检索结果-内蒙古大学图书馆

2024 CSAA/IET International Conference on Aircraft Utility Systems, AUS 2024

作者： Mou, Quanrun Liu, Xiaochao Wang, Zhenyu Qiu, Zhongyi Li, Juefei Jiao, Zongxia School of Aeronautic Science and Engineering Beihang University Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China Ningbo Institute of Technology Beihang University Ningbo China Science and Technology on Aircraft Control Laboratory Beihang University Beijing China Tianmushan Laboratory Xixi Octagon City Yuhang District Hangzhou310023 China

In this paper, an active load-sensitive valve-controlled variable displacement motor drive system is introduced, aiming at solving the problem of large energy waste in valve-controlled fixed-displacement system. The fixed-displacement system is unable to match the variable load conditions promptly due to the fixed displacement, resulting in serious throttling losses under small load conditions. This study analyses the energy consumption characteristics by establishing a mathematical model of the active load-sensitive drive system. In addition, the nonlinear mapping of displacement and load pressure difference is designed, and simulation verification of comparing active load-sensitive drive system with the valve-controlled fixed-displacement motor drive system is completed. By analysing the simulation results, it can be seen that the active load-sensitive drive system can reduce the average flow rate by 68% and the peak flow rate by nearly 66% under the small load condition, which effectively solves the problem of heavy throttling loss in the valve-controlled hydraulic system. © The Institution of engineering & Technology 2024.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Individual Pitch control for Blade Fatigue Load Reductions for a 15 MW Wind Turbine

Multi-Objective Optimization of Individual Pitch Control for...

引用

European control Conference (ECC)

作者： Manuel Lara Francisco Vázquez Jan-Willem van Wingerden Sebastiaan Paul Mulders Juan Garrido Department of Electrical Engineering and Automation University of Cordoba Cordoba Spain Delft Center for Systems and Control Faculty of Mechanical Engineering Delft University of Technology Delft The Netherlands

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In order to mitigate periodic blade loads in wind turbines, recent research has analyzed different Individual Pitch control (IPC) approaches, which typically use the multi-blade coordinate (MBC) transformation. Some of these studies show that the introduction of an additional tuning parameter in the MBC, namely the azimuth offset, helps to decouple the nonrotating axes in the MBC transformation and enhances the IPC performance. However, these improvements have been studied without considering the increased control effort performed by the pitch signal, which is the main negative side effect of the IPC. This work addresses this trade-off between pitch signal effort and blade fatigue reduction for IPC applied to a wind turbine operating in the full load region. Here, two IPC schemes, with and without additional azimuth offset, are designed and applied to a 15 MW monopile offshore wind turbine simulated with OpenFAST software. The optimal tuning of the IPC parameters is performed by means of a multi-objective optimization solved by genetic algorithms. The optimization procedure minimizes two objective functions related to pitch signal effort and blade fatigue load. The resulting Pareto fronts show a range of optimal solutions for each IPC scheme. The selected optimal solution for IPC with azimuth offset compared to the optimal solution for IPC without offset achieves improvements of more than 10% in blade load reduction maintaining similar pitch signal effort.

关键词： Azimuth Blades Simulation Fatigue Linear programming Software Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation and Tracking control of MIMO Linear Systems Without Prior Knowledge of control Signs and Parameter Bounds

引用

IEEE Transactions on Automatic control 2024年第6期70卷 3695-3710页

作者： Xu, Yuchun Zhang, Yanjun Zhang, Ji-Feng Chinese Academy of Sciences Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Beijing100190 China Beijing Institute of Technology School of Automation Beijing100081 China Beijing Institute of Technology State Key Lab of Automation Intelligent Unmanned Systems Beijing100081 China University of Chinese Academy of Sciences School of Mathematics Sciences Beijing100149 China Zhongyuan University of Technology School of Automation and Electrical Engineering Zhengzhou450007 China Chinese Academy of Sciences Academy of Mathematics and Systems Science Beijing100190 China

Dealing with the uncertain high-frequency gain matrix, denoted as Kp, is a fundamental problem in multivariable adaptive control systems. In this paper, we propose a new solution for parameter estimation and adaptive control for a general class of multi-input multi-output discrete-time linear time-invariant systems. The proposed scheme does not require any prior knowledge of the sign or bound information of Kp, and thus, significantly relaxes the design conditions in traditional multivariable adaptive control systems. Compared with the commonly used Nussbaum gain or multi-model techniques for addressing the unknown signs of Kp, the proposed scheme does not rely on any additional design conditions or any switching mechanism, while still ensuring closed-loop stability and asymptotic output tracking. Specifically, an output feedback adaptive control law is developed based on a matrix decomposition technique, which leads to derivation of a modified estimation error model. Subsequently, a gradient-based parameter update law is formulated only relying on the non-zero condition of the leading principle minors of Kp. Through designing gain functions and stable filters, the controller is always non-singular and does not involve any causal contradiction problem. Simulation study showcases the design process and demonstrates the effectiveness of the proposed scheme. © 1963-2012 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Audio-visual speech enhancement by using the correlation deeply 4

Audio-visual speech enhancement by using the correlation dee...

引用

4th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2021

作者： Wang, Xiaolong Zhang, Jing Li, Wei School of Electrical Engineering and Automation Anhui University China School of Control Science and Engineering Shandong University China

ISBN: (纸本)9781450385053

Audio-visual speech separation aims to separate distinct voice from an audio mixture of multiple simultaneous speakers. The problem is that visual information can't be fully utilized. We propose a network which can improve the functioning of speech enhancement by using the correlation between audio and vision deeply. We propose that we could extract visual feature information by utilizing speech before using visual information to improve speech enhancement performance. We make a continuous dataset, CRF, to fit the network at the same time. The results demonstrate that the combination of them can improve the performance of speech enhancement effectively. © 2021 ACM.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Optimizing Indoor Vertical Farming with DDPG Reinforcement Learning: Enhancing control of Nutrient Levels, Climate Conditions, and Plant Health

Optimizing Indoor Vertical Farming with DDPG Reinforcement L...

引用

International Conference on Technology, Informatics, Management, engineering, and Environment (TIME-E)

作者： Albert Good Fried Panggabean Rahmat Romadhon Ramot Lubis Endra Joelianto Doctoral Program in Engineering Physics Institut Teknologi Bandung Bandung Indonesia Faculty of Informatics and Electrical Engineering Institut Teknologi Del Toba Indonesia Engineering Physics Study Program Institut Teknologi Bandung Bandung Indonesia Instrumentation Control and Automation Research Group Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9798350364750

ISBN: (纸本)9798350364767

In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as nutrient levels, climate conditions, and plant health indicators. To address these challenges, this paper presents a novel approach for optimizing indoor vertical farming using Deep Deterministic Policy Gradient (DDPG), a reinforcement learning algorithm well-suited for environments with continuous action spaces. Our study focused on the control and monitoring of key parameters, including nutrient levels (pH and EC), climate conditions (temperature, humidity, light, and CO2 levels), and plant health indicators (biomass accumulation and leaf size structure). By defining a comprehensive state and action space, we simulated an indoor farming environment and trained the DDPG model to maximize crop yield and health.

关键词： Smart agriculture Precision agriculture Reinforcement learning Humidity Aerospace electronics Nutrients Temperature control Informatics Monitoring Farming

来源：评论

学校读者我要写书评

暂无评论

Classification of skin lesions using morpho-granulometry features derived from color clusters

Classification of skin lesions using morpho-granulometry fea...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Gigi Tăbăcaru Simona Moldovanu Marian Barbu Department of Automatic Control and Electrical Engineering Faculty of Automation Computers Electrical Engineering and Electronics "Dunarea de Jos" University of Galati Galati Romania Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics The Modelling & Simulation Laboratory "Dunarea de Jos" University of Galati Galati Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

The skin lesion can be thought of as a biological system, so the morpho-granulometry of significant color clusters found in skin lesions is one of the elements that reproduce in a natural way the structure of the lesion, this novelty is highlighted in this study. Important features of skin lesions can be modulated by fusing neural networks (NN) and machine learning (ML). By choosing the nevus and melanoma classes, the primary goal was accomplished, and three databases were used to test the methodology. The characteristics based on morpho-granulometry allowed for the identification of microstructure within the images, which can be very helpful in characterizing the biological system. Based on random forest (RF) and extreme gradient boosting (XGboost) classifiers, this work aimed to improve the classification performance of important feature selection. The selected features from three free image databases with three NNs were classified. In a binary classification of nevus vs. melanoma, the results showed that the pattern recognition neural network (PRNN), according to the PH2 database, provided an accuracy of 0.923 and an F1-score of 0.876. The classification is interpretable if it is not validated. In our study, the best results were verified with a logistic regression (LR) classifier.

关键词： Accuracy Recurrent neural networks Image color analysis Melanoma Biological systems Artificial neural networks Feature extraction Skin Lesions Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control with Disturbance Compensation for Trajectory Tracking of Three-Degree-of-Freedom Spherical Joint Actuator 27

Model Predictive Control with Disturbance Compensation for T...

引用

27th International Conference on electrical Machines and Systems, ICEMS 2024

作者： Wen, Yan Chen, Ziyang Li, Guoli Wang, Qunjing Zhang, Qian Ju, Lufeng Anhui University School of Internet Hefei China Anhui University School of Electrical Engineering and Automation Hefei China Anhui University National Engineering Laboratory of Energy-Saving Motor & Control Technology Hefei China Anhui University Anhui Key Laboratory of Industrial Energy-Saving and Safety Hefei China Anhui University Anhui Collaborative Innovation Center of Industrial Energy-Saving and Power Quality Control Hefei China

ISBN: (纸本)9784886864406

To address tracking errors and susceptibility to interference in the actual trajectory of the three-degree-of-freedom (3-DOF) spherical joint actuator, a model predictive tracking control scheme incorporating disturbance compensation is proposed. Firstly, the nonlinear dynamics model of the 3-DOF spherical joint actuator is linearized through the feedback linearization. Then, model predictive control is employed to manage the multivariate constraint problem and achieve online rolling optimization. On this basis, disturbance compensation is added to eliminate the influence of external disturbance and to control the 3-DOF spherical joint actuator more accurately. Finally, the simulation results demonstrated the effectiveness and precision of the proposed control algorithm. This strategy effectively ensures the stability of the system's closed-loop system. It maintains strong robustness in the presence of external disturbance, which allows the 3-DOF spherical joint actuator to reach the desired position steadily. © 2024 The Institute of electrical Engineers of Japan.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation Integrated with Feature-Enhanced Convolutional Neural Network for Imbalanced Fault Diagnosis in Rolling Bearings 13

Data Augmentation Integrated with Feature-Enhanced Convoluti...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Wang, Li Qu, Qilin Wang, Yanwei Wong, David Shan-Hill Zheng, Ying School of Artificial Intelligence and Automation Huazhong University of Science and Technology China -Belt and Road Joint Laboratory on Measurement and Control Technology Wuhan430074 China School of Mechanical & Electrical Engineering Wuhan Institute of Technology 693 Chuxiong Road Wuhan430073 China National Tsing-Hua University Department of Chemical Engineering Hsinchu30071 Taiwan

ISBN: (纸本)9798350361674

Imbalance in fault samples is a key problem with most rolling bearing datasets in real industrial processes, limiting the performance of fault detection. In addition, existing fault diagnosis methods for rolling bearings do not adopt a modular division between the initial layer and the classification layer. This lack of modularization inhibits the full activation of the network's feature extraction capabilities and impedes subsequent model improvements. In this paper, a novel fault diagnosis method based on data augmentation integrated with a feature-enhanced convolutional neural network (DA-FECNN) is proposed. First, Variational Autoencoder-Generative Adversarial Network (VAE-GAN) is utilized to expand the number of fault samples and improve the diversity of few-shot. Second, a uniform feature-enhanced structure is designed with a feature extraction module, a multi-scale classification module, and a reconstruction module. The network's ability on feature extraction is improved by focusing on high quality features. Thereby, accurate fault classification is realized simultaneously. Experiments on real world data show the effectiveness of the proposed method on fault diagnosis task. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Recognizing knee pathologies by using gait dynamics via kernel principal component analysis and deterministic learning theory

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第11期14卷 15535-15543页

作者： Deng, Muqing Feng, Xiaoreng Zeng, Wei Cao, Jiuwen Zhang, Yu Zheng, Tongjia Institute of Information and Control Hangzhou Dianzi University Hangzhou China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin Hong Kong Department of Orthopaedics and Traumatology Queen Mary Hospital the University of Hong Kong Pok Fu Lam Hong Kong College of Mechanical and Electrical Engineering Longyan University Longyan China Department of Orthopaedic Surgery Guangzhou General Hospital of Guangzhou Military Command Guangzhou China College of Engineering University of Notre Dame Notre DameIN United States

This study concentrates on dynamical motion characteristics of knees during treadmill walking, and describes the application of kernel principal component analysis and deterministic learning theory to the detection of abnormal gait dynamics induced by knee pathologies. First, twelve-dimensional knee joint rotation and translation parameters are measured by a marker-based motion analysis system during treadmill walking. Second, the dimension of the gait parameter signal is reduced based on kernel principal component analysis. Third, gait dynamics underlying time-varying gait parameter signal is captured by using localized radial basis function neural networks through deterministic learning mechanism. This kind of dynamics information represents the frame-to-frame temporal change of kinematics and kinetics modifications during treadmill walking, which is shown to be sensitive to the variance during knee pathologies. Gait patterns are represented as the gait dynamics underlying time-varying gait parameters. The training patters under different knee pathologies further constitute a uniform training dataset, containing all kinds of gait dynamics under different knee pathologies. By comparing the training patterns with a test knee gait pattern to be recognized, a set of recognition errors are generated. The average L1 norms of the errors are taken as the classification measure between the dynamics of the training gait patterns and the dynamics of the test pattern. A rapid recognition scheme can be achieved according to the smallest error principle. Experimental results show that encouraging recognition accuracy can be achieved. The proposed method is sensitive for the detection of knee pathologies and is capable of discharge of patients without knee pathologies. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Structural Design of Permanent Magnet Momentum Sphere for Attitude control of a Small-sized Spacecraft 26

Structural Design of Permanent Magnet Momentum Sphere for At...

引用

26th International Conference on electrical Machines and Systems, ICEMS 2023

作者： Fang, Zhaowei Guo, Xiwen Zhou, Rui Wang, Qunjing Zhang, Ronglin Anhui University School of Electrical Engineering and Automation Hefei China Anhui University National Engineering Laboratory of Energy-Saving Motor and Control Technology Hefei China Anhui University Collaborative Innovation Center of Industrial Energy-Saving and Power Quality Control Hefei China State Grid Lu'an Electric Power Supply Company Lu'an China

ISBN: (纸本)9798350317589

With the increasing application of small spacecraft, the momentum actuator, the core component of its attitude control system, has received more and more attention. Most of the traditional momentum actuators are redundantly designed with multiple single-direction momentum structures. The structure is complex and the efficiency is low, which is not conducive to the long-term on-orbit operation of the small spacecraft. Aiming at the above problems, a permanent magnet momentum sphere (PMMS) is proposed. Firstly, the basic structure of PMMS is given, and the mechanism of cogging torque is expounded according to the structure. Then, the model of PMMS is established in ANSYS by using virtual displacement method. According to the design requirements of PMMS, the relevant structural parameters are simulated and analyzed to reduce the influence of the cogging torque, and the optimal parameters that meet the design requirements are obtained. The simulation results confirm the rationality and effectiveness of PMMS design. © 2023 IEEE.

关键词： Permanent magnets

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：