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

A Multi-Gas Detection System Based on Convolutional Neural Network 43

A Multi-Gas Detection System Based on Convolutional Neural N...

引用

43rd Chinese control Conference, CCC 2024

作者： Chen, Si-Wen Li, Hong-Yue Hou, Hui-Rang Meng, Qing-Hao 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

The emission of carbon oxides (COx), nitrogen oxides (NOx), sulfur compounds, and volatile organic compounds (VOCs) from vehicles has significantly impacted the air quality, thus posing threats to the environmental resources and human health. This work presents the development of a non-dispersive infrared (NDIR) multi-gas detection system featuring three broadband light sources, a sealed gas chamber, and three multi-channel pyroelectric detectors with a response time shorter than 32 ms. The proposed system is used for constructing an odor dataset comprising five target gases, including carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), sulfur dioxide (SO2), and propane (C3 H8). We perform odor recognition experiments using the traditional machine learning methods, as well as one-dimensional convolutional neural network (1D-CNN) and depthwise separable convolutional neural network (DS-CNN). The results show that the proposed DS-CNN model achieves an accuracy of 94.75% in recognizing different odors, thus outperforming other classification algorithms. This work demonstrates that the proposed detection system exhibits rapid response and precise recognition, thus establishing it as an effective approach for analyzing the primary components of automobile exhaust. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

COA Optimized PEMFC Remaining Useful Life Prediction for CRJ Networks 25

COA Optimized PEMFC Remaining Useful Life Prediction for CRJ...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Feng, Ze Shi, Peng Wang, Wenhao Xu, Liang Tianjin University of Technology Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin China Tianjin Institute of Metrological Supervision and Testing Tianjin China

ISBN: (纸本)9798350366600

Aiming at the RUL (remaining useful life) prediction problem of PEMFC (Proton Exchange Membrane Fuel Cell), this paper proposes a PEMFC remaining service life prediction model based on the long-nosed raccoon algorithm (COA) optimized deterministic jump cycle (CRJ) network model. After smoothing the data with equal interval sampling and SG convolutional smoothing, the 24 feature variables in the original data of the PEMFC were downscaled by principal component analysis. Then optimal input features were determined by the cumulative contribution rate, and then the optimization of the CRJ network was carried out by using the optimization of the CRJ network's cyclic ring weights rc, jump weights rj and the leakage rate parameter. The optimized CRJ network was used to make a prediction of the RUL of the PEMFC. In the simulation experiments, by comparing with the unoptimized CRJ network and COA-BP network prediction model, the MAE, PMSE and R2 of this paper's method are better, reaching 0.0026104,0.003582 and 0.94715, respectively. © 2024 IEEE.

关键词： echo state network PEMFC raccoon optimization algorithm residual lifetime

来源：评论

学校读者我要写书评

暂无评论

Principal Polynomial Analysis Based Status Monitoring for Gas-Liquid Two-Phase Flow in Horizontal Pipe 42

Principal Polynomial Analysis Based Status Monitoring for Ga...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhang, Liyuan Wu, Wentao Dong, Feng School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581543

As a kind of flow process with complex and variable flow structure, multiple process variables and nonlinear characteristics, the flow status of multiphase flow shows non-stationary characteristics, and it is difficult to achieve accurate online monitoring. For the nonlinear characteristics of the flow status of gas-liquid two-phase flow, a monitoring method based on principal polynomial analysis is proposed to extract the nonlinear characteristics of the flow status information. This method performs dimensionality reduction in multiple steps and uses polynomials for feature fitting, which can fully extract flow status information. Multiple sensors are used to obtain data representing different fluctuation characteristics in the flow process, models of different flow statuses are established, and status monitoring is realized based on statistical indicators. In the comparison with the principal component analysis method, it can be found that the principal polynomial analysis method can extract the nonlinear features and can describe the flow status more comprehensively, which can improve the accuracy of status monitoring. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Investigation of Elongated Bubble Centring in Slug Flow Based on Image processing 42

Investigation of Elongated Bubble Centring in Slug Flow Base...

引用

42nd Chinese control Conference, CCC 2023

作者： Xue, Ting Yuan, Yuqing College of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581543

The intermittent slug flow in horizontal circular pipes occurs commonly in industrial applications such as pipeline transportation and nuclear reactor cooling. The phenomenon of elongated bubble centring in slug flow can affect the bubble interface morphology, resulting in fluctuations of characteristic parameters. Therefore, it is important to acknowledge the extent to which bubble centring occurs and the possible influencing factors. This paper aims to investigate the elongated bubble centring in moderately sized pipes based on the laser-induced fluorescence method. A new image processing procedure is developed to measure the centring degree. A novel segmentation method is proposed to improve measurement accuracy by combining the global threshold algorithm with the Grey Wolf Optimization. The statistical analysis shows a positive correlation between the Froude number and the degree of bubble centring. Furthermore, the effect of superficial flow rate ratios is explored in the cases of similar Froude numbers. Finally, the results are verified by the models and the experimental data previously published. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Multi-Block Integrated Monitoring of Gas-Liquid Two-Phase Flow Based on Conductance Signal Analysis 42

Multi-Block Integrated Monitoring of Gas-Liquid Two-Phase Fl...

引用

42nd Chinese control Conference, CCC 2023

作者： Li, Zhao Zhang, Shumei Tan, Chao Dong, Feng School of Electrical and Information Engineering Tianjin Key Laboratory of Process Measurement and Control Tianjin University Tianjin300072 China

ISBN: (纸本)9789887581543

The state monitoring of gas-liquid two-phase flow with complex and diverse structures is the key to ensure the safe and stable operation of related industrial production. In order to achieve effective monitoring with limited sensing equipment, a multi-block integrated monitoring strategy for gas-liquid two-phase flow based on conductance signal analysis in time, frequency and multiscale domain is proposed. Three-block information including water holdup in time-domain, continuous wavelet transforms (CWT) based coarse scale approximation (CSA) coefficients in frequency-domain and CWT based local wavelet energy (LWE) coefficient maps in multiscale-domain are used for block-based modeling and monitoring. Considering the original structure of each block, the traditional principal component analysis (PCA) is adopted to model and monitor 1-D information including water holdup and CSA coefficients, while the tensor PCA is adopted for the 2-D LWE coefficient map. Three-block monitoring results are integrated through Bayesian inference to realize final monitoring. The dynamic experiment results demonstrate that the proposed multi-block integrated monitoring outperforms single-block information monitoring. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Gas-Water Two-Phase Flow Status Identification Based on Jointly Specific and Shared Dictionary Learning 42

Gas-Water Two-Phase Flow Status Identification Based on Join...

引用

42nd Chinese control Conference, CCC 2023

作者： Wu, Wentao Zhang, Shumei Tan, Chao Dong, Feng School of Electrical and Information Engineering Tianjin Key Laboratory of Process Measurement and Control Tianjin University Tianjin300072 China

ISBN: (纸本)9789887581543

Gas-water two-phase flow is a complex and changeable process, which widely exists in a variety of industrial scenarios. The gas-water two-phase flow has complex flow characteristics and fluid structure, which can be changed into different flow statuses. There are both differences and similarities among various flow statuses. In order to realize the accurate identification of gas-water two-phase flow, a jointly specific and shared dictionary learning (JSSDL) method is proposed. Based on multi-sensor data, the specific discrimination dictionary for different flow statuses and the shared dictionary for similar characteristics are established respectively to solve the problem of gas-water two-phase flow status identification. In the horizontal gas-water two-phase flow circuit, the effectiveness of the method is verified by experiments. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Two phase flow

来源：评论

学校读者我要写书评

暂无评论

Efficient production of 14α‑OH‑AD by engineered Mycolicibacterium neoaurum via coupled cofactor and reconstructed electron transport system

引用

Systems Microbiology and Biomanufacturing 2023年第2期3卷 358-369页

作者： Chenwei Zhang Yanbing Shen Yuanyuan Gao Zehui Zan Min Wang Key Laboratory of Industrial Fermentation Microbiology Ministry of EducationTianjin Key Laboratory of Industrial MicrobiologyTianjin University of Science and TechnologyTianjinChina Engineering Research Center of Microbial Metabolism and Fermentation Process Control College of BiotechnologyTianjin University of Science and TechnologyTianjin 300457People’s Republic of China

14α-hydroxy-androst-4-ene-3,17-dione(14α-OH-AD)is an important precursor for the synthesis of steroid drugs with anticancer and carcinolytic ***,14α-OH-AD was mostly synthesized by whole-cell fermentation of mold fungi using androstenedione(AD)as a substrate,which had difficulties in product isolation and purification as well as problems of high production *** this study,the source of the 14α-hydroxylase gene was *** 14α-hydroxylase genes were heterologously expressed in Mycolicibacterium neoaurum(MNR)M3ΔksdD,which enabled the one-step biotransformation from the cheap substrate phytosterols(PS)to 14α-OH-AD,reducing the difficulty of product purification and production *** is more,to alleviate the problem of poor activity of 14α-hydroxylase,the 14α-hydroxylase gene was co-expressed with the electron transport chain element genes and the coenzyme regeneration genes,and a superior engineered strain MNR M3ΔksdD/pMV261-14α-G6PDH was ***,the transformation conditions were optimized for the transformation of PS by the engineered *** molar yield of 14α-OH-AD reached to 60.4±2.3%(about 0.22 g/L productivity).This study investigated for the first time the effects of the tandem electron transport chain element genes and the tandem coenzyme regeneration genes on the 14α-hydroxylation reaction,providing a theoretical basis for the industrial production of 14α-OH-AD.

关键词： 14α-hydroxy-androst-4-ene-3,17-dione Mycolicibacterium neoaurum 14α-hydroxylase Electron transportation Coenzyme regeneration

来源：评论

学校读者我要写书评

暂无评论

Hemorrhage Detection by Magnetic Induction Tomography with Helmholtz Coil 42

Hemorrhage Detection by Magnetic Induction Tomography with H...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhu, Zilong Tan, Chao Chen, Yixuan Dong, Feng School of Electrical and Information Engineering Tianjin Key Laboratory of Process Measurement and Control Tianjin University Tianjin300072 China

ISBN: (纸本)9789887581543

Due to the nonradioactive, noninvasive, low cost and portable features, magnetic induction tomography (MIT) is a promising technology in medical imaging. The conventional MIT sensor array generates divergent excitation magnetic field, resulting in poor sensitivity intensity and uniformity. To improve the intensity and uniformity of the sensitivity in MIT for hemorrhage detection, a local MIT method with Helmholtz coil is proposed. The Helmholtz coil provides a uniform background magnetic field in the measured region. To obtain sufficient independent measurements for hemorrhage reconstruction, the open planar MIT sensor array with gradiometers is applied in combination with the Helmholtz coil. The structure and excitation-detection strategy of the MIT sensor array are designed. The distribution of the magnetic field, phase sensitivity and the phase response of hemorrhages under the designed MIT sensor array are analyzed. The results indicate that the open planar MIT sensor array with Helmholtz coil can effectively improve the intensity and uniformity of the phase sensitivity. In addition, it can also enhance the intensity of the hemorrhage signals for different depths and volumes of the hemorrhages. The proposed method provides a solution to improve the detection accuracy and the detection depth of the hemorrhage by MIT. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Magnetic fields

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

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：