检索结果-内蒙古大学图书馆

11th International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2023

作者： Liu, Shui Huang, Jiao College of Art and Design Changchun Humanities and Sciences College Jilin Changchun130117 China College of Foreign Languages and Literature Changchun Humanities and Sciences College Jilin Changchun130117 China

With the growth of personalized demand and the development of Industry 4.0, the limitations of traditional printing technology are increasingly prominent, and people's requirements for printing quality are constantly improving. In this study, the existing 3D printing control system is first studied, and then an AI control system based on DNN is designed and implemented. The system can optimize printing parameters by learning historical printing data, and automatically adjust the printing process to improve printing quality and resource utilization. The experimental results show that the printing speed of the automatic control system of 3D printing based on DNN can reach 297 cm/s, the surface roughness can be as low as 2μm, and the resource utilization rate can reach 88%, which significantly reduces the energy consumption and material waste in the printing process, and improves the surface quality and structural integrity of printed materials. © 2024 The Authors. Published by Elsevier B.V.

关键词： 3D Printing Artificial Intelligence automation control system Deep Neural Networks

来源：评论

学校读者我要写书评

暂无评论

3D Printing automation control system Based on Artificial Intelligence

引用

Procedia Computer Science 2024年 247卷 477-484页

作者： Shui Liu Jiao Huang College of Art and Design Changchun Humanities and Sciences College Changchun 130117 Jilin China College of Foreign Languages and Literature Changchun Humanities and Sciences College Changchun 130117 Jilin China

关键词： Artificial Intelligence 3D Printing automation control system Deep Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Implementation of reinforcement learning for enhanced pressure control in a 190,000-barrel crude distillation unit: The first full-scale commercial deployment

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 156卷

作者： Seo, Dongchan Kim, Dongil Son, Hyoeun Kim, Yusung Sungkyunkwan Univ Dept Semicond & Display Engn 2066 Seobu ro Suwon 16419 Gyeonggi Do South Korea Samsung Display Co Ltd 181 Samsung ro Asan 31454 Chungchengnam D South Korea SK Incheon Petrochem Co Ltd 415 Bongsu daero Incheon 22771 South Korea Sungkyunkwan Univ Dept Comp Sci & Engn 2066 Seobu ro Suwon 16419 Gyeonggi Do South Korea

We introduce the first successful full-scale implementation of a Reinforcement Learning-based Pressure control system (RLPCS) within a Crude Distillation Unit (CDU) in the petroleum refining industry. Our approach utilizes an offline reinforcement learning (RL) technique that leverages log data from multiple operators' manual operations to derive an optimal automated operational model. This method is safe as it does not interfere with the system currently in operation and does not incur additional operational costs. The trained model automates pressure control decisions, effectively resolving problems associated with manual control methods, such as high labor intensity and inconsistent operator control. To achieve this, we overcame various challenges related to training artificial intelligence (AI) in complex industrial environments. Our approach involved designing an appropriate Markov Decision Process (MDP) and incorporating a legacy control system for continuous data integration. We trained the Soft Actor-Critic (SAC) algorithm using offline data. However, applying the standard SAC algorithm to offline data and deploying this model directly in the online system posed substantial estimation problems. To address these, we integrated conservative loss and Return to Go into the SAC algorithm. Consequently, our model reduced operator intervention time by 84%, and variability in pressure control decreased significantly, resulting in a 12.8% reduction in cumulative errors. This demonstrates that RLPCS has reached the stage where it can be applied to permanent operations in real-world refining processes, not just a temporary demonstration. Building on this proven operational readiness, our work represents the industry's first large-scale commercial deployment of an RL-based pressure control model in a CDU. The novelty lies in the comprehensive integration of MDP formulation, model architecture, and algorithmic strategies, each carefully tailored to the complex industrial

关键词： Deep reinforcement learning automation control system Crude distillation unit Offline to online reinforcement learning Industry artificial engineering Artificial intelligence control system

来源：评论

学校读者我要写书评

暂无评论

Rapid and Automatic Image Acquisition system for Structural Surface Defects of High-Speed Rail Tunnels

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2024年第2期28卷 967-989页

作者： Qin, Shaojie Qi, Taiyue Lei, Bo Li, Zongyang Southwest Jiaotong Univ Sch Civil Engn Chengdu 610000 Peoples R China Highway Engn Consultants Supervis Co Chengdu 610000 Peoples R China

Continuous high-speed (>80 km/h) tunnel-image detection introduces new challenges to defect image acquisition, including machine recognition of entry and exit from a tunnel, storage of massive image data streams, image distortion due to surface photography, and encoder errors. In this study, an automatic image acquisition system is designed, and several critical technologies are proposed for high-speed rail tunnels. The system realizes quick tunnel identification and automatic camera control and uses the proposed line-scan software-matching method to obtain accurate images. Before storage, the real-time modification of the distorted images is implemented using an error-correction algorithm. An alternative mapping storage algorithm is proposed to improve the efficiency and stability of long-term storage. The test results show that the proposed method effectively reduces photographic errors. The lateral pixel-error rate of the corrected image is 1.60%, which is 10 times lower than that of the pre-correction, and the error rate of the longitudinal image is controlled within 10% when the system is moving at a variable speed and within 1% when it is moving at a constant speed. Furthermore, experiments have proven that the alternate mapping storage algorithm improves the storage efficiency of RAID by 50% and ensures data integrity;storage is accomplished by 8 HDDs at a camera throughput of 1.52 GB/s. This study will contribute to improvements in the speed and accuracy of tunnel defect-image detection.

关键词： High-speed rail tunnel Line-scan automation control system Image acquisition Data stream storage

来源：评论

学校读者我要写书评

暂无评论

Pumping system of the Vacuum Chamber of the Tokamak T-15MD Unit

引用

PHYSICS OF ATOMIC NUCLEI 2024年第7期87卷 876-883页

作者： Anashkin, I. O. Kochin, V. A. Obraztsov, I. S. Kurchatov Inst Natl Res Ctr Moscow 123098 Russia

This article presents describes the vacuum chamber pumping system of the new Tokamak T-15MD unit, including measurement of vacuum and mass spectrometry of working and residual gases, as well as a brief description of the vacuum pumping automation system and the main calculated vacuum characteristics. After assembling the unit at the site of the National Research Center Kurchatov Institute, the chamber was pumped out using the full range of standard vacuum pumping equipment and automation equipment. As a result, the residual pressure in the vacuum chamber was similar to 5 x 10(-6) Torr, and the leakage was similar to 5 x 10(-3) L Torr/s. The specified pumping system is being considered for the initial stages of the unit;in the future, installation of divertor pumping of the chamber is envisaged.

关键词： vacuum screw pump Roots pump turbomolecular pump cryosorption pump ultimate vacuum pressure pumping rate conductance automation control system

来源：评论

学校读者我要写书评

暂无评论

Choosing an IT Strategy for Digital Transformation of Production Based on Game Theory

Choosing an IT Strategy for Digital Transformation of Produc...

引用

2024 International Conference "Quality Management, Transport and Information Security, Information Technologies", QM and TIS and IT 2024

作者： Sheptunov, Sergey A. Sukhanova, Natalia V. Institute of Design-Technology Informatics The Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9798350367522

There are several strategies for the digital transformation of production. The choice of strategy is based on the criterion of product quality improvement. A model based on game theory is proposed. There are two players in the game: The first player is the external environment. The second player is the enterprise management system. Each player chooses and forms his own game strategy. Each player has his own goal and his own criteria for winning the game. The result of the implementation of different strategies is the win. The amount of each player's winnings is estimated in conditional points. It is necessary to choose the strategy that gives the greatest gain. To solve this problem, it is proposed to use game theory, fuzzy logic, and artificial neural networks. The expected result is the increase of the product quality. © 2024 IEEE.

关键词： artificial intelligence methods artificial neural networks automation control system externalenvironment fuzzy logic game theory internal production environment of the enterprise management strategies

来源：评论

学校读者我要写书评

暂无评论

A Long Distance Low Bandwidth Firmware Update process for LPWAN - Taking LoRaP2P+as example 37

A Long Distance Low Bandwidth Firmware Update process for LP...

引用

37th International Conference on Information Networking (ICOIN)

作者： Khieng, Daniel Ho Teck Xie, Yu-Zhe Zhang, Jia-Cheng Huang, Nen-Fu Natl Tsing Hua Univ Hsinchu Taiwan Natl Tsing Hua Univ Dept Comp Sci Hsinchu Taiwan

ISBN: (纸本)9781665462686

The increment of IoT devices in the world due to the manpower shortage can be commonly seen around the world nowadays. In agriculture, revolutionary technologies which involve automation has been anticipated in order to face this serious issue. With LPWAN technologies, we can achieve automated mass irrigation almost without the need for manpower involvement. For most crops, production and yield are directly related to crop water use, hence resulting in the importance of precise watering. Device firmware updates for the endpoint devices play an important role to maintain the reliability and security of these system. For a system that is using LPWAN, which is commonly deployed in rural areas, the firmware update over the air(FUOTA) feature can provide the possibility of rolling out a system update without the need to have physical contact with the device while also ensuring all the devices are up-to-date. In this article, we designed a FUOTA process for LPWAN. Through FUOTA, the update patches can be deployed to the devices effortlessly and efficiently further reducing the manpower shortage problem while improving the feature and functionality of the system.

关键词： Wireless LPWAN LoRaP2P LoRaP2P+ Reliability automation control system FUOTA Firmware Update

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based High-Quality Code Intelligent Matching Tool for Industrial control Programs 25

A Cloud-Based High-Quality Code Intelligent Matching Tool fo...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Yingzhe Bao Danfeng Sun Junhui Liu Jin Fan Huifeng Wu Zhejiang Key Laboratory of New Industrial Internet Control Technology Hangzhou Dianzi University hangzhou China

ISBN: (纸本)9798400713316

The programmable logic controller (PLC) is the core of automation control systems. With Industry 4.0, PLCs have evolved from simple controllers to intelligent industrial nodes. However, as technologies such as cloud computing and artificial intelligence integrate into industrial automation, traditional monolithic development software struggles with scalability and efficiency, failing to meet the rapid iteration needs of control programs in complex industrial scenarios. This paper introduces a cloud-based high-quality code intelligent matching tool for industrial control programs, aimed at shortening the development time of control systems and enabling rapid iterative development of programs. The matching tool includes two main modules: the code matching module and the code quality assessment module. These modules enable rapid code reuse based on the source program database.

关键词： automation control system

来源：评论

学校读者我要写书评

暂无评论

Plate Production Line automation control system based on Automatic Gauge control

Plate Production Line Automation Control System based on Aut...

引用

2nd International Conference on Green Power, Materials and Manufacturing Technology and Applications (GPMMTA 2012)

作者： Yu, Wenwei Wang, Xuetao Changzhou Inst Mechatron Technol Changzhou Peoples R China

ISBN: (纸本)9783037854969

The automation control system to plate production line is developed independently. It has been applied several plants in China and has a good effect. The whole automaton control system is designed as several levels: basic automation. system process, automation system. and HMI system. The control functions are realized with these levels. With AGC function in plate mill area basic automation system, the plate thickness accuracy can be guaranteed.

关键词： Plate Mill automation control system Basic automation system Process automation system

来源：评论

学校读者我要写书评

暂无评论

Pick a Right Puppy from a Litter, Toward a Secure controller Framework in Physical, Human and Cyber Triad

Pick a Right Puppy from a Litter, Toward a Secure Controller...

引用

IEEE Information Technology, Networking, Electronic and automation control Conference (ITNEC)

作者： Li, Depeng Univ Hawaii Manoa Dept Informat & Comp Sci Honolulu HI 96822 USA

ISBN: (纸本)9781467391948

Malicious controllers can possibly manipulate a flight from various channels, e.g. pilots, automation control devices, or cyber remote control. To mitigate potential risks and possible damages, this paper provides the early stage study through proposing a theoretical framework for access control and malicious controller detection in physical, human and cyber triad. Its goal is first to construct an access control mechanism by granting appropriate access right for each controller regarding each control action and more importantly, assign the threshold the number of controllers from each channel for each control action to ensure that the control action cannot be executed without sufficient controllers' endorsement. Second, a detailed architecture and data flow between neighbor layers are demonstrated. Third, we try to build a misbehavior identification and reputation index to recognize bad controllers. Our future work is to further profile and model the malicious behaviors which will be justified by well-designed experiments based on critical parameters and metrics for concrete case studies.

关键词： access control mechanism automation control system aircraft safety cyber physical system secret sharing scheme

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：