检索结果-内蒙古大学图书馆

第35届中国过程控制会议

作者： Yifan Jiang Jinshui Chen Jiangang Lu State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Zhejiang Laboratory

In industrial production, flaw detection in X-ray images is a crucial process to prevent defective tires from entering the market. To address the current issues of low accuracy, false positives and missed detections in tire surface defect detection, we propose a tire defect detection algorithm based on RT-DETR. Firstly, we replace the multi-scale feature fusion network with a more efficient feature focusing and diffusion pyramid network to enhance the network's ability to represent cross-scale features, thereby improving defect detection accuracy. Secondly, we substitute the GIoU loss function with the Inner-WiseIoU loss function for optimizing bounding box regression, enhancing the generalization ability of the loss function and improving the precision of bounding box localization. Experimental results demonstrate that the improved algorithm, compared to the original model, increases the mean Average Precision(mAP)@0.5 by 10.0% and mAP@0.5:0.95 by 8.9%, while maintaining a high Frame rate Per Second(FPS). When compared with algorithms such as YOLOv8 and YOLOv9, our algorithm also achieves higher detection accuracy and competitive real-time performance, indicating its effectiveness.

关键词： Defect detection RT-DETR Feature pyramid Loss function

来源：评论

学校读者我要写书评

暂无评论

基于数据扩充及风力发电机组功率曲线分段回归的自适应监测方法

引用

Journal of Central South University 2023年第5期30卷 1601-1617页

作者：荆华赵春晖 State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Zhejiang University NGICS Platform Hangzhou 310027China

准确的功率曲线可以反映风机的运行状况,在风力发电机组的监测中至关重要。然而,一些新安装的风力发电机组由于没有足够的训练数据来拟合准确的功率曲线,从而导致监测结果不佳。本文提出了一种基于数据扩充的分段回归方法实现对风电机... 详细信息

准确的功率曲线可以反映风机的运行状况,在风力发电机组的监测中至关重要。然而,一些新安装的风力发电机组由于没有足够的训练数据来拟合准确的功率曲线,从而导致监测结果不佳。本文提出了一种基于数据扩充的分段回归方法实现对风电机组的自适应监测,该方法可分为离线建模阶段和在线监测阶段。在离线建模时,首先,设计了一种新的映射函数,通过将其他数据集的数据映射到目标数据集上,从而实现对目标数据集的扩充,进而使得目标风力发电机组有足够的数据用于模型训练。然后,设计了一种分段建模策略,将扩充后数据的信息精炼到少量样本中,再进行功率曲线拟合,可以以较低的计算复杂度准确拟合出功率曲线。在线监测时,可依据功率曲线模型对功率进行预测,最后将预测结果与实际功率进行比较,从而实现对运行状态的监测。此外,我们提出一种增量学习策略,以利用新的数据实时更新模型提高预测和监测的准确度。实验采用真实风电数据,结果表明,所提监测方法能够在数据不足的情况下能准确地发现异常行为,监测准确率可达92.77%。

关键词：功率曲线数据不足映射函数分段建模策略自适应监测方法

来源：评论

学校读者我要写书评

暂无评论

Adaptive modification of turbofan engine nonlinear model based on LSTM neural networks and hybrid optimization method

引用

Chinese Journal of Aeronautics 2022年第9期35卷 314-332页

作者： Yanhua MA Xian DU Ximing SUN School of Microelectronics Dalian University of TechnologyDalian 116024China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of EducationDalian University of TechnologyDalian 116024China School of Control Science and Engineering Dalian University of TechnologyDalian 116024China

An accurate and reliable turbofan engine model which can describe its dynamic behavior within the full flight envelop and lifecycle plays a critical role in performance optimization, controller design and fault diagnosis. However, due to the performance differences caused by the tolerance of engine manufacturing and assembly, and performance degradation during continuously stringent environmental regulations, the model accuracy is severely reduced. In this paper, an adaptive modification method of turbofan engine nonlinear Component-Llevel Model(CLM) based on Long Short-Term Memory(LSTM) Neural Network(NN) and hybrid optimization algorithm is pro-posed. First, a dynamic compensator with a combined LSTM NN architecture is constructed to compensate for the initial error between the experimental data and CLM of a turbofan engine under health condition. Then, a sensitivity analysis approach based on the entropy coefficient and technique for order preference by similarity to an ideal solution integrated evaluation is developed to choose the unmeasurable health parameters to be adjusted. Finally, a parallel hybrid optimization algorithm is developed to complete the adaptive model modification when the performance degrades. The proposed method is verified on a military low-bypass twin-spool turbofan engine, and the experimental results show the effectiveness of the proposed method.

关键词： Hybrid optimization Long short-term memory Model modification and testing Sensitivity analysis Turbofan engines

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2838-2852页

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises' demand for dynamic multi-dimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A Production Plan and Error Feedback DBN-DNN based prediction method for LDG Generation in steel industry 41

A Production Plan and Error Feedback DBN-DNN based predictio...

引用

第41届中国控制会议

作者： Xu Han Feng Jin Jun Zhao Wei Wang Key Laboratory of Intelligent Control and Optimization for Industrial Equipment (Dalian University of Technology) Ministry of Education School of Control Science and Engineering Dalian University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Linz Donawiz converter Gas(LDG) is a kind of important secondary energy source in iron and steel *** prediction of LDG generation may provide guidance for scheduling *** this paper,a two-stage method for predicting LDG generation is *** to the characteristics of LDG generation data,an improved k-means clustering integrating dynamic time warping is proposed to divide the time series data into typical characteristic ***,an error feedback deep belief network(EF-DBN-DNN) model is established to predict the starting time of LDG generation by considering the relationship between production plan and the actual performance,Actual data of LDG system in an iron and steel enterprise are employed to verify the effectiveness of the proposed method,and the results show that the prediction accuracy of the proposed one is suitable for practical application.

关键词： LDG generation production plan improved k-means clustering error feedback DBN-DNN

来源：评论

学校读者我要写书评

暂无评论

A Novel A-ESO Composited Non-Recursive control Methodology for Complex High-Order Disturbed Nonlinear Systems 42

A Novel A-ESO Composited Non-Recursive Control Methodology f...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhang, Cong Liu, Shiji Liu, Shuang School of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066004 China

ISBN: (纸本)9789887581543

This paper mainly focuses on a disturbance rejection control methodology for a series of mismatched and matched disturbed complex systems. Firstly, a novel finite-time arbitrary-order extended state observer (A-ESO) is proposed to accurately estimate the system states, disturbances, and their corresponding order derivatives. And then, a novel concise nonrecursive control ideology utilizing all the estimations of A-ESO is proposed to strictly guarantee finite-time stability and convergence of the whole closed-loop system. Significantly, compared with the existing nonrecursive control methods, the essential characteristic is that all the estimation information is utilized to construct the composite controller. This will be tremendously conducive to cost-saving and promoting practical implementations. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Research on river surface velocimetry monitoring method Based on video surveillance

Research on river surface velocimetry monitoring method Base...

引用

第35届中国过程控制会议

作者： Jiaqi Xu Yining Zhao Xinao Jin Yuqi Cao Guangxin Zhang Dibo Hou State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

The allocation and utilization of water resources have always been the focus of social development concerns. River flow velocity is the basis for flow rate estimation and is very important hydrological information. The most widely used contact flowmeters require manual wading to place the instrument in water, making them difficult to deploy over large areas. In this paper, an optical flow estimation method of river surface velocity detection based on RAFT is constructed to obtain flow velocity and direction information. To solve the interference problem caused by flying insects and birds, a flow velocity and direction outlier identification method based on Gaussian Mixture Model is investigated. Results demonstrate that the method can effectively and accurately realize real-time monitoring of river surface velocity, providing important information for water allocation, flood prevention and control.

关键词： River Surface Velocity Optical Flow Estimation Adaptive Histogram Equalization Gaussian Mixture Model Pixel-Based Adaptive Segmenter

来源：评论

学校读者我要写书评

暂无评论

Two-Degree-of-Freedom control with Linear Extended State Observer for PMSM Drive System 41

Two-Degree-of-Freedom Control with Linear Extended State Obs...

引用

第41届中国控制会议

作者： Kai Lin Ping Lin Bin Yang School of Control Science and Engineering Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In permanent magnet synchronous motors(PMSM) drive system,it is difficult to achieve the optimal performance of command tracking and disturbance rejection simultaneously when the speed loop designed with the conventional one-degree-of-freedom(1-DOF) PI *** solve this problem,this paper proposes a speed control structure of two-degree-of-freedom(2-DOF) P-PI controller with linear extended state observer(LESO).There are two sets of parameters that can be designed independently in the controller,which improves the command tracking performance without degrading the disturbance rejection *** addition,a linear extended state observer(LESO) is designed to estimate the total disturbance in the speed *** to the estimated value,the output of the 2-DOF P-PI controller is compensated feedforward equivalently,which further enhances the disturbance rejection ***,simulations verify the effectiveness of the proposed control strategy.

关键词： permanent magnet synchronous motors(PMSM) two-degree-of-freedom(2-DOF)P-PI linear extended state observer(LESO) disturbance compensation

来源：评论

学校读者我要写书评

暂无评论

Security Offloading Scheduling and Caching Optimization Algorithm in UAV Edge Computing

引用

IEEE Systems Journal 2025年第1期19卷 96-106页

作者： Qiu, Jianli Kuang, Zhufang Huang, Zhenqi Lin, Siyu Central South University of Forestry and Technology College of Computer and Mathematics Changsha410004 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Beijing Jiaotong University State Key Laboratory of Rail Traffic Control and Safety Beijing100044 China

Mobile edge computing, a prospective wireless communication framework, can contribute to offload a large number of tasks to unmanned aerial vehicle (UAV) mobile edge servers. Besides, the demand for server computational resources increasingly ascends as the volume of processing tasks grows. However, in reality, many devices have similar computing tasks and require the same computing data. Therefore, servers can effectively reduce server computing latency and bandwidth costs by caching task data. This investigation explores task security offloading and data caching optimization strategies in scenarios with multiple interfering devices. With the goal of minimizing the total energy consumption, the UAV trajectories, transmission power, task offloading scheduling strategies, and caching decisions is jointly optimized. The corresponding optimization problem, which consists of mixed integer nonlinear programming problem, is formulated. To make this problem solved, the original problem is decomposed into three tiers, and an iterative algorithm named CDSFS which is based on the coordinate descent, successive convex approximation, and flow shop scheduling is proposed. Simulation results demonstrate the stability and superiority of the proposed algorithm. © 2007-2012 IEEE.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Preconditioning Based Iterative Learning control for Initialized Fractional Order Systems with Nonuniform Trial Lengths

Preconditioning Based Iterative Learning Control for Initial...

引用

第35届中国过程控制会议

作者： Xiaofeng Xu Jinshui Chen Jiangang Lu State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

Nonuniform Trial Length is a frequent non-repetitive factor in iterative systems. To maintain the effectiveness of iterative learning control for such systems, this paper proposes a preconditioning based iterative learning control scheme for initialized fractional order nonlinear systems with iteration-varying trial lengths. A generalized system tracking error based on probability distribution is applied to address the uncertain trial lengths. In addition, the system preconditioning strategy is adopted to suppress the unknown initialization responses and maintain the repeatability of system dynamics. On this basis, the convergence condition of a novel Dα-type iterative updating law is strictly derived, and the result shows that the tracking error can converge to any desired range by adjusting the preconditioning horizon. Compared with existing results, the proposed strategy has better applicability and physical interpretability. Finally, a numerical example is presented to demonstrate the theoretical results.

关键词： Fractional Calculus Iterative Learning control System Preconditioning Nonuniform Trial Length

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：