Heping Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Heping Hou has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chongshuai Nie
School of Printing, Packaging and Digital Media, Xian University of Technology, Xian, China
1 shared publication - Jie Liu
School of Printing Packaging and Digital Media, Xi’an University of Technology, Xi’an, China
1 shared publication - Jingsong Xie
School of Traffic and Transportation Engineering, Central South University, Changsha 410075, China
1 shared publication - Ruijie Wang
School of Printing, Packaging and Digital Media, Xian University of Technology, Xian, China
1 shared publication - Xiangju Zhang
College of Forestry, Henan Agricultural University, Zhengzhou 450046, China
1 shared publication - Xiaofang Wang
College of Forestry, Henan Agricultural University, Zhengzhou 450046, China
1 shared publication
Latest Publications
- 16 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Remaining Useful Life Prediction of Bearings Based on Graph Isomorphism Network With Graph-in-Graph Framework
The graph neural networks (GNNs) have drawn much attention for predicting the remaining useful life (RUL) due to their excellent performance in processing correlation relationship among data. Spatio-temporal evolution information and spatial correlation are key factors in the bearing degradation process. Multi–graph structures can comprehensively leverage the spatial correlation and temporal evolution characteristics inherent in different graph topologies to extract multi–scale spatio–temporal information. In this paper, a new graph isomorphism network (GIN-GIG) based on graph framework in graph is proposed to predict bearing RUL. Firstly, the feature spatial graph is constructed according to the correlation coefficients between the optimal features. Its output is used as the node feature of the new temporal path graph. The graph-in-graph (GIG) framework is constructed by embedding and fusing the feature spatial graphs and the temporal path graphs. Then, the graph isomorphism network (GIN) is established to capture the spatial information in the first-hierarchy spatial graph and the local temporal information in the second-hierarchy temporal path graph. Meanwhile, the self-attention mechanism is introduced to achieve adaptive hierarchical fusion of GIN output, so as to enrich the feature information. Finally, the time convolution network (TCN) is established to further extract the global temporal information for performing the RUL prediction. The effectiveness and superiority of the GIN-GIG method is validated using the PHM2012 and IMS bearing datasets, and some comparative experiments have been performed to show its advantage for the RUL prediction.
- 16 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Remaining Useful Life Prediction of Bearings Based on Graph Isomorphism Network With Graph-in-Graph Framework
The graph neural networks (GNNs) have drawn much attention for predicting the remaining useful life (RUL) due to their excellent performance in processing correlation relationship among data. Spatio-temporal evolution information and spatial correlation are key factors in the bearing degradation process. Multi–graph structures can comprehensively leverage the spatial correlation and temporal evolution characteristics inherent in different graph topologies to extract multi–scale spatio–temporal information. In this paper, a new graph isomorphism network (GIN-GIG) based on graph framework in graph is proposed to predict bearing RUL. Firstly, the feature spatial graph is constructed according to the correlation coefficients between the optimal features. Its output is used as the node feature of the new temporal path graph. The graph-in-graph (GIG) framework is constructed by embedding and fusing the feature spatial graphs and the temporal path graphs. Then, the graph isomorphism network (GIN) is established to capture the spatial information in the first-hierarchy spatial graph and the local temporal information in the second-hierarchy temporal path graph. Meanwhile, the self-attention mechanism is introduced to achieve adaptive hierarchical fusion of GIN output, so as to enrich the feature information. Finally, the time convolution network (TCN) is established to further extract the global temporal information for performing the RUL prediction. The effectiveness and superiority of the GIN-GIG method is validated using the PHM2012 and IMS bearing datasets, and some comparative experiments have been performed to show its advantage for the RUL prediction.
- Open Access
Plant Diversity Research in Shangqiu Yellow River Ancient Course National Forest Park, China
The Shangqiu Yellow River Ancient Course National Forest Park, the only national forest park in China created entirely from man-made forests, plays a critical role in ecological conservation. Our research employed plot surveys and quantitative ecological methods, including a diversity index analysis and importance value analysis, to investigate the diversity of arboreal, shrub, and herbaceous plants. This study revealed the composition and distribution of plant communities and analyzed invasive species. It identified dominant plant families, genera, and species and evaluated the types, distribution, and characteristics of invasive plants. We documented 70 families, 177 genera, and 254 species, highlighting that local environmental factors and human activities significantly affect the composition and distribution of plant communities. The presence of 29 invasive plant species poses a risk to the ecosystem. We constructed a phylogenetic tree of the plant community based on rbcL (ribulose-1,5-bisphosphate carboxylase/oxygenase large subunit) gene sequences, revealing the evolutionary relationships among species, and evaluated the community’s stability using the NTI (nearest taxon index) and NRI (net relatedness index). This research aims to provide a scientific foundation for conserving plant diversity and promoting sustainable development, and it can inform ecological protection and biodiversity studies in similar regions.
Open AccessPlant Diversity Research in Shangqiu Yellow River Ancient Course National Forest Park, China
The Shangqiu Yellow River Ancient Course National Forest Park, the only national forest park in China created entirely from man-made forests, plays a critical role in ecological conservation. Our research employed plot surveys and quantitative ecological methods, including a diversity index analysis and importance value analysis, to investigate the diversity of arboreal, shrub, and herbaceous plants. This study revealed the composition and distribution of plant communities and analyzed invasive species. It identified dominant plant families, genera, and species and evaluated the types, distribution, and characteristics of invasive plants. We documented 70 families, 177 genera, and 254 species, highlighting that local environmental factors and human activities significantly affect the composition and distribution of plant communities. The presence of 29 invasive plant species poses a risk to the ecosystem. We constructed a phylogenetic tree of the plant community based on rbcL (ribulose-1,5-bisphosphate carboxylase/oxygenase large subunit) gene sequences, revealing the evolutionary relationships among species, and evaluated the community’s stability using the NTI (nearest taxon index) and NRI (net relatedness index). This research aims to provide a scientific foundation for conserving plant diversity and promoting sustainable development, and it can inform ecological protection and biodiversity studies in similar regions.