检索结果-内蒙古大学图书馆

data-driven simulation of aero-engine rotor assembly process optimization for unbalance based on fusion algorithm

AEROSPACE SCIENCE AND TECHNOLOGY 2025年 158卷

作者： Xu, Haitao Gao, Jie Wen, Jinan Du, Jinsong Wang, Wei Chinese Acad Sci Shenyang Inst Automat Shenyang 110016 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Key Lab Intelligent Detect & Equipment Technol Lia Shenyang 110169 Peoples R China Liaoning Liaohe Lab Shenyang 110169 Peoples R China

Improper rotor blade sequencing can lead to excessive rotor unbalance, causing severe engine vibration. Traditional unbalance mechanism models struggle to capture nonlinear factors in rotor operation, while heuristic blade sorting algorithms cannot guarantee global optimality. To address these challenges, this paper proposes a data-driven approach to optimize the aero-engine rotor assembly process, combining the Harris Hawk Optimization algorithm with the Simulated Annealing algorithm (HHOSA). The algorithm framework incorporates a diffusion model for dataset augmentation, a rotor unbalance prediction model based on Long Short-Term Memory network (LSTM) for capturing nonlinear factors during rotor operation, and an HHOSA algorithm for blade sequencing. The experimental results demonstrate that the LSTM prediction errors MAE and MSE are 0.61 g & sdot;mm, and 0.56 g & sdot;mm, respectively. Using HHOSA to sort a set of blade sequences, the unbalanced value of the rotor after sorting is 2.06 g & sdot;mm, which is 98.3% better than the genetic algorithm. The results provide evidence for the effectiveness and superiority of the proposed algorithm in solving blade sequencing optimization problems, offering valuable insights and practical guidance for aero-engine assembly.

关键词： data-driven simulation Diffusion model Heuristic algorithm Unbalance forecast Aero-engine rotor assembly

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation-based decision support system for resource allocation in industry 4.0 and smart manufacturing

引用

JOURNAL OF MANUFACTURING SYSTEMS 2024年 72卷 287-307页

作者： Mahmoodi, Ehsan Fathi, Masood Tavana, Madjid Ghobakhloo, Morteza Ng, Amos H. C. Univ Skovde Sch Engn Sci Div Intelligent Prod Syst S-54128 Skovde Sweden Uppsala Univ Div Ind Engn & Management POB 534 S-75121 Uppsala Sweden La Salle Univ Distinguished Chair Business Analyt Business Syst & Analyt Dept Philadelphia PA USA Univ Paderborn Fac Business Adm & Econ Business Informat Syst Dept Paderborn Germany

data-driven simulation (DDS) is fundamental to analytical and decision-support technologies in Industry 4.0 and smart manufacturing. This study investigates the potential of DDS for resource allocation (RA) in high-mix, low-volume smart manufacturing systems with mixed automation levels. A DDS-based decision support system (DDS-DSS) is developed by incorporating two RA strategies: simulation-based bottleneck analysis (SB-BA) and simulation-based multi-objective optimization (SB-MOO). To enhance the performance of SB-MOO, a unique meta-learning mechanism featuring memory, dynamic orthogonal array, and learning rate is integrated into the NSGA-II, resulting in a modified version of the NSGA-II with meta-learning (i.e., NSGA-II-ML). The proposed DSS also benefits from a post-optimality analysis that leverages a clustering algorithm to derive actionable insights. A real-life marine engine manufacturing application study is presented to demonstrate the applicability and exhibit efficacy of the proposed DSS and NSGA-II-ML. To this aim, NSGA-II-ML was tested against the original NSGA-II and differential evolution (DE) algorithm across a set of test problems. The results revealed that NSGA-II-ML surpassed the other two in terms of the number of non-dominated solutions and hypervolume, particularly in medium and large-sized problems. Furthermore, NSGA-II-ML achieved a 24% improvement in the best throughput found in the real case problem, outperforming SB-BA, NSGA-II, and DE. The post-optimality analysis led to the extraction of valuable knowledge about the key, influencing decision variables on the throughput.

关键词： Resource allocation High-mix low-volume Multi-objective optimization data-driven simulation Decision support system Industry 4.0 Meta-learning

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation of continuous-time linear time-invariant systems: the autonomous case 22

Data-driven simulation of continuous-time linear time-invari...

引用

22nd IFAC World Congress

作者： Rapisarda, P. van Waarde, H.J. Çamlibel, M.K. University of Southampton United Kingdom Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Netherlands

ISBN: (纸本)9781713872344

We use orthogonal bases for continuous-time function spaces to state a version of Willems' lemma (Willems et al., 2005) for autonomous systems. We assume that an infinite number of representation coefficients of a "sufficiently rich" trajectory is given, and we illustrate how to compute solutions to initial and boundary conditions problems from such data. Copyright © 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： autonomous system data-driven simulation function approximation fundamental lemma orthogonal basis

来源：评论

学校读者我要写书评

暂无评论

Optimal decision-making in relieving global high temperature-related disease burden by data-driven simulation

引用

Infectious Disease Modelling 2024年第2期9卷 618-633页

作者： Xin-Chen Li Hao-Ran Qian Yan-Yan Zhang Qi-Yu Zhang Jing-Shu Liu Hong-Yu Lai Wei-Guo Zheng Jian Sun Bo Fu Xiao-Nong Zhou Xiao-Xi Zhang School of Global Health Chinese Center for Tropical Diseases ResearchShanghai Jiao Tong University School of MedicineShanghaiPeople's Republic of China Institute of One Health Shanghai Jiao Tong UniversityShanghaiPeople's Republic of China School of Public Health Shanghai Jiao Tong University School of MedicineShanghaiPeople's Republic of China School of Data Science Fudan UniversityShanghaiPeople's Republic of China

The rapid acceleration of global warming has led to an increased burden of high temperature-related diseases(HTDs),highlighting the need for advanced evidence-based management *** have developed a conceptual framework aimed at alleviating the global burden of HTDs,grounded in the One Health *** framework refines the impact pathway and establishes systematic data-driven models to inform the adoption of evidence-based decision-making,tailored to distinct *** collected extensive national-level data from authoritative public databases for the years 2010–*** burdens of five categories of disease causes–cardiovascular diseases,infectious respiratory diseases,injuries,metabolic diseases,and non-infectious respiratory diseases–were designated as intermediate outcome *** cumulative burden of these five categories,referred to as the total HTD burden,was the final outcome *** evaluated the predictive performance of eight models and subsequently introduced twelve intervention measures,allowing us to explore optimal decision-making strategies and assess their corresponding *** model selection results demonstrated the superior performance of the Graph Neural Network(GNN)model across various *** simulations driven by the GNN model,we identified a set of optimal intervention strategies for reducing disease burden,specifically tailored to the seven major regions:East Asia and Pacific,Europe and Central Asia,Latin America and the Caribbean,Middle East and North Africa,North America,South Asia,and Sub-Saharan *** mitigation and adaptation measures,acting upon our categories of Infrastructure&Community,Ecosystem Resilience,and Health System Capacity,exhibited particularly strong performance for various regions and *** out of twelve interventions were included in the optimal intervention package for each region,including raising low-carbon energy use,increasing energy intensity,improving

关键词： High temperature-related diseases data-driven simulation Optimal intervention Disease burden Graph neural network Global warming

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation for general-purpose multibody dynamics using Deep Neural Networks

引用

MULTIBODY SYSTEM DYNAMICS 2021年第4期51卷 419-454页

作者： Choi, Hee-Sun An, Junmo Han, Seongji Kim, Jin-Gyun Jung, Jae-Yoon Choi, Juhwan Orzechowski, Grzegorz Mikkola, Aki Choi, Jin Hwan Kyung Hee Univ Dept Mech Engn Integrated Engn 1732 Deogyeong Daero Yongin 17104 Gyeonggi Do South Korea Kyung Hee Univ Dept Ind & Management Syst Engn 1732 Deogyeong Daero Yongin 17104 Gyeonggi Do South Korea FunctionBay Inc R&D Ctr 5FPangyo Seven Venture Valley 1 Danji 2 Dong Seongnam Si Gyeonggi Do South Korea LUT Univ Dept Mech Engn Yliopistonkatu 34 Lappeenranta 53850 Finland

In this paper, we introduce a machine learning-based simulation framework of general-purpose multibody dynamics (MBD). The aim of the framework is to construct a well-trained meta-model of MBD systems, based on a deep neural network (DNN). Since the main advantage of the meta-model is the enhancement of computational efficiency in returning solutions, the modeling would be beneficial for solving highly complex MBD problems in a short time. Furthermore, for dynamics problems, not only the accuracy but also the smoothness in time of motion solutions, such as displacement, velocity, and acceleration, are essential aspects to consider. We analyze and discuss the influence of training data structures on both aspects of solutions. As a result of the introduced approach, the meta-model provides motion estimation of system dynamics without solving an analytical equation of motion or a numerical solver. Numerical tests demonstrate the performance of the proposed meta-modeling for representing several MBD systems.

关键词： Multibody dynamics Meta-model Deep neural network Feed forward network data-driven simulation

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation of continuous-time linear time-invariant systems: the autonomous case

引用

IFAC-PapersOnLine 2023年第2期56卷 2244-2249页

作者： P. Rapisarda H.J. van Waarde M.K. Çamlibel University of Southampton UK Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen The Netherlands

We use orthogonal bases for continuous-time function spaces to state a version of Willems’ lemma (Willems et al., 2005) for autonomous systems. We assume that an infinite number of representation coefficients of a “sufficiently rich” trajectory is given, and we illustrate how to compute solutions to initial and boundary conditions problems from such data.

关键词： orthogonal basis data-driven simulation autonomous system function approximation fundamental lemma

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation for NARX Systems 29

Data-Driven Simulation for NARX Systems

引用

29th European Signal Processing Conference (EUSIPCO)

作者： Mishra, Vikas K. Markovsky, Ivan Fazzi, Antonio Dreesen, Philippe Vrije Univ Brussel VUB Dept ELEC Pl Laan 2 B-1050 Brussels Belgium Katholieke Univ Leuven Dept Elect Engn ESAT STADIUS Kasteelpk Arenberg 10 B-3001 Leuven Belgium

ISBN: (纸本)9789082797060

Nonlinear phenomena can be represented as nonlinear autoregressive exogenous (NARX) systems. NARX systems can be seen as a nonlinear version of linear infinite impulse response filter. data-driven approaches are witnessing considerable interests in recent times and they are well-flourished for linear time-invariant systems. However, for nonlinear systems, they are still limited and attempts have been made to generalize the results for linear systems to nonlinear systems. In this paper, we study the problem of data-driven simulation for NARX systems: compute the output trajectory from a given input trajectory and initial conditions without explicitly identifying the parametric model;the model is implicitly identified by observed trajectory. Next, we develop an algorithm for the implementation of our approach. Finally, we illustrate the developed algorithm by numerical experiments.

关键词： data-driven simulation NARX System identification

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation of multivariate nonstationary wind velocity with explicit introduction of the time-varying coherence functions

引用

JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS 2022年 220卷 104872-104872页

作者： Li, Chunxiang Luo, Kexing Cao, Liyuan Shanghai Univ Sch Mech & Engn Sci Dept Civil Engn 333 Nanchen Rd Shanghai 200444 Peoples R China

An S-transform (ST) based data-driven simulation methodology is proposed of multivariate nonstationary wind velocity with explicit introduction of the time-varying coherence functions. This framework differs from that based on the evolutionary spectral theory that uniform or non-uniform modulation functions needs to be assigned. In defining the time-frequency power spectral density (TFPSD) in accordance with the ST coefficients, the Parseval's theorem is considered to ensure energy preservation. The proposed method is firstly applied to simulated nonstationary wind velocity. For comparisons, the results of the discrete orthonormal S transform (DOST) are also included. The research demonstrates that the ST based results agree well with the original, but a bias exists between the results simulated by DOST and the original, indicating that the feasibility of the proposed method. Employing four measured downburst records to simulate multivariate nonstationary wind velocity by the proposed method further validates its feasibility. In order to enhance the simulation fidelity, the inverse S transform (IST) based regulation and control method (IST-RCM) of high precision is developed, where the balancing parameter is defined and formulated to express quantitatively the relationship between accuracy and efficiency. It is found that the results with IST-RCM get more close to the actual wind velocity records.

关键词： Wind engineering Nonstationary wind velocity data-driven simulation S-transform Regulation and control method

来源：评论

学校读者我要写书评

暂无评论

data-driven simulation of pedestrian collision avoidance with a nonparametric neural network

引用

NEUROCOMPUTING 2020年第0期379卷 130-140页

作者： Martin, Rafael F. Parisi, Daniel R. Inst Tecnol Buenos Aires Lavarden 315C1437FBG Ca De Buenos Aires Argentina Inst Tecnol Buenos Aires CONICET Lavarden 315C1437FBG Ca De Buenos Aires Argentina

data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, which does not have to deal with a huge number of free parameters as in the case of multi-layer neural networks. Although the method is general, we focus on the one pedestrian - one obstacle problem. Experimental data were collected in a motion capture laboratory providing high-precision trajectories. The proposed model allows us to simulate the trajectory of a pedestrian avoiding an obstacle from any direction. Together with the methodology specifications, we provide the data set needed for performing the simulations of this kind of pedestrian dynamic system. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Pedestrian dynamics data-driven simulation Navigation Steering Generalized regression neural network Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Digital twins of multiple energy networks based on real-time simulation using holomorphic embedding method, Part II: data-driven simulation*

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2023年第1期153卷

作者： Tian, Hang Zhao, Haoran Li, Haoran Huang, Xiaoli Qian, Xiaoyi Huang, Xu Shandong Univ Sch Elect Engn Jinan 250061 Peoples R China State Grid Tianjin Elect Power Co Tianjin 300010 Peoples R China

Digital twins can act as a transformative role in improving the operational performance of multiple energy networks (MEN) by examining the impact of implementing newer technologies, extra equipment, control strategies, etc. The objective of this series of papers is to present digital twins of MEN that can be simulated in real-time using the holomorphic embedding method. While Part I concentrated on mechanism-driven modeling of the holomorphic embedding-based model (HEM), this paper (Part II) focuses on data-driven simulation to ensure the twin is synchronized with actual physical objects. A parametric synchronization method (PSM) is proposed, which assists HEM in closely matching the actual dynamic behavior with time-varying characteristics. A machine learning surrogate model (MLSM) is proposed to accelerate the search of HEM's convergence radius, which is critical to maintaining the twin's real-time computational performance. Finally, the finalized digital twins are tested on the OPAL-RT simulation platform equipped with a real-time simulator. In a medium-sized MEN test case with a minor time step of 0.01 s, the digital twins can be validated with a faster than real-time performance even without the assistance of parallel computing.

关键词： Digital twins Holomorphic embedding Multiple energy networks Real-time simulation data-driven simulation

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：