检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Sun, Lei Ju, Dongjie Ke, Shi School of Electrical Engineering and Automation Binshui Xidao Extension 391 Tianjin300384 China Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Binshui Xidao Extension 391 Tianjin300384 China

ISBN: (纸本)9798350320831

Image colorization has always been a hot topic in computer vision. Since the emergence of deep learning and its excellent performance in many image-processing tasks, image colorization methods based on convolutional neural networks (CNN) emerge in an endless stream, including automatic colorization methods and A coloring method based on a reference image. In the coloring method based on the reference image, an existing problem is that an algorithm for calculating the similarity between the grayscale image and the reference image needs to be designed to map the color blocks in the reference image to the grayscale image. And we use the attention mechanism to spread color implicitly, and propose an attention-guided image colorization network, which extracts features and corresponding color information from the reference image through a reference encoding sub-network, and simultaneously passes a target encoding sub-network The network extracts grayscale features from grayscale images, uses attention to calculate the correlation between the two types of features, and then restores the features and reconstructs colors through the decoding network. Our method can quickly capture the color of the reference feature, accurately transfer it to the target feature, and effectively solve the problem of small target loss during downsampling. By validating on multiple datasets, the results show that our method is effective, outperforming multiple state-of-the-art image colorization algorithms. © 2023 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Embedded Implementation of a Neural Network emulating Nonlinear MPC in a process control application*

Embedded Implementation of a Neural Network emulating Nonlin...

引用

European control Conference (ECC)

作者： Sebastian Leonow Raphael Dyrska Martin Mönnigmann Department of Mechanical Engineering Automatic Control and System Theory Ruhr-Universität Bochum Bochum Germany

We present the design, training, and implementation of a nonlinear autoregressive neural network for the control of a multi-input, multi-output hydraulic plant. The network mimics the optimal control signals of a nonlinear model predictive controller and is implemented on a low-level microcontroller. While trained with simulation data only, experiments on the real plant show that not only the setpoint tracking, but to some degree also the constraint satisfaction and unmeasured disturbance rejection are adapted by the neural network. In contrast to the optimization-based predictive controller, the neural network easily runs on an ESP32 microcontroller and Micropython with guaranteed evaluation time and still achieves similar control performance as the predictive controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Time-Delay Approach to Extremum Seeking with Large Measurement Delays*

引用

IFAC-PapersOnLine 2023年第2期56卷 168-173页

作者： Xuefei Yang Emilia Fridman Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China. School of Electrical Engineering Tel-Aviv University Israel

In this paper, we present a time-delay approach to gradient-based extremum seeking (ES) with known large distinct measurement delays, for N-dimensional (ND) static quadratic maps. We assume that the Hessian has a nominal known part and norm-bounded uncertainty, the extremum point belongs to a known ball, and the extremum value to a known interval. By using the orthogonal transformation, we first transform the original static quadratic map into a new one with the Hessian containing a nominal diagonal part. By applying a time-delay approach to the resulting ES system, we arrive at the neutral type system with a nominal linear time-delay system. We further present this system as a retarded one and employ variation of constants formula for practical stability analysis. To obtain tight bounds we exploit positivity of the fundamental matrix that corresponds to the nominal system with delays. Explicit conditions in terms of simple scalar inequalities depending on tuning parameters and delay bounds are established to guarantee the practical stability of the ES control systems. An example from the literature illustrates the efficiency of the new approach.

关键词： Extremum seeking Averaging Time-delay Practical stability

来源：评论

学校读者我要写书评

暂无评论

Improvement of the Predictive control Method for the High-Level controller 17

Improvement of the Predictive Control Method for the High-Le...

引用

17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer engineering, TCSET 2024

作者： Budashko, Vitalii Sandler, Albert Glazeva, Oksana Educational and Scientific Institute of Automation and Electrical Engineering National University 'Odessa Maritime Academy' NUOMA Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of the theory of automatic control and computer technology Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of electrical engineering and electronics Odesa Ukraine

ISBN: (纸本)9798331520564

Automation of ship maneuvering in limited sailing conditions usually requires 100% redundancy of thrusters (THRs) of various modifications and their locations in accordance with the matrix. The hierarchy of the motion control system is branched by levels using high-level motion controllers and THRs control distribution algorithms, which allows for a modular design with software, where the high-level controller (HLC) can be designed without comprehensive information about the thruster motors, and the input signal branching and speed limits are handled by the motion controller. But, for certain THRs configurations, this branching leads to the decrease in control efficiency due to the limitation of data on the physical characteristics of the ships and the operation of the motion controller. This research examines different approaches to improving control efficiency using methods of nonlinear predictive control models as a basis for developing motion controllers with decision optimization based on relevant constraints. The implemented branched system is the result of solving two simple problems of ship's motion, which highlight the related problems. The use of different approaches to eliminate the identified shortcomings made it possible to develop the nonlinear controller that combines the motion controller with distributed control of the THRs and ensuring the certain level of system reliability. The modularity of the control system is provided by the expansion of the closed system, which made it possible to achieve an increase in efficiency during the combined mode of operation. The obtained solution of nonlinear control with time-varying constraints made it possible to increase the accuracy of the control with a decrease in the duration of the pause in response to the change of the disturbance within 10% © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

A Time-Delay Approach to Extremum Seeking with Measurement Noise*

引用

IFAC-PapersOnLine 2023年第2期56卷 2413-2418页

作者： Bowen Zhao Xuefei Yang Emilia Fridman Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China. School of Electrical Engineering Tel-Aviv University Israel

In this paper, we present a time-delay approach to extremum seeking (ES) corrupted by white noise for uncertain static quadratic maps. We first apply a time-delay approach to the ES system and arrive at a neutral type time-delay system with stochastic perturbations. Then we further present the latter system as a retarded one and employ the variation of constants formula for the mean-square exponential ultimate boundedness analysis. Under the assumption that the upper bound of the 6th moment of the estimation error is a known arbitrarily large constant L , explicit conditions in terms of simple scalar inequalities depending on the bound L , tuning parameters and the intensity of measurement noise are established to guarantee the mean-square exponential ultimate boundedness of the ES control systems. Comparatively to the existing results for ES with measurement noise via the qualitative analysis, our approach can provide a quantitative analysis and simplify the stability analysis process as well. A numerical simulation is given to illustrate the efficiency of the proposed method.

关键词： Extremum seeking Averaging Measurement noise Mean-square ultimate boundedness

来源：评论

学校读者我要写书评

暂无评论

EBD-YOLO：a lightweight auxiliary driving detection algorithm based on YOLOv5

引用

Optoelectronics Letters 2025年

作者： SUN Lianshuai SHI Tao DING Yao LI Song Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems， School of Electrical Engineer-ing and Automation， Tianjin University of Technology College of Electrical Engineering， North China University of Science and Technology

A lightweight road-assistant detection algorithm， EBD-YOLO， based on YOLOv5s is proposed to address the problems of high model complexity， computation cost， and difficulty in deployment on resource-limited embedded terminals in existing assisted driving detection algorithms. First， lightweight Transformer model EfficientViT was used as the backbone feature extraction network of YOLOv5s model to reduce network parameters and calculation costs. Secondly， a Focal-GIoU Loss function is proposed for bounding box regression to accelerate model convergence and reduce loss. Thirdly， the feature pyramid structure is improved to a weighted bi-directional feature pyramid network (BiFPN) to enhance localization and semantic features. Then， a dynamic head framework is added to unify the attention mechanism with the object detection head to improve its performance. Finally， a Soft-CIoU＿NMS algorithm is proposed in the post-processing stage to enhance occluded targets' localization and detection ability and reduce the missed detection rate. We conducted experiments on the KITTI and BDD100K datasets for autonomous driving， and the results showed that the EBD-YOLO model reduced in size by 38.4% and 37.2%， respectively. In comparison， the computational cost was reduced by 48.1%. As measured by mAP@0.5， the detection accuracy improved by 0.5% and 5.8%， respectively， and mAP@0.5:0.95 improved by 2.8% and 7%， respectively. These improvements satisfied the requirements for deployment on embedded terminals in cars.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Allocating Hybrid Teaching Credit Hours Using Hierarchical Analysis

A Method for Allocating Hybrid Teaching Credit Hours Using H...

引用

System Simulation Technology and its Application (CCSSTA), IEEE China Conference on

作者： Xiangang Meng Xiaojing Li Liang Xu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (数字)9798350366600

ISBN: (纸本)9798350366617

Hybrid teaching combines traditional teaching and flipped classroom, which is a new teaching mode with the advantages of both modes. In hybrid teaching mode, reasonable allocation of credit hours between traditional teaching and flipped classroom is an important issue for the teaching work. This paper first proposes a method of using hierarchical analysis to allocate credit hours for hybrid teaching of Digital Electronic Technology courses. Firstly, we divided hybrid teaching into stage and content layers, and determined the various elements of stage and content layers. Secondly, the requirements of the Analytic Hierarchy Process were applied to organize these two levels, and pairwise importance comparisons were made for each element within the level. Index judgment matrices were established for the stage level and content level, respectively. Then, the calculation steps of the Analytic Hierarchy Process were designed, and matrix operations were used to obtain the normalized weights of each element in the stage and content layers of traditional teaching and flipped classrooms. This weight was used to determine the class hours to be allocated for each stage and content. Finally, the feasibility and effectiveness of the method proposed in this paper were verified using the example of hybrid teaching hour allocation in Chapter 4 of the Digital Electronic Technology course at Tianjin University of Technology.

关键词： Electronic learning Logic circuits Education Analytic hierarchy process Systems simulation Resource management Online services Indexes

来源：评论

学校读者我要写书评

暂无评论

Accelerating Distributed Nash Equilibrium Seeking

Accelerating Distributed Nash Equilibrium Seeking

引用

European control Conference (ECC)

作者： Tatiana Tatarenko Angelia Nedić Department of Control Theory and Intelligent Systems TU Darmstadt German School of Electrical Computer and Energy Engineering Arizona State University USA

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This work proposes a novel distributed approach for computing a Nash equilibrium in convex games with restricted strongly monotone pseudo-gradients. By leveraging the idea of the centralized operator extrapolation method presented in [4] to solve variational inequalities, we develop the algorithm converging to Nash equilibria in games, where players have no access to the full information but are able to communicate with neighbors over some communication graph. The convergence rate is demonstrated to be geometric and improves the rates obtained by the previously presented procedures seeking Nash equilibria in the class of games under consideration.

关键词： Extrapolation Europe Games Nash equilibrium Topology Convergence

来源：评论

学校读者我要写书评

暂无评论

DH Detector: One-stage detection model with double-head detector and efficient convolution

DH Detector: One-stage detection model with double-head dete...

引用

IEEE International Conference on Mechatronics and Automation

作者： Ziyuan Feng Lei Sun School of Electrical Engineering and Automation Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

This article explores advanced techniques to build a network model, including the use of a double-head(DH) detector: one section of which is responsible for performing classification and the other for object prediction. This is followed by information stitching, which allows the model to learn more appropriate parameters. Subsequently, a CSP structure incorporating an attention mechanism is used to improve the feature extraction capabilities of the model. Finally, dynamic convolution is added to enhance the feature representation. Our model is trained from scratch on the COCO Dataset without taking a pre-trained model, the results of which are listed below. Based on 300 epochs of training, the mAP values for the four versions of DH Detector (s, m, l, x, the network model becomes larger in turn) are 40.8, 46.1, 48, and 49.8(100 epoch), respectively. The experiment results show that this method outperforms other competing methods in terms of both quantity and quality. In addition, the mAP of DH-s and DH-l reached 43.0 and 50.1 at an input image size of 960. A comparison of DH Detector with other algorithms is provided in Figure 1.

关键词： YOLO Training Solid modeling Attention mechanisms Convolution Computational modeling Detectors

来源：评论

学校读者我要写书评

暂无评论

Research on Seismic Bracing Monitoring System Based on Wireless Transmission

Research on Seismic Bracing Monitoring System Based on Wirel...

引用

IEEE International Conference on Mechatronics and Automation

作者： Lujia Wang Baofeng Zhang Wei Wang Zhiwei Li Junchao Zhu Tianjin Key Laboratory of Control Theory & Application of Complex Systems School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Real-time data acquisition and monitoring of seismic bracings can help to maintain their effectiveness during service life and to improve the seismic resistance and disaster mitigation effects when strong earthquakes occur. In order to monitor real-time states of the seismic bracing, an intelligent monitoring system based on wireless transmission technology was designed. The system used CC2530 Zigbee module to establish a ZigBee wireless LAN, and combined MEMS vibration sensors and strain gauges. Meanwhile, the system used ESP32 to upload the measurement data to OneNET cloud platform through MQTT wireless communication protocol. The function of data visualization was designed so as to realize real-time monitoring of seismic bracing states. The experimental results showed that the proposed wireless monitoring system can reliably execute real-time data collection, storage, display, and hazard warning to guarantee the effectiveness of seismic bracings.

关键词： Wireless communication Vibrations Wireless sensor networks Wireless LAN Disasters Data visualization Zigbee

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：