基于改进最低水平线方法与遗传算法的矩形件排样优化算法

传统的最低水平线方法用于矩形件排样时可能产生较多未被利用的空白区域,造成不必要的材料浪费.针对此缺陷,在搜索过程中引入启发式判断,实现空白区域的填充处理,提高板材利用率.在应用遗传算法优化矩形件排样顺序时,在进化过程中采用分阶段设置遗传算子的方法,改善算法的搜索性能与效果.通过改进最低水平线方法与基于分阶段遗传算子的遗传算法相结合,共同求解矩形件排样问题.排样测试数据表明,所提出的矩形件排样优化算法能够有效改善排样效果,提高材料利用率.     

不规则零件优化排样的神经网络混合优化算法

 提出一种利用人工神经网络求解不规则件排样问题的混合优化方法.该方法首先把排样和制造工艺联系起来,将多边形各边向外扩充,为零件预留加工余量;然后采用自组织特征映射模型（SOM）和Hopfield人工神经网络相结合的方法,运用SOM神经网络对初始在板材内随机排布的不规则零件进行平移,逐步减小不规则零件之间的重叠面积,求得各零件的最优位置,再运用Hopfield神经网络对平移后的零件旋转,进行迭代运算,当能量函数达到稳定状态时,得到各排样零件的最优旋转角度组合,实现自动排样.算法可以解决不规则件和矩形件在规则板材以及不规则板材上的排样问题,实例证明了该算法的有效性和实用性.     

缺陷板材非规则件优化排样

针对理论上属于NPC问题的非规则件优化排样问题,论文提出一种基于小生境技术的自适应遗传模拟退火算法与基于内靠接临界多边形最低点的启发式布局算法相结合的方法。考虑到算法中交叉概率和变异概率的选择影响到算法收敛性,提出了自适应的交叉概率和变异概率,通过基于小生境技术的遗传模拟退火算法对非规则件排样的最优顺序和各自的旋转角度进行优化搜索。将非规则件定位在有缺陷原材料和非规则件多边形的内靠接临界多边形最低点以实现个体的解码,同时避开了原材料表面缺陷。排样实例表明,该优化排样算法行之有效,具有广泛的适应性。     

一个实用的矩形件优化排样启发式算法

仔细研究了传统矩形件优化排样近似算法及存在的主要问题，提出一个新的启发式算法。该算法根据最后板材的实际排放情况，采用了多种排放策略，克服了原算法的在零件数较少时的缺陷。在此基础上用Visual C 6．0开发了一个实用的矩形件计算机辅助排样系统。实际应用表明，新算法可获得比原近似算法更好的优化排样结果。笔者给出了算法的具体实现方法和步骤．     

定序列矩形件优化排样新算法

针对目前矩形件优化排样方法的不足,提出了一个新的定序列矩形件排样算法。采用对矩形件排入板材后生成的矩形空白区域合并的策略,将矩形件优先排入到位置较低的空白区域中,实现了矩形件的插空摆放,有效的利用了排样过程中已排入矩形件间的空隙。实际应用表明,该算法显著提高了单次排样的材料利用率,得到了较好的排样效果。给出了算法的具体步骤。     

“一刀切”排样问题的遗传算法与蚁群算法整合研究

对于"一刀切"矩形件优化排样问题,采用遗传算法与蚁群算法的混合算法进行研究.针对两种算法的传统混合策略和现有混合策略的不足,对两种算法的混合策略进行改进,并利用种群本身的染色体适值来判断种群进化是否停滞,确定了算法的最佳融合时机.对具体算例的分析验证表明,改进后的混合策略可有效减少算法的冗余迭代次数,提高搜索速度,是一种行之有效的排样算法.     

遗传算法和碰撞算法混合求解冲裁件自动排样问题

针对冲裁件的实际情况,提出了一种利用遗传算法和碰撞算法混合求解冲裁件自动优化排样的方法.在排样中对冲裁件的纵向偏距、放置角度和排样方式进行编码,通过碰撞理论来计算每个个体所对应排样的排样步距.论文给出了运用遗传算法求解的步骤、遗传代码的构造方式和排样步距的求解方法.     

满足“一刀切”要求的木工板排样优化研究

 针对木工板手工排样效率低和材料利用率低问题,提出木工板“一刀切”排样优化算法．在剩余矩形填充算法中添加启发式分块原则,改进的剩余矩形填充算法满足“一刀切”工艺要求．采用遗传算法对矩形件进行排样优化,以提高木工板利用率,降低企业生产成本．为提高算法的优化精度,使用基于指数变换的非线性动态适应度函数,引入精英保护策略,应用部分填充交叉（partially matched crossover）算子．结合剩余矩形填充“一刀切”算法对遗传种群进行解码计算原料利用率,并作为适应度函数值,进行迭代搜索最优解．排样实例表明木工板“一刀切”排样优化算法能够很好地解决多品种大规模木工板排样问题．     

小生境遗传算法在反演堤坝地震勘探数据中的应用

基于反演问题的不确定性和目标函数的多峰性,本文提出引入小生境遗传算法,采用自适应控制交配概率和变异概率,求解出目标函数的若干个局部峰(或全局峰),然后利用先验知识,判定得到满意解。本文对实测资料进行了层速度与厚度的反演,通过实际值与反演值的比较,验证了进行多峰优化的有效性。     

优化排样技术在包装印刷中的应用

以优化排样的理论方法研究为基础,主要是针对不规则形状进行排样优化.通过对现有的几种常见的主流算法分析比较、选定出一种适用于包装纸盒排板的优化排样方法,并在此基础之上提出了改进方案,以得到最有效的算法.根据提出的算法思路,利用计算机编程语言开发出包装纸盒排版排样优化的系统程序,将这种算法得以实现.     

A hybrid genetic algorithm for the single row layout problem

The arrangement of machines or departments along a straight line is known as single row layout and it is a widely employed configuration in flexible manufacturing systems. In this paper, a hybrid genetic algorithm (HGA) is proposed to solve the single row layout design problem with unequal sized machines and unequal clearances. The algorithm is developed by hybridisation of a genetic algorithm with a local search operator. The proposed HGA is tested on 51 well known data sets from the literature with equal and unequal clearances, and the results are compared with the best known solutions. Finally, algorithm's effectiveness in reaching previously known best solutions is revealed and improvements up to 7% in problems with unequal clearance are obtained.     

Simulated annealing based parallel genetic algorithm for facility layout problem

The facility layout problem (FLP), a typical combinational optimisation problem, is addressed in this paper by implementing parallel simulated annealing (SA) and genetic algorithms (GAs) based on a coarse-grained model to derive solutions for solving the static FLP with rectangle shape areas. Based on the consideration of minimising the material flow factor cost (MFFC), shape ratio factor (SRF) and area utilisation factor (AUF), a total layout cost (TLC) function is derived by conducting a weighted summation of MFFC, SRF and AUF. The evolution operations (including crossover, mutation, and selection) of GA provide a population-based global search in the space of possible solutions, and the SA algorithm can lead to an efficient local search near the optimal solution. By combing the characteristics of GA and SA, better solutions will be obtained. Moreover, the parallel implementation of simulated annealing based genetic algorithm (SAGA) enables a quick search for the optimal solution. The proposed method is tested by performing a case study simulation and the results confirm its feasibility and superiority to other approaches for solving FLP.     

A genetic algorithm and queuing theory based methodology for facilities layout problem

Facilities layout, being a significant contributor to manufacturing performance, has been studied many times over the past few decades. Existing studies are mainly based on material handling cost and have neglected several critical variations inherent in a manufacturing system. The static nature of available models has reduced the quality of the estimates of performance and led to not achieving an optimal layout. Using a queuing network model, an established tool to quantify the variations of a system and operational performance factors including work-in-process (WIP) and utilisation, can significantly help decision makers in solving a facilities layout problem. The queuing model utilised in this paper is our extension to the existing models through incorporating concurrently several operational features: availability of raw material, alternate routing of parts, effectiveness of a maintenance facility, quality of products, availability of processing tools and material handling equipment. On the other hand, a queuing model is not an optimisation tool in itself. A genetic algorithm, an effective search process for exploring a large search space, has been selected and implemented to solve the layout problem modelled with queuing theory. This combination provides a unique opportunity to consider the stochastic variations while achieving a good layout. A layout problem with unequal area facilities is considered in this paper. A good layout solution is the one which minimises the following four parameters: WIP cost, material handling cost, deviation cost, and relocation cost. Observations from experimental analysis are also reported in this paper. Our proposed methodology demonstrates that it has a potential to integrate several related decision-making problems in a unified framework.     

A multi-improved genetic algorithm for facility layout optimisation based on slicing tree

For the facility layout optimisation problem, we use the slicing tree structure based on the order of traversal to form a new chromosome encoding system demonstrating facilities’ order, the relationship and the location. We generate the initial solution based on two principles namely the facilities’ adjacency and random generation. The structure of chromosome is made up with three sections in the research so that we can do the genetic operations to these three sections respectively, and we use dynamic and feedback mechanisms to improve the penalty function. As a result, the analysis of typical cases shows that there are certain improvements to this algorithm both in effectiveness and efficiency.     

Solving facility layout problems with strict geometric constraints using a two-phase genetic algorithm

This article puts forward a two-phase genetic algorithm that is able to solve facility layout problems strictly respecting the geometric constraints imposed on activities. In the first phase the algorithm attempts to locate an optimum slicing tree to group the activities appropriately. In the second phase the layout is obtained from this tree. In order to assess the slicing trees in the first phase we propose an evaluation function able to predict if, by making the appropriate cuts, the tree structure is able to generate layouts that satisfy the geometric restrictions imposed on the facilities to be arranged, and to minimize the cost of transporting materials between the production activities. It also permits the determination of the most suitable aspect ratio of the layout zone in order to minimize non-compliance with the geometric restrictions. The algorithm and the method of calculating the indicator proposed in the evaluation function are described, and the results obtained in the experiments carried out are also given.     

A genetic algorithm for optimal unequal-area block layout design

The use of a genetic algorithm (GA) to optimise the binary variables in a mixed-integer linear programming model for the block layout design problem with unequal areas that satisfies area requirements is analysed. The performance of a GA is improved using a local search through the possible binary variables assignment; results encourage the use of this technique to find a set of feasible solutions for the block layout design with more than nine departments.     

Robust fixture layout design for multi-station sheet metal assembly processes using a genetic algorithm

The optimal fixture layout is crucial to product quality assurance in the multi-station sheet metal assembly processes. Poor fixture layout may lead to product variation during the assembly processes. In this paper, a genetic algorithm (GA)-based optimisation approach has been presented for the robust fixture layout design in the multi-station assembly processes. The robust fixture layout is developed to minimise the sensitivity of product variation to fixture errors by selecting the appropriate coordinate locations of pins and slot orientations. In this paper, a modified state space model for variation propagation in the multi-station sheet metal assembly is developed for the first time, which is the mathematical foundation of optimal algorithm. An e-optimal is applied as the robust design criteria. Based on the state space model and design criteria, a genetic algorithm is used to find the optimal fixture layout design. The proposed method can greatly reduce the sensitivity level of product variation. A four-station assembly process of an inner-panel complete for a station wagon (estate car) is used to illustrate this method.     

Generalisation of unidirectional loop layout problem and solution by a genetic algorithm

Unidirectional loop layouts (ULLs) are the preferred layouts in manufacturing systems owing to their relative low investment costs, high material handling elasticity and routing flexibility. Existing formulations of the unidirectional loop layout problem are concentrated on the arrangement of workstations under the assumption that the number and location of loading and unloading stations are known. In this study, the unidirectional loop layout problem is generalised by consideration of potentially attachable loading/unloading equipment to each workstation and releasing of the predetermined number of loading and unloading stations. Thus, more efficient and effective loop layout designs are allowed by eliminating some artificial restrictions. The present ULL model is generalised and a genetic algorithm is developed to solve the problem. Solutions obtained by the genetic algorithm outperformed those obtained by conventional methods. Additionally, comparisons of the generalised model with existing models on randomly generated test problems yielded encouraging results.     

遗传算法与惩罚函数法在机械优化设计中的应用

提出了应用于机械优化设计的"遗传算法+惩罚函数法"的通用算法.它非常适合求解复杂的非线性约束优化问题.本通用算法既克服了传统优化方法的缺点,得到了一个较为理想的全域最优解;同时也改善了遗传算法的局限性.