Query：
学者姓名：钟建华
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Accurate prediction of the remaining useful life (RUL) of rolling bearings in mechanical equipment is crucial for ensuring the reliable operation of equipment and implementing effective maintenance measures. It also plays a key role in safeguarding personnel and property by reducing the risk of failures. Recently, converting monitoring data into a graph structure to capture the mutual influence between samples has emerged as an innovative approach in RUL prediction. However, existing methods cannot effectively extract features from graph-structured data with varying receptive fields and establish strong dependencies between nodes. This research proposes a novel bearing RUL prediction model based on the multi-region hypergraph self-attention network (M-HGSAN) to address these challenges. Firstly, the original data is concatenated and resampled using the sliding window with width L, and the two-dimensional sample set is constructed by time domain feature and frequency domain feature, which enriches the diversity of samples. The multi-scale synchronous semi-shrink attention network (MSSSAN) is used to obtain different channel features and multi-region features from different receptive fields, which enhances the dependence between features. Secondly, a hypergraph selfattention network (HGSAN) is designed, which combines the advantages of a hypergraph neural network (HGNN) and a self-attention mechanism. Obtain the ability to learn higher-order correlation and key features between nodes. In addition, the data is fed into residual stacked gated recurrent units (RSGRU) and fully connected (FC) layers to capture the nodes' temporal sequence features and predict the bearings' RUL. Finally, model interpretability experiments are carried out with XAI technology to help us understand the influence of each feature on RUL. Experimental results demonstrate the effectiveness of the M-HGSAN model, highlighting its potential to significantly enhance predictive maintenance strategies in industrial applications, thereby improving equipment reliability and safety.
Keyword ：
Attention Attention GRU GRU Hypergraph neural network Hypergraph neural network Residual Residual RUL RUL
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Jianhua , Jiang, Haifeng , Gu, Kairong et al. Remaining useful life prediction of rolling bearing based on multi-region hypergraph self-attention network [J]. | MECHANICAL SYSTEMS AND SIGNAL PROCESSING , 2025 , 225 . |
| MLA | Zhong, Jianhua et al. "Remaining useful life prediction of rolling bearing based on multi-region hypergraph self-attention network" . | MECHANICAL SYSTEMS AND SIGNAL PROCESSING 225 (2025) . |
| APA | Zhong, Jianhua , Jiang, Haifeng , Gu, Kairong , Zhong, Shuncong . Remaining useful life prediction of rolling bearing based on multi-region hypergraph self-attention network . | MECHANICAL SYSTEMS AND SIGNAL PROCESSING , 2025 , 225 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mechanical metastructures consisting of periodic cells with adjustable output force charactersitics and ranges have received increasing attention in recent years owing to its unique capability to tune mechanical properties such as stiffness and Poisson's ratio etc. In this paper, we present the design, simulation, and experimental characterization of a mechanical metastructure that realizes customized constant force output. The metastructure consists of periodic constant force units that are formed by combining a positive and negative stiffness element. Notably, the force unit also contains a unique flexure design with solid and hollow pins to reduce the lateral stress by 50%, which allows for precise control of the output force. By using a programmable design method, the force unit forms 2D and 3D metastructures via parallel and tendem stacking. Simulations were performed to optimize the design and predict the device performance. Finally, experiments were devised and performed to verify the simulation results of the metastructures. The promising results warrant the wide application of the new mechanical metastructure as well as the programmable design method, such as low-pass mechanical filters, noise and vibration cancellation devices etc.
Keyword ：
constant force constant force mechanical metastructures mechanical metastructures programmable metastructures programmable metastructures
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Jianhua , Li, Jin , Ding, Bingxiao et al. Design and experimental verification of programmable metastructures based on constant force cells [J]. | SMART MATERIALS AND STRUCTURES , 2025 , 34 (1) . |
| MLA | Zhong, Jianhua et al. "Design and experimental verification of programmable metastructures based on constant force cells" . | SMART MATERIALS AND STRUCTURES 34 . 1 (2025) . |
| APA | Zhong, Jianhua , Li, Jin , Ding, Bingxiao , Chen, Shih-Chi . Design and experimental verification of programmable metastructures based on constant force cells . | SMART MATERIALS AND STRUCTURES , 2025 , 34 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Meta-learning has been widely applied and achieved certain results in few-shot cross-domain fault diagnosis due to its powerful generalization and robustness. However, existing meta-learning methods mainly focus on cross-domain fault diagnosis within the same machine, ignoring the fact that there are more significant domain distribution differences and sample imbalance problems between different machines, leading to poor diagnostic performance. This paper proposes a semi-supervised prototypical network with dual correction to address these issues. First, a dual-channel residual network is utilized to comprehensively extract sample features, capturing deep and shallow information. Then, correct the semi-supervised prototypical network by weighting the features and adding a shift term on support set samples and query set samples, respectively, to diminish its intra-class and extra-class bias. Meanwhile, a regularization term is introduced into the model to balance the distribution among different class prototypes, enhancing distinctiveness. Finally, few-shot cross-machine fault diagnosis experiments are conducted on three datasets to validate the method's effectiveness. Additionally, an interpretability analysis of the model is conducted using the gradient-weighted class activation mapping (Grad-CAM) technique to discern its primary regions of focus in the classification tasks.
Keyword ：
cross-domain cross-domain fault diagnosis fault diagnosis interpretability analysis interpretability analysis meta-learning meta-learning semi-supervised prototypical network semi-supervised prototypical network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Guigang , Gu, Kairong , Jiang, Haifeng et al. A semi-supervised prototypical network with dual correction for few-shot cross-machine fault diagnosis [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2025 , 36 (4) . |
| MLA | Liu, Guigang et al. "A semi-supervised prototypical network with dual correction for few-shot cross-machine fault diagnosis" . | MEASUREMENT SCIENCE AND TECHNOLOGY 36 . 4 (2025) . |
| APA | Liu, Guigang , Gu, Kairong , Jiang, Haifeng , Zhong, Jianhua , Zhong, Jianfeng . A semi-supervised prototypical network with dual correction for few-shot cross-machine fault diagnosis . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2025 , 36 (4) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the continuous development of computer technology, deep learning has been widely used in fault diagnosis and achieved remarkable results. However, in actual production, the problem of insufficient fault samples and the difference in data domains caused by different working conditions seriously limit the improvement of model diagnosis ability. In recent years, meta-learning has attracted widespread attention from scholars as one of the main methods of few-shot learning. It can quickly adapt to new tasks by training on a small number of samples. A fine-tuning prototypical network is proposed on meta-learning methods to address the challenges of fault diagnosis under few-shot and cross-domain. Firstly, the shuffle attention is used to enhance the feature extraction ability of the network and suppress irrelevant features. Then, the support set of the target domain is split into two parts: pseudo support set and pseudo query set, which are used to fine-tune the prototypical network and improve the model generalization. Finally, experiments are conducted on three rotating equipment datasets to verify the method’s effectiveness. © 2024 IOP Publishing Ltd.
Keyword ：
cross-domain cross-domain fault diagnosis fault diagnosis few-shot few-shot prototypical network prototypical network shuffle attention shuffle attention
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, J. , Gu, K. , Jiang, H. et al. A fine-tuning prototypical network for few-shot cross-domain fault diagnosis [J]. | Measurement Science and Technology , 2024 , 35 (11) . |
| MLA | Zhong, J. et al. "A fine-tuning prototypical network for few-shot cross-domain fault diagnosis" . | Measurement Science and Technology 35 . 11 (2024) . |
| APA | Zhong, J. , Gu, K. , Jiang, H. , Liang, W. , Zhong, S. . A fine-tuning prototypical network for few-shot cross-domain fault diagnosis . | Measurement Science and Technology , 2024 , 35 (11) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In response to the need for multiple complete bearing degradation datasets in traditional deep learning networks to predict the impact on individual bearings, a novel deep learning-based rolling bearing remaining life prediction method is proposed in the absence of fully degraded bearng data. This method involves processing the raw vibration data through Channel-wise Attention Encoder (CAE) from the Encoder-Channel Attention (ECA), extracting features related to mutual correlation and relevance, selecting the desired characteristics, and incorporating the selected features into the constructed Autoformer-based time prediction model to forecast the degradation trend of bearings' remaining time. The feature extraction method proposed in this approach outperforms CAE and multilayer perceptual-Attention Encoder in terms of feature extraction capabilities, resulting in reductions of 0.0059 and 0.0402 in mean square error, respectively. Additionally, the indirect prediction approach for the degradation trend of the target bearing demonstrates higher accuracy compared to Informer and Transformer models, with mean square error reductions of 0.3352 and 0.1174, respectively. This suggests that the combined deep learning model proposed in this paper for predicting rolling bearing life may be a more effective life prediction method deserving further research and application.
Keyword ：
Autoformer Autoformer deep learning deep learning rolling bearings rolling bearings
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Jianhua , Li, Huying , Chen, Yuquan et al. Remaining Useful Life Prediction of Rolling Bearings Based on ECA-CAE and Autoformer [J]. | BIOMIMETICS , 2024 , 9 (1) . |
| MLA | Zhong, Jianhua et al. "Remaining Useful Life Prediction of Rolling Bearings Based on ECA-CAE and Autoformer" . | BIOMIMETICS 9 . 1 (2024) . |
| APA | Zhong, Jianhua , Li, Huying , Chen, Yuquan , Huang, Cong , Zhong, Shuncong , Geng, Haibin et al. Remaining Useful Life Prediction of Rolling Bearings Based on ECA-CAE and Autoformer . | BIOMIMETICS , 2024 , 9 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
由于实际工况下的轴承退化数据有限，无法获得足够的退化数据来训练神经网络，在深度学习网络中很难得到好的预测结果，所以提出一种新的结合机器学习和统计数据驱动的方法。首先对原始振动信号做特征提取，通过集合经验模态分解奇异值分解(Ensemble Empirical Mode Decompositiont Singular Value Decomposition,EEMD+SVD)得到数十维特征，加上剩余寿命预测常用的诸如峭度、均值等有效特征，利用决策树筛选出15维特征；将所筛选特征进行双指数拟合并通过t分布随机近邻嵌入(t-distributed Stochastic Neighbor Embedding,t-SNE)将退化信号降维成线性趋势。线性退化趋势在预测上相比于指数趋势有更好的泛化性，同时预测准确度相比于指数模型支持向量回归(Support Vector Regression,SVR)和深度信念网络(Deep Belief Network,DBN)都有较高的提升。
Keyword ：
t-SNE t-SNE 剩余寿命预测 剩余寿命预测 双指数模型 双指数模型 特征提取 特征提取 轴承 轴承
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 钟建华 , 黄聪 , 钟舜聪 et al. 基于t-SNE降维方法的滚动轴承剩余寿命预测 [J]. | 机械强度 , 2024 , 46 (04) : 969-976 . |
| MLA | 钟建华 et al. "基于t-SNE降维方法的滚动轴承剩余寿命预测" . | 机械强度 46 . 04 (2024) : 969-976 . |
| APA | 钟建华 , 黄聪 , 钟舜聪 , 肖顺根 . 基于t-SNE降维方法的滚动轴承剩余寿命预测 . | 机械强度 , 2024 , 46 (04) , 969-976 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to the limited bearing degradation data under actual working conditions, it is impossible to obtain enough degradation data to train the neural network, it is difficult to obtain good prediction results in the deep learning network, so a new fusion method was proposed. Firstly, the features of the original vibration signal was extracted, dozens of dimensional features were obtained through the ensemble empirical mode decomposition (EEMD) and the singular value decomposition (SVD), and the effective features such as kurtosis and mean value commonly used in remaining useful life prediction were added, then the decision tree to filter out 15-dimensional features was used the data was obtained by double exponential model fitting and the degraded signal was reduced to a linear trend through t-SNE. The linear degradation trend has better generalization in prediction than the exponential trend, and the prediction accuracy is superior to support veotor regression(SVR) and deep belief network (DBN) model. © 2024 Chinese Mechanical Engineering Society. All rights reserved.
Keyword ：
Bearing Bearing Double exponential model Double exponential model Feature extraction Feature extraction Remaining useful life prediction Remaining useful life prediction t-distributed stochastic neighbor embedding t-distributed stochastic neighbor embedding
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, J. , Huang, C. , Zhong, S. et al. REMAINING USEFUL LIFE OF ROLLING BEARING BASED ON t-SNE; [基于 t-SNE 降维方法的滚动轴承剩余寿命预测] [J]. | Journal of Mechanical Strength , 2024 , 46 (4) : 969-976 . |
| MLA | Zhong, J. et al. "REMAINING USEFUL LIFE OF ROLLING BEARING BASED ON t-SNE; [基于 t-SNE 降维方法的滚动轴承剩余寿命预测]" . | Journal of Mechanical Strength 46 . 4 (2024) : 969-976 . |
| APA | Zhong, J. , Huang, C. , Zhong, S. , Xiao, S. . REMAINING USEFUL LIFE OF ROLLING BEARING BASED ON t-SNE; [基于 t-SNE 降维方法的滚动轴承剩余寿命预测] . | Journal of Mechanical Strength , 2024 , 46 (4) , 969-976 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The paper proposes an unsupervised deep convolutional dynamic joint distribution domain adaptive network model for the problem of bearing fault diagnosis under variable conditions, which involves missing labeling of target domain data and large differences in the distribution of source and target domain data. The model consists of the following steps: (1) converting the original vibration signal of the bearing into a time-frequency map representation and performing feature extraction on the labeled source domain samples and the unlabeled target domain samples by the deep convolutional feature extractor; (2) dynamically aligning the marginal distribution and conditional distribution of the two domain features by the marginal distribution adaptation module and the conditional distribution adaptation module, so that the trained network model can classify the unlabeled target domain samples accurately according to the label mapping relationship of the source domain samples; (3) validating the model on two rolling bearing datasets; (4) experiment with model interpretability in conjunction with XAI techniques to help us understand what the model actually does. The experimental results on two rolling bearing datasets show the validity of the proposed model.
Keyword ：
Deep domain adaption Deep domain adaption Fault diagnosis Fault diagnosis Rolling bearing Rolling bearing Variable conditions Variable conditions
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Jianhua , Lin, Cong , Gao, Yang et al. Fault diagnosis of rolling bearings under variable conditions based on unsupervised domain adaptation method [J]. | MECHANICAL SYSTEMS AND SIGNAL PROCESSING , 2024 , 215 . |
| MLA | Zhong, Jianhua et al. "Fault diagnosis of rolling bearings under variable conditions based on unsupervised domain adaptation method" . | MECHANICAL SYSTEMS AND SIGNAL PROCESSING 215 (2024) . |
| APA | Zhong, Jianhua , Lin, Cong , Gao, Yang , Zhong, Jianfeng , Zhong, Shuncong . Fault diagnosis of rolling bearings under variable conditions based on unsupervised domain adaptation method . | MECHANICAL SYSTEMS AND SIGNAL PROCESSING , 2024 , 215 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The outstanding performance of current machine-learning fault diagnosis methods is mainly attributed to the availability of a large amount of labeled training data. However, in practical dynamic weighing systems, the high costs and variability of operating conditions limit the availability of reliable training data, hampering engineering fault diagnoses in dynamic weighing systems. To address this issue, this study proposes a novel cross-sensor fault diagnosis method based on multi-feature fusion using a transfer component analysis (TCA)-weighted k-nearest-neighbor (WKNN) network. Using this method, time- and frequency-domain features are extracted from a laboratory-simulated set of fault data with small batches of real operational data. Source and target domain features are fused, and TCA is applied to map the source and target domain samples to a latent space using kernel functions to reduce the distribution differences among the samples. Finally, the WKNN is employed as a metric learner to enhance small-sample data matching and classification to improve diagnostic accuracy. The results show that with three samples per support set, the proposed method achieves a diagnostic accuracy of 93.33%. Compared with other approaches, the proposed method exhibits stronger generalizability for diagnostic knowledge transference from sensor to dynamic weighing failure data, effectively improving precision in on-site small-sample environments and reducing sample imbalances.
Keyword ：
cross-sensor cross-sensor dynamic weighing system dynamic weighing system fault diagnosis fault diagnosis multi-feature fusion multi-feature fusion transfer component analysis transfer component analysis weighted k-nearest neighbor algorithm weighted k-nearest neighbor algorithm
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liang, Wei , Chen, Zhixiong , Zhong, Jianhua et al. Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (1) . |
| MLA | Liang, Wei et al. "Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing" . | MEASUREMENT SCIENCE AND TECHNOLOGY 35 . 1 (2024) . |
| APA | Liang, Wei , Chen, Zhixiong , Zhong, Jianhua , Liao, Huazhong , Zhong, Shuncong . Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the continuous development of computer technology, deep learning has been widely used in fault diagnosis and achieved remarkable results. However, in actual production, the problem of insufficient fault samples and the difference in data domains caused by different working conditions seriously limit the improvement of model diagnosis ability. In recent years, meta-learning has attracted widespread attention from scholars as one of the main methods of few-shot learning. It can quickly adapt to new tasks by training on a small number of samples. A fine-tuning prototypical network is proposed on meta-learning methods to address the challenges of fault diagnosis under few-shot and cross-domain. Firstly, the shuffle attention is used to enhance the feature extraction ability of the network and suppress irrelevant features. Then, the support set of the target domain is split into two parts: pseudo support set and pseudo query set, which are used to fine-tune the prototypical network and improve the model generalization. Finally, experiments are conducted on three rotating equipment datasets to verify the method's effectiveness.
Keyword ：
cross-domain cross-domain fault diagnosis fault diagnosis few-shot few-shot prototypical network prototypical network shuffle attention shuffle attention
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Jianhua , Gu, Kairong , Jiang, Haifeng et al. A fine-tuning prototypical network for few-shot cross-domain fault diagnosis [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (11) . |
| MLA | Zhong, Jianhua et al. "A fine-tuning prototypical network for few-shot cross-domain fault diagnosis" . | MEASUREMENT SCIENCE AND TECHNOLOGY 35 . 11 (2024) . |
| APA | Zhong, Jianhua , Gu, Kairong , Jiang, Haifeng , Liang, Wei , Zhong, Shuncong . A fine-tuning prototypical network for few-shot cross-domain fault diagnosis . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (11) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
