共查询到20条相似文献,搜索用时 62 毫秒
1.
2.
3.
AGV(automatic guided vehicle)作为物料运输的载体,使生产线物料按节拍流动,是产线设计的关键部分。针对产线初步规划方案中AGV的数量、配送量及速度参数未确定影响产线最佳方案设计的问题,将产线产品生产周期、暂存区总容量、设备平均利用率及AGV平均利用率作为多个目标。采用全因子试验方法,探究AGV的数量、配送量及速度3个因素对多个目标的影响及其变化规律,确定关键因子与优化目标。建立多目标数学模型,采用遗传算法求解,调整并行工序数量,获得优化方案并仿真验证。研究结果表明:该方法能够有效求解问题,使作业的AGV数量减少至1辆,提高资源利用率,降低企业投资成本。 相似文献
4.
5.
乘坐舒适性的需求受到人们越来越广泛的关注,动力总成的振动是影响乘坐舒适性的主要因素,动力总成解耦优化已成为了学者们研究的热点。由于传统的优化算法难以满足动力总成复杂非线性关系下的工程需求,并且速度慢、难以得到最优解,该研究主要基于多岛遗传算法,对企业某型号动力总成悬置系统进行解耦优化研究。首先,通过对动力总成动力学理论分析,建立相应动力学模型;然后,基于能量法解耦理论,建立以刚度为设计变量、频率配置为约束条件以及最大解耦率为目标函数的MATLAB数学模型;最后,采用多岛遗传算法进行解耦优化,通过MATLAB与ADAMS进行对比验证。优化结果表明,解耦运算效率和精度得到显著提高,刚度组合能够更好地满足工程实际需求。 相似文献
6.
遗传算法是一种模拟生命进化机制的搜索和优化方法,其全局优化和隐含并行性使得遗传算法适合求解大规模的复杂优化问题。并在介绍遗传算法的基础上,提出了基于遗传算法的行星传动多目标模糊优化方法。算例计算表明,遗传算法在机械多目标优化方面具有较好的应用前景。 相似文献
7.
以动物肌肉结构和工作特性为模拟对象的仿生肌肉,其控制对象数量多,控制较为复杂.首先将仿生肌肉控制转化为多目标优化控制问题,将多目标函数合成为单一目标函数,以对该多目标优化问题进行求解;其次就遗传算法在该多目标优化求解问题中的应用进行了讨论;最后对由形状记忆合金构成的仿生肌肉进行仿真实验,结果表明仿生肌肉的多目标优化控制方法是一种有效的优化控制方法. 相似文献
8.
以动物肌肉结构和工作特性为模拟对象的仿生肌肉,其控制对象数量多,控制较为复杂。首先将仿生肌肉控制转化为多目标优化控制问题,将多目标函数合成为单一目标函数,以对该多目标优化问题进行求解;其次就遗传算法在该多目标优化求解问题中的应用进行了讨论;最后对由形状记忆合金构成的仿生肌肉进行仿真实验,结果表明仿生肌肉的多目标优化控制方法是一种有效的优化控制方法。 相似文献
9.
基于BP网络和Pareto遗传算法的多目标协同优化 总被引:1,自引:0,他引:1
多学科设计优化(MDO)问题往往是多目标的。Pareto遗传算法(PGA)所求得的Pareto最优解集为设计决策提供了很大方便。针对在CO的计算构架中直接使用PGA会导致计算量过大的问题,提出基于BP神经网络和pareto遗传算法的多目标协同优化方法。采用试验设计方法选择设计点,构造具有全局近似能力的各学科优化神经网络响应面,进而采用PGA进行系统层优化问题的多目标寻优。用上述方法对某型干线客机进行总体多目标优化。与直接采用PGA求解MDF单级多目标优化模型所得的计算结果对比表明,所提出的方法能有效近似该问题的Pareto最优前沿.、 相似文献
10.
11.
《计算机集成制造系统》2015,(9)
针对箱体类零件的可重构生产线平衡问题,提出一种基于多色集合理论的机加工线平衡优化求解方法,综合考虑机加工过程中的工艺、工位约束信息,将各约束分为三类,运用多色集合理论为各类约束快速构建直观的约束模型,并为模型求解设计了以生产节拍、机床投入、机床利用率为优化目标的启发式算法,该方法使问题求解过程中无需检验即可获取满足所有约束的解方案,较大地提高了运算效率,采用Pareto最优解集的方式筛选方案,获取具备增产能力的最优方案集,通过复杂实例验证了该方法的有效性和快速性。 相似文献
12.
针对数控加工中心机床工艺路线工序集中、工步复杂、加工刀具类型多带来的排序规模大、成本核算困难的特点,用一种改进的遗传算法实现工艺路线的优化。算法中以加工时间最短和加工成本最低两个目标作为组合的优化目标函数,从而构造出适应度函数。改进的算法对不同的加工面设立了加工标识位码,并制定了加工标识位码的优先原则、加工标识位码相同原则;优先原则实现了工艺路线排序原则;相同原则实现了工步中的刀具类型的选择及刀具成本的核算。由于算法中加入了加工标识位码相同原则,去除掉不必要工艺路线组合方案,从而使得算法收敛更快。通过实例对算法进行了系统仿真实验,得出了最优路线方案,验证了方案的合理性。 相似文献
13.
14.
Sung Soo Kim Il-Hwan Kim V. Mani Hyung Jun Kim 《The International Journal of Advanced Manufacturing Technology》2008,38(9-10):884-895
In this paper, we consider the machining condition optimization models presented in earlier studies. Finding the optimal combination of machining conditions within the constraints is a difficult task. Hence, in earlier studies standard optimization methods are used. The non-linear nature of the objective function, and the constraints that need to be satisfied makes it difficult to use the standard optimization methods for the solution. In this paper, we present a real coded genetic algorithm (RCGA), to find the optimal combination of machining conditions. We present various issues related to real coded genetic algorithm such as solution representation, crossover operators, and repair algorithm in detail. We also present the results obtained for these models using real coded genetic algorithm and discuss the advantages of using real coded genetic algorithm for these problems. From the results obtained, we conclude that real coded genetic algorithm is reliable and accurate for solving the machining condition optimization models. 相似文献
15.
《计算机集成制造系统》2015,(6)
在考虑产品需求速率的前提下,提出了调整加工成本的新方法,建立了混流装配线平衡问题的多目标优化模型。设计了基于自然数序列和拓扑排序的改进遗传算法对模型进行求解,改进交叉、变异操作来保护优秀基因,提出了种群扩张机制。对经典问题的计算试验结果表明,改进遗传算法在降低生产节拍的同时能优化产品加工成本,在求解效率和求解质量方面有显著的成效。 相似文献
16.
Multi-objective parametric optimization on machining with wire electric discharge machining 总被引:1,自引:1,他引:0
Kapil Kumar Sanjay Agarwal 《The International Journal of Advanced Manufacturing Technology》2012,62(5-8):617-633
The selection of optimum machining conditions, during wire electric discharge machining process, is of great concern in manufacturing industries these days. The increasing quality demands, at higher productivity levels, require the wire electric discharge machining process to be executed more efficiently. Specifically, the material removal rate needs to be maximized while controlling the surface quality. Despite extensive research on wire electric discharge machining process, determining the desirable operating conditions in industrial setting still relies on the skill of the operators and trial-and-error methods. In the present work, an attempt has been made to optimize the machining conditions for maximum material removal rate and maximum surface finish based on multi-objective genetic algorithm. Experiments, based on Taguchi’s parameter design, were carried out to study the effect of various parameters, viz. pulse peak current, pulse-on time, pulse-off time, wire feed, wire tension and flushing pressure, on the material removal rate and surface finish. It has been observed that a combination of factors for optimization of each performance measure is different. So, mathematical models were developed between machining parameters and responses like metal removal rate and surface finish by using nonlinear regression analysis. These mathematical models were then optimized by using multi-objective optimisation technique based on Non-dominated Sorting Genetic Algorithm-II to obtain a Pareto-optimal solution set. 相似文献
17.
Jian Zhao Gengdong Cheng Shilun Ruan Zheng Li 《The International Journal of Advanced Manufacturing Technology》2015,78(9-12):1813-1826
18.
19.
20.
N. Lenin M. Siva Kumar M. N. Islam D. Ravindran 《The International Journal of Advanced Manufacturing Technology》2013,67(5-8):1777-1790
This paper presents the development of a genetic algorithm for determining a common linear machine sequence for multi-products with different operation sequences and facilities with a limited number of duplicate machine types available for a job. This work aims to minimize the total flow distance traveled by products, reduce the number of machines arranged in the final linear sequence, and decrease the total investment cost of the machines used in the final sequence. We assume that product flow runs only in the forward direction, either via in-sequence or bypass movement. We demonstrate the effectiveness of the proposed algorithm by solving a typical layout design problem taken from literature, and several randomly generated problems. Results indicate that the proposed algorithm serves as a practical decision support tool for resolving layout problems in manufacturing facilities. 相似文献