检索结果-内蒙古大学图书馆

43rd Chinese control Conference, CCC 2024

作者： Zhang, Zhongyi Xu, Chenyang Jin, Licheng Hou, Huirang Meng, Qinghao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

Electroencephalography (EEG) contains a wealth of information, including neuron activity, allowing for a partial understanding of the brain's state. As a reliable tool, EEG, combined with deep neural networks, has been increasingly utilized to assist in the detection of depression and has achieved satisfactory results. However, there are still some limitations in the current models. Firstly, it is worth noting that many existing models are binary classification models. These models can determine whether a subject is depressed or not, but they lack the capability to differentiate the severity of depression. Besides, the variations in EEG signals among various individuals have not been thoroughly taken into account, leading to subpar performance when applying the trained model to new subjects. To address the aforementioned issues, we suggest implementing a multi-classification model that utilizes a graph convolutional neural network (GCN) to identify levels of depression. Additionally, to mitigate the problem of imbalanced samples in multi-classification tasks, we introduce a penalty coefficient for the smaller categories. At the same time, the issue of signal discrepancies among subjects was taken into account, leading to the introduction of the domain generalization module. Finally, the depression level identification task on the MODMA and PRED+CT dataset achieved an accuracy of 75.47% and 77.97% respectively, surpassing the performance of the state-of-the-art (SOTA) model. In addition, numerous ablation experiments were conducted to validate the efficacy of each module. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control Based Reference Generation for Optimal Proportional Integral Derivative control 32

Model Predictive Control Based Reference Generation for Opti...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Gashi, Fatos Abuibaid, Khalil Ruskowski, Martin Wagner, Achim KaiserslauternD-67663 Germany RPTU Kaiserslautern-Landau Machine Tools and Control Systems Department of Mechanical and Process Engineering KaiserslauternD-67663 Germany

ISBN: (纸本)9798350395440

We introduce an alternative approach towards optimal proportional integral derivative (PID) control, consisting of model predictive control (MPC) based reference generation. To this end, we have integrated the reference as part of optimization variables of the resulting problem, where a deliberate sequence of errors is induced to obtain an optimal PID control action. In addition, the desired behavior of the PID controller is achieved without the need for internal modification of the PID gains. To better highlight the ability of coping with poor PID tuning, several test cases consisting of progressively degraded PID gains are presented. Validation of the proposed strategy is displayed by comprehensive simulations using two different plants. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Learning to traverse challenging terrain using BGRU-Attention

Learning to traverse challenging terrain using BGRU-Attentio...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Liu, Huazheng Xu, Yanbin Dong, Jiajun Dong, Feng Tianjin University Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin300072 China

ISBN: (纸本)9798350325706

In this paper, we present a model-free deep reinforcement learning (DRL) algorithm to control the locomotion of a quadruped robot adaptively at challenging terrain. This approach is used to improve the robot's ability to traverse unstructured ground. Combining Bidirectional Gate Recurrent Unit (BGRU) and attention mechanism, we train the quadruped robot to climb up and down stairs, traverse various field terrain and bricks. We train the controller in simulation using knowledge distillation, and deploy on real robots without any adjustment. In the simulation, the performance of our Student Module even exceeds that of Teacher Module. The experimental results demonstrate that our proposed approach can make the quadruped robot traverse obstacles swiftly. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monocular 3D Object Detection Based on Pseudo-LiDAR Point Cloud for Autonomous Vehicles 41

Monocular 3D Object Detection Based on Pseudo-LiDAR Point Cl...

引用

第41届中国控制会议

作者： Yijing Wang Sheng Xu Zhiqiang Zuo Zheng Li Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Pseudo-LiDAR point clouds are generated from monocular *** with the point cloud from LiDAR,it can provide denser *** to the inaccuracy of depth estimation,there is still a performance gap between the pseudo-LiDAR point cloud and the LiDAR *** this paper,we propose an approach to eliminate the performance degradation caused by deviation of depth estimation and realize 3 D object detection based on pseudo-LiDAR point *** results on KITTI 3 D benchmark illustrate that in contrast to other methods,our scheme can achieve more reliable performance on both object localization and shape estimation.

关键词： 3D object detection pseudo-LiDAR point cloud image morphing depth estimation

来源：评论

学校读者我要写书评

暂无评论

Comprehensive evaluation of an ionic liquid based deep purification process for NH_(3)-containing industrial gas

引用

Journal of Environmental Sciences 2024年第2期136卷 698-708页

作者： Guoxiong Zhan Fei Cao Jianjun Chen Zhen Chen Yuanmeng Duan Fei Chang Shaojuan Zeng Yinge Bai Zengxi Li Xiangping Zhang Junhua Li State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China Sino-Danish College University of Chinese Academy of SciencesBeijing 100049China Institute of Process Engineering Chinese Academy of SciencesBeijing 100190China College of Chemical and Engineering University of Chinese Academy of SciencesBeijing 100049China

Ammonia(NH_(3))emission has caused serious environment issues and aroused worldwide *** emerging ionic liquid(IL)provides a greener way to efficiently capture NH_(3).This paper provides rigorous process simulation,optimization and assessment for a novel NH_(3)deep purification process using *** process was designed and investigated by simulation and optimization using ionic liquid[C_(4)im][NTF_(2)]as *** objective functions,total purification cost(TPC),total process CO_(2)emission(TPCOE)and thermal efficiency(ηeff)were employed to optimize the absorption *** simulation and optimization results indicate that at same purification standard and recovery rate,the novel process can achieve lower cost and CO_(2)emission compared to benchmark *** process optimization,the optimal functions can achieve 0.02726$/Nm~3(TPC),311.27 kg CO_(2)/hr(TP-COE),and 52.21%(ηeff)for enhanced ***,compared with conventional process,novel process could decrease over$3 million of purification cost and 10000 tons of CO_(2)emission during the life *** results provide a novel strategy and guidance for deep purification of NH_(3)capture.

关键词： NH_(3) Capture process Ionic Liquid process Simulation process Optimization Deep purification

来源：评论

学校读者我要写书评

暂无评论

Local Characteristics Preservation Based State Identification in Oil-gas-water Three-phase Flow process 41

Local Characteristics Preservation Based State Identificatio...

引用

第41届中国控制会议

作者： Zhao Li Shumei Zhang Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Oil-gas-water three-phase flow process is a dynamic non-stationary system,and the flow states are extremely complicated due to the three-phase *** at state identification of water-based dispersed three-phase flow,a strategy combining locality preserving projections(LPP) and Gaussian-weighted k-nearest neighbor(GWKNN) is *** on statistics pattern analysis(SPA),rich state information can be *** constructing the combined model of LPP and GWKNN,the local neighborhood structures are preserved and the local characteristics of flow states are *** effectiveness of the strategy is demonstrated by experiments.

关键词： Oil-gas-water three-phase flow state identification statistics pattern analysis locality preserving projections Gaussian-weighted k-nearest neighbor

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Deep Reinforcement Learning for Microgrid Energy Scheduling 41

Multi-agent Deep Reinforcement Learning for Microgrid Energy...

引用

第41届中国控制会议

作者： Zhiqiang Zuo Zhi Li Yijing Wang Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we study the energy scheduling problem of solar-powered aircraft microgrid with multi-agent deep reinforcement learning algorithm under a centralized training and decentralized execution *** problem is modeled as a multi-agent Markov decision process and embedded in a multi-agent proximal policy optimization framework.A scheduling policy is proposed by offline training and then utilized for online ***,two forms of action spaces are constructed to explore a more favorable *** experiments show that the algorithm enables us to obtain an effective policy in solving the energy scheduling problem.

关键词： Multi-agent deep reinforcement learning Scheduling policy Energy dispatch Solar-powered aircraft

来源：评论

学校读者我要写书评

暂无评论

Two-phase Flow Pattern Diagnosis Based on Chaotic Recursive Graph and Spectral Analysis 41

Two-phase Flow Pattern Diagnosis Based on Chaotic Recursive ...

引用

第41届中国控制会议

作者： Ziqi Cui Chao Tan Hanrui Zhang Xuewei Shi Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

It is difficult to accurately measure the flow parameters of gas-liquid two-phase flow in horizontal pipe because of its complexity and *** of two-phase flow pattern is helpful to analyze fluid flow state and provide more information for accurate measurement of flow *** this paper,a two-phase flow pattern diagnosis algorithm based on acoustic-electrical data fusion is ***,chaos recursive analysis is performed on the data obtained by electronic resistance tomography(ERT) *** wavelet transform is performed on ERT data and the total energy of wavelet transform is ***,spectrum analysis is used on the ultrasonic Doppler data,and statistical characteristics of spectrum bandwidth and average velocity are *** vector machine(SVM) and K-nearest neighbor were used to distinguish these features objectively,and the recognition accuracy are 88% and 92%.

关键词： Flow patterns ERT Ultrasonic doppler Recursive analysis SVM

来源：评论

学校读者我要写书评

暂无评论

Consensus of One-Sided Lipschitz Multi-Agent Systems with Input Saturation and Disturbance over Directed Graph 41

Consensus of One-Sided Lipschitz Multi-Agent Systems with In...

引用

第41届中国控制会议

作者： Zhiqiang Zuo Jiewen Ji Yijing Wang Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper investigates the consensus of one-sided Lipschitz(OSL) multi-agent systems(MASs) in the presence of input saturation and external disturbance over directed communication topology.A saturation avoidance strategy is suggested to handle the input *** enables us to deal with both open-loop stable and open-loop unstable *** employing the Lyapunov theory,the consensus problem is changed into the stabilization one through the error *** design a control protocol and convert the problems of disturbance rejection and domain of attraction into the optimization of two invariant ***,some numerical simulations are given to verify the effectiveness of the proposed consensus protocol.

关键词： Consensus One-sided Lipschitz Directed network Input saturation Disturbance

来源：评论

学校读者我要写书评

暂无评论

Gas-water Two-phase Flow Status Monitoring based on CA-KCVA Method 41

Gas-water Two-phase Flow Status Monitoring based on CA-KCVA ...

引用

第41届中国控制会议

作者： Wentao Wu Chao Tan Shumei Zhang Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Gas-water two-phase flow process is complex and ***-time monitoring of flow status evolution is helpful to the safe *** progress of multi-sensor technology makes it possible to accurately measure the flow information,which lays a data foundation for the establishment of flow status monitoring *** to the instability and randomness of flow,there are both nonstationary and stationary signals in the measurement *** this paper,the augmented Dickey Fuller(ADF) test is used to distinguish nonstationary signals from stationary *** analysis(CA) can deal with the problem that the fluctuation of nonstationary signals masks the change trend of flow *** stationary signals,kernel canonical variate analysis(KCVA) is used to realize the nonlinear mapping and obtain the canonical features reflecting the dynamic *** monitoring indexes are built and combined to monitor the flow ***-KCVA method is applied to the data of gas-water two-phase flow in horizontal *** monitoring results prove the effectiveness.

关键词： Gas-water two-phase flow flow status monitoring augmented Dickey Fuller test cointegration analysis kernel canonical variate analysis

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：