Article
Engineering, Electrical & Electronic
Jianbo Yu, Xingkang Zhou, Liang Lu, Zhihong Zhao
Summary: This article proposes a new CNN, multiscale fusion global sparse network (MFGSNet) for feature extraction from vibration signals and gearbox fault diagnosis. It outperforms typical DNNs like ResNet and DenseNet in gearbox fault diagnosis.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Multidisciplinary
Fan Li, Liping Wang, Decheng Wang, Jun Wu, Hongjun Zhao
Summary: In this paper, an end-to-end Adaptive Multiscale Fully Convolutional Network (AMFCN) is proposed for intelligent bearing fault diagnosis in various noise environments. The AMFCN demonstrates superior performance compared to five advanced baseline models, surpassing conventional CNNs and other advanced multiscale CNNs. It enhances feature extraction ability, noise immunity, and robustness, making it an effective solution for accurate and robust fault diagnosis using CNNs in noisy environments.
Article
Engineering, Electrical & Electronic
Yuanhang Sun, Jianbo Yu
Summary: The novel adaptive weighted adjacent difference sparse representation (AINAD-SR) proposed in this article for bearing fault diagnosis enhances sparsity while reducing noise interference. By adaptively setting regularization parameters in vibration signals, this method improves feature extraction performance and applicability. An effective optimization algorithm is suggested for solving the sparse optimization problem, demonstrating fast convergence speed and superior feature extraction.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Chemical
Ruoshi Qin, Jinsong Zhao
Summary: In this paper, a novel fault diagnosis model called adaptive multiscale convolutional neural network (AMCNN) is proposed. It incorporates a new multiscale convolutional learning structure and an adaptive attention module to automatically mine multiple-scale features from time-series data and adjust the selection of relevant fault pattern information. The triplet loss optimization approach is used to enhance the discrimination capability of the model under multimode conditions. The experimental results demonstrate the outstanding fault diagnosis performance and generalization ability of AMCNN.
CHINESE JOURNAL OF CHEMICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Linshan Jia, Tommy W. S. Chow, Yu Wang, Yixuan Yuan
Summary: A novel fault diagnosis framework called MRA-CNN is proposed in this article to learn discriminative multiscale features from vibrational signals and reduce noises. Experimental results show that the proposed method achieves higher accuracy in highly noisy environments compared to state-of-the-art methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Zhuang Ye, Jianbo Yu
Summary: A novel deep neural network called MWMNet is proposed in this article for extracting impulses from vibration signals and performing fault diagnosis. MWMNet utilizes a smoothly embedded morphological layer to filter out noise and employs multiple branches with different scales and adaptive weighted fusion to extract impulse signals. Experimental results demonstrate that MWMNet can learn fault-related features and filter out noise, outperforming other DNN models in fault diagnosis performance.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Chemistry, Analytical
Xiaorui Shao, Chang-Soo Kim
Summary: This article proposes a domain adaptive and lightweight framework for fault diagnosis based on 1D-CNN, which can extract features with robustness and domain invariance through CORAL processing to minimize domain shifts, effectively improving FD performance.
Article
Engineering, Multidisciplinary
Hyeongmin Kim, Chan Hee Park, Chaehyun Suh, Minseok Chae, Hye Jun Oh, Heonjun Yoon, Byeng D. Youn
Summary: This paper proposes a novel preprocessing method called stator current operation compensation (SCOC) for fault diagnosis of a permanent magnet synchronous motor (PMSM) using deep learning under variable operating conditions. SCOC includes two stages: tacho-less resampling and main operating component subtraction with rescaling, which can reduce the variability caused by changes in operating conditions and effectively improve the fault diagnosis performance of PMSMs.
Article
Engineering, Electrical & Electronic
Zilong Zhang, Zhibin Zhao, Xiaolong Li, Xingwu Zhang, Shibin Wang, Ruqiang Yan, Xuefeng Chen
Summary: This article proposes a faster adaptive multiscale dictionary learning method for monitoring the condition of traction motor bearings. The method has two core traits, including shorter learning time and adaptive parameter estimation, making it more suitable for practical industrial applications.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Acoustics
Prashant Tiwari, S. H. Upadhyay
Summary: This paper proposes a novel signal processing method called Concealed Component Decomposition (CCD) for developing a precise bearing fault diagnosis model, which has been validated over different simulated and experimental datasets of different fault types, demonstrating its superiority over other existing signal decomposition approaches.
JOURNAL OF SOUND AND VIBRATION
(2021)
Article
Computer Science, Information Systems
A. Sivapriya, N. Kalaiarasi, Rajesh Verma, Bharatiraja Chokkalingam, Josiah Lange Munda
Summary: This paper proposes a new multiscale kernel convolution neural network (MKCNN) for fast fault diagnosis of cascaded MLI. The method utilizes frequency domain samples instead of raw signals and constructs a multiscale convolution network model to capture low- to high-level fault features. Simulation results demonstrate high diagnostic accuracy rate (98.3%) and robustness of the proposed method, outperforming other intelligent models.
Article
Engineering, Multidisciplinary
Baokun Han, Shuo Xing, Jinrui Wang, Zongzhen Zhang, Huaiqian Bao, Xiao Zhang, Xingwang Jiang, Zongling Liu, Zujie Yang, Hao Ma
Summary: A multichannel deep adaptive adversarial network (MCDAAN) based on fusing acoustic and vibration signals is proposed in this paper to improve the accuracy and adaptability of fault diagnosis. The MCDAAN is trained and classified through neural network feature extraction, convolutional block attention adjustment, fusion feature measurement, and classifiers. Experimental results show that MCDAAN outperforms other comparison methods in terms of accuracy.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Ao Ding, Yong Qin, Biao Wang, Limin Jia, Xiaoqing Cheng
Summary: Intelligent fault diagnosis of train bogie bearings based on edge computing is a promising technology to ensure the safety and reliability of train operation, which can give fault diagnosis systems better real-time performance and lower communication costs. This article proposes a new multiscale lightweight network with adaptive pruning for the intelligent diagnosis fault of train bogie bearings in edge computing scenarios. Experimental results demonstrate that the accuracy and complexity of the proposed network are superior to other state-of-the-art lightweight bearing fault diagnosis networks under varying operating conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Multidisciplinary
Junxia Wang, Changshu Zhan, Sanping Li, Qiancheng Zhao, Jiuqing Liu, Zhijie Xie
Summary: An adaptive VMD method using the AOA optimization algorithm is proposed for rotating machinery fault diagnosis. The method can extract fault characteristics more effectively by selecting appropriate parameters.
Article
Physics, Multidisciplinary
Xiaoan Yan, Yadong Xu, Minping Jia
Summary: The intelligent bearing fault diagnosis method based on self-adaptive hierarchical multiscale fuzzy entropy proposed in this paper integrates the advantages of HFE and MFE to extract multidimensional feature matrices of the original bearing vibration signal, with key parameters automatically determined using the BSA. The introduction of the SMM classifier allows for learning and automatic identification of different bearing health conditions from the extracted multidimensional feature matrix, achieving high identification accuracy and robustness according to experimental results.
Article
Chemistry, Multidisciplinary
Jianguo Sun, Bin Li, Long Hu, Junjun Guo, Xufeng Ling, Xuliang Zhang, Chi Zhang, Xianxin Wu, Hehe Huang, Chenxu Han, Xinfeng Liu, Youyong Li, Shujuan Huang, Tom Wu, Jianyu Yuan, Wanli Ma
Summary: Solution processable semiconductors like organics and emerging lead halide perovskites (LHPs) are ideal candidates for photovoltaics. This study investigates a novel device architecture involving block copolymer/perovskite hybrid bulk heterointerfaces, which enhances light absorption, energy level cascade, and provides a thin hydrophobic layer to improve carrier generation and prevent moisture invasion. The resulting hybrid solar cell exhibits high efficiency and stability, and the approach can be extended to other LHPs.
ADVANCED MATERIALS
(2023)
Article
Biochemistry & Molecular Biology
Fei Gao, Jianjun Han, Li Jia, Jun He, Yun Wang, Mi Chen, Xiaojun Liu, Xia He
Summary: miR-30c enhances NK cell cytotoxicity to lung cancer cells by decreasing GALNT7 and inactivating the PI3K/AKT pathway, suggesting that regulating miR-30c expression may be a promising approach for enhancing NK cell-based antitumor therapies.
Article
Engineering, Electrical & Electronic
Jiahui Wang, Yabin Gao, Yue Zhao, Zhiguang Feng, Jianxing Liu
Summary: A dynamic sliding-mode variable-structure control (VSC) combined with fuzzy neural networks (FNNs) is proposed for voltage tracking control in DC-DC boost converters. Two types of FNNs are used to approximate uncertainties, with the control system analyzed to be boundedly stable under this method. Validation and superiority of the proposed dynamic VSC method are demonstrated through comparative simulations.
INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS
(2023)
Article
Materials Science, Multidisciplinary
F. Y. Han, Q. Shi, C. Zheng, M. Z. Li, H. Feng, C. J. Zhang, S. Z. Zhang, X. Y. Fan, X. F. Niu, J. C. Han, T. Wang
Summary: In this study, a Mg-Zn-Al-Ca alloy was processed using forward extrusion and post ECAP method. The evolution of microstructure and mechanical properties of the alloy was systematically investigated. The results showed that the decreased-temperature ECAP processing led to significant grain refinement and the production of substructures in the alloy. The alloy achieved a minimum average grain size of 1.04 μm after specific passes of ECAP at certain temperatures. Furthermore, the texture type of the alloy changed after ECAP deformation. The Mg-5Zn-2Al-1Ca alloy exhibited excellent mechanical properties after the last passes of ECAP, with strength increase contributed by grain boundary strengthening, texture strengthening, and Orowan strengthening effect.
JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE
(2023)
Article
Automation & Control Systems
Song Zhang, Jianeng Lin, Yugen You, Ningbo Yu, Jianda Han
Summary: This study proposes a strategy called CorrCA-RFG which uses correlated components analysis and random forest regressor to achieve accurate motion estimation from surface electromyogram (sEMG) signals. The proposed method outperforms three other methods in terms of estimation performance, demonstrating the effectiveness of extracting user-independent sEMG features for robust motion estimation.
MEASUREMENT & CONTROL
(2023)
Article
Automation & Control Systems
Xiao Liang, Hai Yu, Zhuang Zhang, Huawang Liu, Yongchun Fang, Jianda Han
Summary: Aerial delivery is becoming a reality with the advancement of microelectronics and communication technology. This article presents a flexible connection and nonlinear control approach for independent payload hoisting and lowering in cable-suspended transportation systems. The proposed method achieves simultaneous quadrotor positioning, payload swing elimination, and hoisting/lowering. Hardware experiments on a self-built aerial transportation platform validate the effectiveness of the approach.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Materials Science, Multidisciplinary
Yu Wang, Jianqiang Han, Yingjie Xia, Bo Zhang
Summary: This study investigates the damage and fracture evolution of rock containing fissures and hollow hole under freeze-thaw and cyclic loads. The results show that the volumetric deformation of rock decreases with increasing freeze-thaw cycles, and both elastic strain energy and dissipated strain energy decrease as well. A coupling damage evolution model considering freezing-thaw and mechanical damage is proposed.
INTERNATIONAL JOURNAL OF DAMAGE MECHANICS
(2023)
Article
Chemistry, Physical
Guangxu Zhao, Jing Zhang, Shuzhi Zhang, Gang Wang, Jianchao Han, Changjiang Zhang
Summary: In this study, a novel CoCuFeNiTiV0.6 high entropy alloy interlayer was used for vacuum diffusion bonding of TiAl alloy and TC4 titanium alloy. The effects of bonding temperature and pressure on the microstructure, element diffusion behavior, and mechanical properties of the joint were investigated. Different diffusion layers were formed at the interface, and their thickness increased with the increase of bonding temperature and pressure. The mechanical properties of the joints were improved compared to traditional bonding methods.
JOURNAL OF ALLOYS AND COMPOUNDS
(2023)
Article
Materials Science, Multidisciplinary
Hou -Bo Zhou, Zi-Bing Yu, Feng-xia Hu, Jian-Tao Wang, Fei-Ran Shen, Jia-Zheng Hao, Lun-Hua He, Qing-Zhen Huang, Yi-Hong Gao, Bing-Jie Wang, Zhuo Yin, Zheng-Ying Tian, Jing Wang, Yun-Zhong Chen, Ji-Rong Sun, Tong-Yun Zhao, Bao-Gen Shen
Summary: This study reports the emergence of the Invar effect with excellent mechanical properties by modulating the electronic structure in LaFe11.6-xCoxSi1.4. The site occupancy of Co atoms was determined using neutron and X-ray diffraction, and ab initio calculations were performed to study the electronic band structure. The results show that the incorporation of Co atoms inhibits spontaneous magnetostriction and enhances the Invar effect in the ferromagnetic region of LaFe10.6Co1.0Si1.4.
Article
Obstetrics & Gynecology
Jian Zhuo, Yanchun Zhao, Jianjun Han, He Li, Ruiying Hao, Yan Yang, Luxian Dai, Ankang Sheng, Xiaohong Yang, Weiguang Liu
Summary: The expression of Rab10 in breast cancer is closely related to prognosis, indicating that it can be used as an effective clinical prognostic biomarker.
CLINICAL AND EXPERIMENTAL OBSTETRICS & GYNECOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Guoliang Zhang, Yaoyao Li, Ruifeng Zhu, Zhe Huang, Dan Zhang, Zhu Long, Yuning Li
Summary: This study addresses the challenges in developing carbon fiber paper-based supercapacitors with high energy density by designing a multi-layered electrode with a specific structure. The use of Cu(OH)(2) nanorods on the surface of a sponge-like carbon fiber paper enriched with oxygen functional groups results in enhanced capacitance and excellent cyclic stability. The assembled solid-state supercapacitor demonstrates superior performance, surpassing previously reported Cu(OH)(2) supercapacitors.
Article
Chemistry, Physical
Shouzhen Cao, Zongze Li, Jiafei Pu, Jianchao Han, Qi Dong, Mingdong Zhu
Summary: TiAl alloys are high-temperature structural materials. The Ti-46Al-8Nb-2.5V alloy exhibited phase transformations and texture evolution during hot compression and subsequent annealing at 900 degrees C. The volume fraction of the alpha(2) phase decreased, and the gamma -> alpha(2) phase transformation occurred during annealing.
Article
Multidisciplinary Sciences
Jian Zhuo, Jianjun Han, Yanchun Zhao, Ruiying Hao, Chong Shen, He Li, Luxian Dai, Ankang Sheng, Hanyu Yao, Xiaohong Yang, Weiguang Liu
Summary: The study provides insights into the role of RAB10 in breast cancer, showing its association with prognosis and its impact on cell proliferation, invasion, and immune cell infiltration. RAB10 may serve as a potential biomarker or molecular target for breast cancer.
SCIENTIFIC REPORTS
(2023)
Article
Chemistry, Multidisciplinary
Boshi Tian, Ruixue Tian, Shaohua Liu, Yan Wang, Shili Gai, Ying Xie, Dan Yang, Fei He, Piaoping Yang, Jun Lin
Summary: This study constructed a biodegradable, porous Mn-doped ZnO nanocluster with enhanced piezoelectric effect through doping engineering, which has the potential application in inhibiting cancer cell growth and inducing ferroptosis. The results showed that lattice distortion and oxygen vacancy generation induced by Mn-doping play important roles in improving the catalytic efficiency.
ADVANCED MATERIALS
(2023)
Article
Physics, Nuclear
Xiang Chen, Li Li, Ying Cui, Junping Yang, Zhuxia Li, Yingxun Zhang
Summary: This study extends a method for reconstructing the impact parameter distributions in heavy ion collisions by using the Bayesian method and K-means clustering method. The reconstructed distributions provide insights into the correlation between multiplicity and transverse momentum at different centralities.