检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Dongchang Wu Wei Xue Xinya Yang Tin Li School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

With the development of radar technology, frequency modulated continuous wave (FMCW) radar has been used for non-contact vital signs detection. In order to suppress the environmental noise and interference of breathing harmonics on heartbeat signal, this paper proposes a new vital sign detection method based on scale-space representation (SSR) and empirical wavelet transform (EWT) for the FMCW radar. First, a low-pass filter is set for the high-frequency noise elimination outside the frequency range of vital sign signals. Second, SSR is used to adaptively segment the spectrum of signals to obtain the initial frequency boundaries, and the kurtosis of the spectrum is applied to segment the spectrum again and obtain the final frequency boundaries to further eliminate noise. Third, the empirical wavelet filter bank is constructed by using the determined boundaries and EWT is used to decompose the signals to several components. Finally, according to the frequency ranges of components and the correlation between the components and vital sign signals, the components are selected to reconstruct the breathing and heartbeat signals. The experimental results show that the proposed method achieves a better detection performance than the classical EWT and empirical mode decomposition (EMD).

关键词： Frequency modulation Correlation Source separation Heart beat Working environment noise Radar detection Filter banks

来源：评论

学校读者我要写书评

暂无评论

Study on anti-interference performance of three-phase voltage mode PWM rectifier

Study on anti-interference performance of three-phase voltag...

引用

2021 China Automation Congress, CAC 2021

作者： Li, Guohong Yang, Weiyue Wei, Pengfei Gao, Ran Tianjin Key Laboratory for Control Theory and Applications in Complex Systems Tianjin University of Technology Binshui Xidao Extension 391 Tianjin300384 China School of Electrical and Electronic Engineering Tianjin University of Technology Binshui Xidao Extension 391 Tianjin300384 China

ISBN: (纸本)9781665426473

The operation of three-phase voltage type PWM rectifier often contains harmonics, voltage fluctuations and other problems. In this paper, based on the traditional sliding mode controller, the first-order active disturbance rejection control (ADRC) is introduced to control the outer voltage loop, and the state variables observed by the linear extended state observer (LESO) are fed back to the sliding mode controller for feedforward compensation. The controller has resonance suppression ability and strong disturbance immunity, and does not depend on the accurate mathematical model. The effectiveness of the control strategy is verified by simulation and experiment. The results show that the control strategy has the advantages of good dynamic performance, strong robustness and strong anti-interference ability. © 2021 IEEE

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A tuning strategy for microwave filter using variable universe adaptive fuzzy logic system

A tuning strategy for microwave filter using variable univer...

引用

2021 China Automation Congress, CAC 2021

作者： Peng, Sai Cao, Weihua Bi, Leyu Yuan, Yan Wu, Min School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

Microwave filters are the core frequency selection device in 5G base station, which play an important role in the field of communication. The errors of design and processing of microwave filter make it difficult to meet the specific requirements of frequency selection, thus the tuning process before delivery is significant. However, the tuning process relies heavily on skilled workers, resulting in low tuning efficiency and high cost. The automatic tuning method based on fuzzy logic does not depend on the model and has strong applicability. It has great practical value to the production trend of multi-variety, small batch and customization of microwave filters. In this paper, a variable universe adaptive fuzzy tuning method is proposed. First, intelligent optimal contraction-expansion factors based on fuzzy inference are proposed according to expert knowledge. Then, the input universe and output universe are multiplied, and the initial rule is transformed into more effective new rules through the transformation which is adaptive to the variable universe. Last, the effectiveness of the proposed tuning method is verified by simulations. © 2021 IEEE

关键词： Microwave filters

来源：评论

学校读者我要写书评

暂无评论

A fault diagnosis method based on multi-feature fusion and broad learning system

A fault diagnosis method based on multi-feature fusion and b...

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Wang, Yan Hu, Wenkai Cao, Weihua Wu, Min China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665401159

Reliable fault diagnosis is of practical significance for process safety in modern industrial facilities. This article proposes a data-driven fault diagnosis method based on multi-feature fusion and broad learning. The contributions are twofold: First, a systematic multi-feature extraction approach is presented to extract long-term trend features, short-term trend features, and binary-valued alarm signals;second, a broad learning system based fault diagnosis method is proposed to diagnose faults based on multi-feature fusion and to update the diagnosis model in an incremental manner. The proposed method has a strong nonlinear modeling capability and can also update the diagnosis model incrementally when unseen fault types are detected. The efficacy of the proposed method is demonstrated by simulations with the benchmark Tennessee Eastman (TE) process. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Psychological Resistance Recognition Based on Acoustic Features Extraction

Psychological Resistance Recognition Based on Acoustic Featu...

引用

2021 China Automation Congress, CAC 2021

作者： Lv, Z. Liu, Z.T. Han, M.T. Wu, B.H. School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

Psychological resistance can express the change of the client's psychological state, which is considered to be an important factor affecting psychological counseling. This paper proposed a method of psychological resistance recognition based on acoustic features extraction. The method includes three main steps, i.e., statistical acoustic feature extraction, feature selection, and classification. Our method uses statistical acoustic features to express psychological resistance, and analyzes the application value of high correlation features obtained from feature selection in the recognition of different psychological resistance. This method can be used to determine the high correlation features of psychological resistance adaptively, and avoid the deficiency of subjective judgment. A speech database of psychological resistance is built for research needs, in which three psychological consultants and four subjects are involved in psychological counseling with 1200 sentences in speech. The experimental results verified the effectiveness of our method. © 2021 IEEE

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Identification of root cause alarms by detecting correlations and time delays between alarm variables

Identification of root cause alarms by detecting correlation...

引用

2021 China Automation Congress, CAC 2021

作者： Cheng, Xin Hu, Wenkai Cao, Weihua Wu, Min School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

Under an abnormal situation in process operations, it is important to find out the root cause, so as to bring the system back to normal timely. In a typical modern industrial facility, there are configured a large number of alarms. Usually, the presence and propagation of a fault may lead to a series of alarms, which hold certain correlations. Therefore, analyzing alarm correlations can help to track the prorogation of faults among alarm variables and thus find out the root cause. This paper proposes a systematic alarm root cause analysis method based on the detection of correlations and time delays between alarm variables. First, two types of alarm correlations based on time stamps of alarm events are defined and the calculation methods are provided. Then, alarms are determined to be correlated or not by comparing with designed thresholds. Last, a causal matrix is formed to present the causal relations between alarms based on the directions of time delays. The effectiveness of the proposed method is demonstrated by both a numerical example and the benchmark Tennessee Eastman model. © 2021 IEEE

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on Deep Learning Network with Non-local Networks

Speech Emotion Recognition Based on Deep Learning Network wi...

引用

2021 China Automation Congress, CAC 2021

作者： Han, M.T. Liu, Z.T. School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

Convolutional Neural Networks (CNN) based Speech Emotion Recognition (SER) has the problem of learning bias towards stronger emotions while giving less weight to relatively faint emotions. This lack of subtleness causes the misclassification of emotions that have similar arousal such as anger and joy. To solve this problem, a novel speaker-independent SER methods consist of CNN with non-local networks and attention-based Bi-directional Long Short-Term Memory (BiLSTM) is proposed. The non-local networks can capture the dependence between any two points globally to enhance the correlation of emotional features at the utterance level. The extracted tri-channel Log-Mel spectrograms features include the raw of Log-Mel spectrums, the Log-Mel spectrums' deltas and delta-deltas respectively. Finally long-term contextual dependencies, local information and non-local information which is obtained by non-local networks is contained in the extracted feature. It was tested on the Interactive Emotional Dyadic Motion Capture Database (IEMOCAP) dataset. The experimental results show that the WAR of SER is 66.85% and the UAR of SER is 61.01%. Compared with several newly proposed SER methods, the effectiveness of the proposed model is demonstrated. © 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

Finite-Time State Estimation for Discrete-Time Nonlinear Singularly Perturbed complex Networks under New Event-Triggered Mechanism† 40

Finite-Time State Estimation for Discrete-Time Nonlinear Sin...

引用

40th Chinese control Conference, CCC 2021

作者： Yang, Chao Wan, Xiongbo China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9789881563804

This paper investigates the finite-time state estimation problem for a class of discrete-time nonlinear singularly perturbed complex networks under a new dynamic event-triggered mechanism (DETM). This new DETM is devised to adjust the date packet transmissions flexibly with hope to save network resources. By constructing a new Lyapunov function dependent on the information of the singular perturbation parameter (SPP) and DETM, a sufficient condition is derived which ensures that the error dynamics of state estimation is finite-time stable. The parameters of the state estimator are given by means of the solutions to several matrix inequalities and the upper bound of the SPP can be evaluated simultaneously. The effectiveness of the designed state estimator is demonstrated by a numerical example. © 2021 Technical Committee on control Theory, Chinese Association of Automation.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Benefit from public unlabeled data: A Frangi filtering-based pretraining network for 3D cerebrovascular segmentation

arXiv

引用

arXiv 2023年

作者： Shi, Gen Lu, Hao Hui, Hui Tian, Jie School of Engineering Medicine School of Biological Science and Medical Engineering Beihang University Beijing100191 China Ministry of Industry and Information Technology of China Beijing100191 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academic of Science Beijing10086 China CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing100190 China

The precise cerebrovascular segmentation in time-of-flight magnetic resonance angiography (TOF-MRA) data is crucial for clinically computer-aided diagnosis. However, the sparse distribution of cerebrovascular structures in TOF-MRA results in an exceedingly high cost for manual data labeling. The use of unlabeled TOF-MRA data holds the potential to enhance model performance significantly. In this study, we construct the largest preprocessed unlabeled TOF-MRA datasets (1510 subjects) to date. We also provide three additional labeled datasets totaling 113 subjects. Furthermore, we propose a simple yet effective pertraining strategy based on Frangi filtering, known for enhancing vessel-like structures, to fully leverage the unlabeled data for 3D cerebrovascular segmentation. Specifically, we develop a Frangi filtering-based preprocessing workflow to handle the large-scale unlabeled dataset, and a multi-task pretraining strategy is proposed to effectively utilize the preprocessed data. By employing this approach, we maximize the knowledge gained from the unlabeled data. The pretrained model is evaluated on four cerebrovascular segmentation datasets. The results have demonstrated the superior performance of our model, with an improvement of approximately 3% compared to state-of-the-art semi- and self-supervised methods. Furthermore, the ablation studies also demonstrate the generalizability and effectiveness of the pretraining method regarding the backbone structures. The code and data have been open source at: https://***/shigen-StoneRoot/FFPN. © 2023, CC BY.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Distributed PV Identification Based on High-Precision Bus Data Analysis

Distributed PV Identification Based on High-Precision Bus Da...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

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

ISBN: (纸本)9781728168531

With the rapid development of distributed photovoltaic (PV), it is necessary to study its low-cost output identification technology. In this paper, a low-cost PV output identification method is proposed by using feature extraction. This paper analyzes the high-precision bus data, and uses harmonic analysis, wavelet analysis and Ensemble Empirical Mode Decomposition (EEMD) to extract the operating features of PV output. Then this paper screens these extracted features with the correlation between features and PV output, the stability of the features at different times and the difference of features in different signals. The appropriate features are selected for PV output identification, and its identification accuracy is calculated. The experimental results show that with the method of the Ensemble Empirical Mode Decomposition, an appropriate operating feature can be extracted. This feature can identify the distributed PV output in small bus bar when the PV is working stably. © 2020 IEEE.

关键词： Empirical mode decomposition

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：