Author name cluster

Hongrui Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2025 Journal Article

Handling data heterogeneity for wind turbine fault diagnosis via dynamic ensemble multilevel interactive learning

Shuangxin Wang
Hongrui Li
Jiading Jiang
Meng Li
Junmei Ou
Dingli Yu

The artificial intelligence methods used in wind turbine fault diagnosis have not adequately considered the inherent heterogeneity of SCADA data. This heterogeneity arises from the stochastic nature of wind and the operational characteristics of turbines. Neglecting the heterogeneity may lead to models struggling to capture fault characteristic patterns across varying wind speed ranges, diminishing diagnostic performance. To handle this, a novel dynamic ensemble multilevel interactive (DEMI) learning method is proposed. Firstly, a new index of wind speed jump value is presented and applied to the fine data division of diagnostic units. This process assists diagnostic units in focusing more on learning fault distribution patterns within each wind speed range. Simultaneously, to capture fault feature information from complex and variable data, deep small-world networks with short-path propagation and high clustering properties are designed within each unit for multilevel feature interaction learning. Subsequently, a multi-wind-speed unit model library is constructed, and a dynamic selection algorithm is employed to find high-performance classifiers to reduce the impact of these networks random topology. Finally, in the diagnostic phase, the final diagnostic results are obtained using online dynamic retrieval ensemble. The experimental results indicate that the DEMI enhances diagnostic performance accuracy compared to the currently advanced methods that overlook heterogeneity, while reducing false alarm rates.

Details DOI

EAAI Journal 2025 Journal Article

Predictive model of bond strength between recycled aggregate concrete and rebar after high-temperature based on conditional table generation adversarial networks data augmentation and gene expression programming algorithm

Hongrui Li
Haifeng Yang

Recycled aggregate concrete (RAC) is recognized as a more environmentally sustainable building material compared to conventional natural aggregate concrete, with environmental advantages highly valued by the contemporary construction industry. Exploring the bond strength ( τ u ) between RAC and rebar following exposure to elevated temperatures is crucial for accurately evaluating structural fire damage and optimizing fire safety strategies. However, determining τ u through experimental methods are costly, effort, and time-consuming. To address this, an artificial intelligence-based gene expression programming (GEP) algorithm was applied in this study to derive mathematical expressions predicting bond strength of RAC and rebar before and after high temperatures. Due to limited data from high-temperature bond tests, a novel synthetic data-driven framework conditional table generation adversarial networks (CTGAN), was developed for data augmentation to form 3243 sets of mixed data to improve the training of the GEP. Additionally, thermal cracking resulting from thermal expansion disparities between RAC and rebar was investigated utilising thick-walled cylinder theory. Results indicated that the CTGAN accurately captured the statistical properties of experimental data, producing synthetic datasets with similar distributions. The coefficient of determination ( R 2 ) for the GEP test set is 0. 984, demonstrating superior performance. The average and maximum errors are 7. 73 % and 6. 46 %, respectively, outperforming alternative regression models. Temperature emerged as the most influential factor, followed by recycled aggregate maximum size, etc. Finally, a formula for calculating thermal crack radius is proposed, and its expansion mechanism is explored. The developed GEP demonstrates high accuracy and interpretability, effectively guiding the engineering design of RAC structures under high-temperature conditions.

Details DOI

NeurIPS Conference 2025 Conference Paper

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

Haonan Wang
Jingyu Lu
Hongrui Li
Xiaomeng Li

Recent advances in neural decoding have enabled the reconstruction of visual experiences from brain activity, positioning fMRI-to-image reconstruction as a promising bridge between neuroscience and computer vision. However, current methods predominantly rely on subject-speciﬁc models or require subject-speciﬁc ﬁne-tuning, limiting their scalability and real-world applicability. In this work, we introduce ZEBRA, the ﬁrst zero-shot brain visual decoding framework that eliminates the need for subject-speciﬁc adaptation. Z EBRA is built on the key insight that fMRI representations can be decomposed into subject-related and semantic-related components. By leveraging adversarial training, our method explicitly disentangles these components to isolate subject-invariant, semantic-speciﬁc representations. This disentanglement allows ZEBRA to generalize to unseen subjects without any additional fMRI data or retraining. Extensive experiments show that ZEBRA signiﬁcantly outperforms zero-shot baselines and achieves performance comparable to fully ﬁnetuned models on several metrics. Our work represents a scalable and practical step toward universal neural decoding. Code and model weights are available at: https: //github. com/xmed-lab/ZEBRA.

PDF Details