基于胞映射算法的转子-挤压油膜阻尼器系统多目标优化设计

将挤压油膜阻尼器设计与转子动力学相结合,使用胞映射方法对定心式挤压油膜阻尼器进行多目标优化设计。阻尼器设计参数为阻尼器径向油膜间隙以及定心弹簧刚度。综合考虑了阻尼器的触底现象、转子系统的动力学响应及稳定性,使用多目标优化设计方法以达到抑制转子过临界转速振幅及支撑外传力的目的。针对所得帕累托集合,对所得全局最优解集进行试验验证,结果表明：该最优解集所得设计变量可满足设计需求,可有效地应用到阻尼器的设计过程。     

基于接头灵敏度分析的驾驶室刚度模态优化

针对商用车驾驶室接头结构设计不合理的问题,文中提出一种基于接头灵敏度分析的驾驶室刚度模态优化方法。首先,从驾驶室有限元模型中截取所需接头,并采用有限元分析技术对其进行力学特性分析,找出接头结构的关键控制因素;其次,以弹性模量为设计变量进行接头灵敏度分析,找出对驾驶室刚度模态影响较大的接头结构;然后,选用第3代遗传算法对该优化问题进行多目标优化;最后,采用TOPSIS算法从帕累托前沿解中选取更符合用户偏好的驾驶室刚度模态优化方案。优化结果表明：在驾驶室质量基本不变的情况下,驾驶室刚度模态均有较大提升。     

基于NSGA-Ⅱ的行星减速器多目标优化设计

为提高行星减速器工作能力,以齿轮强度和减速器体积为优化目标,对行星减速器进行多目标优化设计。以矿用提升绞车中的NGW型行星减速器为优化对象,以中心太阳轮尺寸参数为优化设计变量,建立配齿条件、齿面接触强度及工作参数等约束条件,构建多目标优化设计模型。利用带精英策略的非支配排序遗传算法(NSGA-II)对多目标优化模型进行优化计算,得到优化目标的帕累托(Pareto)最优解分布。通过对比得到优化目标间的相互影响规律,利用模糊集合理论从最优解集中选择出合理参数作为最终设计结果。分析结果表明本文提出的优化设计方法提高强度的同时,有效减小减速器体积,实现了行星减速器的多目标优化设计。     

基于NSGA-Ⅱ的复摆式破碎机多目标优化设计

为提高复摆式颚式破碎机工作能力,以破碎生产率和动颚行程特性值为优化目标,对颚式破碎机进行多目标优化设计。以PE250×400型颚式破碎机为优化对象,以各构件尺寸为优化设计变量,建立机构参数、腔形参数及工作参数等约束条件,构建多目标优化设计模型,利用带精英策略的非支配排序遗传算法(NSGA-II)处理多目标优化模型,得到帕累托(Pareto)最优解集。通过对比两目标的最优解分布,确定出待优化目标间的相互影响规律,并从最优解集中选择出合理参数作为最终设计结果。分析结果表明:文中提出的优化设计方法在获得更大生产率的同时,有效减小了动颚磨损,实现了颚式破碎机的多目标优化设计。     

单晶硅的电火花线切割过程建模与优化研究

单晶硅的电火花线切割过程中,切削效率与表面粗糙度是两个重要的目标,生产过程中希望提高单晶硅切割效率的同时保证工件表面质量。运用响应曲面法建立关于单晶硅电火花线切割加工过程中切割效率与表面粗糙度的目标函数;采用第二代基于强度帕累托进化算法(SPEA-Ⅱ)得出一组关于切割效率与表面粗糙度的帕累托最优解。在相同条件下将SPEA-Ⅱ得到的帕累托最优解与第二代非支配排序遗传算法(NSGA-Ⅱ)得到的解集进行对比,测试两种算法对目标函数的优化性能。     

基于证据理论的气门弹簧可靠性设计优化

以气门弹簧净质量最小、刚度误差最小为双优化设计目标,考虑可靠性等约束条件,建立了可靠性优化设计数学模型,用线性加权组合法对多目标优化设计的目标函数进行处理,采用基于证据理论和区间分析的可靠性优化设计方法进行求解,得到了有价值的优化方案。设计实例验证了该方法的有效性和实用性。     

基于改进NSGA-Ⅱ算法的RV减速器参数多目标优化研究

旋转矢量(RV)减速器是工业机器人核心部件,对于机器人的性能起到关键作用。针对提升RV减速器综合性能的问题,从优化传动压力角的相关参数出发,对其结构参数(摆线轮齿数、短幅系数、针径系数、摆线轮宽度等)的多目标优化设计进行了研究。首先,研究了摆线轮平均压力角、传动效率和传动机构体积三者的相关参数之间的关系;然后,以此为优化目标,在摆线轮标准齿廓方程的基础上建立了多目标优化数学模型(该模型采用了基于非支配占优排序遗传学算法(NSGA-Ⅱ)改进了交叉算子系数生成的改进NSGA-Ⅱ算法);通过模型求解得到了帕累托最优解集,根据模糊集合理论的相关方法选取了最优解;最后,以某公司220-BX型RV减速器为例,进行了优化设计,建立了3D模型后进行了有限元分析,并加工出实验样机,进行了传动效率对比实验。实验结果表明：摆线轮平均压力角减小了7.19%,体积减小了11.1%,传动效率提高了4.9%。研究结果表明：该模型交互性强,能提高设计效率并节省设计开销,可为实际RV减速器工程优化设计提供参考。     

帕累托耦合遗传算法对车辆振动模型优化与动力学仿真

为研究车辆行驶产生振动严重问题,提高车辆座椅的舒适性,构造了5自由度车辆振动模型,推导出车辆行驶运动控制微分方程,采用帕累托耦合遗传算法对5自由度车辆振动模型的五目标函数进行优化.优化对象包括前轮速度、后轮速度、簧载质量和前轮的相对位移、簧载质量和后轮的相对位移及车辆座椅垂直方向加速度.在五目标函数优化处理后,找出最佳运动学仿真优化值,通过Matlab/Simulation软件进行动力学仿真,与其他优化方法进行对比.仿真结果显示,在同等条件下,帕累托耦合遗传算法优化后的车辆经过地面凸起障碍物时,车辆座椅垂直方向产生加速度峰值降低了50%,车辆抖动次数较少.帕累托耦合遗传算法对车辆振动模型优化后,车辆行驶过障碍物相对平稳,改善了车辆座椅在行驶过程中的舒适性.     

考虑轴承沟道表面完整性的磨削效率优化

为了提高轴承沟道磨削效率,提出考虑轴承沟道表面完整性约束的多目标优化方法。通过正交试验选取合适的设计点,根据试验结果建立磨削参数与响应输出的响应面模型。构建磨削切向力和粗糙度的显式表达式,进而得到满足质量要求的约束条件。应用NSGA-II遗传算法对磨削时间和材料去除率进行多目标优化,求解帕累托集。研究结果表明,使用优化的磨削参数可以很好地减少磨削时间,提高材料去除率,进一步丰富了高速高效磨削技术理论。     

多目标模拟退火算法求解混装线平衡与排序

针对混流装配线平衡排序优化问题,提出了一种多目标模拟退火算法。考虑到工位负载影响装配线的生产效率、工人越过工位边界干扰生产等问题,建立了以最小工位绝对负载偏差与最小工位越界距离的优化目标。所提出的模拟退火算法在初始化中将启发式任务分配规则融入平衡问题,根据产品投产需求随机生成产品序列;引入了基于帕累托阶层和拥挤距离作为多目标适应度评价指标;对帕累托前沿解集进行重启操作,避免算法陷入局部最优;采用一种新的接受策略,提高了算法寻优能力。通过测试标准问题实验,对所提出的算法进行参数校验。将所提出的算法与快速非支配遗传算法进行对比,采用收敛性和多样性两个评价指标,验证所提出算法的优越性。     

基于支持向量回归的熔丝制造3D打印能效优化模型

基于响应面法和支持向量回归模型对熔丝制造3D打印能效进行预测与优化。首先,利用田口方法设计六因素三水平正交试验,通过响应面法分析得出对加工能效影响较为显著的3个因素即层高、打印速度和热床温度;然后,通过支持向量回归方法建立加工能效预测模型,并与BP神经网络方法进行对比,结果表明支持向量回归方法建模预测性能更优;最后,建立以加工时间和能效为目标的优化模型,利用NSGA-Ⅱ、MOEA/D、SPEA2和MOPSO 4种算法分别对模型进行求解,分析比较4种算法的Pareto前沿,结果表明NSGA-Ⅱ算法在求解此问题时综合表现最佳,对比NGSA-Ⅱ算法求得的优化结果与试验结果可知,NSGA-Ⅱ算法具有有效性和合理性。     

基于神经网络和遗传算法的液压机上梁轻量化和刚度优化设计

提高刚度和轻量化是液压机设计中重点研究的内容。针对传统设计方法难以解决上梁刚度和轻量化之间的矛盾问题,提出了基于神经网络和遗传算法的液压机上梁轻量化和刚度优化设计方法。在液压机设计过程中,建立了上梁有限元分析的参数化模型。采用正交试验设计安排试验方案,获取试验数据。以试验数据为训练和检测样本,建立了设计参数与刚度和质量目标之间的非线性映射关系的神经网络模型。运用NSGA-Ⅱ遗传进化算法对神经网络模型进行优化,在指定参数区域内找出设计参数的Pareto最优解集。结果表明:该方法对于液压机上梁的多目标优化具有明显的效果。     

Pareto lexicographic α-robust approach and its application in robust multi objective assembly line balancing problem

Robustness in most of the literature is associated with min-max or min-max regret criteria. However, these criteria of robustness are conservative and therefore recently new criteria called, lexicographic α-robust method has been introduced in literature which defines the robust solution as a set of solutions whose quality or jth largest cost is not worse than the best possible jth largest cost in all scenarios. These criteria might be significant for robust optimization of single objective optimization problems. However, in real optimization problems, two or more than two conflicting objectives are desired to optimize concurrently and solution of multi objective optimization problems exists in the form of a set of solutions called Pareto solutions and from these solutions it might be difficult to decide which Pareto solution can satisfy min-max, min-max regret or lexicographic α-robust criteria by considering multiple objectives simultaneously. Therefore, lexicographic α-robust method which is a recently introduced method in literature is extended in the current research for Pareto solutions. The proposed method called Pareto lexicographic α-robust approach can define Pareto lexicographic α-robust solutions from different scenarios by considering multiple objectives simultaneously. A simple example and an application of the proposed method on a simple problem of multi objective optimization of simple assembly line balancing problem with task time uncertainty is presented to get their robust solutions. The presented method can be significant to implement on different multi objective robust optimization problems containing uncertainty.     

基于多目标遗传算法的高频磁致伸缩换能器优化设计

磁致伸缩换能器在高频激励下存在铁心涡流损耗大、磁场分布不均匀、电磁转化效率低等问题,需要从换能器本体优化设计方面寻求解决。首先对换能器的线圈高度和磁轭回路结构进行仿真分析以初步确定磁路结构;然后基于非支配排序遗传算法对换能器提出了一个整体的多目标优化设计模型,该模型以增大磁致伸缩棒内磁场强度、提高棒内的磁场分布均匀度和减少换能器高频损耗为优化目标,引入规范化排序和熵权法对该优化方法得到的Pareto前沿解进行决策支持,筛选一组最优设计方案;最后对该最优解进行仿真分析,磁场分布和数值计算结果验证了该优化方法的有效性,根据优化结果制作了一台换能器样机,样机输出特性的测试结果表明了优化设计方法的可行性。     

Multi-component optimization of a vertical inline pump based on multi-objective pso and artificial neural network

The vertical inline pump is a single-stage single-suction centrifugal pump with a curved inlet pipe before the impeller, which is widely used in where the constraint is installation space. In this paper, with the objective functions of efficiencies at 0.5Q_d, 1.0Q_d, and 1.5Q_d, a multi-objective optimization on inlet pipe and impeller was proposed to broaden the efficient operating period of a vertical inline pump. Two 5th order Bézier curves were adopted to fit the shape of the mid curve of the inlet pipe and the trend of the blade angle of the impeller. Fourteen design variables were selected after the data-mining process. 300 sample cases were generated using Latin hypercube sampling (LHS), and they were solved by 3D RANS code to obtain the objective functions. The feed-forward artificial neural network with a hidden layer and an output layer was adopted to fit the two objective functions and the 14 design variables. The Pareto frontiers were generated for the three objectives using multi-objective particle swarm optimization (MOPSO), and three different configurations on the Pareto front are selected for detailed study by computational fluid dynamics (CFD). The results showed that the profile of the inlet pipe and the blade have a dramatic impact on the performance of the vertical inline pump. The Pareto frontiers reported that the performance under the overload condition usually keeps stable when the nominal efficiency is lower than 82 %, or the part-load efficiency is lower than 62 %, and it will decrease rapidly after that. After optimization, the improvement of efficiencies at the part-load condition and nominal condition of the picked case were 9.65 % and 7.95 %, respectively.

     

An integrated solution—KAGFM for mass customization in customer-oriented product design under cloud manufacturing environment

In hot strip rolling process, rolling schedule is a key technology which directly influences strip product quality. Rolling schedule optimization is actually a problem of load distribution. To make a better rule of the load distribution of aluminum hot tandem rolling, multi-objective optimization algorithm is used to optimize rolling schedule. Preventing slipping, power margin and minimum energy consumption are selected as the optimization objectives. To make a precision calculation of rolling schedule, an adaptive neural network which is based on classification system is applied to improve the prediction ability for the rolling force, and its on-line training system reduces the prediction errors caused by different rolling conditions. The improved differential evolution algorithm is used to search the Pareto front, and it obtains a good approximation of the Pareto-front and decreases computation time. Load distribution strategies focused on different objectives are generated from the Pareto front to meet the requirements of industrial spots. The experiment result shows the algorithm covers the front quickly and distributes well. Comparing with the original schedule, the proposed method reduces the probability of slippage and energy consumption.     

Investigation and optimization of the internal cylindrical surface lapping process of 440c steel

A new lapping method is proposed for internal cylindrical surfaces finishing. Regression analysis and artificial neural network (ANN) were used for modeling this lapping process and predicting the effects of parameters of rotational speed of the lapping tool (ω), the length of the lapping tool (L) and difference in external diameter of the lapping tool and internal diameter of the workpiece (D) on the material removal rate (MRR), out-of-cylindricity (C) and surface roughness (Ra) of the lapped holes. Comparison of the results of the regression and ANN models with the values obtained from the experiments indicates that the MRR, Ra and C are more accurately predicted using ANN models. MRR, Ra and C of the lapped holes have been optimized using genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. The results show that the highest MRR, which is equal to 2029 μg/min, has been achieved at ω of 400 rpm, D of 0.1 mm and L of 45 mm. The lowest Ra of the lapped hole is 64 nm which has been obtained at ω of 100 rpm, D of 0.1 mm and L of 20.82 mm. The minimum C of the lapped hole is 3 μm, which was obtained at ω of 212 rpm, D of 0.1 mm and L of 28.3 mm. The most important problem in the lapping process is the low MRR which causes increased cost and production time. Therefore, in the lapping process, the selection of conditions, that in addition to the production of pieces with geometric accuracy and surface roughness needing a high MRR, is very important. In this study, MRR, Ra and cylindricity of the lapped holes was optimized using multi-objective PSO (MOPSO) algorithm and non-dominated sorting genetic algorithm II (NSGA II), and the Pareto optimal solutions were obtained. Comparison of the results obtained from NSGA II and MOPSO shows that both of these algorithms can achieve optimal Pareto front with the same accuracy, but the time required to reach the MOPSO algorithm to the optimal Pareto front is 25 % less than the NSGA II.

     

基于混合粒子群算法求解多目标混流装配线排序

针对生产调度中的多目标混流装配线排序问题,建立以最小化超载时间、产品变化率与总切换时间为优化目标的数学模型,并提出一种改进的多目标粒子群算法求解。该算法采用基于工件的编码方式,并提出新的解码方法;应用Pareto排序和小生境数评价个体,在此基础上形成了一种新的适应度函数。在个体最优解的更新中,为避免最优解丢失,对非支配粒子与支配粒子采用差异化方法更新。此外,运用两种策略解决粒子群算法过早收敛的问题:在个体最优解的更新中引入模拟退火思想,并将全局最优解的选择扩大到整个种群。通过数值算例研究了算法的收敛性、分布性和执行效率,结果表明了所提算法的优越性。     

A new method based on LPP and NSGA-II for multiobjective robust collaborative optimization

The multiobjective robust collaborative optimization framework consists of optimization both at the system and autonomous subsystem levels. Linear physical programming is used in the system level optimization, which avoids the difficulty in choosing the multidimensional Pareto set. The non-dominated sorting genetic algorithm (NSGA-II) is used in the subsystem optimization with physical objectives. The interdisciplinary incompatibility function and physical objectives have different priority levels. At the first priority level, the best individual should be in the feasible region of the subsystem. At the second priority level, the interdisciplinary incompatibility function of the best individual should be no more than the feasibility threshold. The physical objectives are improved after the achievement of the above levels. A method for producing initial population with feasibility and diversity is proposed to improve the calculation efficiency and accuracy of the subsystem optimization at the first priority level. A method for setting dynamic feasibility threshold is proposed for the non-dominated sorting to help the physical objectives to obtain better solutions at the second priority level. Finally, the results of the speed reducer show that the presented method is efficient.