Search | Engineering

订阅投稿

首页学术期刊学术焦点学术视频工程成就工程前沿联系我们 English

资源类型

期刊论文 170

年份

2023 2

2022 9

2021 12

2020 14

2019 12

2018 13

2017 14

2016 11

2015 9

2014 9

2013 3

2012 8

2010 3

2009 4

2008 6

2007 5

2006 7

2005 6

2004 4

2003 5

展开︾

关键词

遗传算法 22

优化 3

神经网络 3

人工神经网络 2

加速遗传算法 2

算法 2

BP神经网络 1

CAESAR竞赛；认证加密算法；分组密码；序列密码；哈希函数；安全性评估 1

Colebrook隐式方程 1

L唱M算法 1

MINLP 1

OFDMA 1

Pareto最优 1

Powell法 1

e-杂交稻 1

eui 1

三维路径规划 1

三酰甘油 1

中国 1

展开︾

检索范围：

排序：展示方式：

Multi-objective genetic algorithms based structural optimization and experimental investigation of the

Pengxing YI,Lijian DONG,Tielin SHI

《机械工程前沿（英文）》 2014年第9卷第4期页码 354-367 doi: 10.1007/s11465-014-0319-5

摘要：

To improve the dynamic performance and reduce the weight of the planet carrier in wind turbine gearbox, a multi-objective optimization method, which is driven by the maximum deformation, the maximum stress and the minimum mass of the studied part, is proposed by combining the response surface method and genetic algorithms in this paper. Firstly, the design points’ distribution for the design variables of the planet carrier is established with the central composite design (CCD) method. Then, based on the computing results of finite element analysis (FEA), the response surface analysis is conducted to find out the proper sets of design variable values. And a multi-objective genetic algorithm (MOGA) is applied to determine the direction of optimization. As well, this method is applied to design and optimize the planet carrier in a 1.5 MW wind turbine gearbox, the results of which are validated by an experimental modal test. Compared with the original design, the mass and the stress of the optimized planet carrier are respectively reduced by 9.3% and 40%. Consequently, the cost of planet carrier is greatly reduced and its stability is also improved.

关键词： planet carrier multi-objective optimization genetic algorithms wind turbine gearbox modal experiment

HTML PDF 收藏

基于遗传算法的火灾环境下建筑内人员安全疏散可靠度计算

汪金辉,陆守香

《中国工程科学》 2006年第8卷第3期页码 58-61

摘要：

将遗传算法（GAs）引入火灾环境下建筑内人员安全疏散的可靠度分析领域，并初步探讨了这一算法的具体实现过程，遗传算法可以方便地对式子复杂和难以求导的功能函数进行优化计算。算例分析的结果表明，遗传算法不仅可以实现人员安全疏散可靠度计算，而且获得了很高的计算精度，为人员安全疏散可靠度研究提供了新的有效方法和途径。

关键词：遗传算法火灾人员疏散可靠度

HTML PDF 收藏

时域有限差分算法与遗传算法在平面螺旋电感设计中的应用

王宏建,李靖,刘和光,姜景山

《中国工程科学》 2004年第6卷第11期页码 38-42

摘要：

文章通过电磁场时域有限差分(FDTD)算法与遗传算法(GA)相结合进行平面螺旋电感设计。通过优化单元网格大小，可优化设计整个平面螺旋电感（包含空气桥）的结构尺寸。介绍了该方法既能够进行严格的电磁场求解，又可以避免繁杂的实验过程，是优化设计的一种有效而准确的手段。

关键词：时域有限差分算法遗传算法平面螺旋电感品质因素

HTML PDF 收藏

基于GA-ANFIS在石灰矿技术经济系统中的参数优化研究与应用实践

杨仕教,戴剑勇,曾晟

《中国工程科学》 2005年第7卷第6期页码 61-65

摘要：

为掌握水泥原料矿山系统中的技术经济参数对矿石成本影响的关联规律性，首先运用自适应模糊神经网络对矿山技术经济系统建模，再用并行遗传算法对模型求解，得到了确保矿石成本最小的各项最优技术经济指标，为提高矿山生产管理与经济效益提供了重要的参考价值。

关键词：自适应模糊神经网络并行遗传算法技术经济参数

HTML PDF 收藏

基于遗传算法的单脉冲阵列天线优化

王宏建,高本庆,刘瑞祥

《中国工程科学》 2002年第4卷第5期页码 84-87

摘要：

采用遗传算法来优化单脉冲阵列天线的和、差方向图和方向性系数。在天线阵综合时，若不考虑差方向图和方向性系数的影响，所进行的方向图优化仅仅显示出和方向图的特性，对单脉冲阵列天线追踪目标的精度和作用距离没有保证。而在天线阵综合时兼顾和、差方向图以及方向性系数的优化，既可使得天线能发现目标，并使天线能准确对目标实施准确角跟踪，提髙雷达的跟踪和作战性能。

关键词：单脉冲阵列天线遗传算法方向图方向性系数

HTML PDF 收藏

基于遗传算法的工程项目投资综合优化探讨

陈耀明,钟登华,付金强

《中国工程科学》 2006年第8卷第7期页码 68-71

摘要：

利用多目标优化理论、多属性效用函数理论建立了工程建设项目工期、成本和质量的综合均衡优化模型，在网络计划技术的基础上，用遗传算法对模型进行求解，可以得到最满意的决策方案和多个近似满意的备选方案，作为工程建设项目投资综合控制的目标。并应用实例对模型的可行性和实用性进行了验证。

关键词：工程项目投资多属性效用函数遗传算法

HTML PDF 收藏

遗传算法在水泥矿山卡车运输调度系统中的应用

戴剑勇,杨仕教,古德生

《中国工程科学》 2006年第8卷第8期页码 77-80

摘要：

根据露天矿山运输调度系统的复杂性与非线性特性，建立了实时运输调度系统模型；运用遗传进化算法中的选择、交叉、变异、插入、迁移算子的寻优迭代计算，成功地解决了在开采工艺、产量、质量等多因素约束条件下的实时运输调度优化问题。并将其用于韶峰水泥原料矿山的生产运输调度系统，既降低了矿山运输成本，又协调了开采工艺、质量、产量之间的关系，取得了较好的效果。同时为矿山企业信息化建设和其他物流企业提供了重要的参考价值。

关键词：遗传算法运输调度系统运输成本

HTML PDF 收藏

基于候选方案排序的进化决策方法

荔建琦,陈火旺,王兵山

《中国工程科学》 2001年第3卷第1期页码 62-70

摘要：

由于无法得到准确的期望效用函数，在信息不完全和结果不确定的环境下作出决策是困难的。提出基于候选方案排序的进化决策方法。通常通过分析得出一组与候选方案期望效用相关的指标，设计决策规则归结为寻找二者之间的相关关系。如果将所有候选方案按其对效用有影响的指标分为n类，并利用进化算法在n!空间中搜索全部方案的期望效用排序，则根据此排序作出最佳决策。提出针对排序问题的遗传算法。该方法较少依赖专家知识，无须显式地构造期望效用函数，能有效处理非数值或非量化指标以及指标冲突和指标相关等问题，在带随机噪声环境下仍能获得稳健解。在仿真机器人控制器设计中的应用表明了该方法的有效性。

关键词：进化决策进化机器人排序问题遗传算法

HTML PDF 收藏

Enhancing fatigue life of cylinder-crown integrated structure by optimizing dimension

Weiwei ZHANG,Xiaosong WANG,Zhongren WANG,Shijian YUAN

《机械工程前沿（英文）》 2015年第10卷第1期页码 102-110 doi: 10.1007/s11465-015-0329-y

摘要：

Cylinder-crown integrated hydraulic press (CCIHP) is a new press structure. The hemispherical hydraulic cylinder also functions as a main portion of crown, which has lower weight and higher section modulus compared with the conventional hydraulic cylinder and press crown. As a result, the material strength capacity is better utilized. During the engineering design of cylinder-crown integrated structure, in order to increase the fatigue life, structural optimization on the basis of the adaptive macro genetic algorithms (AMGA) is first conducted to both reduce weight and decrease peak stress. It is shown that the magnitude of the maximum principal stress is decreased by 28.6%, and simultaneously the total weight is reduced by 4.4%. Subsequently, strain-controlled fatigue test is carried out, and the stress-strain hysteresis loops and cyclic hardening curve are obtained. Based on linear fit, the fatigue properties are calculated and used for the fatigue life prediction. It is shown that the predicted fatigue life is significantly increased from 157000 to 1070000 cycles after structural optimization. Finally, according to the optimization design, a 6300 kN CCIHP has been manufactured, and priority application has been also suggested.

关键词： cylinder-crown integrated hydraulic press (CCIHP) adaptive macro genetic algorithms (AMGA) strain-controlled fatigue test

HTML PDF 收藏

基于交互式遗传算法模型的群体论证方法

宋东明,朱耀琴,吴慧中

《中国工程科学》 2009年第11卷第11期页码 64-69

摘要：

针对综合集成研讨厅进行复杂决策问题研讨时，群体专家提出的众多定性意见最终如何实现收敛的问题，提出了基于交互式遗传算法模型的群体论证方法，使专家的群体思维与计算机技术紧密结合，达成共识。实践证明，该方法可以较好地获得复杂决策问题的优化解，且更符合实际的研讨论证过程。

关键词：综合集成研讨厅复杂决策问题交互式遗传算法性能指标论证

HTML PDF 收藏

基于可拓学的设计方案进化推理方法

赵燕伟,,刘海生,张国贤

《中国工程科学》 2003年第5卷第5期页码 63-69

摘要：

在分析现有概念设计求解策略的基础上，提出了基于可拓学理论与遗传算法相结合的概念设计求解模型。利用遗传算法模拟物元变换过程，建立了产品方案物元描述的内部模型和外部模型，探讨了内、外模型的转换关系并通过关联函数将内、外部模型联系起来。根据内部模型给出了遗传算法的编码形式以及与之相适应的交叉、变异策略，并通过可拓评价方法建立了遗传算法的适应值函数，基本解决了产品概念设计中的知识组合爆炸和矛盾冲突问题。最后通过求解减速器方案验证了该方法的可行性。

关键词：概念设计物元变换遗传算法进化推理可拓评价

HTML PDF 收藏

计算管内湍动流体摩擦因数的显式新方程

王勇,阮奇

《中国工程科学》 2006年第8卷第6期页码 83-88

摘要：

管内湍动流体摩擦因数是雷诺数和相对粗糙度的二元非线性函数，由Colebrook隐式方程计算摩擦因数要用迭代的方法求解，很不方便。为了得到形式简单、精度高的计算摩擦因数的显式方程，提出了二元非线性多项式智能拟合法。该法将二元非线性多项式转化成多元线性多项式并建立线性最小二乘法标准矩阵，用遗传算法结合矩阵法对多项式的项数、项型式项指数及项系数进行搜索得到最优的拟合函数式。用该法拟合了Colebrook方程解的数据，得到一个计算管内湍动流体摩擦因数的显式新方程。在雷诺数3.000≤Re≤10⁸、相对粗糙度0≤e/d≤0.05的范围内，该方程计算结果与Colebrook方程的平均偏差为0.5%，最大偏差不超过1.8%，与实验数据偏差为2.3%。新方程具有形式简单、精度高、适用范围广的优点，且便于简化成光滑管或阻力平方区等情况下的计算摩擦因数的方程。

关键词：湍动流动摩擦因数 Colebrook隐式方程遗传算法智能拟合法显式方程

HTML PDF 收藏

Predicting beach profile evolution with group method data handling-type neural networks on beaches with seawalls

M. A. LASHTEH NESHAEI, M. A. MEHRDAD, N. ABEDIMAHZOON, N. ASADOLLAHI

《结构与土木工程前沿（英文）》 2013年第7卷第2期页码 117-126 doi: 10.1007/s11709-013-0205-y

摘要： A major goal of coastal engineering is to develop models for the reliable prediction of short- and long-term near shore evolution. The most successful coastal models are numerical models, which allow flexibility in the choice of initial and boundary conditions. In the present study, evolutionary algorithms (EAs) are employed for multi-objective Pareto optimum design of group method data handling (GMDH)-type neural networks that have been used for bed evolution modeling in the surf zone for reflective beaches, based on the irregular wave experiments performed at the Hydraulic Laboratory of Imperial College (London, UK). The input parameters used for such modeling are significant wave height, wave period, wave action duration, reflection coefficient, distance from shoreline and sand size. In this way, EAs with an encoding scheme are presented for evolutionary design of the generalized GMDH-type neural networks, in which the connectivity configurations in such networks are not limited to adjacent layers. Also, multi-objective EAs with a diversity preserving mechanism are used for Pareto optimization of such GMDH-type neural networks. The most important objectives of GMDH-type neural networks that are considered in this study are training error (TE), prediction error (PE), and number of neurons ( ). Different pairs of these objective functions are selected for two-objective optimization processes. Therefore, optimal Pareto fronts of such models are obtained in each case, which exhibit the trade-offs between the corresponding pair of the objectives and, thus, provide different non-dominated optimal choices of GMDH-type neural network model for beach profile evolution. The results showed that the present model has been successfully used to optimally prediction of beach profile evolution on beaches with seawalls.

关键词： beach profile evolution genetic algorithms group method of data handling Pareto reflective beaches

HTML PDF 收藏

Crack detection of the cantilever beam using new triple hybrid algorithms based on Particle Swarm Optimization

《结构与土木工程前沿（英文）》页码 1127-1140 doi: 10.1007/s11709-022-0838-9

摘要： The presence of cracks in a concrete structure reduces its performance and increases in the size of cracks result in the failure of the structure. Therefore, the accurate determination of crack characteristics, such as location and depth, is one of the key engineering issues for assessment of the reliability of structures. This paper deals with the inverse analysis of the crack detection problems using triple hybrid algorithms based on Particle Swarm Optimization (PSO); these hybrids are Particle Swarm Optimization-Genetic Algorithm-Firefly Algorithm (PSO-GA-FA), Particle Swarm Optimization-Grey Wolf Optimization-Firefly Algorithm (PSO-GWO-FA), and Particle Swarm Optimization-Genetic Algorithm-Grey Wolf Optimization (PSO-GA-GWO). A strong correlation exists between the changes in the natural frequency of a concrete beam and the crack parameters. Thus, the location and depth of a crack in a beam can be predicted by measuring its natural frequency. Hence, the measured natural frequency can be used as the input parameter of the algorithm. In this paper, this is applied to identify crack location and depth in a cantilever beam using the new hybrid algorithms. The results show that among the proposed triple hybrid algorithms, the PSO-GA-FA and PSO-GWO-FA algorithms are much more effective than PSO-GA-GWO algorithm for the crack detection.

关键词： crack cantilever beam triple hybrid algorithms Particle Swarm Optimization

HTML PDF 收藏

Development of surface reconstruction algorithms for optical interferometric measurement

Dongxu WU, Fengzhou FANG

《机械工程前沿（英文）》 2021年第16卷第1期页码 1-31 doi: 10.1007/s11465-020-0602-6

摘要： Optical interferometry is a powerful tool for measuring and characterizing areal surface topography in precision manufacturing. A variety of instruments based on optical interferometry have been developed to meet the measurement needs in various applications, but the existing techniques are simply not enough to meet the ever-increasing requirements in terms of accuracy, speed, robustness, and dynamic range, especially in on-line or on-machine conditions. This paper provides an in-depth perspective of surface topography reconstruction for optical interferometric measurements. Principles, configurations, and applications of typical optical interferometers with different capabilities and limitations are presented. Theoretical background and recent advances of fringe analysis algorithms, including coherence peak sensing and phase-shifting algorithm, are summarized. The new developments in measurement accuracy and repeatability, noise resistance, self-calibration ability, and computational efficiency are discussed. This paper also presents the new challenges that optical interferometry techniques are facing in surface topography measurement. To address these challenges, advanced techniques in image stitching, on-machine measurement, intelligent sampling, parallel computing, and deep learning are explored to improve the functional performance of optical interferometry in future manufacturing metrology.

关键词： surface topography measurement optical interferometry coherence envelope phase-shifting algorithm