检索结果-内蒙古大学图书馆

An Optimization Approach to Select Koopman Observables for Data-Based Modeling Using Dynamic Mode Decomposition with Control

引用

PROCESSES 2025年第1期13卷

作者： Marti-Coll, Amanda Rodriguez-Ramos, Adrian Llanes-Santiago, Orestes Univ Tecnol Habana Jose Antonio Echeverria Dept Automat & Comp CUJAE Calle 114 11901 Marianao 19390 Cuba

The advent and evolution of Industry 4.0 have been driven by technologies such as the Industrial Internet of Things, Big Data, and Cloud Computing. Within this framework, digital twins have gained significant popularity and are now employed across a wide range of industries and processes. A crucial step in developing a digital twin is deriving the system model, for which numerous methods are available. Among these, the Koopman operator and Dynamic Mode Decomposition with control have demonstrated their effectiveness and are widely recognized in the scientific community. This paper proposes a procedure for the automatic selection of Koopman observables by solving an optimization problem. The objective is to identify the minimal set of observables, belonging to a predefined dictionary, that minimize the error between actual process observations and predictions made by the estimated linear model-a key requirement for digital twin development. To tackle the optimization challenge, any algorithm available in the literature can be utilized. In this paper, the evolutive algorithms, including Genetic Algorithm and Differential Evolution Algorithm, are applied to evaluate the proposed approach in a benchmark problem. In both cases, the algorithms obtained the minimum set of observable functions from the dictionary used that achieve the lowest error obtained between the real process and the model, confirming the validity of the proposed method.

关键词： optimization process digital twins Koopman observables dynamical mode decomposition with control evolutive algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysis of multi-objective optimization applied to the simulation of a natural gas separation plant

GAS SCIENCE AND ENGINEERING

引用

GAS SCIENCE AND ENGINEERING 2024年 128卷

作者： Lemos, Israel dos Santos Santos, Lizandro de Sousa Univ Fed Fluminense Dept Chem & Petr Engn Rua Passo Patria 156 BR-24210240 Niteroi RJ Brazil

This study concentrated on simulating and optimizing a natural gas separation plant using Unisim Design (R) software. The optimization procedure aimed to maximize gas production and the higher-molecular-weight hydrocarbons (yC5+) in the produced gas. The maximum water dew point of -45 degrees C of the produced gas was specified. The Nelder Mead/Weight Sum Method (NM/WSM) algorithm was employed in Python to optimize five decision variables involving the temperature and pressure of the main process streams. Results indicated that the relative deviations below 1%, compared to reference values, were obtained for the main process variables. The multi-objective optimization (MOO) results showed an increase in gas production of up to 5.58% (maximum value of 62,736.10 kg/h) and a rise in the molar fraction of yC5+ by up to 32.2% compared to the reference values. However, it was noted that maximizing gas production indirectly maximizes the yC5+, with only a single decision variable differing in the optimal direction, represented by the intermediate temperature of one compression stage. A Pareto curve was built to display the range of optimal solutions, showing variations of 0.035% in optimal gas production and 0.11% in yC5+. Furthermore, various simulation scenarios were optimized with different thermodynamic conditions at the unit's inlet. In all cases, the optimization resulted in an average gain of 1.57% in gas production regarding the reference (non-optimal case).

关键词： Multi -objective optimization evolutive algorithms Process simulation Pareto front Gas processing

来源：评论

学校读者我要写书评

暂无评论

evolutive Adversarially-Trained Bayesian Network Autoencoder for Interpretable Anomaly Detection 11

Evolutive Adversarially-Trained Bayesian Network Autoencoder...

引用

International Conference on Probabilistic Graphical Models

作者： Casajus-Setien, Jorge Bielza, Concha Larranaga, Pedro Univ Politecn Madrid ETS Ingenieros Informat Boadilla Del Monte 28660 Spain

Semi-supervised detection of outliers with only positive and unlabeled data, which is among the most frequent forms of the anomaly detection (AD) problem in real scenarios, requires for a model to capture the normal behaviour of data from a training set exclusively comprised of normal-labelled data, so new unseen data can be afterwards compared to the induced notion of normality to be flagged -or not- as anomalous. In modelling a certain pattern of behaviour, generative models such as generative-adversarial networks (GANs) have proved to have great performance. Thus, numerous AD algorithms with GANs at its core have been proposed, most of them powered by deep neural networks and relying on an autoencoder for the AD task. In the present work, a novel approach to semi-supervised AD with Bayesian networks using generative-adversarial training and an evolutive strategy is proposed, which aims to palliate the intrinsic lack of interpretability of deep neural networks. The proposed model is tested on a real-world AD problem in cybersecurity.

关键词： Bayesian networks Generative models Adversarial training evolutive algorithms Autoencoder Anomaly detection Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Optimized Perforation Schemes in Railway Wheels Toward Acoustic Radiation Mitigation

引用

JOURNAL OF VIBRATION AND ACOUSTICS-TRANSACTIONS OF THE ASME 2020年第4期142卷 041009页

作者： Gutierrez-Gil, J. Garcia-Andres, X. Martinez-Casas, J. Nadal, E. Denia, F. D. Univ Politecn Valencia Ctr Invest Ingn Mecan CIIM Camino Vera S-N Valencia 46022 Spain

Rolling noise emitted by railway wheels is a problem that affects human health and limits the expansion of the railway network. It is caused by the wheel vibration due to the wheel-rail contact force, and it is important in almost all the vehicle velocity range. The minimization of noise radiation associated with changes on the wheel web is discussed in this work, focusing on potential shape modifications in existing wheels in the form of a perforation distribution over the web. Such a post-manufacturing technique is a cost-effective solution that can be performed in a relatively short term. The implemented objective function is directly related to the overall radiated sound power, which is minimized using a genetic algorithm-based optimizer. In the acoustic model, radiation efficiencies are approximated to unity, the accuracy of this assumption being also studied in the work. The results reflect that an optimized distribution of perforations on the web of a railway wheel can reduce the total sound power level, by about 5 dB(A) and 2 dB(A) for curved and straight web, respectively. The mitigation of the radiated sound power is due to the fact that certain wheel vibration modes are modified and shifted to other frequencies where they are less excited. Finally, the relevance of the cross-sectional curvature of the web is explored by studying two different web geometries, suggesting that it can strongly influence the noise mitigation effects of the perforation pattern.

关键词： acoustic radiation analysis railway wheel perforations optimization evolutive algorithms response surface acoustic emission noise control propagation and radiation

来源：评论

学校读者我要写书评

暂无评论

The JaCalIVE framework for MAS in IVE: A case study in evolving modular robotics

引用

NEUROCOMPUTING 2018年 275卷 608-617页

作者： Rincon, J. A. Garcia, Emilia Julian, V. Carrascosa, C. Univ Politecn Valencia DSIC Camino Vera S-N Valencia Spain

This paper presents a framework specially designed for the execution and adaptation of Intelligent Virtual Environments. This framework, called JaCalIVE, facilitates the development of this kind of environments managing in an efficient and realistic way the evolution of parameters for the adaptation of the physical world. The framework includes a design method and a physical simulator which is in charge of giving the Intelligent Virtual Environment the look of the real or physical world, allowing to simulate physical phenomena such as gravity or collision detection. The paper also includes a case study which illustrates the use of the proposed framework as an evolutive algorithm which allows the automatic adaptation of modular robots. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Multi-agent systems Virtual environments evolutive algorithms

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristic based autoscaling of cloud-based parameter sweep experiments with unreliable virtual machines instances

引用

COMPUTERS & ELECTRICAL ENGINEERING 2018年 69卷 364-377页

作者： Monge, David A. Pacini, Elina Mateos, Cristian Garcia Garino, Carlos ITIC CONICET Mendoza Argentina UNCuyo Univ Mendoza Fac Ciencias Exactas & Nat Mendoza Argentina UNCuyo Univ Mendoza Fac Ingn Mendoza Argentina UNICEN CONICET ISISTAN Tandil Buenos Aires Argentina

Cloud Computing is the delivery of on-demand computing resources over the Internet on a pay-per-use basis and is very useful to execute scientific experiments such as parameter sweep experiments (PSEs). When PSEs are executed it is important to reduce both the makespan and monetary cost. We propose a novel tri-objective formulation for the PSEs autoscaling problem considering unreliable virtual machines (VM) pursuing the minimization of makespan, monetary cost and probability of failures. We also propose a new autoscaler based on the Non-dominated Sorting Genetic Algorithm II able to automatically determine the right amount for each type of VM and pricing scheme, as well as the bid prices for the spot instances. Experiments show that the proposed autoscaler achieves great improvements in terms of makespan and cost when it is compared against Scaling First and Spot Instances Aware Autoscaling. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Autoscaling Parameter sweeping Multi-objective optimization evolutive algorithms

来源：评论

学校读者我要写书评

暂无评论

Wavenet identification of dynamical systems by a modified PSO algorithm

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2018年 73卷 1-9页

作者： Carrillo-Santos, C. A. Seck-Tuoh-Mora, J. C. Hernandez-Romero, N. Ramos-Velasco, L. E. Autonomous Univ Hidalgo State Engn Acad Area Carr Pachuca Tulancingo Km 4-5 Pachuca 42184 Mexico Metropolitan Polytech Univ Hidalgo State Educ Program Aeronaut Engn Blvd Acceso Tolcayuca 1009 Ex Hacienda San Javier 43860 Mexico

This paper presents a new method for the identification of nonlinear dynamical systems employing a wavelet neural network (wavenet) coupled to an infinite impulse response filter (WIIR). It is well known that a neural network trained by a gradient method is susceptible to fall in a minimum local. In order to solve this problem, we train the wavenet with a modified particle swarm optimization (mPSO) evolutionary algorithm, which integrates an elitist selection in order to conserve the best qualified particles. This approach is called mPSOWIIR algorithm. Basically, the idea is that the mPSO generates different sets of parameters that are evaluated in the dynamical system to be identified in order to obtain the fitness of every set. The best one and the best historical values of every set are taken into account to improve the set of parameters, keeping the diversity of new solutions and training the wavenet only with the first time steps of the dynamical system. This approach is able to reduce the number of possible solutions, avoid local minima and extend the search space of the wavenet;eluding the problem of finding good initial parameters by trial and error. One of the main features of the proposed method is that the number of parameters remains constant in all the training process. The mPSOWIIR algorithm is applied to identify nonlinear dynamical systems commonly used in specialized literature, obtaining satisfactory results.

关键词： Identification dynamical system Wavelet neural networks IIR filter Particle swarm optimization evolutive algorithms

来源：评论

学校读者我要写书评

暂无评论

Real-time video thresholding using evolutionary techniques and cross entropy 11

Real-time video thresholding using evolutionary techniques a...

引用

11th IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)

作者： Hinojosa, Salvador Oliva, Diego Cuevas, Erik Perez-Cisneros, Marco Pajares, Gonzalo Univ Complutense Madrid Fac Informat Dept Ingn Software & Inteligencia Artificial Madrid Spain Univ Guadalajara Div Elect & Comp CUCEI Guadalajara Jalisco Mexico

ISBN: (纸本)9781538613764

Evolutionary algorithms (EAs) are present in most areas of science and engineering where difficult problems arise. However, EAs are often applied to design problems where the speed is not a crucial factor. This tendency has lead EAs to be excluded from real-time applications due to its iterative nature. Image processing has benefited from EAs on many off-line applications, but little research has been made for real-time image processing problems. This paper presents the evaluation of EAs applied to the thresholding of a stream of images in real-time. Results indicate that Differential Evolution (DE) can be modified to achieve real-time performance on a single core implementation without any form of parallelization. These circumstances indicate that the performance can be further improved with multi-core implementations or GPU parallelization.

关键词： evolutive algorithms image processing thresholding real-time

来源：评论

学校读者我要写书评

暂无评论

evolutive algorithms for Visual Fall Detection in Intelligent Spaces

Evolutive Algorithms for Visual Fall Detection in Intelligen...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Canas, Jose M. Marugan, Sara Marron, Marta Garcia, Juan C. Univ Rey Juan Carlos Robot Grp Mostoles 28933 Spain Univ Alcala de Henares Dept Elect Alcala De Henares 28871 Spain

ISBN: (纸本)9781424463916

Artificial vision provides a remarkable good sensor when developing applications for intelligent spaces. Cameras are passive sensors that supply a great amount of information and are quite cheap. This paper presents an application for elderly care that detects falls or faints and automatically triggers the health alarm. It promotes the independent lifestyle of elder people at their homes as the monitoring application will call for timely health assistance when needed. The system extracts 3D information from several cameras and performs 3D tracking of the people in the intelligent space. Two evolutive multimodal algorithms have been developed to continuously estimate the 3D position in real time, one based on 3D points and another one based on 3D prisms. Both learn the visual appearance of the persons and use color and movement as tracking cues. The system has been validated with some experiments in different real environments.

关键词： 3D information extraction artificial intelligence artificial vision elderly care evolutive algorithms good sensor handicapped aids health alarm intelligent spaces monitoring application passive sensors timely health assistance visual fall detection

来源：评论

学校读者我要写书评

暂无评论

Time series prediction evolving Voronoi regions

引用

APPLIED INTELLIGENCE 2011年第1期34卷 116-126页

作者： Luque, Cristobal Valls, Jose M. Isasi, Pedro Univ Carlos III Madrid Dept Informat Madrid 28911 Spain

Time series prediction is a complex problem that consists of forecasting the future behavior of a set of data with the only information of the previous data. The main problem is the fact that most of the time series that represent real phenomena include local behaviors that cannot be modelled by global approaches. This work presents a new procedure able to find predictable local behaviors, and thus, attaining a better level of total prediction. This new method is based on a division of the input space into Voronoi regions by means of Evolution Strategies. Our method has been tested using different time series domains. One of them that represents the water demand in a water tank, through a long period of time. The other two domains are well known examples of chaotic time series (Mackey-Glass) and natural phenomenon time series (Sunspot). Results prove that, in most of cases, the proposed algorithm obtain better results than other algorithms commonly used.

关键词： Time series Artificial intelligence evolutive algorithms Evolution strategies Machine learning Voronoi regions

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：