检索结果-内蒙古大学图书馆

An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

Computers, Materials & Continua 2024年第8期80卷 3333-3349页

作者： Ruobing Zuo Xiaohan Huang Xuguo Jiao Zhenyong Zhang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou310027China Key Laboratory of Computing Power Network and Information Security Ministry of EducationQilu University of Technology(Shandong Academy of Sciences)Jinan250353China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang550025China

In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation *** growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative ***,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection *** paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking ***,we develop a novel dataset to fill the gap,as there is a lack of publicly available *** dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor ***,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing ***,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency *** show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.

关键词： YOLOv5s smoke detection deep learning SENet

来源：评论

学校读者我要写书评

暂无评论

Barrier Lyapunov Function-Based Finite-Time Dynamic Surface control for Output-Constrained Nonstrict-Feedback Systems

引用

Journal of Systems science & Complexity 2023年第2期36卷 524-539页

作者： YU Jinpeng FU Cheng LIU Jiapeng MA Yumei The College of Automation Qingdao UniversityQingdao 266003China Shandong Key Laboratory of Industrial Control Technology Qingdao UniversityQingdao 266003China The School of Control Science and Engineering Shandong UniversityJinan 250100China

This paper investigates a finite-time tracking problem for the uncertainty nonlinear systems in nonstrict-feedback form,in which the output signal is restricted in a *** on the barrier Lyapunov function and dynamic surface control scheme,a novel adaptive neural controller is proposed by using the finite-time Lyapunov *** the aforementioned literature on finite time tracking control,the violation of system output constraint is avoided by combining the barrier Lyapunov function method with finite-time *** structural characteristics of neural network is introduced to expand the adaptive neural finite-time backstepping method to the uncertainty nonlinear systems in the non-strict ***,the dynamic surface control is introduced to cope with the problem of“explosion of complexity”inherent in conventional backstepping *** is shown that the designed controller can achieve finite-time tracking control and all the variables in the closed-loop system are bounded with output constraint guaranteed form stability analysis and simulation results.

关键词： Adaptive neural network control explosion of complexity finite-time tracking nonstrictfeedback form

来源：评论

学校读者我要写书评

暂无评论

Residual Tensor Train: A Quantum-Inspired Approach for Learning Multiple Multilinear Correlations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1101-1113页

作者： Chen, Yiwei Pan, Yu Dong, Daoyi Zhejiang University Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China University of New South Wales School of Engineering and Information Technology CanberraACT2600 Australia

states of quantum many-body systems are defined in a high-dimensional Hilbert space, where rich and complex interactions among subsystems can be modeled. In machine learning, complex multiple multilinear correlations may also exist within input features. In this article, we present a quantum-inspired multilinear model, named residual tensor train (ResTT), to capture the multiple multilinear correlations of features, from low to high orders, within a single model. ResTT is able to build a robust decision boundary in a high-dimensional space for solving fitting and classification tasks. In particular, we prove that the fully connected layer and the Volterra series can be taken as special cases of ResTT. Furthermore, we derive the rule for weight initialization that stabilizes the training of ResTT based on a mean-field analysis. We prove that such a rule is much more relaxed than that of tensor train (TT), which means that ResTT can easily address the vanishing and exploding gradient problem that exists in the existing TT models. Numerical experiments demonstrate that ResTT outperforms the state-of-the-art tensor network and benchmark deep learning models on MNIST and Fashion-MNIST datasets. Moreover, ResTT achieves better performance than other statistical methods on two practical examples with limited data, which are known to have complex feature interactions. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Influences of clean fracturing fluid viscosity and horizontal in-situ stress difference on hydraulic fracture propagation and morphology in coal seam

引用

International Journal of Coal science & technology 2024年第3期11卷 159-175页

作者： Gang Wang Shuxin Wang Yixin Liu Qiming Huang Shengpeng Li Shuliang Xie Jinye Zheng Jiuyuan Fan College of Safety and Environmental Engineering Shandong University of Science and TechnologyQingdao266590China Mine Disaster Prevention and Control-Ministry of State Key Laboratory Breeding Base Shandong University of Science and TechnologyQingdao266590China

The viscosity of fracturing fluid and in-situ stress difference are the two important factors that affect the hydraulic fracturing pressure and propagation morphology. In this study, raw coal was used to prepare coal samples for experiments, and clean fracturing fluid samples were prepared using CTAB surfactant. A series of hydraulic fracturing tests were conducted with an in-house developed triaxial hydraulic fracturing simulator and the fracturing process was monitored with an acoustic emission instrument to analyze the influences of fracturing fluid viscosity and horizontal in-situ stress difference on coal fracture propagation. The results show that the number of branched fractures decreased, the fracture pattern became simpler, the fractures width increased obviously, and the distribution of AE event points was concentrated with the increase of the fracturing fluid viscosity or the horizontal in-situ stress difference. The acoustic emission energy decreases with the increase of fracturing fluid viscosity and increases with the increase of horizontal in situ stress difference. The low viscosity clean fracturing fluid has strong elasticity and is easy to be compressed into the tip of fractures, resulting in complex fractures. The high viscosity clean fracturing fluids are the opposite. Our experimental results provide a reference and scientific basis for the design and optimization of field hydraulic fracturing parameters.

关键词： Clean fracturing fluid Hydraulic fracturing Viscosity Horizontal in-situ stress difference Hydraulic fracture morphology Acoustic emission

来源：评论

学校读者我要写书评

暂无评论

Tailored gradient nanocrystallization in bulk metallic glass via ultrasonic vibrations

引用

材料科学技术（英文版） 2025年第7期210卷 109-120页

作者： Yu Zhang Sajad Sohrabi Xin Li Shuai Ren Jiang Ma School of Materials Science and Engineering Wuhan University of TechnologyWuhan 430070China Shenzhen Key Laboratory of High Performance Nontraditional Manufacturing College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen518060China Shenzhen Key Laboratory of High Performance Nontraditional Manufacturing College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen518060China

To advance materials with superior performance,the construction of gradient structures has emerged as a promising *** this study,a gradient nanocrystalline-amorphous structure was induced in Zr46Cu46Al8 bulk metallic glass(BMG)through ultrasonic vibration(UV)*** a 20 kHz ultrasonic cyclic loading in the elastic regime,controllable gradient structures with varying crystallized volume fractions can be achieved in less than 2 s by adjusting the input UV *** contrast to tradi-tional methods of inducing structural gradients in BMGs,this novel approach offers distinct advantages:it is exceptionally rapid,requires minimal stress,and allows for easy tuning of the extent of structural gradients through precise adjustment of processing *** tests reveal higher hard-ness near the struck surface,attributed to a greater degree of nanocrystal formation,which gradually di-minishes with *** a result of the gradient dispersion of nanocrystals,an increased plasticity was found after UV treatment,characterized by the formation of multiple shear *** in-vestigations suggest that UV-induced nanocrystallization originates from local atomic rearrangements in phase-separated Cu-rich regions with high diffusional *** study underscores the tunability of structural gradients and corresponding performance improvements in BMGs through ultrasonic energy modulation,offering valuable insights for designing advanced metallic materials with tailored mechanical properties.

关键词： Bulk metallic glass Nanocrystallization Ultrasonic vibration Plasticity Structural heterogeneities

来源：评论

学校读者我要写书评

暂无评论

Anti-Windup Active Power control for Wind Turbines Considering Loads Reduction 13

Anti-Windup Active Power Control for Wind Turbines Consideri...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Wang, Guozhong Luo, Hao Jiao, Xuguo Yang, Zhibo Zhao, Xinxin School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

In recent years, the proportion of wind power in electricity contribution is increasing, and wind power generation technology has developed rapidly. How to enhance the stability of wind turbine systems and extend their service life are still challenging problems due to uncertain and intermittent characteristics of natural wind. In order to ensure that variable speed wind turbines track the active power instructions released by the power system, an improved anti-windup rotor speed control strategy is designed to switch different control strategies according to the wind turbine rotor speed value, with the aim of optimizing the mechanical loads of pitch systems. Firstly, in the low wind speed region, the maximum wind energy capture is achieved by optimal torque control. When the rotor speed increases to a critic value, torque control determined by the turbine's rated output power and rotor speed is adopted. In the high wind speed region, the pitch controller is used to adjust the wind energy capture coefficient to maintain the rotor speed at its rated value. Moreover, in order to solve the problem of integral saturation in traditional rotor speed control methods, this paper proposes a bounded constraints assisted Proportional-Integral (PI) pitch angle control scheme to optimize the operation of pitch system. This control method can effectively eliminates integral saturation, mitigate fatigue loads of wind turbines, reduces overshoot of rotor speed and ensures safe and stable operation of wind turbines. Finally, the proposed method is simulated on OpenFAST platform to verify its advancement. © 2024 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Strong Structural controllability Based on Leader-Follower Framework

引用

Journal of Systems science & Complexity 2023年第4期36卷 1498-1518页

作者： QI Wei JI Zhijian LIU Yungang LIN Chong Insitute of Complexity Science College of AutomationQingdao UniversityQingdao 266071China Shandong Key Laboratory of Industrial Control Technology Qingdao UniversityQingdao 266071China School of Control Science and Engineering Shandong UniversityJinan 250061China

In this paper,the strong structural controllability of the leader-follower framework is ***,the authors analyze different edge augmentation methods to preserve the strong structural controllability of the path-bud *** following four cases are considered:Adding edges from the path to the bud;adding edges from the bud to the path;adding the reverse or forward edges to the path or bud;and adding both the reverse and forward edges to the path or *** sufficient conditions are derived for the strong structural controllability of the new topologies which are generated by adding different *** addition,it is proved that rank[A B]=n is a necessary condition for the strong structural ***,three examples are given to verify the effectiveness of the main results.

关键词： Edge augmentation leader-follower framework path-bud topology strong structural controllability

来源：评论

学校读者我要写书评

暂无评论

Interval Weight state Update Approach with Deep Reinforcement Learning for Dynamic Load Change Tasks in Air Separation Processes 13

Interval Weight State Update Approach with Deep Reinforcemen...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Qiu, Ruiyu Yang, Guanghui Xu, Zuhua Shao, Zhijiang College of Control Science and Engineering Zhejiang University State Key Lab of Industrial Control Technology Hangzhou310027 China HuZhou Research Institute of Industrial Control Technology China

ISBN: (纸本)9798350361674

The air separation unit (ASU) is important for producing high-purity oxygen, nitrogen, and argon, and dynamic load change operation helps meet the needs of downstream industries. The ASU has an extremely long delay, and the requirements for this operation are strict, and model predictive control (MPC) is usually used for this task. However, the burden of online MPC computation is a key issue in improving production and economic efficiency. In this paper, a framework based on Reinforcement Learning (RL) is proposed to solve the long-delayed task in ASU. The state and reward function are specially designed for this task. First, training increases the sampling time of the original model to create a low resolution environment, which makes training more efficient. As a sacrifice, the control precision is reduced in the original high resolution environment. Then, an algorithm called Interval Weighted state Update (IWSU) is proposed to restore the agent and keeps the action accuracy in the original environment. The dynamic load change task works as the case in this paper. The performance of RL is compared with that of MPC, and results show that RL is almost exactly the same as MPC in key flow indicators, and can well meet the remaining content and purity range requirements. IWSU shows good performance compared with directly applying the agent to the original high resolution environment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Accuracy analysis for distributed dynamic state estimation in large-scale systems with a cyclic network graph

引用

science China(Information sciences) 2023年第9期66卷 78-93页

作者： Mingyan ZHU Rui WANG Xiaodong MIAO Tianju SUI School of Control Science and Engineering Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Aeronautics and Astronautics Dalian University of Technology Key Laboratory of Advanced Technology for Aerospace Vehicles School of Mechanical and Power Engineering Nanjing Tech University

This paper addresses a distributed dynamic state estimation problem in large-scale systems characterized by a cyclic network graph. The objective is to develop a distributed estimation algorithm for each node to generate local state estimations, based on the coupled measurements and boundary information exchanged with neighboring nodes. Our proposed approach is grounded in the maximum a posteriori(MAP)estimation method, which yields suboptimal results in acyclic network graphs compared with the centralized MAP approach. We extend this approach to systems with a cyclic network graph. Furthermore, we provide an accuracy analysis by deriving bounds for the differences in estimation error covariance and state estimation between the proposed distributed algorithm and the suboptimal centralized MAP method. These bounds apply to a specific category of systems that satisfy certain conditions, including cyclic topology and sparse connections. We demonstrate that these bounds converge asymptotically, with the rate of convergence determined by the loop-free depth of the graph. The loop-free depth of the graph refers to the maximum number of nodes that can be traversed in a cycle without revisiting any node. Finally, we demonstrate the validity of the algorithm through numerical examples.

关键词： distributed state estimation maximum a posteriori estimation cyclic network graph

来源：评论

学校读者我要写书评

暂无评论

Dynamic Feature Extractor for industrial key Variable Prediction Based on Enhanced Gating Mechanism

Dynamic Feature Extractor for Industrial Key Variable Predic...

引用

2023 China Automation Congress, CAC 2023

作者： Qiu, Cheng Zhang, Xinmin Qian, Jinchuan Zhu, Zheren Song, Zhihuan Chen, Zhichao College of Control Science and Engineering Zhejiang University The State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350303759

In real-world industrial processes, the realtime measurement of key variables is vital to the control of industrial systems. Soft sensing, as a method of predicting key variables using auxiliary variables, has been widely used in industrial environments. To construct an accurate soft-sensing model, the effective extraction of data features is crucial, especially for industrial processes with complex nonlinearity and dynamism. However, traditional dynamic feature extractors often lose information over extended time durations, disappearing with the increase in time-step length through iterations. To address this issue, this study proposes an advanced dynamic feature extractor called ATTENREG-DFE, which has a novel gated mechanism. In addition, in ATTENREG-DFE, the attention mechanism is employed for feature extraction from the input data, and it ensures the inclusion of long-duration information within the output features. To verify the effectiveness of the proposed method, it was applied to actual synthetic ammonia industrial processes, and the experimental results show that the proposed method is superior to other state-of-the-art methods. © 2023 IEEE.

关键词： Ammonia

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：