检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Morales, Rigoberto E.M. Santana, Ana L.B. da Silva, Marco J. dos Santos, Eduardo N. Marcelino Neto, Moisés A. Multiphase Flow Research Center NUEM Graduate Program in Mechanical and Materials Engineering – PPGEM Federal University of Technology of Parana PR Curitiba Brazil

Experiments in downward vertical air-water annular flow in a 26-mm ID, 14-m length pipe were conducted to analyze and improve the understanding of the main characteristics of the liquid film. The downstream evolution of the flow was analyzed at two test sections placed at 90D and 335D from the flow inlet. A non-intrusive conductance sensor and a high-speed camera were deploy*d to measure the characteristics of the liquid film in the test sections. Thirty-five combinations of superficial air and water velocities were investigated, ranging from 0 m/s to 20 m/s and 0.05 m/s to 0.25 m/s, respectively. The analysis of the liquid film time-series provided quantitative features such as the average film thickness, roughness of the liquid film, velocity, frequency, amplitude, length and the appearance of the disturbance waves. Individual identification of the disturbance waves was performed so as to investigate the velocity and frequency concerning the distribution of the waves and their interaction. Moreover, variations for all annular flow characteristics were observed in the flow direction and new correlations to predict the main parameters of the unit wave in Downward Vertical Annular Flows (DVAF) are proposed. © 2023, The Authors. All rights reserved.

关键词： Liquid films

来源：评论

学校读者我要写书评

暂无评论

Whale Optimization Algorithm for structural damage detection, localization, and quantification

引用

Discover Civil engineering 2024年第1期1卷 1-22页

作者： Monteiro, Daniele Kauctz Miguel, Letícia Fleck Fadel Zeni, Gustavo Becker, Tiago de Andrade, Giovanni Souza de Barros, Rodrigo Rodrigues Graduate Program in Civil Engineering (PPGEC) Federal University of Rio Grande Do Sul (UFRGS) Porto Alegre Brazil Department of Mechanical Engineering (DEMEC) Graduate Program in Mechanical Engineering (PROMEC) Graduate Program in Civil Engineering (PPGEC) Federal University of Rio Grande Do Sul (UFRGS) Porto Alegre Brazil Graduate Program in Mining Metallurgy and Materials Engineering (PPGEM) Federal University of Rio Grande Do Sul (UFRGS) Porto Alegre Brazil Department of Mechanical Engineering (DEMEC) Federal University of Rio Grande Do Sul (UFRGS) Porto Alegre Brazil Applied Mechanics Group (GMAp) School of Engineering Federal University of Rio Grande Do Sul (UFRGS) Porto Alegre Brazil

This paper introduces an approach for vibration-based damage detection based on matrix updating aided by the Whale Optimization Algorithm (WOA). The methodology uses the Data-driven Stochastic Subspace Identification (SSI-DATA) technique to determine the modal parameters, which are compared with those obtained from both healthy and damaged conditions of the structure. The methodology’s efficacy is assessed through three distinct steps: numerical simulations, experimental data, and real-world data from a bridge. Initially, numerical analyses are conducted on a cantilever beam, a 10-bar truss, and a Warren truss subjected to environmental vibrations with varying damage cases and noise levels. Subsequently, experimental validations are performed on a test system and in the Z24 Bridge. Results from the computational simulations demonstrate the method’s promise to identify, locate, and quantify single and multiple damage cases, even amidst signal noise, variations in the first vibration mode as minimal as 0.015%, and complex structures with 54 elements. Moreover, the matrix updating method utilizing WOA showcased superior accuracy compared to existing techniques in the literature. In addition, the Z24 Bridge example validated the capability of the presented damage detection method to localize structural damage solely based on natural frequencies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Online Application of Edge-Cloud Computing for Lithium-Ion Battery with SOC Estimation

An Online Application of Edge-Cloud Computing for Lithium-Io...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Joelton Deonei Gotz João Pedro dos Reis Mendes José Rodolfo Galvão Emilson Ribeiro Viana Fernanda Cristina Corrêa Milton Borsato Graduate Program in Mechanical Engineering (PPGEM) Federal Technological University of Paraná Curitiba-PR Brazil Graduate Program in Electrical Engineering (PPGEE) Federal Technological University of Paraná Ponta Grossa-PR Brazil Graduate Program in Physics and Astronomy (PPGFA) Federal Technological University of Paraná Curitiba-PR Brazil

The adoption of cloud and edge computing for several application motivates the monitoring and controlling a Lithium-ion batteries (LIB) online and remotely. In these scenarios, this work presents a case of study by the application of a hybrid concept of edge-cloud computing. The edge collects the data from the cells and sent directly to the cloud where several Machine Learning algorithms can be built, trained and tested. Then, the trained models are downloaded to the edge and do inferences in real time. The proposed idea presented still an SOC estimator based on Long Short-Term Memory (LSTM) with average error below 5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Manta Ray Foraging Optimization Approaches on Multivariable PID Controller Tuning

Manta Ray Foraging Optimization Approaches on Multivariable ...

引用

Congress on Evolutionary Computation

作者： Yan Lieven Souza Luúio Luiza Scapinello Aquino Da Silva Viviana Cocco Mariani Leandro Dos Santos Coelho Electrical Engineering Graduate Program (PPGEE) Federal University of Parana (UFPR) Curitiba Brazil Department of Electrical Engineering Mechanical Engineering Graduate Program (PPGEM) Pontifical Catholic University of Parana (PUCPR) and Federal University of Parana (UFPR) Curitiba Parana Brazil Department of Electrical Engineering Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) and Federal University of Parana (UFPR) Curitiba Brazil

This work presents a performance comparison between the newly developed Manta Ray Foraging Optimization (MRFO) and two different variants created for tuning a decentralized fractional order proportional-integral-derivative (FOPID) controller for a multiple-input multiple-output (MIMO) application. The application consists of a ball mill pulverizing system to pulverize coal and maximize fuel efficiency. MRFO and its applications have the task of finding the optimal controller variable values to control the system's temperature and pressure. The MRFO is a metaheuristic based on the behavior of manta rays, and although it shows efficient performance it may be improved through the use of techniques which generate new variants of the algorithm. Two techniques were used in the de-velopment of new variants: Quantum mechanics and opposition-based learning. The three different versions of MRFO were used to minimize a custom fitness function which is a combination of the integral time squared error (ITSE) and the overshoot of the system response. Simulations were carried using Simulink and Matlab softwares. For analyzing the performances, statistical measures such as minimum, maximum, best, mean, median, and standard deviation of the fitness function over 50 runs were used. Additionally, the different variants were also compared for minimizing 10 benchmark functions. The results show that the use of the previously mentioned techniques improve the performance of the original MRFO in optimizing the FOPID to control the ball mill pulverizing system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Grouped Grey Wolf Optimization of PID Controllers Applied to a Water Treatment Plant Model

Multi-Objective Grouped Grey Wolf Optimization of PID Contro...

引用

Congress on Evolutionary Computation

作者： Yan Lieven Souza Lúcio Viviana Cocco Mariani Leandro Dos Santos Coelho Electrical Engineering Graduate Program (PPGEE) Federal University of Parana (UFPR) Curitiba Parana Brazil Department of Electrical Engineering Mechanical Engineering Graduate Program (PPGEM) Pontifical Catholic University of Parana (PUCPR) and Federal University of Parana (UFPR) Curitiba Parana Brazil Department of Electrical Engineering Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) and Federal University of Parana (UFPR) Curitiba Parana Brazil

A comparison of proportional-integral-derivative (PID) controller tuning for a 2x2 Multiple-Input Multiple-Output (MIMO) water treatment plant model is presented. The PID tuning procedures are based on Multi-Objective Grey Wolf Optimizer (MOGWO) and Multi-Objective Grouped Grey Wolf Optimizer (MOGGWO) are performed under two different initial conditions. The tuning procedure is structured as a multi-objective optimization problem with four objective functions, the integral time-squared error is minimized in each output response, and the integral of the control actions is minimized in each input. MOGWO is a metaheuristic based on the hunting behavior of grey wolves, following the hierarchy and leadership procedures that these animals have, while the proposed MOGGWO is a new version proposed in this study with two different groups with different functionalities. The performance was analyzed by 50 runs based on statistical metrics. MOGGWO can find more local minima since its Pareto front is more dispersed than that found by MOGWO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improve industrial performance based on systematic analyses of manufacturing data

引用

IFAC-PapersOnLine 2021年第1期54卷 709-716页

作者： M. Lisboa E. Jesus R. Seixas P. Valle F. Deschamps C. Strobel Institute of Applied Technology Solutions (InSTA) Manufacturing Engineering Graduate Program (PPGEM) Department of Mechanical Engineering (DEMEC) Federal University of Paraná (UFPR) Curitiba Brazil

This Article was written based on a systematic review of the literature considering three reference axes, Industry 4.0, Data Analytics and Predictive Maintenance, including specific combination of search terms to ensure a reasonable quantity of articles keeping adherence to the topic that is decision making based on collection and analysis of relevant data on B2B (Business to Business). The study focuses on the area of predictive maintenance, which has been strongly highlighted by the fourth industrial revolution, due to the mechanical and mainly the electronic embedded systems complexity increases in the last decades, as well as network connectivity possibilities for equipment’s data acquisition, enabling technologies for predictive maintenance as a key factor for competitiveness, reducing costs, increasing equipment’s availability, or as a servitization strategy. The article is divided into five parts, starting with the research model and selection of articles, including the proposal for a data analysis framework and the application of systematic analysis of these data, concluding with the opening of a discussion and the indication of future directions.

关键词： Industry 4.0 Industrial Internet of things (IIOT) Data Analytics Predictive Maintenance

来源：评论

学校读者我要写书评

暂无评论

Space and Time Efficiency Analysis of Data-Driven Methods Applied to Embedded Systems

Space and Time Efficiency Analysis of Data-Driven Methods Ap...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Iron Tessaro Roberto Zanetti Freire Viviana Cocco Mariani Leandro dos Santos Coelho Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil Mechanical Engineering Graduate Program (PPGEM) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil

ISBN: (纸本)9781728190495

One of the applications of data-driven methods in the industry is the creation of real-time, embedded measurements, whether to monitor or replace sensor signals. As the number of embedded systems in products raises over time, the energy efficiency of such systems must be considered in the design. The time (processor) efficiency of the embedded software is directly related to the energy efficiency of the embedded system. Therefore, when considering some embedded software solutions, such as data-driven methods, time efficiency must be taken into account to improve energy efficiency. In this work, the energy efficiency of three data-driven methods: the Sparse Identification of Nonlinear Dynamics (SINDy), the Extreme Learning Machine (ELM), and the Random-Vector Functional Link (RVFL) network were assessed by using the creation of a real-time in-cylinder pressure sensor for diesel engines as a task. The three methods were kept with equivalent performances, whereas their relative execution time was tested and classified by their statistical rankings. Additionally, the space (memory) efficiency of the methods was assessed. The contribution of this work is to provide a guide to choose the best data-driven method to be used in an embedded system in terms of efficiency.

关键词： Support vector machines Ranking (statistics) Radio frequency Embedded systems Neurons Energy efficiency Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Applied to a Sparse-Reward Trading Environment with Intraday Data

SSRN

引用

SSRN 2023年

作者： Takara, Lucas de Azevedo Alves Portela Santos, André Mariani, Viviana Cocco dos Santos Coelho, Leandro Department of Electrical Engineering PPGEE Federal University of Parana UFPR Avenida Coronel Francisco Herácito dos Santos Parana Curitiba81530–000 Brazil CUNEF Universidad Calle Almansa 101 Madrid28040 Spain Mechanical Engineering Graduate Program PPGEM Pontifical Catholic University of Parana PUCPR Imaculada Conceição Parana Curitiba80215–901 Brazil Industrial and Systems Engineering Graduate Program PPGEPS Pontifical Catholic University of Parana PUCPR Imaculada Conceição Parana Curitiba80215–901 Brazil

Deep reinforcement learning (DRL) achieved significant progress in several areas enabling computers to perform complex decision-making tasks. Applied to quantitative trading, DRL trading agents can optimize their decisions during distinct market scenarios to reach a profitable strategy by learning from previous experiences. This work proposes a trading system containing a variant of the Deep Q-Network (DQN) algorithm as its main component called Extended Trading DQN (ETDQN). It can adapt its learning to trade across numerous market-behavior moments, receiving feedback only when a trade is liquidaded, differently from recent approaches that provide constant feedback. Based on distributional learning and other independent extensions suggested by the DRL community, the algorithm optimizes its decision-making process by replaying prioritized experiences containing different sub-goals, assisting the agent in collecting the maximum value of profits and removing the need for fine-tuning rewards. ETDQN learned to trade on three distinct financial time series signals, identifying trading opportunities during volatile price moments. The algorithm showed more aggressive behavior regarding the volatility of its annual returns than the Trading DQN benchmark, achieving a 1.46 and 7.13 better performance with respect to average daily cumulative returns in Western Digital Corporation and Cosmos cryptocurrency historical market data. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-step ahead Bitcoin Price Forecasting Based on VMD and Ensemble Learning Methods

Multi-step ahead Bitcoin Price Forecasting Based on VMD and ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ramon Gomes da Silva Matheus Henrique Dal Molin Ribeiro Naylene Fraccanabbia Viviana Cocco Mariani Leandro dos Santos Coelho Industrial & Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Parana Brazil Department of Mathematics Federal Technological University of Parana (UTFPR) Pato Branco Parana Brazil Mechanical Engineering Graduate Program (PPGEM) Pontifical Catholic University of Parana (PUCPR) Curitiba Parana Brazil Department of Electrical Engineering Federal University of Parana (UFPR) Curitiba Parana Brazil

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Bitcoin is the leading currency in the cryptocurrency market capturing attention worldwide. Forecasting the Bitcoin price as accurate as possible is essential, but due to its high volatility this task is challenging. Many researchers try, through the years, to develop efficient models for predicting the Bitcoin price using several different data-driven approaches. The objective of this paper is to develop a novel decomposition-ensemble learning model that combines Variational Mode Decomposition (VMD) and Stacking-ensemble learning (STACK) with machine learning algorithms to forecast the Bitcoin price multi-step ahead. The algorithms are k-Nearest Neighbors, Support Vector Regression with Linear kernel, Feed-forward Artificial Neural Network with single-layer perceptron, Generalized Linear Model, and Cubist. Correlation matrix (CORR), principal component analysis (PCA), and Box-Cox transformation (BOXCOX) were used as data preprocessing techniques. Estimating the performance of the proposed models (namely VMD-STACK-CORR, VMD-STACK-PCA, and VMD-STACK-BOXCOX) using relative root mean square error, symmetric mean absolute percentage error, and absolute percentage error measures, defined that for one-day-ahead forecast VMD-STAK-BOXCOX model presented the better performance, and for two and three-days-ahead forecast VMD-STACK-CORR model was chosen, compared to VMD, STACK, and machine learning algorithms models' performance. Diebold-Mariano statistical test was conducted to evaluate a reduction in forecasting errors. Therefore, the proposed models (VMD-STACK-CORR, VMD-STACK-PCA, and VMD-STACK-BOXCOX) indeed forecast accurately Bitcoin price and outperformed the compared models (VMD, STACK, and machine learning models).

关键词： Predictive models Biological system modeling Data models Bitcoin Training Machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Experimental analysis of waxy crude oil startup flow in pipelineS

引用

Journal of Pipeline Science and engineering 2025年

作者： Nezia de Rosso Diogo E.V. Andrade Cezar O.R. Negrão Federal University of Technology – Paraná – UTFPR Research Center for Rheology and Non-Newtonian Fluids – CERNN 81280-340 R. Deputado Heitor Alencar Furtado 5000 - Bloco N - Ecoville Curitiba PR Brazil Federal University of Rio Grande do Sul - UFRGS Department of Mechanical Engineering – DEMEC Graduate Program in Mechanical Engineering – PROMEC Rheology and Non-Newtonian Fluid Flow Laboratory – ReoSul Rua Sarmento Leite 425 90050-170 Porto Alegre RS Brazil Federal University of Technology – Paran – UTFPR Department of Mechanics DAMEC Postgraduate Program in Mechanical and Materials Engineering – PPGEM Research Center for Rheology and Non-Newtonian Fluids – CERNN 81280-340 R. Deputado Heitor Alencar Furtado 5000 - Bloco N - Ecoville Curitiba PR Brazil

This study presents an experimental investigation into the startup flow of waxy crude oils in pipelines. An experimental rig was assembled with two syringe pumps connected to a 56.6-meter-long pipeline with an internal diameter of 10.3 mm. The experimental setup was placed within a thermal chamber to control the system temperature. The system was able to control thermal and shear history. The primary objective was to evaluate the start-up pressure required when initiating flow at a constant inlet flow rate. Unlike most prior works in the open literature, which discuss the rheological properties of crude oils at low temperatures, the current work explores the effect of the shear history, initial cooling temperature, aging time, and final cooling temperature in a startup flow loop. We also show in a pioneering experimental analysis that pressurizing the pipeline during the cooling evinces the effect of compressibility due to shrinkage on the startup of waxy crude oil.

关键词： Waxy crude oils Experimental loop Startup flow Compressibility

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：