检索结果-内蒙古大学图书馆

6th International Conference on Information Technologies and Electrical engineering, ICITEE 2023

作者： Lin, Bingrong Yang, Zhi Yang, Minsheng Xie, Xiaole Wang, Xiong Liu, Huiting Lan, Yang College of Computer and Electrical Engineering Huan University of Arts and Science China College of Computer and Electrical Engineering Huan University of Arts and Science Key Laboratory of Distributed Electric Propulsion Vehicle Control Technology China

ISBN: (纸本)9798400708299

Handwritten digit recognition technology is increasingly used in a wide range of fields, but the recognition rate still has room for further improvement. Currently, there are a large number of studies focusing on the use of activation functions to improve the handwritten digit recognition rate, compared with ReLU, Sigmod and other activation functions, this paper chooses to take the Mish activation function to optimise the handwritten digit recognition algorithm, using Pytorch machine learning framework, designed a deep convolutional neural network model based on the MNIST dataset to carry out digit recognition, and to improve the accuracy of model recognition through the learning of image features for digit classification to improve the model recognition accuracy. The experimental results show that the Mish activation function can increase the accuracy of handwritten digit recognition to 99%. keywords: Handwritten digit recognition, Deep convolutional neural network, Mish activation function, MNIST Dataset, Pytorch © 2023 ACM.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection of Wooden Boards Based on Multi-Modal Fusion

Surface Defect Detection of Wooden Boards Based on Multi-Mod...

引用

2023 China Automation Congress, CAC 2023

作者： Zhang, Hongchuan Zheng, Song Zhu, Yuhang Lin, Ye Ai, Zhijie Xu, Zhezhuang Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing College of Electrical Engineering and Automation Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350303759

Automated wood defect detection is of great significance for improving wood utilization. However, the stains on the wood surface resemble defect features and it is difficult to distinguish the appearance of wane from defect-free regions. Relying solely on machine vision for extracting surface features of wood makes it difficult to achieve accurate defect detection. To address these challenges, we propose MMDNet, a multimodal detection network that combines point cloud and image data. By adaptively fusing point cloud and image features at multiple stages, the network effectively highlights wood surface defect regions. Additionally, we introduce an Atrous Spatial Pyramid Pooling (ASPP) module into the network, which expands the network's receptive field and enables a comprehensive perception of the defects. Furthermore, we employ a deep supervision strategy to encourage the network to learn discriminative feature representations, enhancing the model's ability to differentiate defect regions. Experimental results validate the effectiveness of our method in detecting defects that are similar to the background and reducing interference from stains. © 2023 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sliding Mode control for Trajectory Tracking in Four-Wheeled Mobile Robots Under Uncertainties and External Disturbances

Adaptive Sliding Mode Control for Trajectory Tracking in Fou...

引用

Chinese control and Decision Conference, CCDC

作者： Naeem Ajilforoushan Saba Ghorbani Barzegar Yongliang Lin Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

In this paper, we propose an adaptive sliding mode control (SMC) design technique to track the desired trajectory of the skid-steering mobile robots in the presence of model uncertainties and perturbations. To enhance the stability of the robot and ensure accurate trajectory tracking, adaptive rules have been employed to estimate the upper bound of perturbations. This estimation, in turn, serves to stabilize the robot and guarantee the desired trajectory. Moreover, we analyze and calculate the convergence time of the sliding surface, ensuring its convergence within finite time. Additionally, efforts have been made to minimize the chattering phenomenon by smoothing the discontinuity of the sliding surface. Simulation results validate the efficacy of the proposed controller, demonstrating its ability to deliver acceptable performance in diverse scenarios.

关键词： Uncertainty Upper bound Trajectory tracking Perturbation methods Estimation Stability analysis Trajectory

来源：评论

学校读者我要写书评

暂无评论

A Fusion Method of Data-driven and Mechanism Analysis for ICPS Integrated Security control

A Fusion Method of Data-driven and Mechanism Analysis for IC...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Chen, Jingjing Li, Wei Li, Yajie Lanzhou University of Technology College of Electrical and Information Engineering Lanzhou China Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou China

ISBN: (纸本)9798350337754

The coordinated design of comprehensive security control and communication is investigated for an industrial cyber-physical system (ICPS) that incorporates stealthy false data injection (FDI) and actuator faults, using data-driven and mechanism analysis methods. Firstly, replacing the conventional discrete event-triggered communication scheme with an adaptive discrete event-triggered communication scheme (ADETCS), a resilient ICPS framework is developed to combat network FDI attacks and actuator faults. Secondly, based on data-driven technology, the ELM prediction model of the FDI attack is established to reconstruct and compensate for the attack accurately. Then, by employing the affine Bessel-Legendre inequality and the augmented Lyapunov-Krasovskii (L-K) functional, the analytical solutions for the robust observer and integrated safety controller are derived. Lastly, the effectiveness of the proposed approach is validated through a quadruple-tank example. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Research on Abnormal Diagnosis Method of Benzene-ethylene Ratio Double-layer Architecture control System based on OHEncoding-XGBoost

Research on Abnormal Diagnosis Method of Benzene-ethylene Ra...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Cao, Huichao Du, Lei Li, Wei Wang, Shengyu Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou China Lanzhou University of Technology College of Electrical and Information Engineering Lanzhou China

ISBN: (纸本)9798350337754

Aiming at a kind of control system based on MPC-PID double-layer architecture in the process industry, due to the complex structure, existing the correlation between control layers and the coupling between control loops, it is difficult to accurately diagnose anomalies of the system control loop. In this paper, an anomaly diagnosis method based on the OHEncoding-XGBoost algorithm is proposed for the Benzene-ethylene ratio system of the Alkylation unit in the styrene production equipment. For the Benzene-ethylene ratio control system with 1 main-loop and 4 vice-loops, combined with the prior knowledge of the system, 5 working conditions between normal and common anomalies are analyzed. According to the evaluation index of the classification model, the One-Hot classification variable coding method is used to construct the feature matrix, and the hidden abnormal information is revealed. The characteristic matrix is used as the input of the diagnosis algorithm, and the abnormal state of the control loop is used as the output, which realizes the effective diagnosis of the abnormal condition of the double-layer Benzene-ethylene ratio control system. Simulation experiments show that the accuracy of the proposed method is 5.16 % higher than that of the traditional XGBoost abnormally diagnosis model. © 2023 IEEE.

关键词： Benzene

来源：评论

学校读者我要写书评

暂无评论

Analyzing Behavior Data of Students in the Classroom with Association Rule Mining

Analyzing Behavior Data of Students in the Classroom with As...

引用

2023 China Automation Congress, CAC 2023

作者： Zeng, Qingbo Xu, Zhezhuang Zheng, Song Liu, Chi Chai, Qinqin Zhang, Ying College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350303759

Students behavior in the classroom has a close relation with the academic performance of students. With the widespread use of mobile phones, the students are easily distracted by mobile phones during the class. Therefore, analyzing the students behavior in the classroom becomes important to improve the quality of teaching. However, the existing methods for analyzing students behavior in the classroom, such as facial recognition, has low efficiency with large amounts of irrelevant data. And it also raises concerns about privacy and ethical issues. To solve this problem, in this paper, a novel mobile software called EasyClass has been developed to collect and quantify students behaviors. Based on the data collected by EasyClass, we propose to utilize user profiling to study students behavior in the classroom. The clustering algorithm is firstly employed to classify the data and generate semantically tags which describe students behavior in the classroom. Then a sequence and association rule analysis method is used to analyze the behavior tags and generated association rules. The results enable educators and non-expert users to gain a deeper understanding of students behavior in the classroom, and further improve the quality of the classroom teaching. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Efficient and High-quality Neural Implicit RGB-D Surface Reconstruction with Volume Feature Rendering

Efficient and High-quality Neural Implicit RGB-D Surface Rec...

引用

Robotics, control and Automation (ICRCA), International Conference on

作者： Jintao Wan Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province Hangzhou China

ISBN: (数字)9798350344721

ISBN: (纸本)9798350344738

Acquiring high-quality 3D surfaces of indoor scenes is essential for applications in VR/ AR and robotics. Recent advancements in neural implicit surface learning and differ-entiable volume rendering methods have significantly improved the accuracy and completeness of geometry. In our work, we propose a volumn feature rendering method for fast and detailed surface reconstruction from muti-view RGB-D frames. We adopt a hybrid scene representation utilizing muti-resolution hash encoding and two shallow MLPs for fast convergence. We suggest improvements by replacing standard volume rendering with vol-ume feature rendering to optimize speed. Additionally, we employ an adaptive sampling strategy guided by dynamic occupancy grids to accelerate training. We introduce a curvature term to promote surface smoothness and hole filling in untexture areas. Experiments on standard benchmarks show that our method can process room-scale scenes in approximately 10 minutes, achieving a 2x speedup compared to Go-Surf [14] in a memory-efficient way, while maintaining comparable or superior reconstruction quality.

关键词： Training Geometry Surface reconstruction Three-dimensional displays Accuracy Rendering (computer graphics) Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Multi-agent evaluation for energy management by practically scalingα-rank

引用

Frontiers of Information Technology & Electronic engineering 2024年第7期25卷 1003-1016页

作者： Yiyun SUN Senlin ZHANG Meiqin LIU Ronghao ZHENG Shanling DONG Xuguang LAN National Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou 310027China College of Electrical Engineering Zhejiang UniversityHangzhou 310027China National Key Laboratory of Human–Machine Hybrid Augmented Intelligence Xi’an Jiaotong UniversityXi’an 710049China

Currently,decarbonization has become an emerging trend in the power system ***,the increasing number of photovoltaic units distributed into a distribution network may result in voltage issues,providing challenges for voltage regulation across a large-scale power grid *** learning based intelligent control of smart inverters and other smart building energy management(EM)systems can be leveraged to alleviate these *** achieve the best EM strategy for building microgrids in a power system,this paper presents two large-scale multi-agent strategy evaluation methods to preserve building occupants’comfort while pursuing systemlevel *** EM problem is formulated as a general-sum game to optimize the benefits at both the system and building ***α-rank algorithm can solve the general-sum game and guarantee the ranking theoretically,but it is limited by the interaction complexity and hardly applies to the practical power system.A new evaluation algorithm(TcEval)is proposed by practically scaling theα-rank algorithm through a tensor complement to reduce the interaction ***,considering the noise prevalent in practice,a noise processing model with domain knowledge is built to calculate the strategy payoffs,and thus the TcEval-AS algorithm is proposed when noise *** evaluation algorithms developed in this paper greatly reduce the interaction complexity compared with existing approaches,including ResponseGraphUCB(RG-UCB)andαInformationGain(α-IG).Finally,the effectiveness of the proposed algorithms is verified in the EM case with realistic data.

关键词： Energy management Multi-agent deep reinforcement learning Strategy evaluation Power grid system

来源：评论

学校读者我要写书评

暂无评论

Short-Term Traffic Flow Prediction of Highway Tunnels Based on SSA and Improved TSK Fuzzy System

Short-Term Traffic Flow Prediction of Highway Tunnels Based ...

引用

2023 China Automation Congress, CAC 2023

作者： Huang, Zhijing Chen, Kang Xu, Zhezhuang Zeng, Qinbo Xu, Zhibin College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350303759

Aiming at the problem that the traffic flow has an low prediction accuracy due to varying randomness and high nonlinearity, an improved TSK fuzzy neural network prediction model by singular spectrum analysis is ***, the original traffic flow time series can be decomposed into several subseries by singular spectrum analysis (SSA). Then, the Takagi-Sugeno-Kang (TSK) fuzzy system was trained using simulated annealing genetic algorithm (SAGA) and minibatch gradient descent method (MBGD) combined with three techniques (RDA) of regularization, DropRule and *** prediction model of TSK fuzzy neural network is established to predict each subseries independently, and the forecasted traffic flow is obtained by superimposing the prediction results of each subseries. Finally, the traffic flow dataset of expressway tunnels in a city is used to verify the effectiveness of the model. Experimental results can show high traffic flow prediction accuracy of the model, and the model can accurately predict multiple different highway tunnels. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive fuzzy asymptotic control design for MIMO nonlinear systems with state constraints

引用

Journal of control and Decision 2023年第4期10卷 610-623页

作者： Yongchao Liu Bowen Zeng Qidan Zhu Lipeng Wang Institute of Complexity Science School of AutomationQingdao UniversityQingdaoPeople’s Republic of China Shandong Key Laboratory of Industrial Control Technology QingdaoPeople’s Republic of China College of Intelligent Systems Science and Engineering Harbin Engineering UniversityHarbinPeople’s Republic of China

This paper addresses the asymptotic control problem of uncertain multi-input and multi-output(MIMO)nonlinear *** considered MIMO systems contain unknown virtual control coefficients(UVCCs)and state *** Lyapunov function by associating with the lower bounds of UVCCs is presented to counteract the adverse effect deriving from *** state constraints are ensured by utilising the barrier Lyapunov ***,the asymptotic tracking controller is recursively constructed by combining the backstepping technique with fuzzy logic *** remarkable character of the designed controller is that the asymptotic tracking performance can be achieved by introducing some smooth functions into adaptive backstepping *** contrast to the existing results,the conditions on the UVCCs are ***,the new control design is illustrated by a practical example.

关键词： Asymptotic tracking control state constraints bound estimation method nonlinear systems

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：