检索结果-内蒙古大学图书馆

Optimizing laser cutting of stainless steel using latin hypercube sampling and neural networks

OPTICS AND LASER TECHNOLOGY 2025年 182卷

作者： Kristijan, Sket David, Potocnik Lucijano, Berus Jernej, Hernavs Mirko, Ficko Univ Maribor Fac Mech Engn Maribor Smetanova 17 SI-2000 Maribor Slovenia

Optimizing cutting parameters in fiber laser cutting of austenitic stainless steel is challenging due to the complex interplay of multiple variables and quality metrics. To solve this problem, latin hypercube sampling was used to ensure a comprehensive and efficient exploration of the parameter space with a smaller number of trials (185), coupled with feedforward neural networks for predictive modeling. The networks were trained with a leave-oneout cross-validation strategy to mitigate overfitting. Different configurations of hidden layers, neurons, and training functions were used. The approach was focused on minimizing dross and roughness on both the top and bottom areas of the cut surfaces. During the testing phase, an average MSE of 0.063 and an average MAPE of 4.68% were achieved by the models. Additionally, an experimental test was performed on the best parameter settings predicted by the models. Initial modelling was conducted for each quality metric individually, resulting in an average percentage difference of 1.37% between predicted and actual results. Grid search was also performed to determine an optimal input parameter set for all outputs, with predictions achieving an average accuracy of 98.34%. Experimental validation confirmed the accuracy and robustness of the model predictions, demonstrating the effectiveness of the methodology in optimizing multiple parameters of complex laser cutting processes.

关键词： Laser cutting optimization Cut surface quality Dross formation latin hypercube sampling Feedforward neural network

来源：评论

学校读者我要写书评

暂无评论

Parameter tuning of the firefly algorithm by three tuning methods: Standard Monte Carlo, quasi-Monte Carlo and latin hypercube sampling methods a

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2025年 87卷

作者： Joy, Geethu Huyck, Christian Yang, Xin-She Middlesex Univ Sch Sci & Technol London NW4 4BT England

There are many different nature-inspired algorithms in the literature, and almost all such algorithms have algorithm-dependent parameters that need to be tuned. The proper setting and parameter tuning should be carried out to maximize the performance of the algorithm under consideration. This work is the extension of the recent work on parameter tuning by Joy et al. (2024) presented at the International Conference on Computational Science (ICCS 2024), and the Firefly Algorithm (FA) is tuned using three different methods: the Monte Carlo method, the Quasi-Monte Carlo method and the latin hypercube sampling. The FA with the tuned parameters is then used to solve a set of six different optimization problems, and the possible effect of parameter setting on the quality of the optimal solutions is analyzed. Rigorous statistical hypothesis tests have been carried out, including Student's t-tests, F-tests, non-parametric Friedman tests and ANOVA. Results show that the performance of the FA is not influenced by the tuning methods used. In addition, the tuned parameter values are largely independent of the tuning methods used. This indicates that the FA can be flexible and equally effective in solving optimization problems, and any of the three tuning methods can be used tune its parameters effectively.

关键词： Algorithm Firefly algorithm Parameter tuning Monte Carlo method latin hypercube sampling Optimization

来源：评论

学校读者我要写书评

暂无评论

A robust force-finding framework for tensegrity structures using gradient-boosting decision trees and latin hypercube sampling

引用

STRUCTURES 2025年 76卷

作者： He, Yutao Guo, Jiamin Ping, Huan Zhu, MingLiang Mangalathu, Sujith Shanghai Maritime Univ Sch Ocean Sci & Engn Shanghai 200135 Peoples R China Southeast Univ Sch Civil Engn Nanjing 210096 Peoples R China JP Morgan & Chase Atlanta GA 30040 USA

In a tensegrity structure with a specified configuration, mechanical performance is significantly influenced by its pre-stress values. Consequently, alongside form-finding, force-finding becomes a task of critical importance. To address the force-finding problem, this paper proposes a novel method integrating machine learning and statistical techniques as an alternative to traditional trial-and-error approaches, thereby eliminating reliance on element group theory and parameters adjustments. The method effectively overcomes challenges such as matrix singularity in finite element analysis and the excessive sample requirements of conventional artificial intelligence techniques. The proposed approach is demonstrated by solving the force-finding problem for both self-stressed and non-self-stressed systems, as well as for symmetric and asymmetric structures. This study also provides an in-depth investigation into three key aspects: the effect of varying element counts (both low and high), the impact of different element groupings (grouped and ungrouped), and the method's performance under various load cases encountered by tensegrity structures. Notably, the proposed method achieves the desired solutions with significantly fewer samples (fewer than 600) for the selected configurations.

关键词： Gradient boosting decision tree latin hypercube sampling Tensegrity structure Self-stressed Non-self-stressed External loads

来源：评论

学校读者我要写书评

暂无评论

Enhancement of random sampling by a combined approach of control variates and latin hypercube sampling for uncertainty quantification in light water reactor lattice calculations

引用

JOURNAL OF NUCLEAR SCIENCE AND TECHNOLOGY 2025年第5期62卷 470-479页

作者： Fujita, Tatsuya Japan Atom Energy Agcy Nucl Safety Res Ctr Ibaraki Japan Hokkaido Univ Grad Sch Engn Kita 13Nishi 8Kita Ku Sapporo Hokkaido 0608628 Japan

This study confirmed the efficiency of a combined approach of the control variates (CV) and the latin hypercube sampling (LHS), which enhanced the random-sampling-based uncertainty quantification due to cross-section (XS) covariance data, by considering the effect of statistical variation. The convergence performance for the uncertainty of infinite multiplication factor (k-infinity) during the random sampling was compared between several efficient sampling techniques such as the antithetic sampling (AS), LHS, CV, and the combined approaches of them in the PWR-UO2 fuel assembly geometry. The k-infinity uncertainty was evaluated by statistically processing several times Serpent2 calculations using perturbed ACE-formatted XS files based on ENDF/B-VIII.0. CV+AS and CV+LHS showed similar higher efficiency than AS, LHS, and CV. In addition, sensitivity analyses were performed to select alternative parameters used in CV. The calculation results obtained in fuel pin-cell and 3 x 3 mini fuel lattice geometries showed almost the same performance as alternative parameters. The reason was qualitatively considered that the influence of XS covariance data for U isotopes was more dominant though the 3 x 3 mini fuel lattice geometry can capture that for Gd isotopes. Consequently, the applicability of CV+LHS for the improvement of convergence performance to evaluate the k-infinity uncertainty during the random sampling was confirmed.

关键词： Uncertainty quantification random sampling antithetic sampling latin hypercube sampling control variates FRENDY Serpent2 ENDF/B-VIII.0

来源：评论

学校读者我要写书评

暂无评论

Multi-objective DOA estimation in automotive radar using a Sailfish optimizer with latin hypercube sampling

引用

Soft Computing 2025年第5期29卷 2433-2461页

作者： P, Geetha Nanda, Satyasai Jagannath Yadav, Rajendra Prasad Department of Electronics and Communication Engineering Malaviya National Institute of Technology Jaipur Rajasthan Jaipur 302017 India

Direction of arrival (DOA) estimation is a challenging problem in automotive radar for target detection and finds potential applications in the design of driver assistance system (DAS). Accurate DOA estimation in automotive radar becomes more difficult in the presence of noise. To address this issue, in this paper, the DOA estimation problem in automotive radar is formulated as a multi-objective optimization problem by simultaneous minimization of two operators: (1) reciprocal of Maximum Likelihood function;and (2) noise variance. Accurate angle estimation can be carried out in the absence of noise, and vice-versa, thus making these two functions contradictory in nature. In this article, a multi-objective Sailfish optimizer algorithm is proposed with latin hypercube sampling and double archive mechanism termed as MOSFO-LH. The latin hypercube generates evenly distributed samples and thus provides potential diversification of the search agents in the objective space. Further, a double archive method is incorporated to keep the good solutions that are responsible for maintaining diversity in the Pareto Front. Superior performance of the proposed MOSFO-LH algorithm is reported over five more comparative algorithms, on ten benchmark multi-objective test functions selected from the ZDT and DTLZ test suite. Case studies are reported for DOA estimation in automotive radar under six noise conditions. Effective performance is demonstrated with estimated DOA angles, box plots of root mean square error values, Pareto optimal fronts, heat map of inverse generalized distance, maximum spread and hyper volume metric. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2025.

关键词： Automotive radar Direction of arrival estimation latin hypercube sampling Multi-objective optimization Sailfish optimizer

来源：评论

学校读者我要写书评

暂无评论

latin hypercube sampling Techniques for Power Systems Reliability Analysis With Renewable Energy Sources

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2011年第4期26卷 2066-2073页

作者： Shu, Zhen Jirutitijaroen, Panida Natl Univ Singapore Dept Elect & Comp Engn Singapore 119077 Singapore

This paper proposes latin hypercube sampling (LHS) methods for reliability analysis of power systems including renewable energy sources, with an emphasis on the fluctuation of bus loads and intermittent behavior of renewable generations such as wind and solar power. The LHS methods that are applicable for systems with correlated random variables-system load and renewable generation-are proposed. Reliability indices such as loss of load expectation and loss of load probability are estimated. Results from Monte Carlo (MC) sequential sampling, MC nonsequential sampling, and that from the proposed LHS methods are compared. It is shown that the proposed methods are as accurate as the other sampling methods while requiring much less CPU time. Two case studies modified from the Electric Reliability Council of Texas (ERCOT) and IEEE Reliability Test System (IEEE RTS) are presented to demonstrate the performances of the proposed sampling methods.

关键词： Correlation analysis latin hypercube sampling Monte Carlo simulation power system reliability renewable energy

来源：评论

学校读者我要写书评

暂无评论

latin hypercube sampling Monte Carlo estimation of average quality index for integrated circuits

引用

ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING 1997年第1-2期14卷 131-142页

作者： Keramat, M Kielbasa, R Ecole Supérieure d‘Electricité (SUPELEC) Service des Mesures Gif-sur-Yvette Cédex France

The Monte Carlo method exhibits generality and insensitivity to the number of stochastic variables, but is expensive for accurate Average Quality Measure (AQI) or Parametric Yield estimation of MOS VLSI circuits. In this contribution a new method of variance reduction technique, viz. the latin hypercube sampling (LHS) method is presented which improves the efficiency of AQI estimation in integrated circuits especially for MOS digital circuits. This method is similar to the Primitive Monte Carlo (PMC) method except in samples generation step where the latin hypercube sampling method is used. This sampling method is very simple and does not involve any further simulations. Moreover, it has a smaller variance with respect to the PMC estimator. Encouraging results have thus far been obtained. A S-dimensional quadratic function, a high pass filter, and a CMOS delay circuit examples are included to demonstrate the efficiency of this technique.

关键词： Monte Carlo methods latin hypercube sampling average quality index

来源：评论

学校读者我要写书评

暂无评论

latin hypercube sampling for uncertainty analysis in multiphase modelling

引用

JOURNAL OF ENVIRONMENTAL ENGINEERING AND SCIENCE 2008年第6期7卷 617-626页

作者： Khan, Amir Ali Lye, Leonard Husain, Tahir Govt NL Dept Environm & Conservat Hydrol Modelling Sect St John NF A1B 4J6 Canada Mem Univ Newfoundland Fac Engn & Appl Sci St John NF A1B 3X5 Canada

To facilitate the uncertainty analysis of a finite element multiphase multi-component transport model MOFAT, this paper provides guidance on latin hypercube sampling Monte Carlo (LHS-MC) sample size selection. To evaluate the ability of LHS-MC to produce output cumulative distribution functions (cdfs) that replicate random sampling Monte Carlo (RS-MC) cdfs, output cdfs obtained with LHS-MC sample sizes of 100, 300, and 500, and a RS-MC sample size of 10000 are compared using the two sample Kolmogorov-Smirnov test. The LHS-MC cdfs for the three;different sample sizes are able to accurately replicate the corresponding RS-MC cdfs for benzene, toluene, ethylbenzene, and xylene (BTEX) concentrations in the water, gas, and solid phases. The stability of LHS-MC is also evaluated by comparing three replicates of a LHS-MC sample. The three replicates are all able to accurately replicate the corresponding RS-MC cdfs for all BTEX concentrations in all three phases.

关键词： uncertainty analysis Monte Carlo latin hypercube sampling sample size MOFAT multiphase multi-component

来源：评论

学校读者我要写书评

暂无评论

latin hypercube sampling and the propagation of uncertainty in analyses of complex systems

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2003年第1期81卷 23-69页

作者： Helton, JC Davis, FJ Sandia Natl Labs Dept 6849 Albuquerque NM 87185 USA Arizona State Univ Dept Math & Stat Tempe AZ 85287 USA

The following techniques for uncertainty and sensitivity analysis are briefly summarized: Monte Carlo analysis, differential analysis, response surface methodology, Fourier amplitude sensitivity test, Sobol' variance decomposition, and fast probability integration. Desirable features of Monte Carlo analysis in conjunction with latin hypercube sampling are described in discussions of the following topics: (i) properties of random, stratified and latin hypercube sampling, (ii) comparisons of random and latin hypercube sampling, (iii) operations involving latin hypercube sampling (i.e. correlation control, reweighting of samples to incorporate changed distributions, replicated sampling to test reproducibility of results), (iv) uncertainty analysis (i.e. cumulative distribution functions, complementary cumulative distribution functions, box plots), (v) sensitivity analysis (i.e. scatterplots, regression analysis, correlation analysis, rank transformations, searches for nonrandom patterns), and (vi) analyses involving stochastic (i.e. aleatory) and subjective (i.e. epistemic) uncertainty. Published by Elsevier Science Ltd.

关键词： aleatory uncertainty epistemic uncertainty latin hypercube sampling Monte Carlo analysis random sampling sensitivity analysis uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

latin hypercube sampling applied to reliability-based multidisciplinary design optimization of a launch vehicle

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2013年第1期28卷 297-304页

作者： Roshanian, Jafar Ebrahimi, Masoud KN Toosi Univ Technol Fac Aerosp Engn Tehran *** Iran

In this paper, Reliability-Based Multidisciplinary Design Optimization (RBMDO) of a two-stage solid propellant expendable launch vehicle (LV) is investigated. Propulsion, weight, aerodynamics (geometry) and trajectory (performance) disciplines are used in an appropriate combination. Throw weight minimization is chosen as objective function. Design variables for system level optimization are selected from propulsion, geometry and trajectory disciplines. Mission constraints contain the final velocity, the height above ground, and flight path angle. The constraints that appear during the flight are also considered. Assuming a normal distribution for the uncertain variables, latin hypercube sampling (LHS) method selects the sample values for simulation runs which are eventually utilized for calculating probability density function of constraints and their reliability at each design point. Sequential Quadratic Programming (SQP) technique is used to achieve the optimal solution. Although the launch vehicle throw weight is increased negligibly in comparison with deterministic optimization, results show that the reliability-based method satisfied desired reliability of the constraints. (C) 2012 Elsevier Masson SAS. All rights reserved.

关键词： Multidisciplinary design optimization Reliability-based design latin hypercube sampling Solid propellant launch vehicle

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：