检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Xiao Liu Luefeng Chen Chengda Lu Haipeng Fan Min Wu Witold Pedrycz School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Department of Computer Engineering Istinye University Istanbul Turkey

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

During the coal seam drilling process, the drill string is subject to compressive deformation, compounded by unpredictable variations in formation hardness and borehole wall friction, leading to challenges in maintaining a stable feeding speed. This paper presents a novel approach by introducing uncertain parameters to describe the effects of formation hardness and borehole wall friction. Drill string axial movement model is modeled as a polyhedral system based on a lumped parameter representation. To meet industrial performance requirements, we design a robust $H_{\infty}$ controller to achieve consistent feeding speed control. Our simulation results demonstrate the controller's effectiveness in ensuring system stability despite fluctuations in formation hardness and drill string friction.

关键词： Drilling Robust control Friction Simulation Geology Velocity control Stability criteria Process control Coal Output feedback

来源：评论

学校读者我要写书评

暂无评论

No-Reference Image Quality Assessment using Meta-SGD

No-Reference Image Quality Assessment using Meta-SGD

引用

2021 China automation Congress, CAC 2021

作者： Van, Qmgqmg Dong, Bei Li, Xin Xiang, Yiwen Luo, Dapeng Wei, Longsheng School of Automation China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of Ministry of Education Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Intelligent Technology co. Ltd of Chinese Construction Third Engineering Bureau Wuhan China School of Electronic Information and Mechanics China University of Geosciences Wuhan China

ISBN: (纸本)9781665426473

Deep learning-based no-reference image quality assessment (NR-IQA) algorithm requires massive training data and labels, but data scarcity usually exists in practical applications. Most of the previous metrics used pre-trained networks to solve this problem by fine-tuning on the target tasks. Unfortunately, the network trained on other tasks cannot be directly applied to IQA tasks and failed when encountering complex distortions. To reduce dependence on labeled data and improve generalization ability of unknown distortion types, a NR-IQA metric based on Meta-SGD is proposed, which can learn the quick adaptability of humans and obtain general meta-knowledge for distortion evaluation. Specifically, we collected a great many NR-IQA tasks with different distortion types to pre-train the model;then a meta-learning metric based on optimization, Meta-SGD, is proposed to acquire the meta-knowledge when evaluating images quality with various known distortions;finally, the obtained pre-trained meta-model can be directly applied to the new NR-IQA tasks only by fine-tuning a few images. Experiments on the TID2013 database demonstrate that the model after meta-learning obviously outperforms than some existing methods, and the average SRCC value for all types of distortion performance tests can reach 0.91. © 2021 IEEE

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Overlapped Human Pose Estimation using Non-Maximum Suppression based on Shape Similarity

Overlapped Human Pose Estimation using Non-Maximum Suppressi...

引用

2021 China automation Congress, CAC 2021

作者： Yu, Xuefu Li, Jinsheng Xiao, Fei Liu, Wei Luo, Dapeng Wei, Longsheng School of Automation China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of Ministry of Education Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Intelligent Technology co. Ltd Chinese Construction Third Engineering Bureau Wuhan China School of Electronic Information and Mechanics China University of Geosciences Wuhan China

ISBN: (纸本)9781665426473

Deep Convolutional Neural Networks (DNNs) have made significant progress on human pose estimation task in recent years. However, the question of whether we are making the most use of the information we get from DNNs has not been well studied. Top-down approach which first detects person body box then utilizes single person pose estimation by heatmap is a widely used method in multi-person pose estimation. However, information that predicted by DNNs contains more information than we consider. In person box prediction process, when two persons are closed to each other, the Non-Maximum Suppression (NMS) we often use filters out the body boxes with smaller scores. For tackling this problem, we apply NMS based on Shape Similarity to person body boxes detection for tackling the problem that deleting the overlapped body boxes with smaller scores, and then extract keypoint coordinates and tag information for filter noise candidates from heatmap by Trasformer to improve the prediction accuracy. At last we develop an algorithm for refining keypoint coordinate by tag information. In experiment, we got mean Average Precision(mAP) of 76.0% in COCO2017 validation dataset, better than 75.6% with TransPose. © 2021 IEEE

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-time Speech Emotion Recognition Based on Syllable-Level Feature Extraction

arXiv

引用

arXiv 2022年

作者： Rehman, Abdul Liu, Zhen-Tao Wu, Min Cao, Wei-Hua Jiang, Cheng-Shan The School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China The Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

Speech emotion recognition systems have high prediction latency because of the high computational requirements for deep learning models and low generalizability mainly because of the poor reliability of emotional measurements across multiple corpora. To solve these problems, we present a speech emotion recognition system based on a reductionist approach of decomposing and analyzing syllable-level features. Mel-spectrogram of an audio stream is decomposed into syllable-level components, which are then analyzed to extract statistical features. The proposed method uses formant attention, noise-gate filtering, and rolling normalization contexts to increase feature processing speed and tolerance to adversity. A set of syllable-level formant features is extracted and fed into a single hidden layer neural network that makes predictions for each syllable as opposed to the conventional approach of using a sophisticated deep learner to make sentence-wide predictions. The syllable level predictions help to achieve the real-time latency and lower the aggregated error in utterance level cross-corpus predictions. The experiments on IEMOCAP (IE), MSP-Improv (MI), and RAVDESS (RA) databases show that the method archives real-time latency while predicting with state-of-the-art cross-corpus unweighted accuracy of 47.6% for IE to MI and 56.2% for MI to IE. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

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

Chinese automation Congress (CAC)

作者： Tianhe Liu Xin Chen Chenyu Hu Xu Jian Shengzu Li Gang Wang School of Automation China University of Geosciences 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 Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Wuhan Power Supply Company China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

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 $\pm 4\text{mm}$ , outperforming other algorithms. The method is characterized as simple and efficient, and it enhances the environmental adaptability of distribution network robots.

关键词： Location awareness Visualization Power transmission lines Accuracy Image color analysis Lighting Distribution networks Grasping Wire Robots

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling Strategy of Limited Electricity Based on Energy Sharing of Multi-microgrid

Optimal Scheduling Strategy of Limited Electricity Based on ...

引用

Chinese automation Congress (CAC)

作者： Zihan Zeng Danyun Li School of Automation China University of Geosciences 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 430074 China Wuhan China

In the environment of limited electricity supply in distribution network, due to the limitation of its own power capacity and the uncertainty of new energy output, there will be insufficient electricity supply in microgrid, which will affect the economy and comfort of users in microgrid system. Therefore, aiming at the situation of limited electricity supply in distribution network, multi-microgrid system is taken as the research object, and the cooperative game method is adopted to realize the energy sharing of multi-microgrid system, and then the limited electricity optimal dispatching model of multi-microgrid system is constructed to realize the reasonable power distribution for different types of loads. Finally, the simulation results show that this strategy can effectively realize power sharing, reduce outage loss and improve user satisfaction.

关键词： Uncertainty Simulation Power distribution Optimal scheduling Games Microgrids Distribution networks

来源：评论

学校读者我要写书评

暂无评论

A Model-Predictive-Enabled Equivalent-Input-Disturbance Approach for Disturbance Rejection

A Model-Predictive-Enabled Equivalent-Input-Disturbance Appr...

引用

Industrial Cyber-Physical Systems (ICPS)

作者： Yujian Zhou Jinhua She Feng Wang Makoto Iwasaki School of Automation China University of Geosciences 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 Engineering Tokyo University of Technology Tokyo Japan Department of Electrical and Mechanical Engineering Nagoya Institute of Technology Nagoya Japan

This paper presents a model-predictive-enabled equivalent-input-disturbance (MPEID) method for disturbance rejection. An EID estimator with a state observer estimates the effect of disturbances in a system. The disturbance estimation will not be directly added to the input channel for disturbance rejection. A cost function that considers the disturbance estimation is designed. An MPC controller calculates an optimal control input by minimizing the cost function. The stability condition of the closed-loop system is analyzed based on the Lyapunov stability theory. Simulation results show that our method has better disturbance-rejection performance than an MPC method when the control input is similar.

关键词： Simulation Estimation Optimal control Predictive models Observers Cyber-physical systems Cost function

来源：评论

学校读者我要写书评

暂无评论

High Precision Waveform Reproduction of Shaking Table Based on Linear Active Disturbance Rejection control 39

High Precision Waveform Reproduction of Shaking Table Based ...

引用

39th Chinese control Conference, CCC 2020

作者： Wang, Sheng Lei, Qi Central South University School of Automation Changsha410083 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

ISBN: (数字)9789881563903

ISBN: (纸本)9789881563903

Seismic simulation shaking table plays a key role in many industrial structural dynamic experiments. High-precision waveform repetition has a great impact on the experimental accuracy of structural dynamic experiments. The equipment of seismic simulation shaker table has obvious uncertainties in the modeling process, so it is difficult to describe the seismic simulation shaker table with a more accurate mathematical model. Therefore, this paper adopt the Linear Active Disturbance Rejection control (LADRC) to achieve high-precision reproduction of the waveform of the seismic simulation shaker. This method will all the model uncertainty and external disturbance as total disturbance, using the extended state observer (ESO) to estimate the total disturbance, and by using state feedback control law of generalized disturbance compensation, to get better performance of resistance to interference. This method does not rely on the model of the specimen and does not need to obtain prior knowledge of the specimen. In this paper, the inertial and single-degree-of-freedom elastic specimens are simulated for vibration test, and the control effect of this strategy is fully verified by comparison with the traditional PID control method. © 2020 Technical Committee on control Theory, Chinese Association of automation.

关键词： Structural dynamics

来源：评论

学校读者我要写书评

暂无评论

On Ground Penetrating Radar Fast Imaging Method Based on Compressed Sensing

On Ground Penetrating Radar Fast Imaging Method Based on Com...

引用

第40届中国控制会议

作者： Guangjun Wang Xinzhao Qi Zhaohui Wang Chengxiang Ding School of Automation P.R.China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Recently, compressed sensing（CS） has been widely used in ground penetrating radar（GPR） imaging due to its low sampling time, high quality performance and high quality underground imaging results. There are always a large number of matrix operations involved in CS based GPR imaging process, which takes a long time. Traditionally, all scanning area was imaged by this CS imaging method. However, with the imaging scene becoming larger, the measurement matrix and the data dictionary in CS imaging model expand, which increases the time of CS-based imaging process. Thus, this paper proposes a fast CS based GPR imaging method to reduce the imaging time. Specifically, the geometric characteristics of the B-scan image can firstly be used to extract the region of interest（ROI） where the target may exist in a layered medium. Then the GPR imaging based on CS can be realized in ROI, which can reduce the imaging area and imaging time. Experimental results present that the method can effectively reduce the time of GPR imaging based on CS.

关键词： Compressed Sensing（CS） Ground Penetrating Radar（GPR） Fast Imaging B-scan image Region of interest（ROI）

来源：评论

学校读者我要写书评

暂无评论

Sound Field control by Using Equivalent Input Disturbance method

Sound Field Control by Using Equivalent Input Disturbance me...

引用

Industrial Cyber-Physical Systems (ICPS)

作者： Toshiki Watanabe Jinhua She Zewen Wang Department of Sustainable Engineering Tokyo university of technology Japan School of Automation China University of Geosciences 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 Laboratory for Future Interdisciplinary Research of Science and Technology (FIRST) Tokyo Institute of Technology Yokohama Kanagawa Japan

Low-frequency noise, such as road noise from automobiles and interior noise from bullet train cars, is detrimental to passenger comfort. Active noise control provides us with a way of suppressing low-frequency noise. It generates a sound of the same amplitude and opposite phase as noise and uses it to cancel the noise. Conventional active noise control is complicated to apply. Thus, the objective of this study is to establish a sound field control system by using the equivalent-input-disturbance method. System identification was performed to obtain an ideal plant of a duct. The control system is constructed based on the equivalent-input-disturbance approach with a low-order controller. The experimental results showed a suppression effect of about 50% of the sound field.

关键词： Roads Noise reduction Ducts Channel estimation Auditory system Cyber-physical systems control systems

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：