检索结果-内蒙古大学图书馆

Dissolved oxygen concentration control in wastewater treatment process based on reinforcement learning

Science China(Technological Sciences) 2023年第9期66卷 2549-2560页

作者： DU ShengLi CHEN PeiXi HAN HongGui QIAO JunFei School of Artificial Intelligence and Automation Beijing University of TechnologyBeijing 100124China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of EducationBeijing 100124China Beijing Laboratory of Smart Environmental Protection Beijing 100124China

In this article, the dissolved oxygen(DO) concentration control problem in wastewater treatment process(WWTP) is *** existing control strategies that control DO concentration at a fixed value, here we develop a different control *** the proposed control framework, an intelligent control method of DO concentration based on reinforcement learning(RL)algorithm is presented to resolve the DO concentration control problem. By using the deep deterministic policy gradient(DDPG)algorithm, the DO concentration of the fifth tank in the activated sludge reactor can be adjusted dynamically. In addition, by designing two different reward functions and by analysing the relationships among effluent quality, energy consumption, and DO concentration, the target of energy-saving and emission-reducing is achieved. The simulation results indicate that the designed control method can reduce energy consumption while ensuring that the effluent quality meet the specified standards.

关键词： dissolved oxygen concentration wastewater treatment process intelligent control reinforcement learning energy-saving and emission-reducing

来源：评论

学校读者我要写书评

暂无评论

Observer-Based SMC for Discrete Interval Type-2 Fuzzy Semi-Markov Jump Models

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1913-1925页

作者： Qi, Wenhai Li, Runkun Shi, Peng Zong, Guangdeng Qufu Normal University School of Engineering Rizhao276826 China The University of Adelaide School of Electrical and Mechanical Engineering AdelaideSA5005 Australia Obuda University Research and Innovation Centre Budapest1034 Hungary Tiangong University School of Control Science and Engineering Tianjin300387 China Weifang University College of Machinery and Automation Weifang261061 China

This study is devoted to the observer-based sliding mode control (SMC) for discrete nonlinear semi-Markov jump models with incomplete sojourn information and application to the quarter-car suspension model. The nonlinear plant with parameter uncertainty is represented by an interval type-2 fuzzy model, where the membership functions of the fuzzy rules are related to the system mode. Since sojourn information is challenging to obtain in practice, the sojourn time probability density function is considered to be incompletely available. The considered system is more general, not only relaxing the traditional assumption that all the sojourn time probability density functions are completely available, but also covering completely available sojourn time probability density functions as a special case. The main innovation is that an observer-based SMC scheme is designed, which makes the discrete nonlinear models have better dynamic performance, and realizes the reachability of discrete quasi-sliding mode. By the interval type-2 fuzzy and classical Lyapunov function, the mean-square stability criterion of the semi-Markov jump models is constructed employing additional matrix variables. Then, an observer-based SMC mechanism is constructed to achieve the reachability of the quasi-sliding mode. Ultimately, the proposed method is validated by a two-degree-freedom quarter-car suspension model. © 1993-2012 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Efficient Mobile Deployment of Lightweight CNN-Transformer Model for Crop Disease Diagnosis in Smart Agriculture 4

Efficient Mobile Deployment of Lightweight CNN-Transformer M...

引用

4th Asia Conference on Information engineering, ACIE 2024

作者： Lv, Zirong China University of Geosciences Hubei Key Lab. of Adv. Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation Wuhan China

ISBN: (纸本)9798350371925

Crop disease diagnosis is of great significance for crop yield and agricultural production. Deep learning methods have become a major research direction for solving crop disease diagnosis. However, recent studies have shown that deploying complex neural network models on mobile devices poses a significant challenge to mobile hardware performance. To address this issue, this paper proposes a lightweight network model based on the Transformer and deploys it on mobile devices. Compared to other lightweight network models, our approach significantly reduces computational complexity using Transformer modules and exhibits a particular advantage in recognition accuracy. It achieves a recognition rate of 97.76% for ten categories of tomato diseases, while the model size is only 3.86 MB. Furthermore, we deploy the model on embedded devices and apply it to tomato crop recognition, enabling farmers to monitor crop conditions in real-time and realizing smart agriculture. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Potato Leaf Disease Detection by Means of Vision Transformer and CoAtNet Architecture 5

Potato Leaf Disease Detection by Means of Vision Transformer...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Kenan Sergio, Mesa Anugerah Stevano Siallagan, Ariel Brandon Joelianto, Endra Institut Teknologi Bandung Engineering Physics Study Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia

ISBN: (纸本)9798350364743

Potatoes are a food source that is beneficial for humans in various aspects, such as having nutritional and economic value. However, potato plants are susceptible to many diseases. To address this issue, various researchers have suggested methods utilizing machine learning and image processing for automatic disease type detection. This paper introduces a disease detection model for potato leaf images, employing two computer vision techniques: Vision Transformer (ViT) and CoAtNet. The dataset used in this paper consisted of 30,760 augmented images divided into seven classes. The ViT model had a test accuracy of 99.32% and a validation accuracy of99.12%. Meanwhile, the CoAtNEt model had a test accuracy of 99.58 % and a validation accuracy of 99.48 %. These results show that both models can be used in the detection of potato leaf diseases. © 2024 IEEE.

关键词： CoAtNet image processing leaf disease potato vision transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-AI Trust by Describing AI Decision-Making Behavior

Enhancing Human-AI Trust by Describing AI Decision-Making Be...

引用

2023 IEEE International Conference on Unmanned Systems, ICUS 2023

作者： Lou, Zhouwei Wei, Haikun School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798350316308

Air combat game is a highly complex and dynamic decision-making problem that is crucial for ensuring national security and improving combat efficiency. In recent years, artificial intelligence (AI) technologies such as deep reinforcement learning have made significant progress in the air combat game field, surpassing human experts' capabilities. However, the decision-making process of AI algorithms often lacks transparency and interpretability, resulting in low trust in them, which limits their promotion and application in practical scenarios. To enhance human-AI trust, this paper proposes a decision explanation method based on natural language generation. As the most direct means of information transmission, natural language can help people quickly understand the behavior and intent of AI algorithms. Taking a one-on-one air combat game as an experimental scenario, this paper constructs a combat dataset mapping temporal states to behavioral explanations and designs an attention-based Encoder-decoder architecture (AED) capable of generating natural language descriptions of current AI decision-making behavior based on a period of combat data. Experimental results show that AED can accurately describe the decision-making behavior of AI algorithms and help improve the level of human-AI trust. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality Application in Digital automation Laboratory

Augmented Reality Application in Digital Automation Laborato...

引用

2023 International Symposium on Electrical and Electronics engineering, ISEE 2023

作者： Khang, Nguyen Trong Tran, Ngoc-Huy Phan, Nguyen-Phuc-Quoc VNU-HCM Faculty of Electrical & Electronics Engineering Department of Control & Automation Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350315486

Traditional automation engineering education using physical training equipment while quite effective, suffers from several limitations in the case there is no equipment access, which can be due to many reasons such as social distancing or financial difficulties. This article proposes a solution to overcome these limitations with the combinational use of mixed reality (MR), which helps the student get used to training equipment they have no access to, and augmented reality (AR), which brings intuitive visualization into real equipment practice. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Software Detection and Warning Method for Pitch Angle Deviation of Road Traffic Radar 9

Software Detection and Warning Method for Pitch Angle Deviat...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Sun, Haokai Zhang, Zheng Jari Technology Lianyungang Jari Electronics Co. Ltd Lianyungang China Jiangsu Automation Research Institute Control Science and Engineering Lianyungang China

ISBN: (纸本)9798350376548

Introduced a software detection and warning method for the installation angle of road traffic radar in the pitch direction. Establish a mathematical model M1 based on the directional pattern of the transmitting antenna in the elevation direction. According to the RCS definition, the normalized curve shape of the received target echo signal strength is the same as model M1. The normalization coefficient is determined by on-site calibration methods or empirical value methods, and the model M1 is inversely normalized to obtain the model M2. Substitute the statistical analysis result A of the received signal strength result P ' calculated after real-time and cumulative sampling into model M2 to obtain the current elevation angle information of the radar. If the change in radar pitch angle exceeds the threshold, an alarm message will be output. This method does not require the addition of hardware sensors, and only estimates the current elevation angle of the radar through software calculations based on mathematical models and on-site sampled target echo signal strength, which has good engineering application value. © 2024 IEEE.

关键词： Radar warning systems

来源：评论

学校读者我要写书评

暂无评论

Combined Model-Compensated and Quasi-Resonant Linear Active Disturbance Rejection control for PMSM Drives

Combined Model-Compensated and Quasi-Resonant Linear Active ...

引用

2023 China automation Congress, CAC 2023

作者： Chen, Songtao Mao, Xuefei Zhao, Lei Wang, Shuoyu Zhang, Jiyang School of Automation Beijing Institute of Technology Beijing100081 China Beijing Institute of Control Engineering Beijing100094 China

ISBN: (纸本)9798350303759

When operating at ultra-low speeds, Permanent Magnet Synchronous Motor (PMSM) is subject to disturbances such as non-linear frictional torque and periodic disturbance torque. These uncertain disturbances can cause fluctuations in speed, which deteriorate the speed loop performance. To address the problem, this paper proposed a linear active disturbance rejection control strategy (LADRC) that combined model-compensation and quasi-resonant control. The Stribeck model was chosen to estimate the non-linear frictional torque and input it into the linear expanding state observer (LESO) to reduce the estimation burden of LESO;The introduction of a quasi-resonant term (QR) in LESO improves the suppression of periodic harmonics in the mid-frequency band by linear active disturbance rejection control. Finally, the effectiveness of the proposed control strategy is verified by simulation experiments. © 2023 IEEE.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

High precision localisation of the sources of noise of a bent-axis motor

引用

Noise and Vibration Worldwide 2023年第7-8期54卷 350-359页

作者： Xu, Chen Xiangming, Meng Qinghong, Gong Hui, Huang Shumei, Chen Heng, Du Yuzheng, Li Xiufang, Lin School of Mechanical Engineering and Automation Fuzhou University Fuzhou China Key Laboratory of Fluid Power and Intelligent Electro-Hydraulic Control Fuzhou University Fuzhou China College of Physics and Electronic Information Engineering Minjiang University Fuzhou China

The hydraulic motor will generate noise in operation and it has fluid-structure coupling and compact internal structure. The sound intensity measurement is difficult to distinguish the noise sources of motor. In this paper, a high-precision localization method for noise sources of bent-axis motor is studied to improve the resolution of the sound intensity images to locate noise sources accurately. Firstly, the structural characteristics of the motor are analyzed, and the sound intensity images are obtained through the experiment. Then the high-resolution optimization method based on compressed sensing is designed according to the characteristics of the sound intensity field. Finally, the sound intensity images with high resolution are constructed. The high-resolution images can distinguish the position of the prominent points, and the error is less than 0.4 dB. The identification distance of noise sources can reach 30 mm, and it breaks through the highest resolution of the traditional sound intensity test. © The Author(s) 2023.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Characterization and identification towards dynamic-based electrical modeling of lithium-ion batteries

引用

Journal of Energy Chemistry 2024年第5期92卷 738-758页

作者： Chuanxin Fan Kailong Liu Yaxing Ren Qiao Peng School of Automation Nanjing Institute of TechnologyNanjing 211167JiangsuChina School of Control Science and Engineering Shandong UniversityJinan 250100ShandongChina School of Engineering University of LincolnLincoln LN67TSUK Information Technology Analytics&Operations GroupQueen’s University BelfastBelfast BT95EEUK

Lithium-ion batteries are widely recognized as a crucial enabling technology for the advancement of electric vehicles and energy storage systems in the *** design of battery state estimation and control algorithms in battery management systems is usually based on battery models,which interpret crucial battery dynamics through the utilization of mathematical ***,the investigation of battery dynamics with the purpose of battery system identification has garnered considerable attention in the realm of battery *** methods in terms of linear and nonlinear response of lithium-ion batteries have emerged as a prominent area of study in this *** review has undertaken an analysis and discussion of characterization methods,with a particular focus on the motivation of battery system ***,this work encompasses the incorporation of frequency domain nonlinear characterization methods and dynamics-based battery electrical *** aim of this study is to establish a connection between the characterization and identification of battery systems for researchers and engineers specialized in the field of batteries,with the intention of promoting the advancement of efficient battery technology for real-world applications.

关键词： Lithium-ion battery Battery dynamics Nonlinear characterization Nonlinear battery model

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：