Review
Engineering, Mechanical
Yonghao Miao, Boyao Zhang, Jing Lin, Ming Zhao, Hanyang Liu, Zongyang Liu, Hao Li
Summary: Fault diagnosis is crucial for the safe operation of machinery equipment. Signal processing techniques, especially blind deconvolution methods, play a significant role in feature extraction, signal denoising, and fault identification. The use of blind deconvolution methods in machinery fault diagnosis has been extensively studied and applied, with a focus on historical background, principles, merits, limitations, performance analysis, research, and applications.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Multidisciplinary
Zhaolun Li, Yong Lv, Rui Yuan, Qixiang Zhang
Summary: This research proposes a novel method called Multivariate Variational Mode Decomposition (MVMD) for processing multi-channel data sets and mechanical failure signals. By introducing a weighted combined fault index and an iterative decomposition algorithm, this method addresses the challenges of MVMD in multi-fault signal processing and achieves adaptive parameter selection.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Changyuan Yang, Sai Ma, Qinkai Han
Summary: Fault diagnosis is an important technology in intelligent manufacturing to maintain high quality and low failure rate. This research proposes a novel feature selection method named unified discriminant manifold learning (UDML) for accurately diagnosing faults in rotating machinery. UDML unifies local linear relationship, distance between adjacent points, and intra-class and inter-class variance, effectively preserving the local structure, global information, and label information of high-dimensional features. Through experimental verifications and comparisons with classical feature selection algorithms, the proposed method achieves more accurate fault diagnosis in rotating machinery.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Automation & Control Systems
Changyuan Yang, Sai Ma, Qinkai Han
Summary: This paper proposes a robust discriminant latent variable manifold learning (RDLVML) algorithm for fault diagnosis of rotating machinery. By selecting features of high-dimensional fault data and extracting low-dimensional fault features with better discrimination, the accuracy of fault diagnosis is improved. A novel weighted neighborhood graph is proposed by constructing the q-Rényi and Prime kernel function to suppress the interference of outliers and noise, making the RDLVML algorithm more robust. Furthermore, a fault diagnosis method for rotating machinery based on RDLVML is presented, which achieves more accurate results compared to classical feature selection algorithms through experimental verifications.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Elizabeth Hofer, Martin Mohrenschildt
Summary: This paper proposes a model-free approach to transform raw sensor data into statistically meaningful feature vectors, and applies it to cluster analysis of vibrating screen data to identify common properties and differences of machines.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Mechanical
Shun Wang, Yongbo Li, Khandaker Noman, Dong Wang, Ke Feng, Zheng Liu, Zichen Deng
Summary: The paper proposes a new entropy measure called cumulate spectrum distribution entropy (CSDEn), which can capture frequency-domain information of fault features. The method is evaluated using synthetic signals and experimental data, showing superior performance in detecting dynamic changes and measuring signal complexity compared to other methods.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Automation & Control Systems
Jingfei Zhang, Qinghua Zhang, Xiao He, Guoxi Sun, Donghua Zhou
Summary: A fused imbalance learning method is proposed in this paper for accurate diagnosis of compound faults in industrial equipment, utilizing the non-linear mapping ability of neural networks, dimensionless parameterization, and time-frequency transformation method for data feature extraction.
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2021)
Article
Automation & Control Systems
Xianzhi Wang, Shubin Si, Yongbo Li
Summary: A fault diagnosis scheme based on multiscale diversity entropy (MDE) and extreme learning machine (ELM) is proposed in this article, which quantifies dynamical complexity and provides a comprehensive feature description for pattern identification of rotating machinery. The effectiveness of the proposed MDE method is verified through simulated signals and experimental signals from bearing test and dual-rotator of aeroengine test, showing superior classification accuracy compared with existing approaches.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Automation & Control Systems
Francesco Ferracuti, Alessandro Freddi, Andrea Monteriu, Luca Romeo
Summary: This article introduces a fault diagnosis algorithm for rotating machinery based on the Wasserstein distance, which is used to distinguish different machine operating conditions by extracting features from vibration signals. A distance weighting stage based on neighborhood component features selection (NCFS) is utilized to achieve robust fault diagnosis under low signal-to-noise ratio conditions and with high-dimensional features.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Industrial
Chenyang Ma, Yongbo Li, Xianzhi Wang, Zhiqiang Cai
Summary: This paper proposes an effective feature extraction method called composite zoom permutation entropy for fault diagnosis of rotating machinery. By employing multiple wavelets to capture complete fault features over the full frequency band and performing composite analysis to improve feature separability, the method can identify different early faults. Experimental results show that the proposed method outperforms existing methods in early fault identification of rotating machinery.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Mechanical
Yongbo Li, Shun Wang, Yang Yang, Zichen Deng
Summary: The paper introduces a method called Symbolic Fuzzy Entropy (SFE) based on symbolic dynamic filtering and fuzzy entropy to extract fault features and eliminate noise, effectively improving calculation efficiency. By extending SFE to multiscale analysis to form MSFE, experimental results demonstrate that MSFE outperforms three other methods in extracting weak fault characteristics.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Automation & Control Systems
Chaoying Yang, Kaibo Zhou, Jie Liu
Summary: This article proposes a graph-based feature extraction method for rotating machinery fault diagnosis. By converting raw data into graphs, hidden structural and topological information can be obtained. Experimental results verify the effectiveness of this method in fault diagnosis.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Automation & Control Systems
Bo Peng, Shuting Wan, Ying Bi, Bing Xue, Mengjie Zhang
Summary: The article introduces a novel diagnosis approach, AFECGP, based on evolutionary learning for identifying different fault types in rotating machinery. By automatically generating informative features and combining them with k-Nearest Neighbors for fault diagnosis, the proposed approach outperforms competitive methods in accuracy.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Engineering, Electrical & Electronic
Zhenling Mo, Zijun Zhang, Kwok-Leung Tsui
Summary: This article proposes a method that integrates learnable variational kernels into a 1-D CNN to better extract important fault-related data features and provide decent performance in machinery fault diagnoses with limited data. Experimental results show that this method performs better in identifying important fault features and conducting machinery fault diagnoses with limited training data.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Automation & Control Systems
Yonghao Miao, Boyao Zhang, Chenhui Li, Jing Lin, Dayi Zhang
Summary: This article introduces a new feature extraction method called Feature Mode Decomposition (FMD) for machinery fault. FMD decomposes different fault modes using adaptive FIR filters and takes into account the impulsiveness and periodicity of fault signals with the help of correlated Kurtosis. The superiority of FMD is demonstrated in adaptively and accurately decomposing fault modes and being robust to interferences and noise, using simulated and experimental data from bearing faults. Furthermore, FMD has been shown to outperform the popular Variational Mode Decomposition in machinery fault feature extraction.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Materials Science, Ceramics
Debao Liu, Baolu Shi, Chenqi Wang, Zeshuai Li, Xianbo Wang, Baosheng Xu, Lijie Qu
Summary: In this study, SiC ceramic aerogels with in-situ growth of SiC nanowires were successfully synthesized using the PDCs method. The morphology, microstructure, and phase composition of the samples were investigated using various techniques. The results revealed the diameter and length of the SiC nanowires, and the formation mechanism was systematically studied. This method can also be applied to synthesize other Si-based porous ceramic aerogels with nanowires.
CERAMICS INTERNATIONAL
(2022)
Article
Acoustics
Yiwei Cheng, Ji Wang, Jun Wu, Haiping Zhu, Yuanhang Wang
Summary: This paper proposes a novel abnormal symptoms-triggered remaining useful life prediction approach for rolling element bearings, where an adaptive kernel spectral clustering model is used to detect abnormal symptoms in real time, and the occurrence time of these symptoms is used as the first prediction time for a new type of particle swarm optimization-quantile regression neural network. Experimental results show the superiority of this approach.
JOURNAL OF VIBRATION AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Zuoyi Chen, Chao Wang, Jun Wu, Chao Deng, Yuanhang Wang
Summary: A novel structural damage detection method is proposed in this paper using deep convolutional transfer learning. The method combines one-dimensional and two-dimensional deep convolutional neural networks to extract fine-grained features from raw vibration data. A novel domain adaptation technology is also developed to align the distribution of different domains and improve transfer performance.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Zhipeng Chen, Haiping Zhu, Jun Wu, Liangzhi Fan
Summary: This paper proposes an embedded LSTM-CNN autoencoder to extract trend features from vibration data, and a transfer learning algorithm is designed to enhance the noise filtering capability of the model. The extracted trend features are fused with a self-organized map to obtain the health indicator (HI), and the effectiveness of the proposed method is verified through case studies on bearing datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Automation & Control Systems
Zhen Li, Peihua Xu, Xian-Bo Wang
Summary: This paper proposes a new method for predicting the remaining useful life (RUL) of rotating machinery equipment. By introducing discrete wavelet transform (DWT) to decrease noise and using sliding average method to weaken transient excitation, the proposed method achieves better RUL prediction efficiency. Experimental results demonstrate that it outperforms existing methods in terms of efficiency and convergence.
MEASUREMENT & CONTROL
(2023)
Article
Automation & Control Systems
Zhi-Xin Yang, Chao -Shun Li, Xian-Bo Wang, Hao Chen
Summary: The tunnel fan is a critical fire-fighting equipment for tunnel traffic. This paper proposes a non-neural deep learning model called hierarchical cascade forest (HCF) to improve fault diagnosis accuracy and training efficiency. Through experiments, HCF shows increased accuracy and reduced training time compared to Deep Forest.
Article
Engineering, Multidisciplinary
Xiaoan Yan, Wangji Yan, Ka-Veng Yuen, Zhixin Yang, Xianbo Wang
Summary: This paper proposes an adaptive variational mode extraction method based on multi-domain and multi-objective optimization (AVME-MDMO) to improve bearing fault feature extraction and diagnosis. The method automatically determines key parameters using a novel multi-objective function and demonstrates superiority over existing methods in excavating fault signatures.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Computer Science, Hardware & Architecture
Zuoyi Chen, Jun Wu, Chao Deng, Xiaoqi Wang, Yuanhang Wang
Summary: This article proposes a novel zero-shot learning method called deep attention relation network (DARN) for bearing fault diagnosis. By training in a known domain, DARN can diagnose fault types from unknown but related domains without prior data input. Experimental results show that DARN outperforms existing transfer learning methods in diagnostic performance.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Article
Automation & Control Systems
Hao Chen, Xian-bo Wang, Zhi-Xin Yang
Summary: This study proposes a fast robust capsule network model augmented with a dynamic pruning technique and a mutual information loss for intelligent fault diagnosis. The model overcomes limitations in pooling layers and scale-invariant feature transformation by learning tensor representations of features. The dynamic pruning method reduces parameter scale and simplifies network topology while increasing robustness. The enhanced capsule function limits the similarity of capsules in the same layer to avoid homogeneous features. The proposed model successfully increases representation learning capacity by integrating local and global information through a multiscale mutual information loss.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Automation & Control Systems
Xiaolong Cui, Yifan Wu, Xiaoyuan Zhang, Jie Huang, Pak Kin Wong, Chaoshun Li
Summary: In this article, a new framework of fault diagnosis for the rotor with multiple bearings is proposed. By using multivariate complex variational mode decomposition (MCVMD) to decompose the complex-valued signals of multiple bearings, multiple orbit features are derived to construct fusion feature images. The deep convolutional network based on transfer learning is utilized for the fault diagnosis, and the experimental results demonstrate its superiority over existing approaches.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Automation & Control Systems
Kui Hu, Yiwei Cheng, Jun Wu, Haiping Zhu, Xinyu Shao
Summary: This article proposes a novel deep bidirectional recurrent neural networks (DBRNNs) ensemble method for the remaining useful life (RUL) prediction of aircraft engines. The method achieves high accuracy in RUL prediction by extracting hidden features from sensory data and iteratively training regression decision tree (RDT) models.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Electrical & Electronic
Yaxin Wang, Donglian Qi, Xianbo Wang, Yunfeng Yan
Summary: In smart grids, uncertain load demand and intermittent renewable energy generation have caused more frequency and voltage stability issues, putting significant pressure on turbine governor action. Load participation in primary control is one potential solution. This study investigates a general class of local load control (LLC) to provide grid frequency and voltage support while minimizing the pre-defined disutility to utilities and clients. The effectiveness and rationality of the proposed approach are verified through simulation-based comparative study and MATLAB/SIMULINK tests under various scenarios.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Engineering, Multidisciplinary
Peihua Xu, Zhaoyu Tu, Menghui Li, Jun Wang, Xian-Bo Wang
Summary: This paper proposes a bearing RUL prediction method combining relevance vector (RV) machine (RVM) and hybrid degradation model to overcome the shortcomings of existing methods such as low accuracy and reliance on expert experience for parameter estimation. The proposed method extracts bearing degradation characteristics from vibration acceleration signals, determines the bearing first predicting time using the time-varying 3σ criterion, regresses the sequence from initial failure time point to inspection time using differential kernel parameter RVM, and selects the best degradation curve based on similarity and extrapolates it to the failure threshold. Experimental results show that the proposed method has better prediction efficiency than conventional exponential models and overcomes the widespread drawbacks of monotonicity and trend bias in model-based methods.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2023)
Article
Chemistry, Analytical
Yi Chen, Yunfeng Yan, Xianbo Wang, Yi Zheng
Summary: Defect detection in power scenarios is crucial for the safety and efficiency of power systems. The existing technology needs improvement in its learning ability from large volumes of data. The integration of IoT with machine learning offers new possibilities for defect detection in power equipment.
Article
Engineering, Electrical & Electronic
Hao Chen, Xian-Bo Wang, Zhi-Xin Yang
Summary: In this study, a semi-supervised self-correcting graph neural network (SSGNN) is proposed for fault diagnosis, which effectively extracts features from vibrational signals and generates a graph-structured representation of fault knowledge. The proposed method shows higher accuracy and faster convergence speed compared to the state-of-the-art methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)