检索结果-内蒙古大学图书馆

Sensor Selection for Mechatronic Systems Based on Closed-Loop control Simulations 1

25th International Symposium on Measurement and control in Robotics, ISMCR 2023

作者： Gincsainé Szádeczky-Kardoss, Emese Varga-Berta, Tamás Kiss, Bálint Fazekas, Csaba Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary Thyssenkrupp Components Technology Hungary Budapest Hungary

ISBN: (数字)9783031510854

ISBN: (纸本)9783031510847

The goal of the paper is to present a tool, which can be used for the selection of sensors in a closed-loop control of a mechatronic system. Several sensor parameters (such as noise power or delay) are simulated and their effects on the whole system’s performance are analyzed. For the simulations, Matlab-Simulink environment is applied. The simulated data are then used to estimate the transfer function of the whole closed-loop system with a controller. The services of the System Identification toolbox are appropriate for this task. If the specifications are given as the required damping and bandwidth of the system, the tool estimates the sensor parameters, which can ensure the desired performance. Some simulation results demonstrate the workflow of our tool, which was implemented using the App Designer of Matlab. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Chinese Address Named Entity Recognition Based on BERT-BiLSTM-ATT-CRF Model 43

Chinese Address Named Entity Recognition Based on BERT-BiLST...

引用

43rd Chinese control Conference, CCC 2024

作者： Chang, Yunshui Zhang, Zhengteng Du, Yaxun Jilin Institute of Chemical Technology College of Information and Control Engineering Jilin132022 China Beihua University College of Electrical and Information Engineering Jilin132013 China

ISBN: (纸本)9789887581581

With the rapid development of the Internet, Chinese addresses are widely present online. However, their complexity and diversity make traditional methods challenging for accurate identification. To address this issue, this paper proposes a Chinese address named entity recognition method based on the BERT-BiLSTM-ATT-CRF model. This model combines BERT's contextual understanding, BiLSTM's sequence modeling, Attention's emphasis focus, and CRF's sequence labeling capabilities, enabling more accurate identification of address entities from Chinese text. Experimental results demonstrate significant progress of the model in Chinese address named entity recognition tasks, improving accuracy, recall, and F1 score for address information identification. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： BERT BiLSTM Chinese address Named Entity Recognition

来源：评论

学校读者我要写书评

暂无评论

An Integrated Seismic Assessment Method for Urban Buildings and Roads

引用

International Journal of Disaster Risk Science 2024年第6期15卷 935-953页

作者： Siwei Zhang Shuang Li Changhai Zhai Jia Xiao Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of TechnologyHarbin 150090China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin 150090China

Seismic simulation of urban buildings and roads is significant for regional pre-disaster mitigation and post-disaster *** consider the interrelated influences of buildings and roads,an integrated seismic assessment method for urban buildings and roads is *** seismic damages of buildings were assessed using various methods based on structural characteristics and different degrees of available building *** physical and topological characteristics of the road network are considered in the proposed method to determine post-earthquake road network traffic *** quantitatively evaluate post-earthquake road network traffic capacity,we comprehensively considered the seismic damage to roads,blockages caused by earthquake-induced debris,and the potential risk of falling debris from damaged *** proposed integrated seismic assessment method was applied to a real earthquake event to demonstrate its feasibility and effectiveness,and also applied to a real city,of which information on buildings and roads was based on open-source data and statistical data,to demonstrate its *** proposed method provides a solid prediction on the seismic performance of urban buildings and road networks,serving as a reference for urban earthquake disaster rescue and relief.

关键词： Earthquake-induced debris Integrated seismic assessment Post-earthquake road traffic capacity Seismic structural damage Urban areas

来源：评论

学校读者我要写书评

暂无评论

An optimization algorithm for active noise control in stamping workshop based on maximum correntropy criterion 24

An optimization algorithm for active noise control in stampi...

引用

6th International Conference on control and Computer Vision, ICCCV 2024

作者： Yang, W.W. Wang, D.X. Cao, Y.D. Zhou, C.X. Tan, H. Liaoning University of Technology School of Electronics & Information Engineering China Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control China

ISBN: (纸本)9798400718045

Aiming at the actual industrial production environment with strong noise in the stamping workshop, an active noise control algorithm of Volterra filter based on noise prediction technology and maximum correntropy criterion is proposed. The algorithm adds noise prediction and time delay estimation to compensate the noise signal, and inputs the compensated signal into the noise reduction system, which effectively solves the time delay problem in the system. At the same time, the second-order Volterra filter is selected as the adaptive controller to overcome the nonlinear problem in the system. In addition, the maximum correntropy criterion (MCC) is integrated into the system operation process, which is used to adaptively adjust the step size of the noise reduction system and the update process of the overall weight. At the same time, according to the change of the variance of the reference signal sample, the kernel size of the MCC is flexibly adjusted to ensure that the algorithm can operate efficiently and robustly in a complex noise environment. Comparative experimental results show that the proposed algorithm has a better noise reduction effect compared to traditional algorithms when dealing with complex noises in real environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Active noise control

来源：评论

学校读者我要写书评

暂无评论

Non-destructive detection of chicken freshness based on multiple features image fusion and support vector machine

引用

International Journal of Agricultural and Biological engineering 2024年第6期17卷 264-272页

作者： Xiuguo Zou Chengrui Xin Chenyang Wang Yuhua Li Shuchen Wang Wentian Zhang Jiao Jiao Li Steven Su Maohua Xiao College of Artificial Intelligence Nanjing Agricultural UniversityNanjing 210031China College of Engineering Nanjing Agricultural UniversityNanjing 210095China School of Electrical and Control Engineering Xuzhou University of TechnologyXuzhou 221018China Faculty of Engineering and Information Technology University of Technology SydneyNSW 2007Australia

With the rise in global meat consumption and chicken becoming a principal source of white meat,methods for efficiently and accurately determining the freshness of chicken are of increasing importance,since traditional detection methods fail to satisfy modern production needs.A non-destructive method based on machine vision and machine learning technology was proposed for detecting chicken breast freshness.A self-designed machine vision system was first used to collect images of chicken breast samples stored at 4℃ for 1-7 *** Region of Interest(ROI)for each image was then extracted and a total of 700 ROI images were *** color features were extracted from two different color spaces RGB(red,green,blue)and HSI(hue,saturation,intensity).Six main Gray Level Co-occurrence Matrix(GLCM)texture feature parameters were also calculated from four *** Component Analysis(PCA)was used to reduce the dimension of these 30 extracted feature parameters for multiple features image *** principal components were taken as input and chicken breast freshness level as output.A 10-fold cross-validation was used to partition the *** machine learning methods,Particle Swarm Optimization-Support Vector Machine(PSO-SVM),Random Forest(RF),Gradient Boosting Decision Tree(GBDT),and Naive Bayes Classifier(NBC),were used to establish a chicken breast freshness level prediction *** these,SVM had the best prediction effect with prediction accuracy reaching *** results proved the feasibility of using a detection method based on multiple features image fusion and machine learning,providing a theoretical reference for the nondestructive detection of chicken breast freshness.

关键词： chicken freshness color space gray level co-occurrence matrix multiple features image fusion machine learning

来源：评论

学校读者我要写书评

暂无评论

A method for locating noise sources in an industrial environment 24

A method for locating noise sources in an industrial environ...

引用

6th International Conference on control and Computer Vision, ICCCV 2024

作者： Tan, H. Wang, D.X. Cao, Y.D. Zhou, C.X. Yang, W.W. Liaoning University of Technology School of Electronics & Information Engineering China Tianjin University of Technology and Education Tianjin Key Laboratory Of Information Sensing And Intelligent Control China

ISBN: (纸本)9798400718045

An improved inverse convolution beamforming algorithm based on compressed matched sample tracking (ICoSaMP-DAMAS) is proposed for real industrial production environments with strong noises such as stamping shops. In order to improve the accuracy of noise source localization, the algorithm firstly decomposes the mutual spectrum matrix of the microphone array by features, and then filters out the possible noise components corresponding to smaller eigenvalues, constructs the higher-order matrix function, and optimizes the inverse convolution beam formation by combining with Tikhonov regularization;secondly, in order to shorten the algorithm’s computation time, the adaptive iterative threshold segmentation is used to preprocess the ambient noise with a smaller sound pressure level;finally, the Then it is improved by using compression perception, and the algorithm of using compressed matched sampling tracking to de-solve the anti-convolution equation (ICoSaMP-DAMAS) is proposed. The experimental results prove the effectiveness of the algorithm. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Accelerated SBR Method Based on MPI for Electromagnetic Scattering Problems

Accelerated SBR Method Based on MPI for Electromagnetic Scat...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Wu, Yang Zhu, Qiangqiang Wang, Sifan Xu, Ruofeng Zhao, Lei Shen, Ziang China University of Mining and Technology School of Information and Control Engineering Xuzhou China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing China

ISBN: (纸本)9798350355581

This paper presents a method called Shooting and Bouncing Rays (SBR) employing the Message Passing Interface (MPI) to address electromagnetic scattering issues arising from complex and electrically large targets. The accuracy of the proposed method has been validated by comparing the simulated results with those obtained from the multilevel fast multipole method (MLFMM). And a good speedup ratio has been achieved for SBR with MPI. © 2024 IEEE.

关键词： Electromagnetic wave scattering

来源：评论

学校读者我要写书评

暂无评论

A Model-free Combined Energy and Thermal Management Strategy for HEVs Based on Reinforcement-Learning Under Low-Temperature

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Li, Kai Chen, Hong Wu, Yuhu Zhao, Jing Ding, Shihong Gao, Jinwu Changchun China Changchun China School of Control Science and Engineering Dalian University of Technology Dalian China Department of Electromechanical Engineering University of Macau Macau China School of Electrical and Information Engineering Jiangsu University Zhenjiang China

To improve vehicle adaptability to low-temperature environments, this paper proposes a combined energy and thermal management strategy (C-ETM) based on twin delayed deep deterministic policy gradient (TD3) algorithm for hybrid electric vehicles (HEVs). First, a vehicle energy management system (EMS) model and a engine-battery-cabin coupled thermal management system (CTMS) model are developed. By analyzing the coupling relationship between the CTMS and the EMS, a multiobjective optimization problem is constructed to minimize fuel consumption and battery aging damage and ensure SOC stability. Facing the challenges of solving optimization problems caused by the high-order complex nonlinearity of thermal-electrical coupling systems, the optimization problems are transformed into a Markov decision process (MDP). A reinforcement learning framework based on the TD3 algorithm is designed to achieve a real-time solution to the problem from a new perspective, overcoming the reliance on the system models and accurate future traffic information. The proposed strategy has efficient performance in terms of fuel economy, battery life, ensuring SOC stability, and adaptability. The total optimization cost reaches 91.42% level of the dynamic programming (DP) strategy, which is 30.3% lower than the model predictive control (MPC) strategy. The online computing burden is only 0.19% of the MPC strategy, which has strong potential for real-time applications. IEEE

关键词： Waste heat

来源：评论

学校读者我要写书评

暂无评论

Enhanced Nature Inspired-Support Vector Machine for Glaucoma Detection

引用

Computers, Materials & Continua 2023年第7期76卷 1151-1172页

作者： Jahanzaib Latif Shanshan Tu Chuangbai Xiao Anas Bilal Sadaqat Ur Rehman Zohaib Ahmad Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information TechnologyBeijing University of Technology100124BeijingChina College of Information Science Technology Hainan Normal UniversityHainan ProvinceHaikou571158China Department of Computer Science University of SalfordManchesterUK Faculty of Information Technology Beijing University of Technology Chaoyang District BeijingChina

Glaucoma is a progressive eye disease that can lead to blindness if left *** detection is crucial to prevent vision loss,but current manual scanning methods are expensive,time-consuming,and require specialized *** study presents a novel approach to Glaucoma detection using the Enhanced Grey Wolf Optimized Support Vector Machine(EGWO-SVM)*** proposed method involves preprocessing steps such as removing image noise using the adaptive median filter(AMF)and feature extraction using the previously processed speeded-up robust feature(SURF),histogram of oriented gradients(HOG),and Global *** enhanced Grey Wolf Optimization(GWO)technique is then employed with SVM for *** evaluate the proposed method,we used the online retinal images for glaucoma analysis(ORIGA)database,and it achieved high accuracy,sensitivity,and specificity rates of 94%,92%,and 92%,*** results demonstrate that the proposed method outperforms other current algorithms in detecting the presence or absence of *** study provides a novel and effective approach to Glaucoma detection that can potentially improve the detection process and outcomes.

关键词： Glaucoma detection grey golf optimization support vector machine feature extraction image classification

来源：评论

学校读者我要写书评

暂无评论

Self-Contrastive Learning Fault Diagnosis Network for Signal Imaging: A Case Study

Self-Contrastive Learning Fault Diagnosis Network for Signal...

引用

2024 China Automation Congress, CAC 2024

作者： He, Wenbin Mao, Jianxu Wang, Yaonan Li, Zhe Yan, Feng Liu, Kexin College of Electrical & Information Engineering National Engineering Research Center of Robot Visual Perception & Control Technology Hunan University Hunan China College of Control Science & Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang China

ISBN: (纸本)9798350368604

The deep convolution method based on MSDP signal imaging has been proven to be an effective means of monitoring the robot grinding process. This method has very high requirements on the quality of imaging and requires a lot of computing resources. This paper proposes an image self-contrastive learning network that can effectively extract fault information from low-pixel fuzzy images and achieve efficient and accurate condition monitoring. The network first calculates the correlation distance matrix between two identical modified symmetrized dot pattern (MSDP) images and uses the generated similarity labels to calculate the contrast loss to extract the embedded features of the image. Finally, the classification network is trained using the cross entropy loss to achieve the classification of fault images. The method was verified on a robotic grinding platform to significantly reduce the calculation time while maintaining the recognition accuracy, which provides reliable technical support for the real-time monitoring of the robotic grinding process. © 2024 IEEE.

关键词： Contrastive Learning fault diagnosis robotic grinding signal imaging

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：