efficient three-dimensional ocean wave reconstruction method based on adaptive strip-wise stereo matching
- Open Access
- 15 May 2026
- Published by Elsevier in SSRN Electronic Journal
Source-decision attention multi-scale ensemble booster for multivariate time series classification
Multivariate Time Series Classification (MTSC) is a core task in time series analysis. While ensemble and multi-scale methods excel at this task, they rely heavily on complex preprocessing, manual strategies, and rigid structures, limiting their flexibility to integrate with other models. To address this, we propose the Source-decision Attention Multi-scale Ensemble Booster (SaMEB), a general, plug-and-play enhancement framework that requires only one hyperparameter, $n$. SaMEB significantly boosts MTSC performance without altering the base classifier's original structure. It integrates three core components: a multi-scale source attention module to adaptively extract key variable features; a probabilistic distribution co-evolution strategy for mutually reinforcing optimization during training; and a decision attention module to fuse multi-scale discriminative outputs into a robust probability distribution. Extensive experiments on the UEA repository, containing 30 multivariate time series datasets, confirm the necessity of these components. Comparisons with 14 state-of-the-art methods demonstrate that SaMEB-enhanced models achieve leading performance across key metrics, including classification accuracy and average ranking.- 15 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSource-decision attention multi-scale ensemble booster for multivariate time series classification
Multivariate Time Series Classification (MTSC) is a core task in time series analysis. While ensemble and multi-scale methods excel at this task, they rely heavily on complex preprocessing, manual strategies, and rigid structures, limiting their flexibility to integrate with other models. To address this, we propose the Source-decision Attention Multi-scale Ensemble Booster (SaMEB), a general, plug-and-play enhancement framework that requires only one hyperparameter, $n$. SaMEB significantly boosts MTSC performance without altering the base classifier's original structure. It integrates three core components: a multi-scale source attention module to adaptively extract key variable features; a probabilistic distribution co-evolution strategy for mutually reinforcing optimization during training; and a decision attention module to fuse multi-scale discriminative outputs into a robust probability distribution. Extensive experiments on the UEA repository, containing 30 multivariate time series datasets, confirm the necessity of these components. Comparisons with 14 state-of-the-art methods demonstrate that SaMEB-enhanced models achieve leading performance across key metrics, including classification accuracy and average ranking. - 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (2) , 698-710
Incremental Data-Driven Fault Diagnosis for Conveyor Rollers With Prior Drift Adaptation: An Online Active Kernel Learning Approach
Conveyor rollers are essential components in the hot steel milling process, responsible for transporting products between various stages of production throughout the entire process. Due to the development of Industrial Internet of Things (IIoT), conveyors are now equipped with sensors to collect real-time data, facilitating data-driven fault diagnosis models. While many well-trained data-driven diagnostic models initially demonstrate accurate performance, their effectiveness may decline over time due to unexpected changes, such as the emergence of new faults. This causes the prior distribution of fault data to change over time, and we refer to this as prior drift. In this study, we provide a mathematical definition of prior drift within the context of fault diagnosis and then develop a general learning criterion to guide the incremental updating of fault diagnosis models under such conditions. Building on this criterion, we propose an online active kernel learning-based fault diagnosis model (OAKL) for conveyor rollers. OAKL updates the diagnosis model in an incremental manner and adapts to prior drift. Particularly, it leverages selective querying and labeling of the most informative samples to facilitate early detection of novel faults, avoid performance bias, and reduce the number of incremental samples required. A rigorous theoretical analysis is conducted to demonstrate the theoretical validity of OAKL. The experimental results on a practical industrial case demonstrate the efficacy of our approach in fault diagnosis.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (2) , 698-710
Incremental Data-Driven Fault Diagnosis for Conveyor Rollers With Prior Drift Adaptation: An Online Active Kernel Learning Approach
Conveyor rollers are essential components in the hot steel milling process, responsible for transporting products between various stages of production throughout the entire process. Due to the development of Industrial Internet of Things (IIoT), conveyors are now equipped with sensors to collect real-time data, facilitating data-driven fault diagnosis models. While many well-trained data-driven diagnostic models initially demonstrate accurate performance, their effectiveness may decline over time due to unexpected changes, such as the emergence of new faults. This causes the prior distribution of fault data to change over time, and we refer to this as prior drift. In this study, we provide a mathematical definition of prior drift within the context of fault diagnosis and then develop a general learning criterion to guide the incremental updating of fault diagnosis models under such conditions. Building on this criterion, we propose an online active kernel learning-based fault diagnosis model (OAKL) for conveyor rollers. OAKL updates the diagnosis model in an incremental manner and adapts to prior drift. Particularly, it leverages selective querying and labeling of the most informative samples to facilitate early detection of novel faults, avoid performance bias, and reduce the number of incremental samples required. A rigorous theoretical analysis is conducted to demonstrate the theoretical validity of OAKL. The experimental results on a practical industrial case demonstrate the efficacy of our approach in fault diagnosis.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
A CNN-MFKAN-Based Fault Diagnosis Method for Rolling Bearings Under Multiple Working Conditions
Fault diagnosis in rolling bearings significantly influences the dependability and performance of industrial equipment. Considering the shortcomings of traditional fault diagnosis methods, such as poor generalization performance and insufficient feature extraction capability, this paper proposes a bearing fault diagnosis method by combining convolutional neural network with multi-scale fast Kolmogorov-Arnold network (CNN-MFKAN), which integrates the feature extraction capability of CNN with the nonlinear processing superiority of MFKAN. In addition, in order to further enhance the fault feature extraction ability, the Convolution Block Attention Module (CBAM) is introduced in this paper under multiple working conditions. Finally, the proposed CNN-MFKAN model is evaluated by utilizing Harbin Institute of Technology aircraft engine inter-shaft bearing system dataset. The experiments show that the presented method maintains high fault identification rate and classification accuracy under multiple working conditions, and the proposed model is obviously superior to the current mainstream transfer learning methods in cross-working conditions, which further illustrates the superiority and effectiveness of this scheme.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
A CNN-MFKAN-Based Fault Diagnosis Method for Rolling Bearings Under Multiple Working Conditions
Fault diagnosis in rolling bearings significantly influences the dependability and performance of industrial equipment. Considering the shortcomings of traditional fault diagnosis methods, such as poor generalization performance and insufficient feature extraction capability, this paper proposes a bearing fault diagnosis method by combining convolutional neural network with multi-scale fast Kolmogorov-Arnold network (CNN-MFKAN), which integrates the feature extraction capability of CNN with the nonlinear processing superiority of MFKAN. In addition, in order to further enhance the fault feature extraction ability, the Convolution Block Attention Module (CBAM) is introduced in this paper under multiple working conditions. Finally, the proposed CNN-MFKAN model is evaluated by utilizing Harbin Institute of Technology aircraft engine inter-shaft bearing system dataset. The experiments show that the presented method maintains high fault identification rate and classification accuracy under multiple working conditions, and the proposed model is obviously superior to the current mainstream transfer learning methods in cross-working conditions, which further illustrates the superiority and effectiveness of this scheme.
- Open Access
- 12 August 2025
- Published by Elsevier in Engineering
- Vol. 60, 142-153
Knowledge-Enhanced Industrial Question-Answering Using Large Language Models
- 12 August 2025
- Published by Elsevier in Engineering
- Vol. 60, 142-153
Open AccessKnowledge-Enhanced Industrial Question-Answering Using Large Language Models
- 29 May 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 174
Singular Value Decomposition-based lightweight LSTM for time series forecasting
- 29 May 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 174
Singular Value Decomposition-based lightweight LSTM for time series forecasting
- 1 May 2025
- Published by Springer Nature
- p. 386-395
Knowledge-Guided Reasoning Chain of Pre-trained LLM in Industrial Domain
- 1 May 2025
- Published by Springer Nature
- p. 386-395
Knowledge-Guided Reasoning Chain of Pre-trained LLM in Industrial Domain
- 1 February 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (2)
Vortex-induced vibration features of a flexible pipe with a low mass ratio at subcritical Reynolds numbers
A new type of riser, such as the thermoplastic composite pipe, features a low mass ratio and is becoming increasingly common in marine engineering projects. However, vortex-induced vibration (VIV) poses a significant concern regarding fatigue damage in risers, and VIV understandings of risers with low mass ratios are still limited and require further investigation. The present study conducted experimental research on a flexible pipe with a critical mass ratio of 0.50 at subcritical Reynolds numbers (Re) through towing in still water. The displacement responses were reconstructed using modal superposition methods. The amplitude, frequency, and phase difference between in-line (IL) flow and cross-flow (CF) directions, motion trajectory, and fatigue damage are analyzed. The results indicate that the unexpectedly larger VIV amplitude with over 1.0 D appears in the IL direction, which is compared to that found in the CF direction. Such higher response amplitude in the IL direction leads to increased fatigue damage. Additionally, the VIVs in both IL and CF directions exhibit no apparent frequency lock-in phenomenon. The frequencies of the VIVs between the IL and CF directions maintain a twice relationship, and the motion trajectory follows a typical “8”-shaped pattern. The present work provides a basic understanding of VIVs in risers with critical mass ratios and offers helpful guidelines for the design of marine risers in engineering applications.
- 1 February 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (2)
Vortex-induced vibration features of a flexible pipe with a low mass ratio at subcritical Reynolds numbers
A new type of riser, such as the thermoplastic composite pipe, features a low mass ratio and is becoming increasingly common in marine engineering projects. However, vortex-induced vibration (VIV) poses a significant concern regarding fatigue damage in risers, and VIV understandings of risers with low mass ratios are still limited and require further investigation. The present study conducted experimental research on a flexible pipe with a critical mass ratio of 0.50 at subcritical Reynolds numbers (Re) through towing in still water. The displacement responses were reconstructed using modal superposition methods. The amplitude, frequency, and phase difference between in-line (IL) flow and cross-flow (CF) directions, motion trajectory, and fatigue damage are analyzed. The results indicate that the unexpectedly larger VIV amplitude with over 1.0 D appears in the IL direction, which is compared to that found in the CF direction. Such higher response amplitude in the IL direction leads to increased fatigue damage. Additionally, the VIVs in both IL and CF directions exhibit no apparent frequency lock-in phenomenon. The frequencies of the VIVs between the IL and CF directions maintain a twice relationship, and the motion trajectory follows a typical “8”-shaped pattern. The present work provides a basic understanding of VIVs in risers with critical mass ratios and offers helpful guidelines for the design of marine risers in engineering applications.