改进的协同粒子群优化算法的研究与应用

为增强现有PSO算法和协同粒子群优化算法的优化性能,提出了一种改进的协同粒子群优化算法及一种新的协同策略。该算法在进化过程中,将寻优粒子群分解为若干子分群,各子分群粒子利用本分群经验和整个种群经验进行搜索,既能在分群内部不断搜索,不迷失寻优方向,又能周期性地共享整群最优值引导粒子找到最好解。分解为多个子种群有利于维持种群的多样性,有效抑制局部最优现象发生。对经典复杂函数的寻优测试表明,改进算法的鲁棒性、收敛速度、精度及全局搜索能力均优于基本PSO算法。最后将改进算法用于建立基于神经网络的旋转机械故障诊断模型,设计了相应的故障诊断系统。结果表明,基于此算法的故障诊断系统具有诊断精度较高、稳定性能较好等特点。     

改进粒子群优化算法在工程优化问题中的应用研究

粒子群优化（PSO）算法是一种群集智能方法，它通过粒子之间的合作与竞争以实现对多维复杂空间的高效搜索。在对于粒子群群体构造和粒子多样性对收敛速度和精度影响的研究基础上提出了一种改进型粒子群优化算法。针对工程中的有约束的优化问题，将改进粒子群算法与函数法相结合进行求解。计算实例表明改进型粒子群优化算法大大改善了传统PSO算法的全局收敛性能，解的精度提高了很多。     

基于改进粒子群优化算法的并联机构位置正解法

本文提出一种基于改进粒子群优化算法的并联机构位置正解法.在深入分析和研究标准粒子群优化算法的基础上,定义了粒子相似性概念,提出基于高斯白噪声干扰变异的粒子群优化算法.该算法在运行过程中通过与当前最优粒子相似性的量化判定,对进入当前最优粒子邻域的粒子施加高斯白噪声干扰变异,从而提高粒子群优化算法后期多样性和收敛速度.将该算法用于并联机构位置正解寻优,仿真实验结果表明有该方法能以较高的收敛精度快速地获得并联机构的位置正解,且算法稳定.     

基于改进粒子群的焊点检测路径规划方法

针对电路板的焊点检测路径优化问题,提出一种改进的粒子群优化算法。在粒子进化过程中,根据时间函数的变化,调整粒子进化参数组合。在焊点空间路径规划过程中,将最小时间函数作为移动准则。在当前焊点检测点,建立路径规划时间函数,利用改进粒子群算法求取时间函数最小点,作为下一路径点,从而逐步得到焊点移动路径。仿真结果表明,利用所提方法可以规划出一条有效最优路径,进行完成焊点路径规划任务。同时实验结果表明,相对于其他粒子群算法,该算法具有较好的收敛精度,且收敛速度可控。     

一种自适应粒子群算法的小波神经网络优化

针对传统粒子群算法易陷入局部最优解的问题,提出了一种变权重粒子群算法.该算法通过引入交叉权重因子和粒子个体状态最优权值,对传统粒子群算法进行了优化,使粒子在移动过程中利用更多的信息来调整各自的移动方向,扩大粒子在运动过程中的自我认知范围,提高了粒子群算法的收敛精度和收敛速度.最后,利用改进的变权重粒子群算法对小波神经网络控制器进行优化,有效地验证了变权重粒子群算法的精确性.     

混合优化算法在氧化铝生产中物料平衡计算上的应用

通过分析传统的单一优化算法所存在的优点与不足,成功将粒子群算法、混沌优化以及单纯形法3种优化算法有机结合起来,提出一种基于混沌-单纯形法的混合粒子群协同优化算法,加强粒子群的局部寻优效率和全局寻优性能,以提高搜索速度和成功率.Benchmark 函数仿真以及氧化铝生产中拜耳法物料平衡计算的最终结果表明:新算法不仅在稳定性和收敛性上优于传统粒子群算法和相应的改进粒子群优化算法,且具有较高的收敛速度和全局收敛能力,同时也是进行物料平衡计算的一种有效的方法.     

基于改进SAPSO算法的永磁直驱风力发电机优化

针对永磁直驱风力发电机的重量、成本和效率的优化,将模拟退火算法的Metropolis准则引入粒子群算法,提出了一种改进的模拟退火粒子群算法,并对发电机进行了优化设计。这种改进的模拟退火粒子群算法不接受差解作为粒子群的全局最优,优化结果显示改进后的模拟退火粒子群算法收敛速度更快,寻优精度更高。有限元仿真结果显示,优化后的发电机设计方案达到了设计要求,与优化前的设计方案相比,发电机的重量减轻了15.3%,材料成本降低了14.1%,进一步验证了发电机设计方案的合理性与优化方法的有效性。     

基于改进粒子群算法的白车身焊接路径优化

为优化白车身焊接路径,提高焊接效率,提出一种改进粒子群算法,在传统粒子群算法思想的基础上,将算法寻优过程分为追随和盘旋两部分.基于较近原则生成初始粒子,以减少种群规模,加快收敛速度;在追随部分,通过个体极值追随全局极值和随机原始参考值以贪婪重组的方式重新生成粒子,在增强算法局部寻优能力的同时加快算法的收敛速度;在盘旋部分,采用多次局部调序的策略,通过随机调整粒子局部排列序,保证算法种群的多样性,防止陷入局部最优解;从种群进化代数和种群个体适应度函数值实现算法各参数的自适应调节,加快收敛速度;对粒子个体采取精英保留策略,保留最优粒子.算法通过Matlab平台实现,实验仿真结果表明,提出的改进粒子群算法对于中小规模的白车身焊点旅行推销员问题(Travelling Salesman Problem,TSP)有良好的寻优能力.     

面向主梁优化的改进果蝇优化算法研究

针对果蝇优化算法收敛速度慢、易陷入局部最优、收敛早熟等不足,引入了自适应步长、粒子群算法中的粒子速度,使得改进后的算法收敛性加强,收敛速度提高,改善了随机性,提高了寻优精度。将改进果蝇优化算法运用到桥式起重机主梁的轻量化中,并运用有限元软件对优化后的主梁进行力学分析,通过实例验证了算法的优越性;最后通过对比优化前后的结果,得出优化后的主梁质量减重效果明显且符合设计要求,对实际工程结构的设计有指导意义。     

基于改进粒子群优化算法的冗余机械臂逆运动学求解

以末端执行器的位姿误差最小为优化目标,将机器人的逆运动学问题转换为一个等效的最优化问题,并利用提出的改进粒子群优化算法对该问题进行求解.该算法从粒子群的初始化、惯性权重调整策略、差分变异进化及搜索空间的越界处理等多方面对标准粒子群优化算法进行综合改进,同时构建了以粒子群进化和差分变异进化为基础的两阶段混合协同进化机制,达到了有效平衡算法全局探索能力与局部开发能力的目的,提高了算法的收敛精度和收敛速度.以平面冗余机械臂和7自由度冗余机械臂的运动学逆解运算为例,将提出算法与对比算法用于逆运动学问题的求解.仿真结果表明,与对比算法比较,该算法具有更高的收敛精度、更快的收敛速度以及更强的寻优稳定性,能有效解决冗余机械臂的逆向运动学问题.     

Broken Rotor Bar Fault Detection of Induction Motors Using a Joint Algorithm of Trust Region and Modified Bare-bones Particle Swarm Optimization

A precise detection of the fault feature parameter of motor current is a new research hotspot in the broken rotor bar(BRB) fault diagnosis of induction motors. Discrete Fourier transform(DFT) is the most popular technique in this field, owing to low computation and easy realization. However, its accuracy is often limited by the data window length, spectral leakage, fence e ect, etc. Therefore, a new detection method based on a global optimization algorithm is proposed. First, a BRB fault current model and a residual error function are designed to transform the fault parameter detection problem into a nonlinear least-square problem. Because this optimization problem has a great number of local optima and needs to be resolved rapidly and accurately, a joint algorithm(called TR-MBPSO) based on a modified bare-bones particle swarm optimization(BPSO) and trust region(TR) is subsequently proposed. In the TR-MBPSO, a reinitialization strategy of inactive particle is introduced to the BPSO to enhance the swarm diversity and global search ability. Meanwhile, the TR is combined with the modified BPSO to improve convergence speed and accuracy. It also includes a global convergence analysis, whose result proves that the TR-MBPSO can converge to the global optimum with the probability of 1. Both simulations and experiments are conducted, and the results indicate that the proposed detection method not only has high accuracy of parameter estimation with short-time data window, e.g., the magnitude and frequency precision of the fault-related components reaches 10~(-4), but also overcomes the impacts of spectral leakage and non-integer-period sampling. The proposed research provides a new BRB detection method, which has enough precision to extract the parameters of the fault feature components.     

基于CLPSO算法的结构系统识别

系统识别问题可以转化成高维多模优化问题。针对基本粒子群优化在分析此类问题时容易出现早熟收敛从而导致局部优化和产生较大误差,提出将基于综合学习策略粒子群优化算法(CLPSO)应用于结构参数识别。由于该方法能够保持群体的多样性,因此可以避免早熟收敛。利用该方法在测量数据不完备且有噪声污染的条件下,同时在没有系统质量和刚度等先验信息的情况下对结构系统进行了识别,通过数值模拟以及对某真实结构进行分析,验证了该方法对结构系统识别的有效性。     

IBPSO-Based MUSIC Algorithm for Broken Rotor Bars Fault Detection of Induction Motors

In spectrum analysis of induction motor current, the characteristic components of broken rotor bars (BRB) fault are often submerged by the fundamental component. Although many detection methods have been proposed for this problem, the frequency resolution and accuracy are not high enough so that the reliability of BRB fault detection is affected. Thus, a new multiple signal classification (MUSIC) algorithm based on particle swarm intelligence search is developed. Since spectrum peak search in MUSIC is a multimodal optimization problem, an improved bare-bones particle swarm optimization algorithm (IBPSO) is proposed first. In the IBPSO, a modified strategy of subpopulation determination is introduced into BPSO for realizing multimodal search. And then, the new MUSIC algorithm, called IBPSO-based MUSIC, is proposed by replacing the fixed-step traversal search with IBPSO. Meanwhile, a simulation signal is used to test the effectiveness of the proposed algorithm. The simulation results show that its frequency precision reaches 10^?5, and the computational cost is only comparable to that of traditional MUSIC with 0.1 search step. Finally, the IBPSO-based MUSIC is applied in BRB fault detection of an induction motor, and the effectiveness and superiority are proved again. The proposed research provides a modified MUSIC algorithm which has sufficient frequency precision to detect BRB fault in induction motors.     

引入单纯形算子的粒子群优化算法在板形模式识别中的应用

将粒子群理论引入板形模糊模式识别系统，对识别后的板形进行优化，提高了板形识别的精度。粒子群算法作为一种全局优化算法，对于复杂优化问题，存在容易陷入局部极值的不足，因此，提出了粒子群和单纯形混合优化算法，将具有良好局部搜索能力的单纯形法与粒子群算法的全局搜索能力结合起来，有效地提高了板形模式识别优化的收敛速度，同时也提高了识别精度。     

IBPSO-Based MUSIC Algorithm for Broken Rotor Bars Fault Detection of Induction Motors

In spectrum analysis of induction motor current, the characteristic components of broken rotor bars(BRB) fault are often submerged by the fundamental component. Although many detection methods have been proposed for this problem, the frequency resolution and accuracy are not high enough so that the reliability of BRB fault detection is a ected. Thus, a new multiple signal classification(MUSIC) algorithm based on particle swarm intelligence search is developed. Since spectrum peak search in MUSIC is a multimodal optimization problem, an improved bare?bones particle swarm optimization algorithm(IBPSO) is proposed first. In the IBPSO, a modified strategy of subpopulation determination is introduced into BPSO for realizing multimodal search. And then, the new MUSIC algorithm, called IBPSO?based MUSIC, is proposed by replacing the fixed?step traversal search with IBPSO. Meanwhile, a simulation signal is used to test the e ectiveness of the proposed algorithm. The simulation results show that its frequency precision reaches 10~(-5), and the computational cost is only comparable to that of traditional MUSIC with 0.1 search step. Finally, the IBPSO?based MUSIC is applied in BRB fault detection of an induction motor, and the e ectiveness and superiority are proved again. The proposed research provides a modified MUSIC algorithm which has su cient frequency precision to detect BRB fault in induction motors.     

Optimal tolerance allocation using a multiobjective particle swarm optimizer

Particle swarm optimizers are routinely utilized in engineering design problems, but much work remains to take advantage of their full potential in the combined areas of sensitivity analysis and tolerance synthesis. In this paper, a novel Pareto-based multiobjective formulation is proposed to enhance the operations of a particle swarm optimizer and systematically distribute tolerances among various components of a mechanical assembly. The enhanced algorithm relies on nonlinear sensitivity analysis and the statistical root sum squares model to simultaneously optimize product performance criteria, the manufacturing cost, and the stack-up tolerance. It is shown that the proposed algorithm can accomplish its optimization task by successfully shifting nominal values of design parameters instead of the expensive tightening of component tolerances. Several numerical experiments for optimal design of a stepped bar assembly were conducted, which highlight the advantages of the proposed methodology.     

多维度惯性权重衰减混沌化粒子群算法及应用

针对标准粒子群优化算法在处理多维、多峰值优化问题时暴露出的易早熟收敛的难题,提出了MDDCIW_PSO算法。算法的主要思路如下:在粒子群进化过程中,赋予每代群体中每个粒子的每一维度以不同的线性衰减混沌化惯性权重,即从纵向看,随着迭代次数的增加,惯性权重呈现线性衰减变化;从横向看,当代的每个粒子的每一维度都在当前衰减半径内呈现独立的混沌变化。MDDCIW_PSO算法从纵横两个方向,最大可能地增强了粒子在搜索后期的群活性和局部搜索能力,从而尽可能地避免陷入局部最优。大量的标准测试函数仿真结果表明:MDDCIW_PSO算法与已有的典型惯性权重改进策略相比,能够较大幅度地提高粒子群算法的搜索精度。最后将MDDCIW_PSO算法应用于印染定型机的能耗模型优化求解中,取得了满意的结果。     

基于改进粒子群算法的神经网络建模

文章利用粒子群算法优化神经网络的参数,提出了基于粒子群算法的神经网络建模方法。为了提高基本粒子群算法的搜索性能,采用了基于外推技巧的引导型更新公式,并在粒子的搜索过程中,不断监测各个粒子的最优位置,多次没有变化并且距离优化目标太远时,粒子跳出当前位置继续搜索,从而避免陷入局部值。最后使用改进后的粒子群神经网络算法对函数进行拟合,仿真结果表明,新的算法有较好的收敛性。     

改进粒子群算法在行星传动设计中的应用

介绍了一种改进的粒子群算法。通过动态改变惯性权重，使其随粒子群的位置和目标函数的性质而变化，正确控制搜索的步长，达到增强算法的搜索能力，提高收敛速度，避免陷入局部搜索的目的。将该方法应用于行星齿轮传动优化中取得了良好的效果。