多目标进化算法的一种基于生成树的分布性维护方法

针对多目标进化算法的种群维护和运行效率相矛盾的问题,提出了一种基于生成树的分布性维护方法,即对整个种群构造一棵生成树,定义一种密度估计指标--树聚集距离,并结合树中的最短树枝和个体度数对种群进行维护.由于树聚集距离和度数具有动态性,每移出一个个体,种群中与之相连个体的信息都会发生相应的变化,因而可即时反映出种群的分布情况.与三个著名的算法NSGA-Ⅱ、SPEA2和C-NSGA-Ⅱ的比较实验表明,该方法能在得到良好分布性解集的同时,能以较快的速度对种群进行维护,具有较好的时间效率.     

几种优化算法在浅海匹配场反演中的性能比较

在分析模拟退火算法、遗传算法、差异进化算法、下山单纯形差异进化算法的优化机理的基础上,定量比较了上述算法在浅海匹配场反演中的效率差异。模拟退火算法与遗传算法只使用目标函数值信息在参数空间搜索全局最优值,效率低且易受参数间耦合的影响。差异进化算法使用种群中个体间的距离与方位信息在参数空间中搜索全局最优值,优化效率随着优化过程的进行而下降。下山单纯形差异进化算法将下山单纯形算法融入差异进化算法,增强了差异进化算法的寻优能力,混合算法对目标函数梯度信息敏感的特性使得这一算法具有较强的解耦能力。浅海匹配场反演仿真算例从最优参数反演结果、最终目标函数值、反演时间等方面检验了上述算法的反演效率。     

基于细菌觅食算法的异步电动机现场效率估算

提出了一种使用优化的细菌觅食算法估算电机的现场效率。该方法虽然有赖于测量定子电流、定子电压、定子电阻、输入功率和电机速度,从而基于电机的等效电路估算电机效率,但无需进行空载和堵转试验。对1台5.5 kW的异步电动机进行了试验,测试结果与粒子群优化算法、遗传算法以及实测的转矩测量法进行了比较,结果表明该方法能较准确地估计电机效率,并且简单、经济。     

一种基于“探测"与“开采"的多目标进化算法

针对实践中多目标优化问题(MOPs)的Pareto解集(PS)未知且比较复杂的特性,提出了一种基于"探测"(Exploration)与"开采"(Exploitation)的多目标进化算法(MOEA)——MOEA/2E。该算法在进化过程中采用"探测"与"开采"相结合的方法,用进化操作不断地探测新的搜索区域,用局部搜索充分开采优秀的解区域,并用隐最优个体保留机制保存每一代的最优个体。与目前最流行且有效的多目标进化算法NSGA-Ⅱ及SPEA-Ⅱ进行的比较实验结果表明,MOEA/2E获得的Pareto最优解集具有更好的收敛性与分布性。     

基于进化算法的多目标闭环物流网络设计

为了帮助生产企业建立科学合理的闭环物流网络系统,提高废旧产品材料的再循环利用率,提出了一个多周期、多产品、多阶段的闭环物流网络选址与运输模型。该模型中,不仅考虑建造混合分销回收中心,还提出了2个优化目标:经济成本最小和时间成本最小。针对该多目标优化问题,本文采用了一种基于优先值编码方法的进化算法对模型求解,最终得到该问题的帕累托(Pareto)前沿。通过与约束法的计算结果相比较,求得误差均值小于5%,说明该进化算法对Pareto前沿的拟合程度较好,计算结果是正确有效的。     

基于离散差分进化算法的随机车辆路径问题

针对差分进化算法求解组合优化问题存在的局限性,引入计算机语言中的2种按位运算符,对差分进化算法的变异算子进行重新设计,用来求解不确定需求和旅行时间下同时取货和送货的随机车辆路径问题（SVRPSPD）。通过对车辆路径问题的benchmark问题和SVRPSPD问题进行路径优化,并同差分进化算法和遗传算法的计算结果进行比较,验证了离散差分进化算法的性能。结果表明,离散差分进化算法在解决复杂的SVRPSPD问题时,具有较好的优化性能,不仅能得到更好的优化结果,而且具有更快的收敛速度。     

基于多链差分进化的贝叶斯有限元模型修正方法

针对传统贝叶斯算法在高维参数下采样效率低且收敛难的问题,建立了基于多链差分进化算法的贝叶斯有限元模型修正方法。在标准马尔可夫链蒙特卡罗（MCMC）方法的基础上,引入差分进化算法,通过多条马氏链间的随机差分运算来自适应选择条件分布的大小和方向以快速逼近目标分布;引入子空间采样算法,通过自适应选择优良的参数维度进行采样以提高采样效率;引入异常链检测算法,通过在采样的非平稳期对马氏链进行异常检测与剔除以提高在平稳期的采样效率。简支梁理论模型和实验室4层框架结构的模型修正结果表明:该方法修正精度较高,且具有良好的抗噪性,在高阶频率以及振型下的修正效果均优于DRAM算法,为解决不确定性模型修正中的计算精度提供了一种新手段。     

Lyapunov指数在异步电动机机械振动识别中的应用

基于非线性动力学理论,研究异步电动机振动信号的Lyapunov指数特征,并应用于故障诊断和识别。首先,搭建试验平台,并模拟异步电动机正常工作、转子不对中和底座安装不良的三种转动状态。分析电动机三种振动信号的波形,并进行去噪和预处理。然后,基于BBA算法计算振动信号在不同工作状态下的Lyapunov指数谱,选取最大Lyapunov指数作为特征用于识别异步电动机的机械振动;最后,为了对该分析方法的有效性及抗干扰性进行验证,引入了随机噪声,分析所提出算法在不同参数下的受噪声的影响水平。研究结果显示,异步电动机在正常运行时,其最大Lyapunov指数值在0.3～0.7;安装不良时其最大Lyapunov指数值在0～0.3,表明这两种工作状态下电动机振动信号序列出自于一个混沌过程;在电动机处于转子不对中状态时,其最大Lyapunov指数值近似为零,表明其振动序列中基本不存在混沌属性。在该研究结果的基础上,配合特征融合与机器学习分类算法,将有效提高异步电动机机械振动识别的准确率和效率。     

基于多目标进化算法的压电换能器优化设计

为了解决单目标优化无法满足实际工程应用需求的问题,通过对一个约束性多目标优化问题的分析,以最大振幅和最小输入电压做为优化目标,设计参数包括连续变量(换能器的尺寸)和离散变量(材料类型),利用基于分析模型的传递矩阵法对压电换能器进行建模,进而导出优化问题的数学描述式,最后应用多目标进化算法NSGA-Ⅱ,估算一系列的pareto优化设计值,分析优化结构,并确定最优设计参数.     

一种高效的匹配场反演混合优化算法

将下山单纯形算法引入差异进化算法,提高了差异进化算法对目标函数梯度信息的利用,改善了差异进化算法的优化效率,由于下山单纯形算法与差异进化算法都是并行算法,混合算法同时具备了并行高效的特点.     

A new multi-objective particle swarm optimizer using empirical movement and diversified search strategies

Most real-world optimization problems involve the optimization task of more than a single objective function and, therefore, require a great amount of computational effort as the solution procedure is designed to anchor multiple compromised optimal solutions. Abundant multi-objective evolutionary algorithms (MOEAs) for multi-objective optimization have appeared in the literature over the past two decades. In this article, a new proposal by means of particle swarm optimization is addressed for solving multi-objective optimization problems. The proposed algorithm is constructed based on the concept of Pareto dominance, taking both the diversified search and empirical movement strategies into account. The proposed particle swarm MOEA with these two strategies is thus dubbed the empirical-movement diversified-search multi-objective particle swarm optimizer (EMDS-MOPSO). Its performance is assessed in terms of a suite of standard benchmark functions taken from the literature and compared to other four state-of-the-art MOEAs. The computational results demonstrate that the proposed algorithm shows great promise in solving multi-objective optimization problems.     

MOIA: Multi-objective immune algorithm

The paper describes a novel algorithm for finding Pareto optimal solutions to multi-objective optimization problems based on the features of a biological immune system. Inter-relationships within the proposed multi-objective immune algorithm (MOIA) resemble antibody-antigen relationships in terms of specificity, germinal center, and the memory characteristics of adaptive immune responses. Gene fragment recombination and several antibody diversification schemes (including somatic recombination, somatic mutation, gene conversion, gene reversion, gene drift, and nucleotide addition) were incorporated into the MOIA in order to improve the balance between exploitation and exploration. Using five performance metrics, MOIA simulation figures were compared with data derived from a strength Pareto evolutionary algorithm (SPEA). The results indicate that the MOIA outperformed the SPEA in several areas.     

A parallel particle swarm optimization algorithm for multi-objective optimization problems

In this article, a new proposal of using particle swarm optimization algorithms to solve multi-objective optimization problems is presented. The algorithm is constructed based on the concept of Pareto dominance, as well as a state-of-the-art ‘parallel’ computing technique that intends to improve algorithmic effectiveness and efficiency simultaneously. The proposed parallel particle swarm multi-objective evolutionary algorithm (PPS-MOEA) is tested through a variety of standard test functions taken from the literature; its performance is compared with six noted multi-objective algorithms. The computational experience gained from the first two experiments indicates that the algorithm proposed in this article is extremely competitive when compared with other MOEAs, being able to accurately, reliably and robustly approximate the true Pareto front in almost every tested case. To justify the motivation behind the research of the parallel swarm structure, the computational results of the third experiment confirm the PPS-MOEA's merit in solving really high-dimensional multi-objective optimization problems.     

Multi-objective hierarchical genetic algorithms for multilevel redundancy allocation optimization

Multilevel redundancy allocation optimization problems (MRAOPs) occur frequently when attempting to maximize the system reliability of a hierarchical system, and almost all complex engineering systems are hierarchical. Despite their practical significance, limited research has been done concerning the solving of simple MRAOPs. These problems are not only NP hard but also involve hierarchical design variables. Genetic algorithms (GAs) have been applied in solving MRAOPs, since they are computationally efficient in solving such problems, unlike exact methods, but their applications has been confined to single-objective formulation of MRAOPs. This paper proposes a multi-objective formulation of MRAOPs and a methodology for solving such problems. In this methodology, a hierarchical GA framework for multi-objective optimization is proposed by introducing hierarchical genotype encoding for design variables. In addition, we implement the proposed approach by integrating the hierarchical genotype encoding scheme with two popular multi-objective genetic algorithms (MOGAs)—the strength Pareto evolutionary genetic algorithm (SPEA2) and the non-dominated sorting genetic algorithm (NSGA-II). In the provided numerical examples, the proposed multi-objective hierarchical approach is applied to solve two hierarchical MRAOPs, a 4- and a 3-level problems. The proposed method is compared with a single-objective optimization method that uses a hierarchical genetic algorithm (HGA), also applied to solve the 3- and 4-level problems. The results show that a multi-objective hierarchical GA (MOHGA) that includes elitism and mechanism for diversity preserving performed better than a single-objective GA that only uses elitism, when solving large-scale MRAOPs. Additionally, the experimental results show that the proposed method with NSGA-II outperformed the proposed method with SPEA2 in finding useful Pareto optimal solution sets.     

采用多目标进化模型的无监督故障特征选择算法

高维故障特征数据易影响诊断的处理速度和识别率,而传统单目标特征选择算法易融入主观偏好,从而影响特征选择的质量。为此,提出一种无监督的多目标进化特征选择算法。采用熵度量作为相关度目标,采用相关系数的概念设计了冗余度目标,算法同时将这两个目标作为优化对象;利用样本在各个特征上的分布信息,设计了导向性的种群初始化过程和变异算子,以提高算法的优化能力;还利用集成的方法得到了所有特征的重要度序列。对5组UCI数据和3组往复式压缩机故障数据的测试结果表明,该算法比已有的几种特征选择算法更具优势。     

矿物质粉体对砂浆及混凝土Cl-渗透性的影响

研究了不同水胶比、不同矿物质粉体掺量的砂浆和混凝土，经标准养护至56天、90天时的导电量。在相同水胶比和相同矿物质粉体掺量下，混凝土的导电量远低于砂浆的导电量。含矿物质粉体的砂浆及混凝土的导电量均低于基准砂浆及混凝土的导电量。导电量随水胶比的降低而降低，也随龄期的增长而降低。     

Aerodynamic optimization using a parallel asynchronous evolutionary algorithm controlled by strongly interacting demes

A parallel asynchronous evolutionary algorithm controlled by strongly interacting demes for single- and multi-objective optimization problems is proposed. It is suitable even for non-homogeneous, multiprocessor systems, ensuring maximum exploitation of the available processors. The search algorithm utilizes a structured topology of evaluation agents organized in a number of inter-communicating demes arranged on a 2D supporting mesh. Once an evaluation terminates and a processor becomes idle, a series of intra- and inter-deme processes determines the next agent to undergo evaluation on this specific processor. Real coding and differential evolution operators are used. Mathematical and aerodynamic-turbomachinery optimization problems are presented to assess the proposed method in terms of CPU cost, parallel efficiency and quality of solutions obtained within a predefined number of evaluations. Comparisons with conventional evolutionary algorithms, parallelized based on the master–slave model on the same computational platform, are presented.     

Optimal reservoir flood operation using a decomposition-based multi-objective evolutionary algorithm

Reservoir flood control operation (RFCO) is a challenging optimization problem with interdependent decision variables and multiple conflicting criteria. By considering safety both upstream and downstream of the dam, a multi-objective optimization model is built for RFCO. To solve this problem, a multi-objective optimizer, the multi-objective evolutionary algorithm based on decomposition–differential evolution (MOEA/D-DE), is developed by introducing a differential evolution-inspired recombination into the algorithmic framework of the decomposition-based multi-objective optimization algorithm, which has been proven to be effective for solving complex multi-objective optimization problems. Experimental results on four typical floods at the Ankang reservoir illustrated that the suggested algorithm outperforms or performs as well as the comparison algorithms. It can significantly reduce the flood peak and also guarantee the dam’s safety.     

Efficient dynamic resampling for dominance-based multiobjective evolutionary optimization

Multi-objective optimization problems are often subject to the presence of objectives that require expensive resampling for their computation. This is the case for many robustness metrics, which are frequently used as an additional objective that accounts for the reliability of specific sections of the solution space. Typical robustness measurements use resampling, but the number of samples that constitute a precise dispersion measure has a potentially large impact on the computational cost of an algorithm. This article proposes the integration of dominance based statistical testing methods as part of the selection mechanism of evolutionary multi-objective genetic algorithms with the aim of reducing the number of fitness evaluations. The performance of the approach is tested on five classical benchmark functions integrating it into two well-known algorithms, NSGA-II and SPEA2. The experimental results show a significant reduction in the number of fitness evaluations while, at the same time, maintaining the quality of the solutions.