检索结果-内蒙古大学图书馆

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Agustina, Nilla Perdana Darwito, Purwadi Agus Physics Engineering Master Program Faculty of Industrial Technology and System Engineering Surabaya Indonesia Physics Engineering Department Faculty of Industrial Technology and System Engineering Surabaya Indonesia

ISBN: (纸本)9798350313956

In this paper, a control system based on Sliding Mode Control (SMC) and Kalman Filter has been designed to stabilize the quadcopter in the takeoff and hover phases as well as at the expected altitude. The control system is needed to support the performance of the quadcopter in carrying out the mission that has been given. The designed control system begins with the creation of a system model equation and is implemented in a real quadcopter simulation. The resulting response in terms of the results of the resulting control signal is stable, meets the trajectory as expected, and can produce a real quadcopter simulation taking off vertically and flying stably. Even though there was an unstable response for about 15 to 20 seconds at the beginning of the resulting response, after that the system showed stability. Tracking the resulting trajectory in accordance with the desired trajectory. Real quadcopter simulation results show that the takeoff phase can be carried out vertically and that the resulting trajectory stability can be stable during takeoff and flight. The height of the quadcopter has reached 100%, namely with a height of 1.5 meters as expected, and the average error value obtained at the x position is 2.93e^-07, the y position is 2.96e^-07, and the z position is 1.80e^-03. The proposed SMC-Kalman filter control system is expected to be implemented in a conventional quadcopter that has been developed. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Loss Balancing for Physics-Informed Neural Networks Considering Procedure for Solving Partial Differential Equations 13

Loss Balancing for Physics-Informed Neural Networks Consider...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Kojima, Manabu Otsuki, Kazuma Suzuki, Masato Abe, Masajiro Baba, Masaaki Yokota, Kazuya Master's Program in Mechanical Engineering Nagaoka University of Technology Nagaoka Japan Nagaoka University of Technology Department of System Safety Engineering Nagaoka Japan Nagaoka University of Technology Department of Mechanical Engineering Nagaoka Japan

ISBN: (纸本)9798350373332

With the development of machine learning, numerical analysis using neural networks has been devised. Remarkably, physics-informed neural networks (PINNs) enable physically consistent numerical analysis by introducing a loss function that conforms to relevant governing equations. Moreover, research is rapidly advancing for the application of PINNs to inverse analysis in areas such as physical property identification. For a PINN to learn governing equations, the weights of the loss functions should be properly determined because they have different roles in components such as boundary conditions, initial conditions, and governing equations. However, weight setting is generally challenging. We propose a loss balancing method considering the procedure for solving partial differential equations. The proposed method is validated through comparisons with conventional solvers. © 2024 IEEE.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Characterization of Municipal Solid Waste Based on Seasonal Diversity as Energy Potential Materials 7

Characterization of Municipal Solid Waste Based on Seasonal ...

引用

7th Astechnova International Energy Conference, ASTECHNOVA 2023

作者： Mariatunnikmah, Khusnul Ain Lubis, M Faisal Wintoko, Joko Budiman, Arief Master Program in System Engineering Universitas Gadjah Mada Jalan Teknika Utara 3 Yogyakarta55281 Indonesia Chemical Engineering Department Universitas Gadjah Mada Jalan Grafika 2 Yogyakarta55284 Indonesia

Interrelated problems related to resource availability and population growth rates, such as energy demand and waste generation, have become pressing global concerns. Municipal Solid Waste (MSW) poses a significant challenge due to its impact on society and the environment, including the associated hazards and threats. This study was conducted at the Piyungan Integrated Santary Landfill (TPST Piyungan) in Yogyakarta, Indonesia, from June to November 2022. The annual waste generation in the city is 586,267.37 tons per year in 2021, with a daily per capita waste generation rate of 0.43 kg/person. Two types of MSW samples were collected during the dry and rainy season to assess their composition. The collected samples were sorted, sun-dried, quartered, and reduced to 1mm particles for proximate analysis. The results of MSW characterization revealed that non-organic combustible materials accounted for a higher percentage during the dry season (62.7%) compared to the rainy season (53.1%). Conversely, organic matter constituted a higher proportion during the rainy season (36.7%) compared to the dry season (30.4%). The moisture content ranged from 4 to 11%, volatile matter content varied between 60% and 66%, and fixed carbon content ranged from 19 to 31%. The energy content of MSW during the dry season was measured at 20.67 MJ/kg, while in the rainy season, it yielded 14.99 MJ/kg. These findings indicate that due to the substantial energy content and waste generation rates, waste-to-energy (WtE) technologies can be effectively applied to manage MSW in Yogyakarta, simultaneously reducing waste volumes and recovering energy. © Published under licence by IOP Publishing Ltd.

关键词： Moisture determination

来源：评论

学校读者我要写书评

暂无评论

A Vision-Based Neural Networks Model for Turbine Trench-Filler Diagnosis 1

引用

7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023

作者： Isaza, Cesar Guerrero-Garcia, Fernando Anaya, Karina Jenab, Kouroush Ortega-Moody, Jorge Networking and Telecommunication Academic Program Polytechnic University of Queretaro Queretaro Mexico Productive System Master Academic Program Polytechnic University of Queretaro Queretaro Mexico School of Engineering and Computer Science Morehead State University MoreheadKY40351 United States

ISBN: (数字)9783031396199

ISBN: (纸本)9783031396182

Vision-based neural networks as artificial intelligence models have been critical in many manufacturing industries, including automotive, food, and aerospace. Machine vision and deep learning have provided practical, promising, and accessible innovations to address many problems during manufacturing and diagnostics. Recent studies offer beneficial results in implementing industrial artificial intelligence systems that require determining, comparing, and evaluating optimal technological solutions. The aerospace industry has to deal with the problem of diagnosing critical components that continually need the expertise of a trained human being. On the other hand, automatic diagnostics are becoming a critical technology to deal with this problem. However, these systems require a particular configuration of computer vision algorithms which, in the case of turbine trench-filling components, have yet to be added to the literature. Considering the above, we report in this paper a new methodology that uses a pre-trained deep neural network framework available online to automatically diagnose geometric nonconformities in aeronautical components that protect the turbines from vibrations and reduce noise from the engines to the aircraft deck. The method is based on the following stages: a computer vision system with a monochrome camera to acquire images, training of deep neural networks with transfer learning, and a stage to analyze nonconformities automatically. In addition, a benchmark of several pre-trained deep neural networks is presented to address the problem. According to the experimental results, the YOLO deep neural network topology significantly contributes to automatic diagnosis with high precision and exact rate. Finally, we show that integrating deep neural networks with control graphs is a promising strategy to optimize online diagnostics in the production lines of the aeronautical industry. © The Author(s), under exclusive license to Springer Nature Switzerland

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluating CO₂ concentration effects on growth kinetics and fatty acid composition in Euglena gracilis

引用

Applied Phycology 2024年第1期5卷 1-11页

作者： Erfianti, Tia Sadewo, Brilian Ryan Daryono, Budi Setiadi Budiman, Arief Suyono, Eko Agus Faculty of Biology Universitas Gadjah Mada Yogyakarta Indonesia Department of Chemical Engineering Faculty of Engineering Universitas Gadjah Mada Yogyakarta Indonesia Center of Excellence of Microalgae Universitas Gadjah Mada Jl. Bhinneka Tunggal Ika Yogyakarta Indonesia Master Program in System Engineering Universitas Gadjah Mada Yogyakarta Indonesia

Industrial development has significantly increased CO2 emissions, from 280 ppm in the pre-industrial era to over 400 ppm today, contributing to the greenhouse effect and climate change. This study investigates the imp... 详细信息

Industrial development has significantly increased CO₂ emissions, from 280 ppm in the pre-industrial era to over 400 ppm today, contributing to the greenhouse effect and climate change. This study investigates the impact of varying CO₂ concentrations on the growth, biomass accumulation, and biochemical composition of Euglena gracilis as microalgae-based carbon capture and utilization. E. gracilis was cultivated with CO₂ concentrations of 0%, 5%, 10%, and 30%, using white LED lights at 3000 lux. Growth was monitored through cell counts and optical density, while biomass and primary metabolites were analysed using standard methods. Fatty acid content was assessed using GC-MS and GC-FID. The results showed optimal growth at 5% CO₂, with biomass reaching 2.3 g l^‒1 on the day of harvest. The highest lipid content was obtained in the 15% CO₂ treatment with a total lipid of 0.35 g l^‒1. As for the decrease in pH, it showed that each treatment experienced a reduction in pH from 3.5 to almost 2.0. Fatty acid content was dominated by polyunsaturated fatty acids (PUFAs), especially in the control group and 15% CO₂ treatment, contributing up to 47.66%, and 46.36% to the group, respectively. The study highlights the importance of optimizing CO₂ levels for microalgae cultivation to enhance biomass and lipid production. Elevated CO₂ levels boost lipid synthesis but can stress cells if too high, suggesting a need for adaptive CO₂ addition methods. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： CO2 Euglena gracilis fatty acids growth kinetics lipid microalgae

来源：评论

学校读者我要写书评

暂无评论

Random Number Generator for Securing Data Exchange in Smart Factory: Recent Trends and Best Practices 3

Random Number Generator for Securing Data Exchange in Smart ...

引用

3rd International Conference on Computer Technologies, ICCTech 2024

作者： Sama, Andi Meyliana Heryadi, Yaya Sahroni, Taufik Roni Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Information System Information System Department Jakarta11480 Indonesia BINUS Graduate Program-Doctor of Computer Science Jakarta Computer Science Department Jakarta11530 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Industrial Engineering Industrial Engineering Department Jakarta11480 Indonesia

ISBN: (纸本)9798350395419

IT/OT convergence in the form of a Cyber-Physical system (CPS) presents an opportunity to apply recent Information Technology (IT) advancements to Operational Technology (OT). The IT/OT convergence introduces cyber security threats for OT. The OT communication protocols, for example, have limited or no security capabilities for securing data exchange beyond basic authentication. The RNG (Random Number Generator) function is crucial in PLC for producing the encryption keys or the initial seed for security algorithms. The software-based PRNG (Pseudo RNG) is the most common approach for RNG in OT, instead of hardware-based RNG. This study provides a systematic literature review of the most recent evidence in digital transformation to secure data exchange in smart factories, within OT, or across OT and IT settings. It does this by looking at the PRNG on PLC and identifying the most recent trends and best practices. The findings include up-to-date data on author countries' distribution, published journals, research trends, industries, and industry types. The findings also address whether data flow is encrypted or shared in plaintext to ensure secure data transfer between IT and legacy OT environments. This paper concludes that while there is known RNG implementation in the actual embedded system in ICS, there is no evidence in the literature for using RNG in ICS networks for PLC implementation to secure data transfer with encryption. © 2024 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Mixed-Reality Simulator for Analysis of Interactions between Humans and Crawler Cranes 13

Mixed-Reality Simulator for Analysis of Interactions between...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Yamanobe, Kenta Yokota, Kazuya Uenoyama, Daigo Fujiura, Daisuke Ogura, Masataka Takahashi, Kengo Abe, Masajiro Nagaoka University of Technology Master's Program in Mechanical Engineering Nagaoka Japan Nagaoka University of Technology Department of Mechanical Engineering Nagaoka Japan Nagaoka University of Technology Bachelor's Program in Mechanical Engineering Nagaoka Japan Nagaoka University of Technology Center for Integrated Technology Support Nagaoka Japan Nagaoka University of Technology Department of System Safety Engineering Nagaoka Japan

ISBN: (纸本)9798350373332

Crawler cranes are used in various applications, including plant construction and civil engineering. However, accidents caused by hazardous events, such as overturning the entire body or overshadowing of a suspended load, can be problematic. Because crawler cranes are large and powerful machines, simulators are required to analyze the relationship between such hazardous events and human operations. This study proposed a framework for a mixed-reality simulator to analyze the interactions between humans and crawler cranes. This framework combined the high-performance graphics capabilities of Unreal Engine 5 with the high-precision multibody dynamics analysis of MATLAB Simscape to create a visually and physically realistic simulation. Moreover, the quantification of the decision-making process was possible based on the eye-tracking information of the operator. This study described the implementation of these features and discussed the prospects for human-crawler crane interaction analysis using this simulator. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Minimizing the Number of Stunting Prevalence Using the Euclid Algorithm Clustering Approach 7

Minimizing the Number of Stunting Prevalence Using the Eucli...

引用

7th IEEE International Conference of Computer Science and Information Technology, ICOSNIKOM 2023

作者： Zarlis, Muhammad Oktavia, Tanty Buaton, Relita Ernawan, Ferda Andrian, Kevin Bina Nusantara University Information System Management Department BINUS Graduate Program - Master of Information System Management Jakarta11480 Indonesia STMIK Kaputama Informatics Engineering Binjai20714 Indonesia Universiti Malaysia Pahang Al-Sultan Abdullah Faculty of Computing Pekan26600 Malaysia BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Department of Information Systems Management Jakarta Indonesia

ISBN: (纸本)9798350360752

Superior and quality human resources are based on healthy human resources with indicators of adequate nutritional intake according to age development. However, the world still faces the problem of hunger and malnutrition today. According to a UNICEF report, the number of people suffering from malnutrition in the world will reach 767.9 million people in 2021. The World Health Organization (WHO) said that malnutrition is a dangerous threat to the health of the world's population. Stunting also has an impact in Indonesia, the prevalence of toddlers experiencing stunting in Indonesia is 24.4% in 2021. The solution created is to classify and cluster the prevalence of stunting to produce a pattern that can be used as best practice to be transmitted to other affected areas. The algorithm used is Euclid. The Euclid algorithm can cluster stunting prevalence data into 4 clusters with the very little category at 79%, the little category at 67%, the many categories at 51%, and the very much category at 21%. The results of the classification and clustering of the best stunting prevalence in cluster one with a very small number, can be used as a source of accurate and updated information that can be used by the government in its efforts to optimize stunting handling in each district/city based on artificial intelligence which can provide handling and optimization patterns. stunting in every district/city. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Reinforcement Learning for Urban Traffic Signal Control 5

Adversarially Robust Reinforcement Learning for Urban Traffi...

引用

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

作者： Hamzah, Muhammad Shafly Joelianto, Endra Sutarto, Herman Yoseph Putri, Adiyana Institut Teknologi Bandung Instrumentation and Control Master Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia PT. Pusat Riset Energi Department of Intelligent System Bandung Indonesia Institut Teknologi Bandung Doctoral Program of Engineering Physics Bandung Indonesia

ISBN: (纸本)9798350364743

Urban traffic congestion presents critical challenges, resulting in delays, environmental pollution, and significant economic costs. While traditional traffic control methods, such as fixed-time and adaptive systems, have been widely implemented, they often fail in unpredictable conditions, particularly when confronted with noisy or inaccurate data. This research proposes a robust reinforcement learning (RL) solution for traffic signal control using the RADIAL-DQN (Robust Adversarial Loss DQN) algorithm. Integrating adversarial training enhances the system's robustness to real-world uncertainties. Evaluations conducted using a SUMO traffic simulation show that the robust agent produced an increase of only 60.71% in queue length under a projected gradient descent (PGD) adversarial attack, outperforming standard RL agents, which experienced an 89% increase. These results demonstrate the potential of robust RL to improve both the reliability and scalability of urban traffic control systems. © 2024 IEEE.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

Techno-Economic Analysis of Utilization Offshore Platform in the Java Sea to Produce Hydrogen with Offshore Wind Turbine-Based Energy Sources 7

Techno-Economic Analysis of Utilization Offshore Platform in...

引用

7th Astechnova International Energy Conference, ASTECHNOVA 2023

作者： Franika, Resistentio Vembre Ridwan, Muhhamad Kholid Perdana, Abram Master Program in System Engineering Universitas Gadjah Mada Jalan Teknika Utara 3 Yogyakarta55281 Indonesia Department of Physics Engineering Universitas Gadjah Mada Jalan Grafika 2 Yogyakarta55284 Indonesia Renewable Energy Systems HertfordshireWD4 8LR United Kingdom

Indonesia's geographical condition, which consists of 70 percent ocean territory, holds the potential for utilizing offshore wind turbines to provide cleaner energy. In this study, economic calculations were conducted for offshore wind turbines to generate green electricity and green hydrogen. The chosen ocean area for this endeavor is around the Papa offshore platform in the Java Sea. This area has experienced an economic decline, making it viable for repurposing as a sub-station for a powerhouse and an electrolyzer plant. Based on meteorological data analysis results, the area around the Papa offshore platform exhibits an average at height of 119 m;the wind speed is 5.5 m/*** prevailing wind direction is East Southeast (ESE), with a frequency of 25.2%. Further analysis of wind farms aimed at generating a capacity of 100.8 MW revealed an optimal potential energy generation of approximately 141,656.9 MWh per year. For scenario 1 (electricity production), the cost is $0.192/kWh. The levelized cost of hydrogen (LCOH) for scenario 2 (offshore electrolyzer) and scenario 3 (onshore electrolyzer) is $9.44/kg and $10.1/kg, respectively. To assess investment feasibility, a Net Present Value (NPV) analysis was conducted. This analysis yielded a selling price of electricity at $0.0271/kWh for the first scenario. For the second scenario, the selling price of hydrogen was calculated at $17.11/kg, and for the third scenario, it was $16.99/kg. Considering its flexibility and potential response to restrictions, the third scenario was deemed the most suitable for offshore utilization to produce clean energy. © Published under licence by IOP Publishing Ltd.

关键词： Offshore wind turbines

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

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

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：