检索结果-内蒙古大学图书馆

IEEE International Conference on Mechatronics and Automation

作者： Jianniang Qiu Yanjuan Wu Qing Li Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Addressing the challenge of the unmanned ship's susceptibility to external environmental disturbances and the impact of model parameter uncertainty on its control system is paramount. Herein, leveraging the motion characteristics of the unmanned vessel, we establish both its kinematic and dynamic models for a three-degree-of-freedom underactuated system. A finite-time observer-based backstepping sliding mode control approach is crafted to anticipate model uncertainties and environmental perturbations. Incorporating the LOS (line-of-sight) guidance law into the controller design aims to mitigate controller input chatter and enhance convergence speed and tracking precision. Furthermore, a first-order filter signal is employed as a substitute for the virtual control law, thereby circumventing differential explosions triggered by its derivative. Validation of the control algorithm's feasibility and practicality is achieved through rigorous simulation experiments.

关键词： Uncertain systems Backstepping Uncertainty Accuracy Tracking Explosions Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Method and system for testing the working characteristics of vehicle fuel injector

引用

Recent Patents on Mechanical Engineering 2021年第1期14卷 63-74页

作者： Liu, Bin Li, Yanhao Han, Fangfang Qiao, Qian Li, Jianwen Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin300384 China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin300384 China

Background: The vehicle fuel injector directly affects the power performance, emission characteristics and economic efficiency of the engine. At present, several testing standards are stipu-lated on accurate measurement of the working characteristics of fuel injectors. Objective: The purpose of this study is to provide an efficient patent about the method and system for testing the working characteristics of a vehicle fuel injector. Methods: Two key techniques are significant to establish a standard test environment. The patent about the pressure control approach and the injector driving method was proposed. The adaptive fuzzy PID approach was applied to control pressure. An adaptive multi-functional driver was designed and developed for both the voltage-driven and current-driven port fuel injectors. Results: The experiments on the two key technologies were conducted. During the dynamic flow test, the settling time using the system was 1ms. For the static flow test, the settling time was 1 s. The maximum changing rate of pressure fluctuation was 1%. Then, the system was verified by test on the flow characteristics and dynamic response of the voltage-driven and current-driven injectors. The linear deviation of each dynamic flow curve was between ± 3% to ± 6%. Furthermore, the deviation of the dynamic flow curves from the repeated test was small. The maximum deviation of the static flow results was less than 4% and the dynamic response of the injector varied with the change of the pressure. Conclusion: The system meets the requirements of the related standards. The experimental results prove that the system is stable and reliable. © 2021 Bentham Science Publishers.

关键词： Dynamic response

来源：评论

学校读者我要写书评

暂无评论

Multiple Demand Response Models for Integrated Energy systems Based on Electric-Heat Loads

Multiple Demand Response Models for Integrated Energy System...

引用

IEEE International Conference on Mechatronics and Automation

作者： Qing Li Yanjuan Wu Jianniang Qiu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Optimal scheduling of power networks can improve the balance of power loads and the efficiency of energy utilisation by reasonably allocating power resources and controlling the power transmission process, providing reliable power support for socio-economic development. Therefore, it is also crucial to strengthen the research on day-ahead scheduling of power networks. Firstly, considering the response variability of different demand-side resources, a multi-type integrated demand response (IDR) model taking into account price-type and incentive-type is established, secondly, to reduce the impact of source and load forecast errors on IES operation, a dual time-scale optimisation smoo thing model is constructed, and lastly, the arithmetic simulation is set up with different scenarios for comparative analyses.

关键词： Analytical models Renewable energy sources Fluctuations Uncertainty Optimal scheduling Predictive models Supercapacitors

来源：评论

学校读者我要写书评

暂无评论

Based on the Optimization and Performance Evaluation of YOLOv8 Object Detection Model with Multi-backbone Network Fusion

Based on the Optimization and Performance Evaluation of YOLO...

引用

IEEE International Conference on Mechatronics and Automation

作者： Jisong Ye Yanjuan Wu Wang Rong Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

The paper aims to enhance the recognition accuracy of the YOLOv8 object detection model in complex scenarios. To achieve this goal, various high-performance backbone networks, including ResNet50, DenseNet169, ConvNeXt, and EfficientNetv2, are integrated with YOLOv8 to construct four novel detection models: YOLOv8-ResNet50, YOLOv8-DenseNet169, YOLOv8-ConvNeXt, and YOLOv8-EfficientNetv2. These models combine the unique characteristics of each backbone network, aiming to further improve detection accuracy while maintaining YOLOv8's real-time performance. Rigorous experimental validation is conducted on a self-constructed leaf mustard dataset. The experimental results demonstrate that YOLOv8-EfficientNetv2 performs the best among these models, achieving a high accuracy of 95.2% in mAP50 and 85.3% in mAP50:95. Compared with the original YOLOv8, YOLOv8-EfficientNetv2 exhibits improvements of 0.87% and 1.6% in mAP50 and mAP50:95, respectively, significantly enhancing the accuracy of object detection. This research provides novel ideas and methods for the application of YOLO series models in complex scenarios, laying a solid foundation for future object detection research.

关键词： YOLO Training Solid modeling Accuracy Object detection Network architecture Solids

来源：评论

学校读者我要写书评

暂无评论

Parameter Recognition of Solar Cell Model Based on ICOOT Algorithm

Parameter Recognition of Solar Cell Model Based on ICOOT Alg...

引用

IEEE International Conference on Mechatronics and Automation

作者： Wang Rong Yanjuan Wu Jisong Ye Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Solar cell model parameter recognition is crucial for accurate photovoltaic power generation prediction, necessitating high accuracy in identification. To tackle this challenge, we introduce the refined Chicken Optimization Algorithm (ICOOT), specifically tailored for solar cell model parameter identification. Initially, we validate the algorithm's superiority by comparing it against existing algorithms, followed by further evaluation using measured data from Radiation Tolerant Cell (RTC) solar cells. After comparing it with four alternative methods, the superiority of the introduced ICOOT model is clearly demonstrated. We demonstrate its practical applicability by selecting French RTC silicon solar cells for parameter identification. A comparative analysis, including Root Mean Square Error (RMSE), is conducted against six other models, highlighting the proposed model's lower RMSE and broader applicability.

关键词： Analytical models Parameter estimation Accuracy Photovoltaic cells Predictive models Prediction algorithms Silicon

来源：评论

学校读者我要写书评

暂无评论

Research on Optical Power Attenuation Compensation Algorithm of φ-OTDR system 20

Research on Optical Power Attenuation Compensation Algorithm...

引用

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

作者： Liu, Yinhao Zhang, Baofeng Zhang, Zhili TianJin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems No. 391 Binshuixi Road Tianjin300384 China Intelligent Manufacturing Institute TianJin Sino-German University of Applied Sciences No. 2 Yashen Road Tianjin300350 China

ISBN: (纸本)9798350320831

The φ-OTDR technology is an optical fibre sensing method that enables real-time monitoring of fibre vibrations by using optical time domain reflection technology. However, during the process of transmitting signals through optical fibres, the issue of optical power attenuation arises, which ultimately results in a reduction of the long-distance signal recognition ability of the φ-OTDR system. This paper presents an innovative optical power attenuation compensation technique that utilizes the φ-OTDR system to address the challenge of signal attenuation in optical fibre. The proposed solution enhances the long-distance recognition ability of weak signals. To solve the attenuation issue, the polynomial fitting method is used. A comparison between the system's performance with and without a Raman amplifier is presented. To locate signals, mean square error and deviation from the average are utilized, while signal strength is determined by calculating the signal-to-noise ratio after fitting. This approach emphasizes precision in detecting relevant signals and optimizing system performance. The results show that the signal recognition ability of the φ-OTDR system improves significantly with the implementation of this compensation algorithm. © 2023 IEEE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Research on the performance of distance measurement system based on binocular vision

Research on the performance of distance measurement system b...

引用

IEEE International Conference on Mechatronics and Automation

作者： Bibo Jiang Jianyuan Zhang Xueshuai Yang Zhiwei Li CNOOC Ener Tech Equipment Technology Co. Ltd Tianjin China Tianjin Key Laboratory for Control Theory and Applications in Complicated System Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Binocular vision is an important technique in 3D (three-dimensional) reconstruction. Two images captured by binocular camera are used to reconstruct 3D information according to the geometric relationship and optical imaging parameters of binocular camera. In binocular vision system, the focal length, base distance and measuring object distance are mutually restricted, and the measurement accuracy is different under different parameter configurations. In this paper, the parameter selection and measurement performance of binocular vision system are studied. A laser scanning binocular vision measuring device is constructed, and the binocular matching speed is accelerated by actively projecting laser line to the measured object. By extracting the center bright line of the laser bright line fringe in the image for stereo matching, parallax is obtained to calculate the distance of the object. By adjusting the system structure parameters, the influence of the system structure parameters on the ranging performance is analyzed and studied. In this paper, combining experimental analysis with theoretical analysis, the parameter setting conditions of binocular vision system high precision measurement are proposed. It helps to improve the performance of the ranging system by rationally designing the parameters of the binocular ranging system.

关键词： Performance evaluation Three-dimensional displays Accuracy Machine vision Measurement by laser beam Length measurement Cameras

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

Point-voxel dual transformer for LiDAR 3D object detection

引用

Optoelectronics Letters 2025年

作者： Tong Jigang Yang Fanhang Yang Sen Du Shengzhi Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot La-boratory， Tianjin University of Technology， 391 Binshui West Road Department of Electrical Engineering， Tshwane University of Technology

Deep learning for point clouds faces the challenge of their inherent unordered nature， which makes traditional CNN-like methods not directly applicable. However， due to the inherent permutation invariance， transformers provide solutions to unordered points problems faced in LiDAR-based object detection. In this paper， a two-stage LiDAR 3D object detection framework is presented， namely Point-Voxel Dual Transformer (PV-DT3D)， which is a transformer-based method. In the proposed PV-DT3D， point-voxel fusion features are used for proposal refinement. Specifically， in the PV-DT3D， keypoints are sampled from entire point cloud scene and used to encode representative scene features via a proposal-aware voxel set abstraction module. Subsequently， following the generation of proposals by the region proposal networks (RPN)， the internal encoded keypoints are fed into dual transformer encoder-decoder architecture. In 3D object detection， the proposed PV-DT3D is the first to take advantage of both pointwise transformer and channel-wise architecture to capture contextual information from the perspective of spatial and channel dimensions. Experiments conducted on the highly competitive KITTI 3D car detection leaderboard show that， the PV-DT3D achieves superior detection accuracy among state-of-the-art point-voxel-based methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High-Precision Edge Detection Algorithm Based on Improved Sobel Operator-Assisted HED 14

A High-Precision Edge Detection Algorithm Based on Improved ...

引用

14th IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems, CYBER 2024

作者： Yuan, Yeborui Chen, Wenyuan Tang, Jie Yang, Jia School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang State Key Laboratory of Robotics 110016 China University of Chinese Academy of Sciences Beijing100049 China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China

ISBN: (纸本)9798331506056

In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detection (HED) network was proposed, which is named ISAHED here. The algorithm is designed as follows. Firstly, an improved Sobel operator based on the traditional Sobel operator was proposed through adding gradient direction. Then, the image output by the improved Sobel operator is taken as the ground-truth image and as the end-to-end comparison object in a HED-like network. Finally, the ISAHED algorithm outputs edge images with better quality through iterative learning of the HED-like neural network. The experimental results prove that the proposed ISAHED algorithm has better edge detection performance by visually observing the final edge images and further evaluating the values of FOM. This work provides an important reference for the further development of the edge detection technology. © 2024 IEEE.

关键词： Contrastive Learning

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：