Article
Engineering, Electrical & Electronic
Fei Zhou, Lei Zhang, Wei Wei
Summary: Learning to generate a task-aware base learner is a promising direction for tackling the few-shot learning problem. Existing methods that use a fixed metric or classifier often fail to generalize to challenging cases due to their limited discriminative capacity. To address this, we propose a novel deep metric meta-generation method that learns to adaptively generate a specific metric for a new few-shot learning task. By utilizing a three-layer deep attentive network, our method is able to generate a discriminative metric for each task. Additionally, we introduce a tailored variational autoencoder that establishes a multi-modal weight distribution conditioned on cross-class sample pairs, allowing us to better adapt to new few-shot learning tasks with satisfactory generalization performance.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Automation & Control Systems
Sichao Fu, Qiong Cao, Yunwen Lei, Yujie Zhong, Yibing Zhan, Xinge You
Summary: In this article, a novel dynamic graph structure preserving (DGSP) model is proposed for few-shot learning. The model updates the graph structure by considering the data correlations from both the feature space and the label space, effectively correcting the local geometry relationships. Extensive experiments demonstrate that the proposed method outperforms existing methods in various benchmarks, backbones, and task settings, achieving state-of-the-art performance.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Yidan Hu, Ruonan Liu, Xianling Li, Dongyue Chen, Qinghua Hu
Summary: A task-sequencing meta-learning method is proposed in this article to address the few-shot fault diagnosis problem. By training a meta-learning model over a series of learning tasks, the method is able to adapt and generalize knowledge with only a few examples. The effectiveness of the method is validated through experiments.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Geochemistry & Geophysics
Chunyan Yu, Baoyu Gong, Meiping Song, Enyu Zhao, Chein- Chang
Summary: This article proposes a multiview calibrated prototype-learning framework for few-shot hyperspectral image classification, which improves the robustness and performance of prototypes through calibrated aggregation, calibrated metric learning, and feature distribution calibration.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Chuanjiang Li, Shaobo Li, Ansi Zhang, Qiang He, Zihao Liao, Jianjun Hu
Summary: This study introduces a novel fault diagnosis method based on model-agnostic meta-learning, which acquires prior knowledge through optimizing initialization parameters and achieves fast and accurate bearing fault diagnosis under unknown working conditions.
Article
Engineering, Electrical & Electronic
Wen Jiang, Kai Huang, Jie Geng, Xinyang Deng
Summary: This paper proposes a novel few-shot learning method called multi-scale metric learning (MSML) to tackle the classification problem in few-shot learning by extracting multi-scale features and learning multi-scale relationships. The method introduces a feature pyramid structure and a multi-scale relation generation network, and optimizes the deep network with the intra-class and inter-class relation loss, achieving superior performance in experimental results on mini ImageNet and tiered ImageNet.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Weihua Li, Jingke He, Huibin Lin, Ruyi Huang, Guolin He, Zhuyun Chen
Summary: A novel light gradient boosting machine-based multiscale weighted ensemble model (MWE-LightGBM) is proposed for effective few-shot fault diagnosis without requiring cross-domain data. The model utilizes multiscale sliding windows for subsampling target samples and employs multiple LightGBM classifiers as an ensemble to reduce diagnostic error and improve generalization ability. Experimental results show that the suggested approach outperforms other comparison methods in few-shot scenarios even without source domain assistance.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Mechanical
Zihao Lei, Ping Zhang, Yuejian Chen, Ke Feng, Guangrui Wen, Zheng Liu, Ruqiang Yan, Xuefeng Chen, Chunsheng Yang
Summary: In recent years, intelligent fault diagnosis based on deep learning has made significant progress in feature representation. However, the lack of high-quality data, especially under severe fault states, and variable operating conditions have limited its industrial application. To address this issue, a novel prior knowledge-embedded meta-transfer learning (PKEMTL) method is proposed for few-shot fault diagnosis. The method focuses on improving adaptability in few-shot fault diagnosis under variable operating conditions by employing a metric-based meta-learning framework and embedding prior knowledge. Experimental results on two case studies demonstrate the effectiveness and superiority of the proposed method.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Jingsong Xie, Jie Liu, Tianqi Ding, Tiantian Wang, Tianjian Yu
Summary: This article proposes a few-shot intelligent diagnosis model based on multiscale feature fusion and self-attention metric learning for bearing fault classification. Experimental results show that the proposed model can accurately classify bearing faults with few-shot cases and has advantages over traditional models.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Meng Cheng, Hanli Wang, Yu Long
Summary: This paper introduces a new model for incremental few-shot object detection, which utilizes meta-learning to overcome the problem of catastrophic forgetting and adapt the model to unseen knowledge. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods in both base classes and all classes detection, while achieving the best performance in detecting novel-class objects.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Jiao Chen, Jianhua Tang, Weihua Li
Summary: This paper addresses the bottleneck of the scarcity of fault samples in large-scale mechanical fault diagnosis methods in the industrial Internet of Things (IIoT). To overcome this limitation, a novel approach based on federated learning is proposed, which allows clients to learn from indirect datasets owned by other collaborators while training a global meta-learner to directly solve the few-shot problem. The framework is enhanced with an easy-to-implement technique and its convergence is analyzed theoretically. Experimental results demonstrate that the proposed approach achieves faster convergence and higher accuracy compared to existing methods.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Xiaoyan Wang, Hongmei Wang, Daming Zhou
Summary: Research on few-shot learning aims to learn new concepts from a small number of labeled samples. A novel feature transformation network (FTN) is proposed for few-shot image classification, which introduces attention-based affinity matrix to enhance sample representation focusing on target attributes.
Article
Computer Science, Artificial Intelligence
Farong Gao, Lijie Cai, Zhangyi Yang, Shiji Song, Cheng Wu
Summary: The study introduces a multi-distance metric network (MDM-Net) for few-shot classification, mapping samples into different feature spaces. The method maximizes inter-class distance and incorporates a task-adaptive margin to adjust distances between sample pairs. Experimental results show that this approach achieves competitive results when tested on miniImageNet and FC100 benchmarks.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Automation & Control Systems
Liang Chang, Yan-Hui Lin
Summary: This article proposes a meta-learning method with adaptive learning rates (MLALR) for few-shot fault diagnosis. MLALR learns from auxiliary tasks to find initialization parameters that can adapt to a few data. The proposed adaptive learning rates tackle the common problems of few-shot learning, and the improved loss functions promote model generalization and training stability. The effectiveness of MLALR is validated using two bearing datasets, with higher accuracies and stabilities compared to baseline and state-of-the-art methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Engineering, Electrical & Electronic
Changchang Che, Huawei Wang, Minglan Xiong, Xiaomei Ni
Summary: This paper proposes an ensemble meta-learning (EML) model for few-shot fault diagnosis of rolling bearing. By transforming the high-dimensional vibration signal into grayscale images and utilizing the episodic training framework and ensemble learning framework, accurate diagnostic results for rolling bearing faults are achieved.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Chemistry, Multidisciplinary
Jun Yang, Jianfang Jing, Wenlu Li, Yongfa Zhu
Summary: This work successfully constructed an electron donor-acceptor (D-A) interface with high charge separation for boosting photocatalytic H-2 evolution. The TPPS/PDI with D-A interface showed significantly improved H-2 evolution rate, stronger internal electric field, and longer excited state lifetime compared to pure TPPS and PDI. This study provides new ideas for designing materials with D-A interface to achieve high photocatalytic activity.
Article
Computer Science, Information Systems
Hanqi DAI, Weining LU, Xianglong LI, Jun YANG, Deshan MENG, Yanze LIU, Bin LIANG
Summary: This research focuses on cooperative planning in multi-agent system gaming, proposing a novel architecture that combines a graph neural network with a task-oriented knowledge fusion sampling method. The two main contributions of this paper are the use of GraphSAGE for feasible and dynamic adjacent information fusion in cooperative planning, and the introduction of a task-oriented sampling method for effective and stable training in the model. Experimental results demonstrate the good performance of the proposed method.
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
(2022)
Article
Engineering, Aerospace
Shu Leng, Xianglong Li, Meng Yu, Jun Yang, Bin Liang
Summary: This paper introduces an online trajectory planning strategy for de-spinning a residual space object under a dual-arm space robotic set-up, which achieves nearly 30 percent performance improvement compared to state-of-the-art methods. The proposed method is flexible and effective in improving performance.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Industrial
Siyue Zhang, Zhenghan Zhou, Rui Luo, Runze Zhao, Yiyong Xiao, Yuchun Xu
Summary: This study focuses on reducing CO2 emissions in logistics systems through optimization planning. By utilizing a mixed-integer linear programming model and a dynamic programming algorithm, the proposed solution optimizes the scheduling of logistics operations considering factors such as time windows, traffic conditions, and energy consumption functions.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Environmental Sciences
Gaochao Zhang, Guowei Wu, Jun Yang
Summary: Short-term exposure to nature has positive effects on psychological functioning and could be used as a public health intervention. This study used experiments in immersive virtual environments to verify the benefits of short-term nature exposure on stress reduction and cognitive performance improvements, and explored the underlying mechanisms.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2023)
Article
Chemistry, Analytical
Youxi Hu, Chao Liu, Ming Zhang, Yu Jia, Yuchun Xu
Summary: Remanufacturing extends the life cycle and increases the residual value of end-of-life products. Disassembly is crucial in retrieving valuable components from these products, and disassembly lines are introduced to improve efficiency. However, existing research on disassembly line balancing problem (DLBP) focuses on straight lines and single-objective optimization methods, lacking representation of the actual disassembly environment. This paper introduces a stochastic parallel complete DLBP and proposes a simulated annealing-based hyper-heuristic algorithm (HH) for multi-objective optimization, demonstrating its feasibility and superiority through computational experiments.
Article
Thermodynamics
Shu Zeng, Zhenguo Yan, Jun Yang
Summary: This research measured the thermal conductivity of three types of sands with different properties and compared and evaluated eight thermal conductivity models. An improved model was proposed based on the analysis of existing models' deficiencies and the microscopic mechanism of soil. The improved model accurately predicted the thermal conductivity of different types of soils and provided more scientific explanations for the limiting cases of porosity and saturation. It also revealed linear relationships between soil thermal conductivity and solid particles and significant nonlinear relationships between thermal conductivity and porosity or saturation.
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER
(2023)
Article
Chemistry, Analytical
Chunpu Lv, Jingwei Huang, Ming Zhang, Huangang Wang, Tao Zhang
Summary: In this paper, the semi-supervised deep kernel active learning (SSDKAL) model is proposed to address the difficulty of measuring the material removal rate (MRR) in the chemical-mechanical planarization (CMP) process. The model utilizes clustering-based phase partition and phase-matching algorithms for feature extraction and a deep network for extracting hidden deep features. Semi-supervised regression and active learning sample selection strategies are applied to make full use of information on the unlabeled samples. Experimental results validate the effectiveness of the proposed method.
Article
Geography, Physical
Zeming Feng, Yuqing Liu, Yan Shi, Jun Yang
Summary: The study tested the feasibility of migrating training samples collected from Landsat MSS data across time and space to reveal historical urban development. Results showed comparable accuracies between migrated and original samples, demonstrating the feasibility of migration in the same urban ecoregion. The findings contribute to using Landsat MSS data for understanding global historical urbanization patterns.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Biology
Siran Lu, Xiangyu Luo, Hongfang Wang, Rodolfo Gentili, Sandra Citterio, Jingyi Yang, Jing Jin, Jianguang Li, Jun Yang
Summary: Common ragweed, an invasive alien species, causes severe allergies in urban residents. This study examines the urban invasion pathways of common ragweed in East China cities using population genetics and occurrence records. The findings suggest that multiple introductions have influenced the spatial genetic patterns of common ragweed. The modern grain trade between the United States and China is identified as the primary invasion pathway. The study highlights the importance of considering cities as potential hubs for the landing and spread of common ragweed.
COMMUNICATIONS BIOLOGY
(2023)
Article
Multidisciplinary Sciences
Yixiong Xiao, Jingbo Zhou, Qu Cheng, Jun Yang, Bin Chen, Tao Zhang, Lei Xu, Bo Xu, Zhehao Ren, Zhaoyang Liu, Chong Shen, Che Wang, Han Liu, Xiaoting Li, Ruiyun Li, Le Yu, Dabo Guan, Wusheng Zhang, Jie Wang, Lin Hou, Ke Deng, Yuqi Bai, Bing Xu, Dejing Dou, Peng Gong
Summary: This study develops a global pandemic simulator to investigate the global dynamics of emerging infectious diseases and explore its application under different scenarios. The findings indicate that without mitigation efforts, diseases like COVID-19 are highly likely to have profound global impacts. The study highlights the urgent need to strengthen global disease monitoring capacity for early outbreak warnings and emphasizes the importance of collective efforts across countries for successful pandemic mitigation.
Review
Green & Sustainable Science & Technology
Xiaoxia Liang, Ming Zhang, Guojin Feng, Duo Wang, Yuchun Xu, Fengshou Gu
Summary: Fault detection and diagnosis are crucial for ensuring the reliability and safety of modern industrial systems. Few-shot learning has emerged as a solution to tackle the limited labeled data problem in fault diagnosis, but its application in the field of mechanical fault diagnosis has been limited.
Proceedings Paper
Engineering, Manufacturing
Ming Zhang, Duo Wang, Yuchun Xu
Summary: The article introduces the application of intelligent fault diagnosis technology based on deep learning in large industrial equipment systems. However, the performance of deep models significantly decreases when the data for each fault category is limited. To address this problem, a few-shot fault diagnosis method is proposed.
PROCEEDINGS OF INCOME-VI AND TEPEN 2021: PERFORMANCE ENGINEERING AND MAINTENANCE ENGINEERING
(2023)
Article
Engineering, Mechanical
Xuanen Kan, Yanjun Lu, Fan Zhang, Weipeng Hu
Summary: A blade disk system is crucial for the energy conversion efficiency of turbomachinery, but differences between blades can result in localized vibration. This study develops an approximate symplectic method to simulate vibration localization in a mistuned bladed disk system and reveals the influences of initial positive pressure, contact angle, and surface roughness on the strength of vibration localization.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Zimeng Liu, Cheng Chang, Haodong Hu, Hui Ma, Kaigang Yuan, Xin Li, Xiaojian Zhao, Zhike Peng
Summary: Considering the calculation efficiency and accuracy of meshing characteristics of gear pair with tooth root crack fault, a parametric model of cracked spur gear is established by simplifying the crack propagation path. The LTCA method is used to calculate the time-varying meshing stiffness and transmission error, and the results are verified by finite element method. The study also proposes a crack area share index to measure the degree of crack fault and determines the application range of simplified crack propagation path.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Rongjian Sun, Conggan Ma, Nic Zhang, Chuyo Kaku, Yu Zhang, Qirui Hou
Summary: This paper proposes a novel forward calculation method (FCM) for calculating anisotropic material parameters (AMPs) of the motor stator assembly, considering structural discontinuities and composite material properties. The method is based on multi-scale theory and decouples the multi-scale equations to describe the equivalence and equivalence preconditions of AMPs of two scale models. The effectiveness of this method is verified by modal experiments.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Hao Zhang, Jiangcen Ke
Summary: This research introduces an intelligent scheduling system framework to optimize the ship lock schedule of the Three Gorges Hub. By analyzing navigational rules, operational characteristics, and existing problems, a mixed-integer nonlinear programming model is formulated with multiple objectives and constraints, and a hybrid intelligent algorithm is constructed for optimization.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Jingjing He, Xizhong Wu, Xuefei Guan
Summary: A sensitivity and reliability enhanced ultrasonic method has been developed in this study to monitor and predict stress loss in pre-stressed multi-layer structures. The method leverages the potential breathing effect of porous cushion materials in the structures to increase the sensitivity of the signal feature to stress loss. Experimental investigations show that the proposed method offers improved accuracy, reliability, and sensitivity to stress change.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Benyamin Hosseiny, Jalal Amini, Hossein Aghababaei
Summary: This paper presents a method for monitoring sub-second or sub-minute displacements using GBSAR signals, which employs spectral estimation to achieve multi-dimensional target detection. It improves the processing of MIMO radar data and enables high-resolution fast displacement monitoring from GBSAR signals.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Xianze Li, Hao Su, Ling Xiang, Qingtao Yao, Aijun Hu
Summary: This paper proposes a novel method for bearing fault identification, which can accurately identify faults with few samples under complex working conditions. The method is based on a Transformer meta-learning model, and the final result is determined by the weighted voting of multiple models.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Xiaomeng Li, Yi Wang, Guangyao Zhang, Baoping Tang, Yi Qin
Summary: Inspired by chaos fractal theory and slowly varying damage dynamics theory, this paper proposes a new health monitoring indicator for vibration signals of rotating machinery, which can effectively monitor the mechanical condition under both cyclo-stationary and variable operating conditions.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Hao Wang, Songye Zhu
Summary: This paper extends the latching mechanism to vibration control to improve energy dissipation efficiency. An innovative semi-active latched mass damper (LMD) is proposed, and different latching control strategies are tested and evaluated. The latching control can optimize the phase lag between control force and structural response, and provide an innovative solution to improve damper effectiveness and develop adaptive semi-active dampers.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Menghao Ping, Xinyu Jia, Costas Papadimitriou, Xu Han, Chao Jiang, Wang-Ji Yan
Summary: Identification of non-Gaussian processes is a challenging task in engineering problems. This article presents an improved orthogonal series expansion method to convert the identification of non-Gaussian processes into a finite number of non-Gaussian coefficients. The uncertainty of these coefficients is quantified using polynomial chaos expansion. The proposed method is applicable to both stationary and nonstationary non-Gaussian processes and has been validated through simulated data and real-world applications.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Lei Li, Wei Yang, Dongfa Li, Jianxin Han, Wenming Zhang
Summary: The frequency locking phenomenon induced by modal coupling can effectively overcome the dependence of peak frequency on driving strength in nonlinear resonant systems and improve the stability of peak frequency. This study proposes the double frequencies locking phenomenon in a three degrees of freedom (3-DOF) magnetic coupled resonant system driven by piezoelectricity. Experimental and theoretical investigations confirm the occurrence of first frequency locking and the subsequent switching to second frequency locking with the increase of driving force. Furthermore, a mass sensing scheme for double analytes is proposed based on the double frequencies locking phenomenon.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Kai Ma, Jingtao Du, Yang Liu, Ximing Chen
Summary: This study explores the feasibility of using nonlinear energy sinks (NES) as replacements for traditional linear tuned mass dampers (TMD) in practical engineering applications, specifically in diesel engine crankshafts. The results show that NES provides better vibration attenuation for the crankshaft compared to TMD under different operating conditions.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Wentao Xu, Li Cheng, Shuaihao Lei, Lei Yu, Weixuan Jiao
Summary: In this study, a high-precision hydraulic mechanical stand and a vertical mixed-flow pumping station device were used to conduct research on cavitation signals of mixed-flow pumps. By analyzing the water pressure pulsation signal, it was found that the power spectrum density method is more sensitive and capable of extracting characteristics compared to traditional time-frequency domain analysis. This has significant implications for the identification and prevention of cavitation in mixed-flow pump machinery.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Xiaodong Chen, Kang Tai, Huifeng Tan, Zhimin Xie
Summary: This paper addresses the issue of parasitic motion in microgripper jaws and its impact on clamping accuracy, and proposes a symmetrically stressed parallelogram mechanism as a solution. Through mechanical modeling and experimental validation, the effectiveness of this method is demonstrated.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)
Article
Engineering, Mechanical
Zhifeng Shi, Gang Zhang, Jing Liu, Xinbin Li, Yajun Xu, Changfeng Yan
Summary: This study provides useful guidance for early bearing fault detection and diagnosis by investigating the effects of crack inclination and propagation direction on the vibration characteristics of bearings.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2024)