检索结果-内蒙古大学图书馆

42nd Chinese control Conference, CCC 2023

作者： Liu, Feng Cai, Gang Zhou, Feifan Wang, Wei Wang, Hua Yang, Xiuqin School of Automation China University of Geosciences Wuhan430074 China Engineering Research Center of Ministry of Education for Intelligent Technology of Earth Exploration China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan4300748 China Boston University Department of Mechanical Engineering BostonMA02215 United States School of Education Minzu University of China Beijing100081 China

ISBN: (纸本)9789887581543

In this paper, a novel smooth magnetron is introduced to construct a fractional memristor Hopfield neural network (fractional order M-HNN). The local stability of equilibrium point are analyzed theoretically. Taking the memristor coupling strength coefficient and the fractional order as bifurcation parameters, the phase trajectory diagram, the bifurcation diagram of the system are drawn to analyze the influence on the dynamic behavior of the neural network. When the system parameters are fixed, the hyperchaos phenomenon of the fractional order M-HNN model is revealed. Finally, the PD controller is applied to the model to enhance the stability of the system. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Wind Speed Data Repairing Method Based on Bidirectional Prediction

Wind Speed Data Repairing Method Based on Bidirectional Pred...

引用

2021 IEEE International Conference on Power Electronics, Computer Applications, ICPECA 2021

作者： Shen, Xincheng Qu, Yi Huang, Shaoxiong Li, Zhi Zhang, Kaifeng Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China State Grid Anhui Electric Power Co. Ltd Department of Dispatch Center Hefei China

ISBN: (纸本)9781728190037

In order to repair the lost data in distributed wind power system, this paper puts forward a wind speed data repairing model based on a new bidirectional prediction method. This model consists of two one-way prediction models. In each prediction model, the original wind speed data are decomposed into several intrinsic mode functions (IMFs) and a residue signal by ensemble empirical mode decomposition (EEMD) method. Then the Savitzky-Golay (SG) filter is used to reduce noise for high-frequency IMFs. Next the long short-term memory (LSTM) model and autoregressive integrated moving average (ARIMA) model are combined to predict low-frequency IMFs and the noise reduction results respectively. At the end, all those forecast results are added and form a one-way result. By weighted average of two one -way results, the repairing result is calculated. The experimental results from multiple prediction cases show that this method can get more accurate results. © 2021 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

The SA-UNet temperature field reconstruction based on GAN data augmentation of wet friction components

引用

measurement: Journal of the International measurement Confederation 2025年 254卷

作者： Wu, Jianpeng Ding, Ao Zhang, Hanshu Zhao, Peng Yang, Chengbing Wang, Liyong Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University 12 Xiaoying East Road Haidian District Beijing China Rice University Department of civil and environmental engineering HoustonTX United States

Wet friction components are critical in mechanical equipment and are crucial for ensuring their safe and stable operation. Ulteriorly, the distribution of temperature fields in wet friction components directly impacts their transmission efficiency and safety performance, thus investigating temperature field reconstruction is significant for the health management of mechanical transmission devices. Firstly, in order to expand the data, this study uses a Generative Adversarial Network (GAN) to augment temperature field data from a finite element model simulation. This augmented dataset is trained by a Self-Attention UNet (SA-UNet) deep learning model. Additionally, 30 sets of experimental data are employed as test samples to reconstruct the surface temperature fields of friction components using the trained SA-UNet reconstruction model. Subsequently, the model performance is analysed to assess the impact of varying numbers, locations, and conditions of the observation points in training samples. The results demonstrate that the MRE of the SA-UNet reconstruction model is 2.4%, reflecting higher accuracy compared to other deep learning models. This study aims to develop a precise and reliable model for reconstructing the temperature distribution in wet friction components, providing valuable insights into their thermal health status. © 2025

关键词： Finite element simulation GAN SA-UNet Temperature field reconstruction Wet friction components

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Railway Foreign Object Detection Method Based on GAN 21

A Semi-Supervised Railway Foreign Object Detection Method Ba...

引用

5th International Conference on Computer Science and Application engineering, CSAE 2021

作者： Chen, Yanqi Tong, Shuzhen Lu, Xiaobo Wei, Yun School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Beijing Mass Transit Railway Operation Corporation Limited Beijing China

ISBN: (纸本)9781450389853

The rapid development of deep learning provides new technical means for railway foreign object detection. However, in practical applications, the datasets of railways with foreign objects are scarce. In order to solve this problem, by improving the loss function and anomaly image evaluation standard, this paper proposes a newsemisupervised anomaly detection method based on GAN (Generative Adversarial Networks). Experiments show that our method can achieve railway foreign object detection without anomaly prior knowledge. Regarding anomaly recognition, a 0.058 AUC (Area Under Curve) and a 6% classification accuracy relative improvement for the railway dataset used in this paper are obtained.. © 2021 Association for Computing Machinery. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

TransTracking for UAV: An Autonomous Real-time Target Tracking System for UAV via Transformer Tracking

TransTracking for UAV: An Autonomous Real-time Target Tracki...

引用

2021 International Conference on Intelligent Technology and Embedded Systems, ICITES 2021

作者： Sun, Xiaolou Xie, Fei Wang, Qi Yao, Yuncong Wang, Hao Wang, Wei Yang, Wankou School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Nanjing University of Information Science and Technology School of Automation Nanjing211800 China

ISBN: (纸本)9781665427555

Most of the existing Siamese-type trackers usually adopt pre-defined anchor boxes or anchor-free schemes to accurately estimate the bounding box of targets. Unfortunately, they suffer from complicated hand-designed components and tedious post-processings. It is not easy to adjust parameters for unique scenes in real applications. So, we propose a new scheme by formulating visual tracking as a direct set prediction problem to alleviate this issue. The main component is a transformer attached to the Siamese-type feature extraction networks. Thus, our new framework can be summarized as Siamese Network with Transformers (SiamTFR). With a fixed small set of learned object queries, we force the final set of predictions via bipartite matching, significantly reducing hyper-parameters associated with the candidate boxes. Due to the unique predictions of this framework, we significantly ease the heavy burden of hyper-parameters search of post-processings in visual tracking. Extensive experiments on visual tracking benchmarks, including GOT-10K, demonstrate that SiamTFR achieves competitive performance and runs at 50 FPS. Specifically, SiamTFR outperforms leading anchor-based tracker SiamRPN++ in the GOT-10K benchmark, confirming its effectiveness and efficiency. Furthermore, SiamTFR is deployed on the embedded device in which the algorithm can be run at 30FPS or 54FPS with TensorRT meeting the real-time requirements. In addition, we design the complete tracking system demo that can work in the real road to narrow the gap between the academic models and industrial deployments. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Research on Image Enhancement Method of Impact Damage of Carbon Fiber Reinforced Plastics Based on Infrared Sequence Images

Research on Image Enhancement Method of Impact Damage of Car...

引用

China Instrument and control Society (ACCIS), Academic Conference of

作者： Lihua Yuan Jianlong Liu Yishun Jin Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang China Department of Measurement and Control Technology and Instruments School of Testing and Optoelectronic Engineering Nanchang Hangkong University Nanchang China

ISBN: (数字)9798350350326

ISBN: (纸本)9798350350333

The long pulse reflection method was used to detect the internal defects of the impact damage of carbon fiber reinforced plastics. Under the excitation of halogen lamp, the thermal imager synchronized the change of the surface temperature field of the test block and stored in the form of infrared sequence images. In order to improve the imaging quality of infrared images, a variety of infrared sequence image processing algorithms were studied, including polynomial fitting method, robust principal component analysis, independent component analysis and pulse phase method. The performance of each sequence image processing algorithm was quantitatively analyzed by using peak signal-to-noise ratio, root mean square error and entropy. The results show that the image quality evaluation indexes of these four sequence image processing algorithms are better than those of the original image, indicating that these four algorithms are suitable for enhancing the infrared thermal image of impact damage. In particular, the peak signal-to-noise ratio and entropy of the robust principal component analysis enhancement results are optimal among all the processing methods, and the root mean square error is suboptimal.

关键词： PSNR Process control Independent component analysis Fiber reinforced plastics Entropy Polynomials Image sequences Carbon Root mean square Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Stability and Bifurcation control of Fractional-Order Coupled Hindmarsh-Rose Neural Networks 42

Stability and Bifurcation Control of Fractional-Order Couple...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Feng Zhou, Feifan Wang, Wei Cai, Gang Wang, Hua O Yang, Xiuqin School of Automation China University of Geosciences Wuhan430074 China Engineering Research Center of Ministry of Education for Intelligent Technology of Earth Exploration China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Boston University Department of Mechanical Engineering BostonMA02215 United States School of Education Minzu University of China Beijing100081 China

ISBN: (纸本)9789887581543

This article investigates a fractional-order coupled Hindmarsh-Rose neural networks model. Firstly, the existence and stability of an equilibrium point in the system are verified. Then, the periodic bifurcation behavior of the system on a two-parameter plane is studied, and numerical simulations show the existence of both non -chaotic and chaotic plus periodic bifurcation behavior on the two-parameter plane. Finally, a feedback controller was designed to stabilize the bifurcation point of the delayed system and increase the stable range of the system. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Distributed Active Disturbance Rejection control of Multiple Mobile Robots for Online Workload Partition

Distributed Active Disturbance Rejection Control of Multiple...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Xin Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798350303759

Considering the actual multi-agent coverage process, the motion trajectories are seriously affected by disturbances and noise. In this paper, a cooperative control method based on active disturbance rejection controller (ADRC) for multiple mecanum-wheeled robots (MWMR) is proposed to improve its robustness. In particular, to suppress the total disturbances during the running of each robot and reduce large computation and observation cost of high order ADRC, a reduced-order cascaded ADRC (RC-ADRC) is proposed. Moreover, distributed controller is proposed to track the expected trajectories of multiple mecanum-wheeled robots under disturbances. Compared with the proposed RC-ADRC based cooperative control scheme and PID based cooperative control one, the favorable motion trajectory tracking performance is obtained. Simulation results verify the superiority of the method. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Estimation of Bottom-Hole Pressure Based on Bayesian Optimization and Bidirectional Long Short-Term Memory Neural Network 43

Estimation of Bottom-Hole Pressure Based on Bayesian Optimiz...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Zihan Lu, Chengda Wang, Yawu Zhou, Yang Wu, Min She, Jinhua China University of Geosciences School of Future Technology Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China China University of Geosciences School of Automation Wuhan430074 China Tokyo University of Technology School of Engineering Hachioji192-0982 Japan

ISBN: (纸本)9789887581581

Bottom-hole pressure (BHP) plays a crucial role in a drilling process. The accurate estimation of BHP ensures safe and efficient drilling operations. Artificial neural networks can predict BHP indirectly by analyzing the non-linear relationship with wellhead variables. This paper introduces a BHP estimation model that leverages Bayesian optimization and a bidirectional long short-term memory neural network (BO-BiLSTM). The model employs Bayesian optimization to determine optimal hyperparameters, including the number of hidden layers, initial learning rate, and L2 regularization parameter. The BO-BiLSTM model achieves a mean absolute percentage error of 2.056% and an R-squared score of 0.94596. The results demonstrate that the presented model enhances estimation precision and outperforms other methods examined in this study. This method facilitates indirect measurement of BHP using wellhead data, and contributes to the exploration of deep-sea resources in complex environments. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Bottom hole pressure

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Based Dynamic Multi-Objective Constrained Evolutionary Algorithm for Open-Pit Mine Truck Scheduling

A Reinforcement Learning Based Dynamic Multi-Objective Const...

引用

2023 China Automation Congress, CAC 2023

作者： Qiu, Junxiang Li, Changhe Yang, Shengxiang School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo- Exploration Ministry of Education Wuhan430074 China School of Computer Science and Informatics De Montfort University Leicester United Kingdom

ISBN: (纸本)9798350303759

Aiming at the truck scheduling problem in the open-pit mine scenario, a truck scheduling model based on real-time ore blending is established, and an adaptive evolution algorithm for truck scheduling based on DCNSGA-III is proposed. In the established scheduling model, the real-time grade variance of the crushing plant is minimized as one of the optimization objectives, and the Q-learning algorithm is introduced to adaptively select one of the most effective operators during the search process. Experiments show that the proposed method can effectively control the grade fluctuation of the ore flow and better scheduling schemes are obtained in comparison with algorithms equipped with the traditional search operator selection methods. © 2023 IEEE.

关键词： Evolutionary algorithms

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：