检索结果-内蒙古大学图书馆

Bearing fault diagnosis method for unbalance data based on Gramian angular field

Journal of Intelligent and Fuzzy Systems 2024年第1-2期47卷 45-54页

作者： Yu, Ping Li, Rong-Bin Cao, Jie Qin, Jun-Hua College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou China Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou University of Technology Lanzhou China National Demonstration Center for Experimental Electrical and Control Engineering Education Lanzhou University of Technology Lanzhou China

In the application of deep learning-based fault diagnosis, more often than not, the network model could perform better with a balanced dataset input, whereby the number of fault data is equivalent to that of normal data. However, in the context of real-world applications, the number of fault data is generally insufficient compared to the normal data. In this study, a new approach for fault diagnosis in unbalanced data sets is proposed using the Gramian angular field (GAF) method. Firstly, the GAF method is employed to convert one-dimensional data into two-dimensional data, which enhances the feature extraction process. Secondly, to balance the sample distribution, fault data is generated using Generative Adversarial Networks (GANs). Finally, the Residual neural network (ResNet) with an attention mechanism is utilized to improve the accuracy of fault diagnosis. The proposed method is experimentally validated using open-source bearing datasets that are published by Case Western Reserve University and the University of Ottawa. The experimental results show that the proposed method has greatly improved fault diagnosis performance in cases of data distribution imbalance, surpassing that of the compared methods. © 2024 - IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SIE: infrared and visible image fusion based on scene information embedding

引用

Multimedia Tools and Applications 2025年第3期84卷 1463-1488页

作者： Geng, Yingnan Diao, Weixuan Zhao, Yan Electrical and Information Engineering Changchun Institute of Technology Kuanping Road Jilin Changchun130103 China Information and Control Engineering Jilin Institute of Chemical Technology Chengde Street Jilin Jilin132022 China College of Communication Engineering Jilin University Qianjin Street Jilin Changchun130015 China

In this article, we proposed an infrared and visible image fusion method based on scene information embedding, which is to obtain an fused image with high-quality target information such as pedestrian crossing, vehicles, signs and rich background texture information. First, scene information is described, so as to effectively represent highlight salient target for infrared image and texture detail for visible image. Second, we embed this scene information into multi-scale fusion framework to fuse these information and reconstruct the desired fused image. It is worth noting that scene information is constructed by pre-trained convolutional neural network, where not only information extracted by convolutional neural network is fully utilized, but also training complexity is not increased. In datasets LLVIP, MSRS, M3FD,TNO, RoadScene and elctricity1, the superiority of our proposed algorithm SIE over state-of-the-arts is demonstrated by subjective evaluation and objective evaluation including information entropy (EN), standard deviation (SD), spatial frequency (SF), average gradient (AG), sum of the correlations of differences (SCD) and mutual information (MI) metrics. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

MPGA-YOLOv8: A Leaf Disease Detection Network Combining Multi-Scale Progressive Feature Network and Global Attention

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第2期52卷 436-446页

作者： Xu, Jiacheng Yang, Yonghui Chu, Maoxiang Student of School of Electronic Information University of Science and Technology Liaoning Anshan114051 China School of Control Science and Engineering University of Science and Technology Liaoning Anshan114051 China

Considering the diversity of natural conditions, including fog, low light, and strong light, as well as the impact of various diseases on leaves, we propose an improved apple leaf disease detection method based on the YOLOv8n model. This method first uses a Multi-Scale Progressive Feature Network(MSPN) as the neck network to integrate multiple morphological lesions and enhance the model’s information integration capability. Then, a Global Self Attention Module (GSAM) is applied at the end of the backbone to help the model capture spatial relationships in the image and reduce interference from extremely complex background conditions. Next, we replace the convolution blocks in the backbone with Receptive Field-Focused Convolution Block (RFFconv) to effectively improve the model’s recognition accuracy through shared receptive field weights. Finally, we add a small object detection layer for small lesions to enhance the model’s generalization performance. Experimental results show that the proposed MPGA-YOLOv8 model effectively detects six types of apple leaf diseases in complex backgrounds, including healthy samples, with an average mAP accuracy of 74.3%. Compared to classic models like SSD, Faster RCNN, YOLOv3 tiny, YOLOv5, and YOLOv6, the mAP performance improves by 20.9%, 38.4%, 9.8%, 10.0%, and 14.3%, respectively. This model enables rapid and accurate detection and recognition of apple leaf diseases, providing viable technical support and solutions for disease prevention and control. © (2025), (International Association of Engineers). All rights reserved.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Breast Tumor Model Based on Magnetoacoustic Concentration Tomography of Magnetic Nanoparticles with Magnetic Induction

引用

Progress In Electromagnetics Research C 2024年 139卷 197-209页

作者： Yan, Xiaoheng Liu, Fangtian Smolik, Waldemar T. Dan, Xinxian Hou, Xiaohan Faculty of Electrical and Control Engineering Liaoning Technology University Huludao125000 China The Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China Faculty of Electronics and Information Technology Warsaw University of Technology Warsaw Poland

Magnetic nanoparticles (MNPs) have been widely investigated as effective drug carriers for targeted tumor therapy. However, the successful application of this technology in the human body requires reliable imaging support. Magnetoacoustic Concentration Tomography of Magnetic Nanoparticles with Magnetic Induction (MACT-MI) is an electromagnetic-ultrasonic coupling imaging technique that holds great promise in improving imaging resolution and providing unique advantages for tumor monitoring and treatment. To evaluate the imaging feasibility of MACT-MI technology for targeted therapy of breast tumors, this study establishes a realistic breast model and takes into account the distribution of magnetic particles within the actual breast tissue environment. A concentration gradient model is introduced, and the finite element method is employed to solve the electromagnetic and sound fields. In addressing the research objective, the forward problem is investigated by analyzing the magnetic force and sound pressure distribution for various tumor sizes and locations, different breast tissues, and both benign and malignant tumors. The results obtained indicate that the magnetoacoustic signal emitted by magnetic particles facilitates accurate mapping of the size and location information of magnetic particles enveloping breast tumors, as well as distinguishing between benign and malignant tumors. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Tomography

来源：评论

学校读者我要写书评

暂无评论

An Attack on a Proposed Construction of Small-State Stream Ciphers and Proposals for New Constructions (Nov, bxac165, 2022)

引用

COMPUTER JOURNAL 2024年第2期67卷 806-806页

作者： Amin-Ghafari, Vahid Attari, Mahmoud Ahmadian School of Information and Control Engineering China University of Mining and Technology Jiangsu 221116 P. R. China Electrical and Computer Engineering School K. N. Toosi University of Technology Tehran *** Iran

Small-state stream ciphers (SSCs) idea is based on using key bits not only in the initialization but also continuously in the keystream generation phase. A time-memory-data tradeoff (TMDTO) distinguishing attack was successfully applied against all SSCs in 2017 by Hamann et al. They suggested using not only key bits but also initial value (IV) bits continuously in the keystream generation phase to strengthen SSCs against TMDTO attacks. Then, Hamann and Krause proposed a construction based on using only IV bits continuously in the packet mode. They suggested an instantiation of an SSC and claimed that it is resistant to TMDTO attacks. We point out that accessing IV bits imposes an overhead on cryptosystems that might be unacceptable in some applications. More importantly, we show that the proposed SSC remains vulnerable to TMDTO attacks 1. To resolve this security threat, the current paper proposes constructions based on storing key or IV bits that are the first to provide full security against TMDTO attacks. Five constructions are proposed for different applications by considering efficiency. Designers can obtain each construction’s minimum volatile state length according to the desirable keystream, key and IV lengths.

关键词： cryptography distinguishing attack IoT security lightweight encryption stream cipher time-memory-data tradeoff attack

来源：评论

学校读者我要写书评

暂无评论

Rolling Bearing Fault Diagnosis Based on MTF Encoding and CBAM-LCNN Mechanism

引用

Computers, Materials & Continua 2025年第3期82卷 4863-4880页

作者： Wei Liu Sen Liu Yinchao He Jiaojiao Wang Yu Gu School of Mechanical and Electrical Engineering Zhoukou Normal UniversityZhoukou466001China School of Information and Control Engineering Jilin Institute of Chemical TechnologyJilin132022China School of Automation Guangdong University of Petrochemical TechnologyMaoming525000China

To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Markov Transition Field(MTF)image encoding combined with a lightweight convolutional neural network that integrates a Convolutional Block Attention Module(CBAM-LCNN).Specifically,we first use the Markov Transition Field to convert the original one-dimensional vibration signals of rolling bearings into two-dimensional ***,we construct a lightweight convolutional neural network incorporating the convolutional attention module(CBAM-LCNN).Finally,the two-dimensional images obtained from MTF mapping are fed into the CBAM-LCNN network for image feature extraction and fault *** validate the effectiveness of the proposed method on the bearing fault datasets from Guangdong University of Petrochemical technology’s multi-stage centrifugal fan and Case Western Reserve *** results show that,compared to other advanced baseline methods,the proposed rolling bearing fault diagnosis method offers faster diagnostic speed and higher diagnostic *** addition,we conducted experiments on the Xi’an Jiaotong University rolling bearing dataset,achieving excellent results in bearing fault *** results validate the strong generalization performance of the proposed *** method presented in this paper not only effectively diagnoses faults in rolling bearings but also serves as a reference for fault diagnosis in other equipment.

关键词： Rolling bearing fault diagnosis markov transition field lightweight convolutional neural network convolutional block attention module

来源：评论

学校读者我要写书评

暂无评论

Combustion characteristics of millimeter-sized aluminum particles in fluidized bed under various O_(2)/CO_(2)/H_(2)O atmospheres Author links open overlay panel

引用

Particuology 2024年第8期91卷 315-322页

作者： Jialing Zhou Rui Zhang Dong Liu Key Laboratory of Thermal Control of Electronic Equipment Ministry of Industry and Information TechnologyNanjing210094China Advanced Combustion Laboratory School of Energy and Power EngineeringNanjing University of Science and TechnologyNanjing210094China

Aluminum is an attractive alternative fuel,but it burns very inefficiently due to the formation of a dense Al_(2)O_(3)layer which prevents O_(2)from diffusion to the surface of Al *** previous experiments,the combustion of millimeter-sized Al(mAl)particles in the fluidized bed has achieved a substantial increase in the combustion efficiency,but further improvements are still *** this study,the effects of reaction atmosphere on the fluidized combustion of mAl particles were *** experiments with different O_(2)/H_(2)O/CO_(2)concentrations were *** experimental results indicate that the combustion efficiency of mAl particles in fluidized bed increases as the mole fraction of O_(2),H_(2)O or CO_(2)increases,and the highest combustion efficiency can reach 38.7%.After the analysis of the oxide film on the surface of aluminum particles,it was found that it is easier to generate the unstableθ-Al_(2)O_(3)under CO_(2)atmosphere,and it is easier to generate the unstableγ-Al_(2)O_(3)andθ-Al_(2)O_(3)under H_(2)O *** unstable Al_(2)O_(3)film is more likely to be abraded in the fluidized bed,which leads to the effective improvement of the combustion efficiency.

关键词： Al combustion Fluidized bed Atmosphere Combustion efficiency

来源：评论

学校读者我要写书评

暂无评论

Asymptotic analysis on bright solitons and breather solutions of a generalized higher-order nonlinear Schrödinger equation in an optical fiber or a planar waveguide

引用

Chinese Physics B 2024年第11期33卷 154-160页

作者： Xin Zhao Zhong Du Li-Jian Zhou Rong-Xiang Liu Xu-Hu Wang College of Information and Control Engineering Qingdao University of TechnologyQingdao 266520China Department of Mathematics and Physics and Hebei Key Laboratory of Physics and Energy TechnologyNorth China Electric Power UniversityBaoding 071003China

We study a generalized higher-order nonlinear Schr¨odinger equation in an optical fiber or a planar *** obtain the Lax pair and N-fold Darboux transformation(DT)with N being a positive *** on Lax pair obtained by us,we derive the infinitely-many conservation *** give the bright one-,two-,and N-soliton solutions,and the first-,second-,and Nth-order breather solutions based on the N-fold *** conclude that the velocities of the bright solitons are influenced by the distributed gain function,g(z),and variable coefficients in equation,h_(1)(z),p_(1)(z),r_(1)(z),and s_(1)(z)via the asymptotic analysis,where z represents the propagation variable or spatial *** also graphically observe that:the velocities of the first-and second-order breathers will be affected by h_(1)(z),p_(1)(z),r_(1)(z),and s_(1)(z),and the background wave depends on g(z).

关键词： optical fiber planar waveguide Darboux transformation bright soliton breather

来源：评论

学校读者我要写书评

暂无评论

Virtual interpolation unitary transformation 2D DOA estimation method for parallel coprime arrays

引用

Zhendong yu Chongji/Journal of Vibration and Shock 2025年第11期44卷 163-171页

作者： Wang, Xuhu Sun, Gaoli Feng, Honghao He, Jinsong School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China

Here, aiming at the problem of insufficient utilization of array received information in existing 2D direction of arrival (DOA) estimation methods to cause degradation of estimation performance, a 2D DOA estimation method for virtual array interpolation under parallel coprime arrays was proposed. This method could perform interpolation for virtual arrays after extending parallel coprime arrays. Then, utilizing the relation between the covariance matrix of interpolated virtual arrays and virtual measurement values, a problem of minimizing the equivalent virtual measurement vector was proposed. Finally, interpolated virtual arrays' covariance matrix was reconstructed using a convex optimization toolbox, and DOA estimation was performed by combining unitary transformation and overall least squares method. Simulation results and lake tests showed that the proposed method can fully use all virtual elements in non-uniform virtual arrays, improve DOFs and estimation accuracy, and be effective. © 2025 Chinese Vibration engineering Society. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Search Algorithm Based on Permutation Group by Quantum Walk on Hypergraphes

引用

Chinese Journal of Electronics 2022年第4期31卷 626-634页

作者： JIANG Yaoyao CHU Pengcheng MA Yulin MA Hongyang School of Science Qingdao University of Technological School of Information and Control Engineering Qingdao University of Technology

Because a significant number of algorithms in computational science include search challenges and a large number of algorithms that can be transformed into search problems have garnered significant attention, especially the time rate and accuracy of search, a quantum walk search algorithm on hypergraphs,whose aim is to reduce time consumption and increase the readiness and controllability of search, is proposed in this paper. First, the data points are divided into groups and then isomorphic to the permutation set. Second, the element coordinates in the permutation set are adopted to mark the position of the data points. Search the target data by the controllable quantum walk with multiparticle on the ring. By controlling the coin operator of quantum walk, it is determined that search algorithm can increase the accuracy and controllability of search. It is determined that search algorithm can reduce time consumption by increasing the number of search particles. It also provides a new direction for the design of quantum walk algorithms, which may eventually lead to entirely new algorithms.

关键词： Search algorithm Quantum walk Permutation groups

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：