检索结果-内蒙古大学图书馆

IAENG International Journal of Computer Science 2024年第12期51卷 2010-2016页

作者： Yu, Tianming Long, Cheng Feng, Guoliang School of Automation Engineering Northeast Electric Power University Jilin Jilin 132012 China School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin Jilin 100190 China

Air compressors are crucial in industrial production, but issues such as equipment aging and improper operation can lead to faults, severely impacting efficiency and safety. Traditional MFCC spectrogram-based diagnostic methods are challenged by background noise interference, making accurate fault feature extraction difficult. To address this, this study proposes an air compressor fault identification algorithm based on low-rank matrix recovery. By applying low-rank background modeling to the MFCC spectrogram to eliminate background noise, the algorithm effectively extracts primary features. The MobileNetV2 model is then used to extract features from the MFCC foreground images, followed by dimensionality reduction using Principal Component Analysis (PCA). The reduced-dimensional fault features are analyzed using k-means clustering. Experimental results show that for Data 2, the VGG19 model achieved an accuracy of 95.90%, an F1-score of 0.91, and a recall of 0.93, with a processing time of 1916 seconds. In comparison, the ResNet50 model attained an accuracy of 94.88%, an F1-score of 0.91, and a recall of 0.93, with a processing time of 826 seconds. These results demonstrate that the foreground features obtained through low-rank background modeling exhibit superior performance in fault identification and clustering, enhancing the accuracy and stability of fault diagnosis. Thus, the proposed algorithm shows promising potential for diagnosing and repairing air compressor faults. © (2024), (International Association of Engineers). All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

controllability of heterogeneous networked sampled-data systems

引用

Science China(information Sciences) 2025年第3期68卷 302-318页

作者： Zixuan YANG Lin WANG Xiaofan WANG Guanrong CHEN Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China School of Mechatronic Engineering and Automation Shanghai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Electrical Engineering City University of Hong Kong

This study investigates the controllability of a general heterogeneous networked sampled-data system(HNSS) consisting of nonidentical node systems, where the inner coupling between any pair of nodes can be described by a unique *** signals on control and transmission channels are sampled and held by zero-order holders, and the control sampling period of each node can be different. Necessary and sufficient controllability conditions are developed for the general HNSS, using the Smith normal form and matrix equations, respectively. The HNSS in specific topology or dynamic settings is discussed subsequently with easier-to-verify conditions derived. These heterogeneous factors have been determined to independently or jointly affect the controllability of networked sampled-data systems. Notably, heterogeneous sampling periods have the potential to enhance the overall controllability, but not for systems with some special dynamics. When the node dynamics are heterogeneous,the overall system can be controllable even if it is topologically uncontrollable. In addition, in several typical heterogeneous sampled-data multi-agent systems, pathological sampling of single-node systems will necessarily cause overall uncontrollability.

关键词： network controllability sampled-data system heterogeneous system inner coupling multi-agent system

来源：评论

学校读者我要写书评

暂无评论

Detection of Oscillations in Process control Loops From Visual Image Space Using Deep Convolutional Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 982-995页

作者： Tao Wang Qiming Chen Xun Lang Lei Xie Peng Li Hongye Su the Department of Electronic Engineering the School of InformationYunnan UniversityKunming 650091China DAMO Academy Alibaba GroupHangzhou 311100China the State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou 310027China

Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant *** numerous automatic detection techniques have been proposed,most of them can only address part of the practical *** oscillation is heuristically defined as a visually apparent periodic ***,manual visual inspection is labor-intensive and prone to missed *** neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction *** this work,an exploration of the typical CNN models for visual oscillation detection is ***,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation *** feasibility and validity of this framework are verified utilizing extensive numerical and industrial *** with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and *** addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.

关键词： Convolutional neural networks(CNNs) deep learning image processing oscillation detection process industries

来源：评论

学校读者我要写书评

暂无评论

Network information Big Data Analysis Platform Based on Deep Learning technology 11th

Network Information Big Data Analysis Platform Based on Deep...

引用

11th International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2023

作者： Yan, Kai Gao, Hao Department of Information and Control Engineering Shenyang Institute of Science and Technology Liaoning Shenyang110000 China

With the rapid development of Internet technology, the amount of information and data is constantly increasing, leading to higher and higher demands for network big data analysis platforms. This paper primarily delves into the application of deep learning technology in digital text classification. In this paper, a deep learning-based algorithm is introduced in detail. It outlines the method of extracting specific numerical eigenvectors from large-scale non-negative eigenattribute samples and converting them into machine-readable code. ased on the aforementioned methodology, an analysis platform is designed, and its basic performance is simulated and tested. The test results indicate that the platform's ability to process abnormal data in Round A is 80, Round B is 90, Round C is 70, Round D is 85, and Round E is 75. The exception handling capacity of each category is represented visually through a bar chart, where the height of the bar signifies the size of the exception handling capacity for that specific category. © 2024 The Authors. Published by Elsevier B.V.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear control for triple inverted pendulum based on three-step method

Nonlinear control for triple inverted pendulum based on thre...

引用

2024 China Automation Congress, CAC 2024

作者： Han, Guangxin Zhang, Baokui College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin City132022 China

ISBN: (纸本)9798350368604

In order to enhance the stabilization control performance of the triple inverted pendulum system, a nonlinear controller based on the three-step method is proposed. Firstly, the state space model of the triple inverted pendulum is established. Secondly, the stabilization control law is derived in according with three-step method, that is, homeostatic-like control, reference dynamic feed-forward control and Error feedback control. Finally, the stability of the closed-loop system is proved by the Lyapunov stability theory. Simulation results show that the proposed control strategy has shorter settling time and smaller overshooting and control input, compared with the LQR algorithm optimized by PSO-AFSA and the Robust HĞ based on LMI. © 2024 IEEE.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Operator Action Recognition Based on Improved ST-GCN 6

Operator Action Recognition Based on Improved ST-GCN

引用

6th International Conference on Communications, information System and Computer engineering, CISCE 2024

作者： Fan, Longxin Sun, Hongbin School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China School of Electrical Engineering Changchun Institute of Technology Changchun130012 China

ISBN: (纸本)9798350353174

With the rapid development of the electric power industry, the safety problems of the personnel working with electricity are becoming more and more prominent. Traditional solutions relying on manual methods perform poorly in ensuring safety and are in urgent need of updating and improvement. In recent years, the application of computer vision technology has provided new possibilities for improving safety standards, especially the important role of human skeletal dynamics in action recognition is becoming more and more prominent. In order to effectively solve the existing safety challenges of power-carrying operations, this paper proposes a power-carrying operation action recognition method based on ST-GCN (Spatio-Temporal Graph Convolutional Networks). The method combines a pose estimation algorithm and an action recognition algorithm to achieve the purpose of action recognition, in which the improved OpenPose algorithm is used for pose estimation to obtain the skeletal data, and then the ST-GCN is used for action recognition, in which a channel attention module CBAM (Convolutional Block Attention Module) is added for enhancement of action features. After experiments, it is confirmed that the spatio-temporal graph convolutional network method proposed in this paper shows excellent results in practical applications and effectively improves the safety and security level of the personnel working with electricity. © 2024 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Residual Tensor Train: A Quantum-Inspired Approach for Learning Multiple Multilinear Correlations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1101-1113页

作者： Chen, Yiwei Pan, Yu Dong, Daoyi Zhejiang University Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China University of New South Wales School of Engineering and Information Technology CanberraACT2600 Australia

States of quantum many-body systems are defined in a high-dimensional Hilbert space, where rich and complex interactions among subsystems can be modeled. In machine learning, complex multiple multilinear correlations may also exist within input features. In this article, we present a quantum-inspired multilinear model, named residual tensor train (ResTT), to capture the multiple multilinear correlations of features, from low to high orders, within a single model. ResTT is able to build a robust decision boundary in a high-dimensional space for solving fitting and classification tasks. In particular, we prove that the fully connected layer and the Volterra series can be taken as special cases of ResTT. Furthermore, we derive the rule for weight initialization that stabilizes the training of ResTT based on a mean-field analysis. We prove that such a rule is much more relaxed than that of tensor train (TT), which means that ResTT can easily address the vanishing and exploding gradient problem that exists in the existing TT models. Numerical experiments demonstrate that ResTT outperforms the state-of-the-art tensor network and benchmark deep learning models on MNIST and Fashion-MNIST datasets. Moreover, ResTT achieves better performance than other statistical methods on two practical examples with limited data, which are known to have complex feature interactions. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

QoI-Aware Configuration Adaptation and Heterogeneous Resource Allocation for Edge Video Analytics

引用

IEEE Internet of Things Journal 2025年第12期12卷 19215-19230页

作者： He, Zixuan Sun, Yanjing Zhang, Beibei Dong, Kaiwen Wang, Bowen Xu, Hongli China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China China University of Mining and Technology IoT Perception Mine Research Center Xuzhou221116 China School of Information and Control Engineering China University of Science and Technology of China School of Computer Science and Technology Anhui Hefei230027 China University of Science and Technology of China Suzhou Institute for Advanced Research Jiangsu Suzhou215123 China

Edge video analytics enables agile responses of machine-centric applications by streaming videos from end devices to edge servers (ESs) for resource-intensive Deep Neural Network (DNN) inference. Quality of Inference (QoI), reflected by end-to-end analytics delay and inference accuracy, is crucial for the high-quality real-time decision-making. Due to the limited ES resources and dynamic network conditions, video configuration adaptation and fine-grained resource allocation are necessary to enhance the QoI of video streams, which involves a delicate balance between delay and accuracy. In this paper, we propose an edge-enabled multi-video analytics framework, in which performing DNN inference relies on heterogeneous resources, including CPU, GPU, and memory. Considering the different impacts of heterogeneous resources on QoI and double-queue backlogs, we formulate the joint video configuration adaptation, CPU-GPU resource allocation, and batch size selection (JCCGB) problem based on semi-Markov Decision Process to maximize the long-term average QoI. Then, Lyapunov optimization is applied to transform the original problem into one that minimizes the Lyapunov drift-plus-penalty upper bound, thereby ensuring the stability of both the transmission and computation queues. To tackle the potential multimodality of the optimal configuration adaptation and resource allocation policy, we propose the diffusion deep reinforcement learning based JCCGB (DD-JCCGB) scheme. This approach effectively enhances the policy performance and accelerates the training process. Experiments driven by real-world network traces demonstrate that the DD-JCCGB algorithm improves the long-term average QoI and outperforms baseline schemes. © 2025 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Windings Reconfigured Fault-Tolerant control for Five-Phase PMSMs with Reduced Torque Ripple

引用

IEEE Transactions on Energy Conversion 2025年第1期40卷 665-676页

作者： Ji, Jinghua Li, Zongwang Zhao, Xiaopeng Yu, Yanjun Zhao, Wenxiang AVIC Xi'an Flight Automatic Control Research Institute Xi'an710065 China Nanjing Institute of Technology School of Electric Power Engineering Nanjing211167 China Jiangsu University School of Electrical and Information Engineering Zhenjiang212013 China

This paper proposes a winding reconfigured fault-tolerant control strategy for five-phase permanent magnet synchronous motors with an open circuit fault. First, a new decoupling matrix is derived from the referenced fault-tolerant currents, which effectively decouples the phase currents into the fundamental subspace and dual-zero-sequence subspace. In order to mitigate the harmonic current, a novel winding connection topology is proposed in which the harmonic plane current can be eliminated without closed-loop control. Thereby, the pulsating term in the torque equation can be eliminated. Moreover, the post-fault four-phase motor can operate in the two-phase mode. As a result, only the currents of two phases are required for coordinate transformation, and the coordinate transformation process can be greatly simplified. The analysis of voltage utilization shows that the elimination of the harmonic subspace can improve the voltage utilization rate. Experimental results verify that the proposed strategy can achieve lower torque ripples, lower system loss and less computation time compared with the existing fault-tolerant strategy. © 1986-2012 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Multi-view stereo based on adaptive expansion propagation 7

Multi-view stereo based on adaptive expansion propagation

引用

7th International Conference on Computer information Science and Application technology, CISAT 2024

作者： Nie, Zixuan Fu, Haohai Jilin Institute of Chemical Technology School of Information and Control Engineering Jilin132022 China Changchun Institute of Technology School of Computer Technology and Engineering Changchun130012 China

ISBN: (纸本)9798350375107

Through computer vision and image processing techniques, a set of images from a scene can be reconstructed in 3D to recover a 3D model of the scene, in which dense reconstruction is a crucial part, and most existing algorithms cannot effectively recover weak texture regions in dense reconstruction. In response to this issue, this article proposes a hypothesis propagation strategy based on adaptive extension. In the hypothesis propagation stage of PatchMatch MVS, an adaptive mechanism for region propagation is introduced, and an update counter is set to regulate the expansion of the sampling area. This ensures that there are enough excellent hypotheses for sampling in this algorithm iteration, and the quality of sampling hypotheses is not limited by fixed sampling pixel positions, thereby improving the probability of excellent hypotheses being sampled in the sampling space. It is demonstrated in the ETH3D dataset that our method reconstructs models with higher integrity, and fewer voids and smoother surfaces in the reconstruction of weakly textured regions. © 2024 IEEE.

关键词： 3D reconstruction

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：