检索结果-内蒙古大学图书馆

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Guangming Zhang, Dexiong Lu, Xiaobo Cao, Yichao School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

With the demand for pollution prevention has increased. Establishing a smoky vehicle inspection and evidence collection system will help to supervise the problem of excessive emissions of vehicles. Because the sample in the training data set is insufficient and unbalanced, the existing methods cannot obtain sufficient classification accuracy in the classification task of the smoky vehicle. This paper uses the transfer learning method to compare the effects of smoky car classification tasks on the five basic networks of DenseNet, NasNet, Inception, VGG19, MobileNet. In addition, for the classification task of the smoke vehicle, it is necessary to consider both the global information of the tail of the vehicle and the detailed information of the smoke area. In this paper, the global average pooling layer is changed to the spatial pyramid pooling layer, and it has achieved better results. Finally, the classification Precision nearly 0.1, Recall 0.3 are obtained, which is much better than the traditional classification method and the shallow non-transfer deep learning method. © 2019 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Research on the weak Signal Detection Method Based on Adaptive Vibrational Resonance 35

Research on the weak Signal Detection Method Based on Adapti...

引用

第35届中国控制会议

作者： JIAO Shang-bin SUN Di LIU Ding HUANG Wei Chao National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

ISBN: (纸本)9781509009107

In this paper,the weak signal detection under a stable noise is investigated based on bistable vibrational resonance(VR) which is driven by a high frequency *** the one hand,the energy of the high frequency drive signal is transferred to the low frequency weak signal when VR occurs;on the other hand,the control of stochastic resonance(SR) is achieved based on VR,which transfers more noise energy into useful signal *** addition,considering the requirements of real-time detection,the amplitude and frequency of the high frequency drive signal are optimized by the knowledge-based particle swarm optimization(KPSO),which takes the mean signal-noise-ratio(MSNR) of output as the fitness function,and the property that VR system produces the best resonance effect just when the valid system parameter a(B,Ω) is greater than zero as ***,the parameter compensation is combined to achieve multi-high frequency weak signals detection with a stable ***,the method is applied to the vibration fault diagnosis of a mono-crystalline silicon furnace,and the experiment results show the effectiveness and practicability of the method.

关键词： Adaptive vibrational resonance weak signal detection knowledge-based particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Smart Energy system Based on Machine Learning 10

Evaluation of Smart Energy System Based on Machine Learning

引用

10th IEEE Data Driven control and Learning systems Conference, DDCLS 2021

作者： Cheng, Xuran Chai, Lin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering and School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781665424233

In the context of the gradual shortage of fossil energy and serious pollution, the voice of energy transformation is increasing year by year. With the development of Internet and artificial intelligence, the smart energy is getting more and more attention, and it is also the key direction of the upgrading of the world energy industry. In this process, in order to better understand its development and effectively guide the future construction and development of smart energy, appropriate and reasonable evaluation is essential. In the past few years, some researchers have put forward some evaluation methods for smart energy systems, and have achieved some good results. However, only traditional evaluation methods are used which are more subjective. Therefore, the application of machine learning method in the evaluation of smart energy system is worth trying and studying. Starting from the requirements of energy system and human development, this paper first introduces the emergence and development of smart energy and its evaluation methods. Simultaneously indicating the necessity of evaluation. Then the formation of the evaluation index system is briefly introduced. Secondly, machine learning algorithm models such as support vector machines, decision trees, and BP neural networks used are introduced respectively. Finally, experiments are carried out to train the model, and then comparing and analyzing the results. The final results show that the machine learning method plays a good role in the research of smart energy system evaluation, which is worthy of further research. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accurate Detection and Tracking of Trucks and Truck Drivers 42

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accura...

引用

42nd Chinese control Conference, CCC 2023

作者： Zheng, Xueqin Su, Jinya Yang, Jun School of Automation Southeast University Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9789887581543

An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during the whole working process. In the proposed method, the improved YOLOX performs object detection and its output is used as the input for multi -object tracking using DeepSORT. The improved YOLOX model is developed through replacing standard convolution with depthwise separable convolution, adding the convolutional block attention module to enhance feature extraction, and using Focal Loss in the loss function to address sample imbalances. Comparative experiments were carried out on a self-built dataset, showing a 4.32% increase in mAP and improved reasoning speed for improved YOLOX compared to the original YOLOX. Furthermore, the optimized method shows a 3.57% increase in Multi-Object Tracking Accuracy and a 1.73% increase in Multi-Object Tracking Precision compared to the benchmark YOLOX+DeepSORT. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Scheduling optimization of silicon single crystal production process based on adaptive improved particle swarm optimization

Scheduling optimization of silicon single crystal production...

引用

2021 China Automation Congress, CAC 2021

作者： Kang, Lu Liu, Ding Wu, Yali Ping, Guozheng School of Automation and Information Engineering Xi'an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China School of Automation and Information Engineering Xi'an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China School of Automation and Information Engineering Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China

ISBN: (纸本)9781665426473

Aiming at the potential safety hazards of silicon single crystal production enterprises in the process of multi-furnace silicon single crystal production, and considering the maximum power load requirements in actual enterprises, a silicon single crystal production process scheduling model with the goal of minimizing the maximum completion time was established. Based on this model, an adaptive improved particle swarm optimization algorithm (Adaptive GPSO) is proposed to solve it. The algorithm retains the individual optimal value and global optimal value of the particle swarm algorithm, and introduces the crossover operation and mutation operation in the genetic algorithm to improve the new individual generation mechanism. At the same time, it performs dynamic iterative calculations on the mutation probability and crossover probability to avoid the algorithm fall into the local optimum, and improve the diversity and convergence of the algorithm. By solving different scales scheduling problems of silicon single crystal production process, the experiments on real-world data shows that the feasibility and effectiveness of the proposed algorithm. © 2021 IEEE

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Improved control Strategies for Totem-Pole PFC With True Full Range ZVS Operation

引用

IEEE Transactions on Industrial Electronics 2023年第3期70卷 2419-2430页

作者： Chen, Jie Tai, Weiyu Xun, Benxin Gong, Chunying Chen, Jiawei Nanjing University of Aeronautics and Astronautics Center for More-Electric-Aircraft Power System Ministry of Industry and Information Technology College of Automation Engineering Nanjing211106 China Chongqing University Key Laboratory of Complex System Safety and Control Ministry of Education College of Automation Chongqing400044 China

Zero voltage switching (ZVS) of power semiconductor devices is an effective way to improve the efficiency and power density of the power electronic converters with extremely high switching frequency. This article aims to analyze and realize the true full-range ZVS operation of a totem-pole power factor correction circuit. The available ZVS control strategies are investigated, and the conditions for the realization of full-range ZVS operation are analyzed. It is revealed that the existed control strategies did not consider the influence of the dead-time, resulting in the failure of ZVS operation in some input voltage ranges. To address this issue, two feasible retrofitted control strategies, namely the turn-off current optimization control and the adaptive dead-time control, are proposed. The merits and drawbacks of the two control strategies are carefully analyzed and compared. It is found that the adaptive dead-time control can not only achieve the true full range ZVS but also significantly reduce the loss of the freewheeling diodes. The design consideration of key parameters is discussed. Finally, the feasibility of the proposed control and the correctness of the theoretical analyses are verified by simulation and experiment. © 1982-2012 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Robust Speed Regulation of PMSM Under Disturbances and Noises Using Composite Model Predictive control 42

Robust Speed Regulation of PMSM Under Disturbances and Noise...

引用

42nd Chinese control Conference, CCC 2023

作者： Mao, Linxuan Su, Jinya Li, Shihua School of Automation Southeast University Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9789887581543

This paper presents a single-loop Model Predictive control strategy that incorporates a reduced-order Generalized Proportional Integral Observe and a Kalman filter to enhance the speed regulation of Permanent Magnet Synchronous Motor systems in the presence of complex disturbances and measurement noises. The proposed controller design seamlessly integrates the predictive control, disturbance observer, and state filter components, and it was evaluated through simulation comparisons. The performance of the proposed method is evaluated using various metrics, including maximum velocity drop, recovery time, and variance of steady-state error, which demonstrate its superior response performance and anti-disturbance ability when compared to other existing methods without state filtering. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

An attention convolutional neural network for forest fire smoke recognition 6

An attention convolutional neural network for forest fire sm...

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Dexiong Cao, Yichao Zhang, Guangming Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

In order to find forest fire in time and accurately, the identification of forest fire smoke based on computer vision has become an important research direction. In this paper, a convolutional neural network model based on the attention mechanism is designed for forest fire smoke recognition. By focusing on the regions with obvious discrimination in the image, more precise local features are extracted for fire smoke identification with the auxiliary of backbone network. The performance of network on the unbalanced forest fire dataset is improved by optimizing the cross-entropy loss function with weights. The experimental results show that attention convolutional neural network improves the accuracy of the model which reached 89.3% while reducing false positives and false negatives. © 2019 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Hand-eye servo and flexible control of an anthropomorphic arm

Hand-eye servo and flexible control of an anthropomorphic ar...

引用

2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013

作者： Ma, Gan Huang, Qiang Yu, Zhangguo Chen, Xuechao Meng, Libo Sultan, Malik Saad Zhang, Wen Liu, Yan IRI School of Mechatronical Engineering Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education China Key Laboratory of Intelligent Control and Decision of Complex System China

ISBN: (纸本)9781479927449

One key technology for a humanoid robot is to sense the environment accurately and control the movement of the robot in realtime. This paper addresses this problem and focuses on the visual servoing control of an anthropomorphic robotic arm. A high precision, image-based visual servo algorithm for an eye-in-hand visual system is proposed to control the movement of the anthropomorphic arm. The control objective of the controller is to lock all the feature points at fixed points on the image plane. Then, impedance control law is implemented to keep the flexible of the arm. Finally, the effectiveness of the proposed methods are verified by experiments on our humanoid robotic arm platform. © 2013 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

An online drilling rate of penetration(ROP) optimization method 41

An online drilling rate of penetration(ROP) optimization met...

引用

第41届中国控制会议

作者： Tuo Wang Chao Gan Weihua Cao School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Drilling rate of penetration(ROP) optimization is crucial due to its vital role in increasing the drilling efficiency and decreasing the non-productive *** existing methods seldom pay attention to updating model parameter during drilling,which is actually important for ROP optimization under dynamical and uncertain downhole *** this paper,an online drilling ROP optimization method is proposed via three stages(drilling data pre-processing,online ROP modelling and online optimal operational parameters optimization).In the first stage,drilling data is pre-processed by resampling and Savitzky-Golay *** this,support vector regression and moving-window strategy are introduced together to establish an online ROP model in the next ***,particle swarm optimization algorithm is applied in the online ROP optimization framework to obtain the optimal operational parameters in the last *** results indicated the effectiveness of the proposed method.

关键词： Rate of penetration Drilling optimization Online optimization Moving-window strategy

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：