检索结果-内蒙古大学图书馆

Possibilities of Implementing Pre-Trained Feed-forward Neural Networks in Mobile Robotics

Transportation Research Procedia 2023年 74卷 418-425页

作者： Vladimír Stenchlák Vladimír Tlach Ivan Kuric Martin Bohušík Zuzana Ságová Dorota Wiecek Department of Automation and Production Systems Faculty of Mechanical Engineering University of Zilina Univerzitná 8215/1 010 26 Zilina Slovakia Department of Production Engineering Faculty of Mechanical Engineering and Computer Sciences University of Bielsko-Biała Willowa 2 43-309 Bielsko-Biała Poland

This paper is describing how artificial intelligence algorithms can be implemented in controlling development boards like Arduino, ST32, or Raspberry for mobile crawler robots. Especially in the classification of decisions based on the input variables. The artificial intelligence algorithms specifically used in this paper and this example are called feed-forward artificial neural networks. In this paper, there is described how a relatively small neural network that is pre-trained in MATLAB platform can be implemented to the Arduino control board for controlling crawler mobile robot. In this article, there is described the mechanical construction and electrical connections of the mobile robot for a better understanding of this application. The designed crawler mobile robot in this article was primarily used for educational purposes.

关键词： Artificial intelligence Mobile Robotics Neural Networks Classification

来源：评论

学校读者我要写书评

暂无评论

Method for Determination Rotor Eccentrity of an Electric Machine

Method for Determination Rotor Eccentrity of an Electric Mac...

引用

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Orazovna, Yussupova Assel Neftissov, Alexandr Olegovna, Potapenko Alexandra Sansyzbayevna, Urazalimova Dariya Toraighyrov University Department Of Electrical Engineering And Automation Pavlodar Kazakhstan Research And Innovation Center 'Industry 4.0' Astana It University Nur-Sultan Kazakhstan Toraighyrov University Faculty Of Computer Science Pavlodar Kazakhstan

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

Modern diagnostic systems for asynchronous motors are widely used in the power industry. The most promising diagnostic systems for rotor eccentricity of induction motors are systems with capacitive measuring transducers in view of their simplicity, reliability and sufficient sensitivity. In the proposed work, the selection of the information sign of damage for the diagnosis system of rotor eccentricity with open and closed slots of an induction motor with a capacitive measuring transducer. © 2022 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

Comparison of risk assessment approaches and analyzes used in technical transport systems

引用

Transportation Research Procedia 2023年 74卷 516-521页

作者： Milan Sága Ivan Kuric Ivana Klačková Dorota Więcek Department of Automation and Production Systems Faculty of Mechanical Engineering University of Zilina Univerzitná 8215/1 010 26 Žilina Slovakia Department of Production Engineering Faculty of Mechanical Engineering and Computer Sciences University of Bielsko-Biała Willowa 2 43-309 Bielsko-Biała Poland

On the basis of current normative and legal bases, such as standards, directives, and laws that control interoperability and safety of systems, the paper's goal is to compare methods for risk assessment of transportation and engineering equipment and protection systems. The initial system definition defined at a high level of abstraction and a few methods used in the development of safety requirements' initial phase are taken into consideration. Eliminating the risk or lowering either of the two criteria that determine the relevant risk, such as the severity of the damage caused by the risk in question and the likelihood that the harm will occur, either independently or concurrently, can accomplish the objective of risk reduction.

关键词： transport safety risk

来源：评论

学校读者我要写书评

暂无评论

Prediction of Temperature Behavior in Hydraulic Circuits

引用

Transportation Research Procedia 2023年 74卷 500-507页

作者： Daria Fedorova Vladimír Stenchlák Vladimír Tlach Ivan Kuric Dariusz Wiecek Department of Automation and Production Systems Faculty of Mechanical Engineering University of Zilina Univerzitná 8215/1 010 26 Žilina Slovakia Department of Production Engineering Faculty of Mechanical Engineering and Computer Sciences University of Bielsko-Biała Willowa 2 43-309 Bielsko-Biała Poland

The increasing complexity of products and systems in modern engineering production requires higher demands on the operation and maintenance of systems. For this reason, the role of maintenance can hardly be underestimated, as the maintenance of machinery and equipment is an integral part of any manufacturing process. Maintenance is closely related to the precision of the parts produced and the quality of the manufacturing process. A current trend in Industry 4.0 is predictive maintenance, which enables real-time detection of faulty equipment conditions based on condition monitoring. Utilizing artificial intelligence for predictive analytics can considerably contribute to the prediction of potential failures. Consequently, maintenance costs related to production downtime and equipment repair will be decreased. In this paper, a non-linear autoregressive neural network for real-time prediction of working fluid temperature parameters in a hydraulic circuit is presented. A testing device is also developed to collect experimental data, optimize, and test the proposed prediction model.

关键词： Neural network NAR predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Data Driven Level Set Fuzzy Modeling for Cryptocurrencies Price Forecasting 14th

Data Driven Level Set Fuzzy Modeling for Cryptocurrencies Pr...

引用

14th International Joint Conference on Computational Intelligence, IJCCI 2022

作者： Maciel, Leandro Ballini, Rosangela Gomide, Fernando Department of Business Administration Faculty of Economics Business and Accounting University of Sao Paulo Sao Paulo Brazil Department of Economic Theory Institute of Economics University of Campinas Sao Paulo Brazil Department of Computer Engineering and Automation School of Electrical and Computer Engineering University of Campinas Sao Paulo Brazil

ISBN: (纸本)9789897586118

The paper develops a data-driven fuzzy modeling procedure based on level set to forecast cryptocurrencies prices. Data-driven level set is a novel fuzzy modeling method that differs from linguistic and functional fuzzy models in how the fuzzy rules are built and processed. The level set-based model outputs the weighted average of output functions associated with the fuzzy rules. Output functions map the activation levels of the fuzzy rules directly in the model outputs. Computational experiments are done to evaluate the level set method to forecast the closing prices of Bitcoin, Ethereum, Litecoin and Ripple. Comparisons are made with ARIMA, ETS, MLP and naïve random walk. The results suggest that the random walk outperforms most methods addressed in this paper, but it is surpassed by the level set model for Ethereum. When performance is measured by the direction of price change, the level set-based fuzzy modeling performs best amongst the remaining methods. Copyright © 2022 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Coreference disambiguation based on two-layer label dependence analysis 7

Coreference disambiguation based on two-layer label dependen...

引用

7th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2023

作者： Xu, Hongfei Li, Yingna Faculty of Information Engineering and Automation Kunming University of Science and Technology 727 Jingming South Rd.Chenggong District Kunming650500 China Yunnan Key Laboratory of Computer Technology Applications 727 Jingming South Rd.Chenggong District Kunming650500 China

ISBN: (数字)9781510668089

ISBN: (纸本)9781510668072

A two-layer labeling-based dependency analysis model is proposed to introduce the location features of words for the coreference disambiguation of entities. Firstly, two layers of labels are used for labeling, the second layer labels the location information of words, the features of sentences are learned using a bidirectional long short-Term memory network, the dependency syntax analysis based on deep graph decoding obtains the dependency tree of sentences, and the two layers of labels are fused to improve the performance and accuracy of coreference disambiguation. Experiments are conducted on the text dataset of power security entity relationship extraction, and the results show that the two-layer labeled dependency analysis has an improved effect on co-finger disambiguation, which verifies the effectiveness of the model for cofinger disambiguation on the experimental dataset. © 2023 SPIE. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Design of an Electronically Controlled Biquadratic Filter Using Commercial ICs

Design of an Electronically Controlled Biquadratic Filter Us...

引用

International Electrical engineering Congress (iEECON)

作者： Somkid Ritnathikul Danupat Duangmalai Khanittha Kaewdang Settasuk Kwuanphet Thanawat Chalermpong Koson Pitaksuttayaprot Department of Computer Engineering Faculty of Agricultural and IndustrialTechnology Phetchabun Rajabhat University Phetchabun Thailand Department of Electrical and Electronic Engineering Faculty of Engineering Ubon Ratchathani University Ubon Ratchathani Thailand Department of Electrical Engineering Faculty of Industrial Technology Nakhon Phanom University Nakhon Phanom Thailand Department of Electronics and Automation Systems Engineering Faculty of Agricultural and Industrial Technology Phetchabun Rajabhat University Phetchabun Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This paper presents an electronically controlled biquadratic filter designed for precise frequency selection in applications such as audio processing, telecommunications, and cochlear implants. The design utilizes AD830, AD844, and LM13700 integrated circuits, facilitating high-pass, band-pass, and low-pass responses with improved stability and real-time tunability. PSPICE simulations validate the filter's adaptability and performance, demonstrating its effectiveness in dynamic environments and its suitability for high-frequency applications requiring flexible frequency control. The results indicate a calculated pole frequency of 2.23 MHz, while simulations yield a slightly lower value of 2.0 MHz, affirming the design's practical viability and alignment with theoretical expectations.

关键词： Band-pass filters Performance evaluation Adaptation models Low-pass filters SPICE Stability analysis Real-time systems Telecommunications Integrated circuit modeling Frequency control

来源：评论

学校读者我要写书评

暂无评论

Study on optimizing the effluent quality parameters for a simulated wastewater treatment plant using dynamic two-dimensional reference point generation: A comparative approach 28

Study on optimizing the effluent quality parameters for a si...

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Roşu, Bogdan Murariu, Gabriel Arseni, Maxim Iticescu, Cǎtalina Mocanu, George Danut Simionescu, Nicoleta-Lucica Roşu, Adrian Dunǎrea de Jos University of Galaţi Faculty of Automation Computer Sciences Electronics and Electrical Engineering Galati Romania Dunǎrea de Jos University of Galaţi REXDAN Research Infrastructure Faculty of Sciences and Environment Galati Romania Dunǎrea de Jos University of Galaţi Faculty of Physical Education and Sport Galati Romania Dunǎrea de Jos University of Galaţi Faculty of Engineering Galati Romania GEOENVIRADI S.R.L Galati Romania

ISBN: (纸本)9798350339918

This paper aims to achieve an optimization of the variables that represent the violation time of limit concentration for the main effluent quality parameters in a simulated wastewater treatment plant WWTP. The main effluent quality parameters considered are Biological Oxygen Demand (BOD), Chemical Oxygen Demand, Total nitrate (Ntot), ammonium nitrogen (SNH), and Total Suspended Solids (TSS). A custom control strategy was also considered to obtain a better performance of the simulated WWTP. In order to generate the database, several Monte Carlo simulations were performed. In this way, the global minimum points were determined, and a method for aligning the obtained global minimum points was proposed. © 2023 IEEE.

关键词： Effluents

来源：评论

学校读者我要写书评

暂无评论

Multi-Blockchain Based Data Trading Markets With Novel Pricing Mechanisms

引用

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2222-2232页

作者： Juanjuan Li Junqing Li Xiao Wang Rui Qin Yong Yuan Fei-Yue Wang IEEE the State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China the School of Artificial Intelligence Anhui UniversityHefei 266114 the Qingdao Academy of Intelligent Industries Qingdao 230031China the School of Mathematics Renmin University of ChinaBeijing 100872China the State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 the Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China

In the era of big data,there is an urgent need to establish data trading markets for effectively releasing the tremendous value of the drastically explosive *** security and data pricing,however,are still widely regarded as major challenges in this respect,which motivate this research on the novel multi-blockchain based framework for data trading markets and their associated pricing *** this context,data recording and trading are conducted separately within two separate blockchains:the data blockchain(DChain) and the value blockchain(VChain).This enables the establishment of two-layer data trading markets to manage initial data trading in the primary market and subsequent data resales in the secondary ***,pricing mechanisms are then proposed to protect these markets against strategic trading behaviors and balance the payoffs of both suppliers and ***,in regular data trading on VChain-S2D,two auction models are employed according to the demand scale,for dealing with users’ strategic *** incentive-compatible Vickrey-Clarke-Groves(VCG)model is deployed to the low-demand trading scenario,while the nearly incentive-compatible monopolistic price(MP) model is utilized for the high-demand trading *** temporary data trading on VChain-D2S,a reverse auction mechanism namely two-stage obscure selection(TSOS) is designed to regulate both suppliers’ quoting and users’ valuation ***,experiments are carried out to demonstrate the strength of this research in enhancing data security and trading efficiency.

关键词： Auction data trading markets multi-blockchain pricing mechanisms

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach For Faults Recognition of Dissolved Oxygen Sensor in Wastewater Treatment Plants

A Deep Learning Approach For Faults Recognition of Dissolved...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Liliana Maria Ghinea Mihaela Miron Harsha Ratnaweera Department of Automatic Control and Electrical Engineering Department Faculty of Automation Computers Electrical Engineering and Electronics Galați Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Galați Romania Faculty of Science and Technology Norwegian University of Life Sciences Oslo Norway

Fault diagnosis in wastewater treatment plants (WWTPs) is important to protect communities and ecosystems from toxic elements discharged into water. In this sense, fault identification of sensors plays an important role as they are the key components of the water plants control, especially because environmental legislation is very strict when referring to failures or anomalies in WWTPs. This paper analyzes the performances of two Deep Learning models, a Feedforward Neural Network (FFNN) and a 1D Convolution Neural Network (1DCNN) for identifying five operating states of the dissolved oxygen (DO) sensor: normal and faulty (bias, stuck, spike and precision degradation faults). The experiments were conducted on the Benchmark Simulator Model No 2 (BSM2) developed by the IWA Task Group. The performance of the Deep Learning (DL) classifiers was evaluated via accuracy, precision, recall, and F1-score metrics. The best overall classification accuracy was obtained by FFNN, 98.32% for training and 98.30% for testing.

关键词：

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：