相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Automation & Control Systems
Yudong Cao et al.
Summary: Deep neural networks have been effective in fault classification and remaining useful life (RUL) prediction for mechanical equipment. However, traditional deep learning models are limited by network depth and require retraining for updating parameters. To address these issues, an incremental learning method based on temporal cascade broad learning system (TCBLS) is proposed. This method achieves high prediction accuracy, saves training time consumption, and handles newly acquired data without retraining.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Industrial
Yifei Ding et al.
Summary: The success of deep learning and transfer learning has expanded the scope of fault diagnosis, especially in improving diagnosis accuracy under multiple working conditions. However, most existing approaches do not account for the diversity of fault mode distributions and weaken the generalization to imbalanced domain adaptation scenarios. This work proposes a novel deep imbalanced domain adaptation framework for fault diagnosis, which overcomes class-imbalanced label shift and improves cross-domain generalization for IDA tasks.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Zuanyu Zhu et al.
Summary: Tensor learning fully leverages rich information in tensor features and has been applied to intelligent fault diagnosis. However, previous tensor learning-based frameworks have limitations in feature extraction and classification. In this study, a new framework is proposed with hierarchical multiscale symbolic diversity entropy and robust twin hyperdisk-based tensor machine, which shows excellent performance in feature extraction and fault recognition compared to state-of-the-art frameworks.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Ke Zhao et al.
Summary: In this paper, a federated multi-source domain adaptation method is proposed for machinery fault diagnosis with data privacy, which comprehensively utilizes user data to achieve accurate identification of target data under the premise of data privacy protection.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Automation & Control Systems
Hao Chen et al.
Summary: This paper proposes a novel fault diagnosis method named deep balanced cascade forest to address the problem of data imbalance in rotating machinery fault diagnosis. By improving resampling techniques and algorithm design, deep balanced cascade forest achieves a fusion of data-level methods and algorithm-level methods, enhancing the performance of imbalance classification. Experimental results demonstrate that deep balanced cascade forest is more stable and effective in handling imbalance fault diagnosis problem compared to popular deep learning methods.
Article
Automation & Control Systems
Saite Fan et al.
Summary: This article proposes a novel general imbalanced sample selection strategy (DiagSelect) based on deep reinforcement learning to solve the problem of data imbalance in fault diagnosis. DiagSelect intelligently selects imbalanced samples to improve diagnosis performance and can be easily used in conjunction with conventional diagnosis models.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Yang Fu et al.
Summary: This paper proposes a task-incremental broad learning system (TiBLS) for multi-component intelligent fault diagnosis (IFD). TiBLS employs a multi-head configuration to sequentially learn different diagnosis tasks, and prevents catastrophic forgetting through parameter isolation. It also incorporates structure-incremental learning ability to enhance the diagnosis performance of each task without retraining.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Mechanical
Xiaoli Zhao et al.
Summary: This paper proposes a class imbalanced fault diagnosis framework based on Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss (NCVAE-AFL), which enhances the feature learning ability of data and balances the diagnosis difficulty for mechanical systems with class imbalanced fault data.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Yuanhong Liu et al.
Summary: Locally linear embedding (LLE) is an effective tool for feature extraction from datasets. However, most existing algorithms assume that the dataset is in a Euclidean space, which is not the case for most of the original data space. This study addresses the issues in conventional LLE by constructing a symmetric positive definite manifold and estimating its tangent space, integrating local and global discriminant information into LLE, and performing feature extraction in the tangent space.
Article
Automation & Control Systems
Mengqi Miao et al.
Summary: This article proposes a new deep neural network, sparse representation convolutional autoencoder (SRCAE), for unsupervised extraction of impulsive components from vibration signals for machinery fault diagnosis. The SRCAE utilizes a sparse representation (SR) block to extract impulsive components and transform the time-domain signal to a sparse domain. It also introduces an unsupervised selective feature transmission mechanism to improve training efficiency and feature filtering. Experimental results demonstrate the effectiveness of SRCAE in rotary machine fault diagnosis, achieving a recognition accuracy of 97.16% based on fivefold cross validation and outperforming state-of-the-art DNNs.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Automation & Control Systems
Nan Wang et al.
Summary: This article proposes a fault diagnosis method using deep learning multimodel fusion. By extracting features separately using LSTM and CNN, and then fusing them, the diagnostic performance of the network is improved.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Wei Fan et al.
Summary: This paper discusses the importance of accurate classification of heartbeats for the treatment of cardiac arrhythmia and proposes a novel class-specific weighted broad learning system to address the class imbalance problem. By using weights to adjust the contribution of each class to the model and assigning higher weights to minority classes, the proposed system improves the accuracy and generalization performance of the model.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Wuxing Chen et al.
Summary: This paper proposes a double kernel-based class-specific broad learning system for addressing multi-class imbalance learning problems. By incorporating class-specific penalty coefficients and a double kernel mapping mechanism, the proposed approach effectively improves the classification performance of multi-class imbalanced data.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Junwei Jin et al.
Summary: In this paper, three discriminative BLS-based models are proposed to address the limitations of the Broad Learning System's learning ability. The models integrate different techniques, such as s-dragging and L2,1 regularization, to improve flexibility, feature selection, and recognition accuracy. Efficient iterative methods are derived to optimize the proposed models. Experimental results demonstrate the outstanding recognition capability of the proposed models compared to other state-of-the-art classifiers.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Industrial
Lin Zuo et al.
Summary: This article presents a probabilistic spiking response model (PSRM) to enhance the performance of spiking neural networks (SNNs) in bearing fault diagnosis. By converting the extracted features from the local mean decomposition (LMD) method into probability pulse sequences and using a multi-layer learning algorithm for training, the proposed PSRM outperforms most state-of-the-art machine learning methods in fault diagnosis.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Computer Science, Artificial Intelligence
Haidong Shao et al.
Summary: Collaborative fault diagnosis can benefit from multisensory fusion technologies, which offer more reliable results with a comprehensive data set. By utilizing a stacked wavelet auto-encoder structure and flexible weighted fusion strategies, the proposed approach overcomes obstacles in integrating multisensory data and fusion of maintenance strategies, providing more accurate fault diagnosis results.
INFORMATION FUSION
(2021)
Article
Automation & Control Systems
Jie Yang et al.
Summary: An enhanced intelligent diagnosis method, J-PDBN, is proposed based on a joint pairwise graph embedded sparse deep belief network and partial least square fine-tuning. The combination of unsupervised learning and PLS fine-tuning results in better fault classification capabilities. Experimental results validate the high accuracy and superiority of the proposed method in gearbox and bearing fault diagnosis.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Engineering, Mechanical
Xinya Wu et al.
Summary: Accurate fault diagnosis is crucial for the safe operation of rotating machinery. The proposed method, hybrid classification autoencoder, utilizes both labeled and unlabeled data for training and achieved high diagnostic accuracies in experiments with minimal labeled data. This approach shows potential for more efficient fault diagnosis in the future.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Huimin Zhao et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2020)
Article
Engineering, Mechanical
Xianzhen Xu et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Automation & Control Systems
Zhong-Xu Hu et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2020)
Article
Automation & Control Systems
Huan Wang et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Engineering, Electrical & Electronic
Andongzhe Duan et al.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2020)
Article
Computer Science, Artificial Intelligence
Chong Zhang et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Bhagat Singh Raghuwanshi et al.
Article
Computer Science, Artificial Intelligence
C. L. Philip Chen et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2018)
Article
Computer Science, Information Systems
Pei Cao et al.
Article
Computer Science, Information Systems
Junwei Jin et al.
SCIENCE CHINA-INFORMATION SCIENCES
(2018)
Article
Computer Science, Theory & Methods
Joffrey L. Leevy et al.
JOURNAL OF BIG DATA
(2018)
Article
Computer Science, Artificial Intelligence
Weiwei Zong et al.
