检索结果-内蒙古大学图书馆

Chinese control and Decision Conference, CCDC

作者： Guowu Zhu Lixiang Ma Bingyou Liu Pan Yang College of Electrical Engineering Anhui Polytechnic University Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Wuhu China Anhui Institute of Information Technology Wuhu China Anhui Dar Intelligent Control System Stock Co. Ltd Wuhu China

In order to preserve the effective information of the image and segment it better, an image segmentation method based on improved wavelet transform is proposed. First, the image is decomposed based on wavelet transform to obtain the horizontal, vertical and diagonal information of the image. Then, the peak and valley points are determined by the decomposed wavelet coefficients, and the segmentation threshold is obtained. Finally, the experimental results show that the improved wavelet transform segmentation method proposed in this paper has better segmentation effect than the traditional segmentation method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

River Turbidity Monitoring Based on Semi-supervised Transfer Learning 9th

River Turbidity Monitoring Based on Semi-supervised Transfe...

引用

9th International Forum on Digital Multimedia Communication, IFTC 2022

作者： Xie, Shuangyi Liao, Xin Bai, Ruxue Zhou, Chengxu Gu, Ke Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Beijing Laboratory of Smart Environmental Protection Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China School of Electronic and Information Engineering Liaoning University of Technology Liaoning China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China

ISBN: (纸本)9789819908554

River turbidity is an important index to evaluate the quality of water environment, which is of great significance to environmental monitoring. Most of the existing monitoring methods rely on turbidity labels measured by river water quality monitoring stations. However, due to the limitation of spatial distribution of water quality monitoring stations, those turbidity data outside the monitoring range are difficult to obtain and the correlation of turbidity data between monitoring stations is poor. Using such data directly might weaken the generalization ability that the model has. In this paper, we propose a new river turbidity monitoring model based on semi-supervised transfer learning (RTMM-SSTL) to solve these problems. First, in the pre-training stage, we innovatively propose a semi-supervised training method combined with big data with pseudo labels for river turbidity monitoring to solve the problem of weakened model generalization ability. Then, the model is fine-tuned using GEE hyper spectral data with ground truth to further improve the monitoring capability of the model. Experiments conducted on the river turbidity monitoring task demonstrate that the proposed model is superior to the advanced learning models, and further proves that our semi-supervised transfer learning method performs better than the state-of-the-art supervision models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Model-Based Prediction of Grinding Surface Roughness With Error Correction via a Knowledge-Based Fuzzy Broad Learning system

引用

IEEE Transactions on Instrumentation and measurement 2025年 74卷

作者： Zewen Hu Hongcai Chen Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China Southeast University Shenzhen Research Institute Shenzhen China

Surface roughness is a key indicator of product quality. Traditional measurement methods generally rely on manual trials and inspections, which are time-consuming and costly. Therefore, developing an accurate and reliable prediction model is vital for automatic grinding, as it enables more informed decision-making, reduces waste, and improves efficiency. However, current model- and data-driven methods suffer from either low accuracy or poor interpretability. To address these challenges, this article proposes an enhanced hybrid framework that integrates a mechanistic model-based predictor with a knowledge-based fuzzy broad learning system (KBFBLS) for error correction. The mechanistic model offers a physically interpretable baseline estimate of surface roughness, while KBFBLS enhances prediction accuracy by learning the mapping from process parameters to the residual errors of the mechanistic model. Built upon the fuzzy broad learning system (FBLS)—an emerging neuro-fuzzy model for efficient nonlinear modeling—KBFBLS integrates expert knowledge-guided fuzzy partition and variance-determined Gaussian membership function (MF) widths, two novel strategies that further improve the system’s expressiveness and adaptability, making it a powerful error corrector. Experimental results on real-world robotic disk grinding tasks show that the proposed framework outperforms representative model-driven, data-driven, and hybrid methods. Furthermore, its adaptability to other machining processes is validated using the wheel grinding and milling datasets.

关键词： Surface roughness Rough surfaces Surface treatment Predictive models Adaptation models Learning systems Training Accuracy Milling Error correction

来源：评论

学校读者我要写书评

暂无评论

ESNet: evolution and succession network for high-resolution salient object detection 24

ESNet: evolution and succession network for high-resolution ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A PSO-RBF neural network for BOD multi-step prediction in wastewater treatment process

A PSO-RBF neural network for BOD multi-step prediction in wa...

引用

2021 China Automation Congress, CAC 2021

作者： Liu, Yonglei Li, Wenjing Faculty of Information Technology Beijing University of Technology Beijing Institute of Artificial Intelligence Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China

ISBN: (纸本)9781665426473

The single-step prediction of the effluent biochemical oxygen demand (BOD) in wastewater treatment process (WWTP) cannot provide the information for future trends, which will affect the decision-making for subsequent control strategies in WWTP. To solve this problem, a radial basis function (RBF) neural network soft-sensing model based on PSO algorithm (PSO-RBF) is proposed for multi-step prediction of the biochemical oxygen demand (BOD) in WWTP. First, we propose an RBF model for multi-step prediction based on MIMO strategy. Then, the PSO algorithm is used to optimize the RBF parameters. Finally, the proposed model is applied to a four-step BOD prediction in WWTP. Experimental results show that this model can better predict BOD in multiple steps compared to traditional models. © 2021 IEEE

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Mesh Stiffness Calculation of Spiral Bevel Gear with Spalling Defect

SSRN

引用

SSRN 2023年

作者： Li, Zhanwei Zhang, Juntao Song, Hansheng Zhu, Rupeng Ma, Hui National Key Laboratory of Science and Technology on Helicopter Transmission Nanjing University of Aeronautics and Astronautics Nanjing210016 China College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China Key Laboratory of Vibration Control of Aero-Propulsion System Ministry of Education Northeastern University Shenyang110819 China

Spiral bevel gears often operate at high speeds and under heavy loads, which can easily lead to the occurrence of spalling faults on the tooth surfaces, particularly in cases of inadequate lubrication. In this study, we introduce an efficient and accurate numerical calculation method to determine the time-varying meshing stiffness (TVMS) of a spiral bevel gear pair with actual spalling faults, taking into consideration the effects of multi-tooth meshing and the flexibility of the gear flank. In parallel, a finite element model is established to verify the accuracy of the proposed method across various spalling parameters. We delve into the impact of spalling length, width, location, and shape. The results demonstrate that the TVMS values obtained from our proposed method align closely with those obtained using the finite element method. The range of TVMS reduction caused by the spalling fault is primarily determined by the spalling location and width. Moreover, the magnitude of TVMS decline is strongly associated with the spalling length. Furthermore, the clearances between two conjugated tooth surfaces change due to the presence of the spalling fault, resulting in a redistribution of contact forces on the same contact surface and other meshing tooth surfaces. © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Accurate Identification and Localization of Transmission Lines under complex Lighting for Distribution Network Power Supply Operation Robots

Accurate Identification and Localization of Transmission Lin...

引用

2024 China Automation Congress, CAC 2024

作者： Liu, Tianhe Chen, Xin Hu, Chenyu Jian, Xu Li, Shengzu Wang, Gang School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan430077 China Distribution Department State Grid Hubei Electric Power Co. Ltd. Wuhan Power Supply Company 430070 China

ISBN: (纸本)9798350368604

Accurate identification and position of transmission lines is critical for robots to safely and effectively perform distribution network operations. However, such tasks are often challenged by complex lighting conditions, where depth information can be easily lost. Transmission lines have limited texture features and reflective surfaces, making it difficult to match image feature points. To address these challenges, this paper proposes a visual perception system for weak texture targets under complex lighting, based on an "eye-on-hand" configuration and a depth complementation algorithm. Furthermore, a high-precision identification and localization method for transmission line grasping points is developed, utilizing the fusion of binocular visual color maps and depth maps. The proposed method has been shown to effectively solve the problem of identifying and localizing the grasping points of transmission lines under complex lighting conditions. Experiments demonstrated that the method can improve the localization accuracy to within ±4mm, outperforming other algorithms. The method is characterized as simple and efficient, and it enhances the environmental adaptability of distribution network robots. © 2024 IEEE.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Research on Methodology for Digital Twin Construction of Powertrain systems Under Time-Varying Conditions

SSRN

引用

SSRN 2024年

作者： Zhang, Dingge Ma, Biao Yu, Liang Xu, Xiaoyu Wang, Liyong Zhang, Jinle School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China School of Software Shandong University Shandong250101 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China China North Vehicle Research Institute Beijing100072 China

The dynamic characteristic investigation of powertrain system under time-varying conditions is highly relied on the dynamic torque signals of each component. However, methods that are sufficiently stable and efficient for obtaining these torque signals have not yet been realized. Thus, a five-dimensional digital twin system, including mechanism, behavior, geometric, statistical, and self-learning models, is established as a virtual mapping of physical system. These models are used to define solution methods, quantify characteristics, visualize displays, statistical analysis, and predict states, respectively. Then, a digital twin monitoring platform is established based on the virtual-real mapping, which can visualize dynamic characteristics of each component based on MQTT protocol. Moreover, the twin signals are verified from the perspectives of dynamics and kinematics through bench and real vehicle experiments, where the relative errors are less than 10%. In addition to the dynamic speed-torque signals of each component, twin signals also include jerk and sliding friction work used to evaluate the shifting quality. Through specific examples, it is demonstrated that the operating state for powertrain system can be monitored and evaluated based on all these twin signals, thus providing sufficient data support for further decision-making and feedback. © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Real-time coordinated control of long-term voltage stability in power grid with VSC-MTDC considering time response characteristics of components

Real-time coordinated control of long-term voltage stability...

引用

2020 IEEE Power and Energy Society General Meeting, PESGM 2020

作者： Gong, Shuai Zhang, Wen Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education School of Electrical Engineering Jinan China

ISBN: (纸本)9781728155081

Considering power grid with VSC-MTDC(Voltage Source Converter based Multi-terminal DC) and time response characteristics of components, a real-time coordinated control method of long-term voltage stability in AC/DC power grid is proposed. Firstly, the control components of AC/DC system considering time response characteristics are established, and then based on trajectory sensitivity, a receding horizon optimization of model predictive control (MPC) is established with the objective of minimizing the deviation of voltage trajectories, the control cost, reactive power margin sharing of generators, and reactive power of VSC-MTDC. According to the recovery of the lowest voltage of the system, different reactive power strategies are proposed. The simulation results of AC/DC hybrid system show that the control method proposed in this paper can fully coordinate all kinds of control means of AC/DC system, improve the long-term voltage stability of the system, and optimize the reactive power of the system. © 2020 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Method for Improving SLAM Localization Accuracy Based on Point-Line Feature

SSRN

引用

SSRN 2023年

作者： Pei, Haodong Zhang, Jin Hong, Lu Zhang, Rui Li, Weishi Xia, Haojie School of Instrument Science and Opto-electronics Engineering Hefei University of Technology Hefei230009 China Anhui Province Key Laboratory of Measuring Theory and Precision Instrument Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

In this article, we propose a visual SLAM positioning accuracy improvement method based on point and line features. Our method leverages the perspective and photometric invariance of point features and the local gradient adaptability of line features to handle low-texture and repetitive-texture scenarios, where point features alone are not reliable. However, line features may suffer from endpoint uncertainty due to occlusion and other factors, which affects the re-projection error calculation based on their direction vectors. This leads to some line features degrading along the camera direction. To tackle this issue, we analyze the causes of line feature degradation and propose a method to identify and filter out these degraded line features. We evaluate our method on the TUM RGB-D benchmark and a real dataset and show that it can effectively reduce the trajectory error of visual SLAM based on point and line features. © 2023, The Authors. All rights reserved.

关键词： Textures

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：