检索结果-内蒙古大学图书馆

Multi-Time-Scale Variational Mode Decomposition-Based Robust Fault Diagnosis of Railway Point Machines Under Multiple Noises

引用

Chinese Journal of Electronics 2024年第3期33卷 814-822页

作者： Junqi LIU Tao WEN Guo XIE Yuan CAO Clive Roberts Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology The School of Electronic and Information Engineering Beijing Jiaotong University Birmingham Centre for Railway Research and Education University of Birmingham

The fault diagnosis of railway point machines(RPMs) has attracted the attention of engineers and *** have studies considered diverse noises along the *** fulfill this aspect,a multi-time-scale variational mode decomposition(MTSVMD) is proposed in this paper to realize the accurate and robust fault diagnosis of RPMs under multiple *** decomposes condition monitoring signals after coarse-grained processing in varying *** this manner,the information contained in the signal components at multiple time scales can construct a more abundant feature space than at a single *** the experimental validation,a random position,random type,random number,and random length(4R) noise-adding algorithm helps to verify the robustness of the *** adequate experimental results demoristrate the superiority of the proposed MTSVMD-based fault diagnosis.

关键词： Railway point machines Fault diagnosis Multi-time-scale Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Classification of Wild Fungi Based on Attention Residual Mechanism 3

Fine-Grained Classification of Wild Fungi Based on Attention...

引用

3rd International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2023

作者： Wen, Shuoyi Yang, Li Duan, Hailong Zhang, Tingting Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin University of Technology and Education Tianjing China

ISBN: (纸本)9781643684444

Identifying wild mushroom species are an important way to prevent poisoning from consuming toxic wild mushrooms. Therefore, an attention-based method for fine-grained classification of wild mushrooms is proposed, in which an attention mechanism is incorporated and a new network model structure is constructed in combination with a residual module. Firstly, nine diseased wild mushroom image samples were collected, and in order to make the model have better generalization ability, the images were pre-processed so that the number of samples reached 7200, and the experimental results showed that the improved deep residual network model achieved about 99.12% accuracy in classifying and recognizing the established wild mushroom database, and the improved neural network had a great improvement in classification accuracy. © 2023 The Authors.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Improved CBAM Rock Image Classification Based on Xception 3

Improved CBAM Rock Image Classification Based on Xception

引用

3rd International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2023

作者： Zhang, Tingting Ren, Shuyan Duan, Hailong Wen, Shuoyi Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin University of Technology and Education Tianjing China

ISBN: (纸本)9781643684444

To address the problems of traditional machine learning algorithms in rock recognition which are time-consuming, labor-intensive and low accuracy, a migration learning method using network weights for feature learning based on Xception network structure and incorporating an improved convolutional attention module (CBAM) to strengthen the important features of rocks, as well as adding a feature map perturbation structure to enhance the generalization ability of the model is proposed. Six types of manually collected rock sample images from five provinces, including Fujian and Zhejiang, are selected to construct the rock dataset and conduct experiments, and the learning rate is set at 0.001. Experiments show that the precision of the proposed method is 98.9% with 0.05 loss, which is higher than other mainstream recognition models with higher recognition accuracy and lower loss. © 2023 The Authors.

关键词： Rocks

来源：评论

学校读者我要写书评

暂无评论

Characteristics Analysis and Classification of Foot Autonomic Movements Based on EEG Signals 5

Characteristics Analysis and Classification of Foot Autonomi...

引用

5th Asia Symposium on Image Processing, ASIP 2023

作者： He, Lin Meng, Tongning Zhuan, Zhikun Bian, Yan Zhang, Zhiwen Li, Junjie Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin China

ISBN: (纸本)9798350323429

To improve the effectiveness of rehabilitation for stroke patients, active training can be used to treat and recover patients' foot dyskinesia. Recognizing the characteristics of different foot motion states is an important part of active rehabilitation for stroke patients. In this study, EEG signals were collected during three different foot actions (foot at rest, 15 ° stretched and 45° stretched) to conduct a classification study on the EEG signals of different voluntary movements of the right foot. Features of autonomous action EEG signals were extracted and support vector machine (SVM) and random forest (RF) were both used for classification. Brain topographic maps and time-frequency maps were utilized to display the characteristics of EEG data. The ground averaged time-frequency map and brain topographic map revealed that the ERD (Event-Related Desynchronization) characteristics of the stretched feet at 45 ° were more obvious than those of the stretched feet at 15°, while the ERD characteristics of the stretched feet at 15° were more obvious than those in the resting state. The classification results showed that the RF algorithm achieved higher classification accuracy (81.89%) compared to the SVM algorithm (74.93%) among the three different action states. The RF classification algorithm was found to be more suitable for the classification of different foot movements with a classification result that was 6.97% higher than that of SVM. Moreover, 90% of the subjects using the RF algorithm achieved an accuracy score of more than 75%. These findings highlight the potential of identifying different voluntary movements of the foot by classifying the characteristics of EEG signals and using them as a basis for the rehabilitation effect evaluation of stroke patients. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Stage Machinery Based on Entropy Weight and Fuzzy Inference Method

Risk Assessment of Stage Machinery Based on Entropy Weight a...

引用

2023 International Conference on Culture-Oriented Science and technology, CoST 2023

作者： Wang, Huiqin Yang, Qingqing Li, Zhen Wang, Huiqi Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing China

ISBN: (纸本)9798350357998

It is of great significance to find out the hidden hazards of the stage machinery in advance and formulate the corresponding protective measures to improve the safety of the stage performance. A comprehensive method that integrates entropy weights and the fuzzy inference is proposed. Firstly, the risk factors are identified through Failure Modes and Effects Analysis (FMEA) method, with the information obtained by field survey and research. Then, the entropy weight method and Fault Tree Analysis (FTA) methods are adopted to analyze the risk factors so as to obtain the probability of the hazardous events. Lastly, the risk level of different event is obtained by the fuzzy inference method. The simulation result proves that the model is reasonable, objective, and feasible. © 2023 IEEE.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Research on Selective Activation of Transit Signal Priority and Signal Timing Optimization 8

Research on Selective Activation of Transit Signal Priority ...

引用

8th International Conference on Electromechanical control technology and Transportation, ICECTT 2023

作者： Zhang, Xinyue Wu, Wenxiang North China University of Technology Beijing Key Laboratory of Urban Road Intelligent Traffic Control Technology Beijing China

ISBN: (纸本)9781510668331

The activation of transit signal priority (TSP) will bring some delay savings to the vehicles running in the same direction, but also increase the delay of vehicles running in the conflicting direction. In order to quantify the impact of transit signal priority activation on the delay change of vehicles in the same direction and other directions, and limit its adverse impact on the overall delay of the road, this paper takes the mixed-traffic road without bus lane as the research object, and simulates the vehicle operation and signal timing scheme on the road with multiple intersections. With the goal of minimizing the total delay of social traffic flow and minimizing the negative impact of transit signal priority on the delay of road travelers, the coordinated timing control of signals at multiple intersections and selective activation of transit signal priority is realized, simulated annealing algorithm and implicit enumeration method are used to implement the model respectively. Finally, the delay of three types of road travelers under various signal schemes is compared. The results show that the optimization scheme can maximize the operation efficiency in the artery and reduce the adverse impact on the cross-street vehicles, so as to improve the operation condition of the vehicles on the road with multiple intersections and reduce the overall delay of the travelers. © 2023 SPIE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Distributed Kalman filtering over sensor networks with fading measurements and random link failures

引用

Journal of the Franklin Institute 2023年第4期360卷 2457-2475页

作者： Zhu, Mingyan Sui, Tianju Wang, Rui School of Control Science and Engineering Dalian University of Technology Dalian116024 China School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China Key Laboratory of Advanced Technology for Aerospace Vehicles Liaoning Province Dalian116024 China

This paper investigates the distributed state estimation problem for a linear time-invariant system characterized by fading measurements and random link failures. We assume that the fading effect of the measurements occurs slowly. Additionally, communication failures between sensors can affect the state estimation performance. To this end, we propose a Kalman filtering algorithm composed of a structural data fusion stage and a signal date fusion stage. The number of communications can be decreased by executing signal data fusion when a global estimate is required. Then, we investigate the stability conditions for the proposed distributed approach. Furthermore, we analyze the mismatch between the estimation generated by the proposed distributed algorithm and that obtained by the centralized Kalman filter. Lastly, numerical results verify the feasibility of the proposed distributed method. © 2023 The Franklin Institute

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Establishment of Rate-Dependent Hysteresis Model and control Method of Piezoelectric Ceramic Actuator

Establishment of Rate-Dependent Hysteresis Model and Control...

引用

7th International Conference on Electronics technology, ICET 2024

作者： Qu, Lili Wang, Yanyan Huang, Yuanting Tianjin in University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin300222 China

ISBN: (纸本)9798350363951

Piezoelectric ceramic actuators (PEA) are commonly utilized for accuracy orientation, precision measurement, vibration isolation, and other fields due to their high positioning accuracy and fast response speed. However, the inherent hysteresis of piezoelectric ceramics seriously influences their positioning precision. Studies have shown that the hysteresis of piezoelectric ceramics has rate-dependent properties. Based on this feature, this paper firstly designs an improved rate-dependent Bouc-Wen hysteresis model and uses particle swarm optimization to identify the model parameters. Secondly, the inverse hysteresis model is established, and a feed-forward controller based on the inverse model is designed to linearize the input and output of the PEA and improve its hysteresis. Finally, the model verification of the established hysteresis model and experimental verification of the feed-forward control method show that the rate-dependent hysteresis of the PEA can be well-fitted based on the improved rate-dependent Bouc-Wen hysteresis model. The experimental results demonstrate that the linearity of the output displacement of the piezoelectric actuator is significantly improved, and the hysteresis error is reduced from 21.9 % to 2.5 % at 1 Hz and from 2 5. 8 % to 7.1 % at 50 Hz, which verifies the validity of the proposed method. © 2024 IEEE.

关键词： Piezoelectric ceramics

来源：评论

学校读者我要写书评

暂无评论

Coal-Rock Interface Image Segmentation Based on U2Net Model with Coordinate Attention 6

Coal-Rock Interface Image Segmentation Based on U2Net Model ...

引用

6th International Conference on intelligent Autonomous Systems, ICoIAS 2023

作者： Song, Chen Xu, Chunyu Tian, Muqin Chen, Rong Taiyuan University of Technology Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control Taiyuan China

ISBN: (纸本)9798350371253

Fast and accurate extraction of segmented images of coal-rock interfaces is one of the most important technologies to realize intelligent operation of comprehensive mining face. In this paper, we propose a multi-mechanism fusion U2Net model for recognizing coal-rock interfaces with complex backgrounds and diverse morphologies. We construct the basic network module by replacing the ordinary convolution in RSU with depth-divisible convolution and expansion convolution;add the coordinate attention mechanism in the last layer of the sampling stage of the improved RSU module to construct a new residual structure;and combine this residual structure with the U2Net model to construct a new U2Net model to realize the automatic learning of segmented images of coal-rock interfaces. Among them, the expansion convolution can obtain a larger sensory field without reducing the resolution;the depth separable convolution helps to simplify the model;the coordinate attention mechanism can suppress the interference of each residual block in the encoding and decoding process, and improve the model performance at a small cost. Compared with the semantic segmentation models commonly used in deep learning, this method improves the accuracy of extracting features from different stages of coal rock images, reduces the model training cost, accelerates the convergence speed of the model, and improves the model's anti-interference. Experiments were conducted to compare U2Net-CA-DC with four semantic segmentation networks (FCN, SegNet, UNet, and U2Net) to verify the effectiveness of the improved model. The accuracy of the method is 95.31% and the mIOU is 93.46% on real coal rock image datasets collected from actual underground wells. The experimental results show that the method provides a new solution for coal rock image segmentation detection and can provide data support for coal rock image segmentation. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bispectral Feature Points and Cross-Correlation 42

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bi...

引用

42nd Chinese control Conference, CCC 2023

作者： Huang, Zhiwei Zong, Hua Xu, Qian Li, Xiaomin Beijing Aerospace Automatic Control Institute National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789887581543

In order to improve the accuracy and real-time performance of X-ray pulsar time delay estimation over short-time observation interval, a method based on bispectral feature points and cross-correlation is proposed in this paper. Firstly, calculate the self-bispectrum of the standard pulsar profile, extract the bispectral feature points by PSO algorithm, and store it in the spacecraft. Secondly, the pulsar photons are received in real-time and get the observation profile by epoch folding. Thirdly, calculate the cross-bispectrum at the bispectral feature points, construct the objective function of time delay estimation, and solve the extremum. Finally, the pulsar time delay estimation is obtained by screening the extreme points using cross-correlation. Simulation experiments based on Insight-HXMT observations of the Crab pulsar show that, the average running time of the proposed algorithm is 41.59ms on Matlab R2017b, and the average estimation error at observation interval below 2.5s is 0.1858ms, which is better than the traditional bispectrum method and the selected bispectrum method. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Pulsars

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：