迭代可调节网络聚类及其在故障诊断中的应用

针对常用聚类算法对复杂分布数据难以有效聚类的问题,把网络分析技术与基于代价函数最优的聚类技术相结合,提出一种新颖的迭代可调节网络聚类算法。该算法采用网络的思想建立样本空间模型,把数据聚类问题转化为基于节点生长连接的网络分析问题;并设计了可调节的节点间相似关系测度和相应的聚类准则来构建节点间邻域搜索及节点生长操作;通过改变调节系数来实现网络节点间连接关系的整体调节。新算法能够在无需预先设定簇数目的情况下,自动获得簇的数目和样本数据的分布位置。采用4组不同样本分布的人工数据集聚类和往复压缩机气阀泄漏故障诊断试验,对比测试了新算法与K均值算法(KM)的性能,结果表明迭代可调节网络聚类算法可实现对复杂分布的流形数据聚类,在准确率及自动处理程度性能指标上明显优于常用的KM算法。     

多视图K-多均值聚类算法

多均值聚类算法假设每个类拥有多个子类,通过求解优化问题的方式来求解每个样本子类的划分和最终类簇的划分.该算法弥补了K-均值算法在非球数据集上的劣势,取得了较好的聚类效果,但是该算法无法被运用到多视图数据集上.本文提出了一种多视图K-多均值聚类算法,保留了K-多均值设置多个子类的设计,引入了视图权重参数,将目标聚类数作为限制条件,通过求解最优问题获得最终的类簇.将本文提出的算法与流行的多视图聚类算法进行对比实验,证明了本文算法的优越性.     

Optimization of the number of clusters: a case study on multivariate quality control results of segment installation

When encountering too many records, each of which has several attributes, clustering of the data is an important issue on mining and classification. Recently many advances on clustering algorithms have been made such that clustering of data is done precisely and quickly. Clustering algorithms use optimization algorithms which simultaneously provide the number of clusters as default. These algorithms cluster the data so that those which belong to a cluster have maximum similarity and those in different clusters have minimum similarity. The k-means algorithm is a traditional algorithm for clustering problems. One of the most important difficulties of clustering algorithms is determining the number of clusters before starting the algorithm. In other words, by having knowledge on distribution of data, the number of clusters should be estimated and then imported to the problem as an input. In this paper, the data collected on quality control of mechanized tunneling are analyzed. They consist of measurements of 16 characteristics for 200 initial installed rings of segments on the tunnel walls inspected by the quality control team. A dynamic validity index is used and combined to the k-means algorithm for clustering the data so that the optimal number of clusters can be determined simultaneously. The application of the algorithm shows that the total installed rings can be clustered into four clusters. These four classes of quality can best describe the total installed rings on the tunnel in comparison of other number of classes (or clusters). Furthermore, this approach helps the quality team to determine the most effective or best performance executive team whom their installed rings have best class and minimum variations.     

A novel algorithm based on hybridization of artificial immune system and simulated annealing for clustering problem

A hybrid clustering method is proposed in this paper based on artificial immune system and simulated annealing. An integration of simulated annealing and immunity-based algorithm, combining the merits of both these approaches, is used for developing an efficient clustering method. Tuning the parameters of method is investigated using Taguchi method in order to select the optimum levels of parameters. Proposed method is implemented and tested on three real datasets. In addition, its performance is compared with other well-known meta-heuristics methods, such as ant colony optimization, genetic algorithm, simulated annealing, Tabu search, honey-bee mating optimization, and artificial immune system. Computational simulations show very encouraging results in terms of the quality of solution found, the average number of function evaluations and the processing time required, comparing with mentioned methods.     

基于ISFLA的K均值聚类算法

针对K均值聚类算法和基于混合蛙跳( Shuffled Frog - Leaping Algorithm,SFLA)的K均值聚类算法的一些缺点,提出了基于改进混合蛙跳(Improved Shuffled Frog- Leaping Algorithm,ISFLA)的K均值聚类算法.该算法首先将生物学中吸引排斥机制应用在S...     

一种K-均值脸谱图聚类新算法

Chernoff脸谱图简单,类似卡通画,能图形化地表示多元数据。但脸谱图聚类算法具有主观性的巨大的对比工作量,脸谱特征分配困难。因此,本文提出一种新的脸谱图聚类算法,它合并了K均值聚类或模糊G均值聚类算法。IRIS和蔬菜油数据集的实验结果表明新算法优于传统的聚类算法。     

一种并行粒子群算法及其在热轧计划中的应用

针对串行优化算法在搜索时间上的不足,提出了一类组合优化问题的并行粒子群算法。该算法将粒子群划分为多子种群异步并行运算,利用不同范围内的多极值,指导粒子速度更新,加入邻域搜索策略,提高了搜索速度,同时也有效地防止了粒子在最优点附近发生的振荡现象。仿真实验表明,该算法与其他搜索方法比较,在搜索时间和求解质量上具有优势。现已应用于钢铁生产热轧计划编制中,并用实际生产数据表明了该算法的可靠性。     

Optimal clustering of MGs based on droop controller for improving reliability using a hybrid of harmony search and genetic algorithms

This paper proposes a novel method to address reliability and technical problems of microgrids (MGs) based on designing a number of self-adequate autonomous sub-MGs via adopting MGs clustering thinking. In doing so, a multi-objective optimization problem is developed where power losses reduction, voltage profile improvement and reliability enhancement are considered as the objective functions. To solve the optimization problem a hybrid algorithm, named HS-GA, is provided, based on genetic and harmony search algorithms, and a load flow method is given to model different types of DGs as droop controller. The performance of the proposed method is evaluated in two case studies. The results provide support for the performance of the proposed method.     

A clustering-based modified variable neighborhood search algorithm for a dynamic job shop scheduling problem

The dynamic job shop scheduling (DJSS) problem occurs when some real-time events are taken into account in the ordinary job shop scheduling problem. Most researches about the DJSS problem have focused on methods in which the problem’s input data structure and their probable relationship are not considered in the optimization process while some useful information can be extracted from such data. In this paper, the variable neighborhood search (VNS) combined with the k-means algorithm as a modified VNS (MVNS) algorithm is proposed to address the DJSS problem. The k-means algorithm as a cluster analysis algorithm is used to place similar jobs according to their processing time into the same clusters. Jobs from different clusters are considered to have greater probability to be selected when an adjacent for a solution is made in an optimization process using the MVNS algorithm. To deal with the dynamic nature of the problem, an event-driven policy is also selected. Computational results obtained using the proposed method in comparison with VNS and other common algorithms illustrate better performance in a variety of shop floor conditions.     

基于异构值差度量的SOM混合属性数据聚类算法

针对传统聚类算法处理混合属性数据聚类质量不高且聚类结果可视化差的问题,提出了基于异构值差度量的自组织映射混合属性数据聚类算法。该算法以自组织映射神经网络为框架,采用基于样本概率的异构值差度量混合属性数据的相异性。利用分类特征项在Voronoi集合中出现频率作为分类属性数据参考向量更新规则的基础,通过混合更新规则实现数值属性和分类属性数据规则的更新。利用UCI公共数据库中的分类属性和混合属性数据集来测试所提出的聚类算法,并与SOM算法和kprototypes、SBAC、KL-FCM-GM算法进行比较。最后将所提出的聚类算法应用于轮式移动机器人的运动状态分析,获得了较好的聚类效果。     

基于一阶导数的中药太赫兹光谱聚类

针对中药等混合物吸收峰重叠导致无明显吸收峰的情况,提出使用K-means、K-me doids和FCM三种无监督聚类算法结合太赫兹吸收谱一阶导数特征,将三七、当归等四种中药品的太赫兹光谱分别与其易混品的太赫兹光谱进行聚类.三种无监督聚类方法补充了监督学习分类方法的适用范围.光谱一阶导数特征可以放大不同物质吸收系数整体或者是局部的微小差异.实验证明,使用原始吸收系数结合其一阶导数作为分类数据,三种聚类算法都取得很好的效果,K-means算法准确率最高,为95.32％.相较于原始吸收系数作为分类数据,聚类准确率提升明显,尤其是对无吸收峰中药易混品的聚类,K-means算法准确率提升了5.38％.三种聚类算法对误差数据都具有很强的抗干扰能力.     

采用人体树图与混合粒子群聚类的行人检测

为提升辅助驾驶系统的可靠性及安全系数,实现更高精度的行人检测,基于人体树图模型提出了一种改进的离线训练、在线检测的行人检测方法。首先,定义人体部件间的共生关系,得到对应父子部件对,结合K-means算法对其位置关系进行聚类获得部件类型。为兼顾类内紧密性与类间分离性,采用MSE和DBI构建具有两阶段适应度函数的混合粒子群聚类算法,在有效估计各部件最优聚类中心数量的同时,消除随机初始化对聚类准确率造成的影响。其次,将优化聚类得到的部件类型作为隐藏变量,通过求解隐结构SVM获取改进后的人体检测模型。最后,通过动态规划算法求解状态转移方程,在多个尺度上有效估计人体部件位置及检测包围盒,并结合非极大值抑制思想得到最终的行人检测结果。实验结果表明,所提方法在检测性能上明显优于5种行人检测方法,并且相比于原始Pose-original方法,在INRIA和ETH数据集上的丢失率分别下降了8.14%和5.05%。实验证明该方法检测性能良好且具有较高的准确性和鲁棒性。     

CLS-SVM:一种时间序列预测的局部建模方法

针对LS-SVM应用于大样本时间序列预测时存在的计算复杂度高和泛化能力降低的问题,提出一种采用局部模型的时间序列预测方法.该方法采用K-means算法对训练样本进行聚类,并以VRC原则确定最佳聚类数,然后利用LS-SVM对聚类后样本进行局部建模;同时,针对一般LS-SVM建模过程中共轭梯度方法计算效率低的问题,采用Cholseky分解方法以实现计算效率的提升.仿真实验和应用测试表明,该方法用于大规模数据分析时,可在保持预测精度的前提下,提高训练效率5 ～ 28倍,在降低计算复杂度的同时,有效地提高了模型的泛化能力.     

APPLYING PARTICLE SWARM OPTIMIZATION TO JOB-SHOPSCHEDULING PROBLEM

A new heuristic algorithm is proposed for the problem of finding the minimum makespan in the job-shop scheduling problem. The new algorithm is based on the principles of particle swarm optimization (PSO). PSO employs a collaborative population-based search, which is inspired by the social behavior of bird flocking. It combines local search (by self experience) and global search (by neighboring experience), possessing high search efficiency. Simulated annealing (SA) employs certain probability to avoid becoming trapped in a local optimum and the search process can be controlled by the cooling schedule. By reasonably combining these two different search algorithms, a general, fast and easily implemented hybrid optimization algorithm, named HPSO, is developed. The effectiveness and efficiency of the proposed PSO-based algorithm are demonstrated by applying it to some benchmark job-shop scheduling problems and comparing results with other algorithms in literature. Comparing results indicate that PSO-based a     

R树上溢结点增量式k均值聚类优化分裂方法

R树能较好地满足逆向工程、CAD/CAM、机器视觉等领域的动态数据维护及空间查询需求,而CR树是其优秀的变体之一。针对CR树的上溢结点分裂算法存在的聚类结果不理想以及计算代价过高等问题,提出一种主元分析导向的增量式k均值算法,可在既有分类中心附近的第一主元方向上搜索新的初始分类中心。将该算法与Silhouette指标相结合应用于求解由上溢结点分裂问题所转化的点集聚类问题,能以较小的计算代价自适应获取近似全局最优的点集聚类结果。试验结果表明,基于增量式聚类的R树上溢结点分裂算法在R树构建效率、存储利用率及空间查询等方面的综合性能优于CR树与RR*树。     

A novel hybrid genetic algorithm for the open shop scheduling problem

In this paper, a hybrid genetic algorithm is proposed for the open shop scheduling problem with the objective of minimizing the makespan. In the proposed algorithm, a specialized crossover operator is used that preserves the relative order of jobs on machines and a strategy is applied to prevent from searching redundant solutions in the mutation operator. Moreover, an iterative optimization heuristic is employed which uses the concept of randomized active schedules, a dispatching index based on the longest remaining processing time rule and a lower bound to further decrease the search space. Computational results show that the proposed algorithm outperforms other genetic algorithms and is very competitive with well-known metaheuristics available in the literature.     

面向INS数据分类的鲁棒性无监督聚类方法

针对惯性导航系统(INS)中加速度计、陀螺仪测量误差随时间积累的问题,提出了一种基于内核模糊C均值的无监督广度优先搜索聚类算法(RUCM),用于INS模块采集数据的去噪及其运动阶段的分类划分。RUCM通过广度优先搜索方法遍历相邻的数据,使用阈值确定聚类数目,同时引入高斯核函数提高RUCM对噪声和异常点干扰的鲁棒性,并验证了其收敛性和鲁棒性。最后,在基于MEMS的INS模块实物系统中验证了该算法,结果表明所提出的方法能够提高随机采样INS数据的聚类性能,抑制了噪声干扰,使其INS运动阶段的聚类划分更加清晰与明确。     

Constraint-based simulated annealing (CBSA) approach to solve the disassembly scheduling problem

Globalization, coupled with environmental requirements, has spearheaded new levels of requirements for product end-of-life, the last phase of product lifecycle management especially for product remanufacturing and recycling which involves product disassembly to retrieve the desired parts and subassemblies. Selection of optimal disassembly schedule is a major challenge for remanufacturing and recycling industries as it directly affects the inventory of the manufacturing unit and influences the final product cost. This paper proposes a constraint-based simulated annealing (CBSA) algorithm methodology to determine the ordering and disassembly schedule to minimize inventory level for products with general assembly product structure, i.e., taking into consideration part commonalities. The proposed CBSA algorithm uses the constraint-based genetic operators integrated with the simulated annealing (SA) approach that makes the algorithm more search exploratory (guarantee the optimal or near-optimal solution) and converge efficiently to the optimal solutions (less time-consuming). The proposed algorithm has higher likelihood of avoiding local optima as compared with standard SA and genetic algorithms. This is achieved by exploring a population of points, rather than a single point in the solution space. The proposed methodology is validated using a numerical case study for disassembly scheduling problem with part commonality.     

云制造平台资源需求的高效匹配策略研究

为快速、精确地从云制造平台资源池中搜索到满足用户需求的资源,实现资源与需求的高效匹配,提出了一种资源需求高效匹配策略。首先,建立了资源与需求的形式化描述模型,在此基础上,采用改进的K-means聚类算法按基本信息进行聚类,对云服务池中的资源进行预处理,形成多个资源簇;其次,计算用户需求与各资源簇聚类中心基本信息的相似度,确立备选资源簇;最后,再分别从资源的状态信息、功能信息和服务信息3个方面对备选资源簇中的备选资源进行筛选匹配。实例分析和研究结果表明:与已有的匹配方法相比,该方法在保持较高匹配精度的同时具有更高的匹配效率。     

基于自适应密度聚类的多准则主动学习方法

主动学习能够以更少的标注成本训练出更好的机器学习模型。 现有的 RD 算法与 QBC 算法的结合有效地解决了只考 虑单一标准的问题。 然而,RD 所基于的 K-means 聚类会将离群点也包括在内进而造成模型性能降低,而 QBC 则需要维护于多 个模型而间接返回样本的信息性. 针对上述问题,本文提出了一种基于自适应密度聚类的高斯过程回归(ADC-GPR)算法,通过 先聚类后直接利用不确定性进而高效选择样本。 该算法中的 ADC 聚类不仅对离群点鲁棒,还能根据数据集分布特性自适应聚 类,并为后续的 AL 提供了代表性样本点和其对应的簇,该方法在无监督选择时保证了代表性和多样性,在有监督选择时考虑 了信息性、代表性和多样性。 实验结果表明,在相同的抽样次数下将 ADC-GPR 算法与 RS、KS 以及 RD-GPR 算法相比,其平均 性能分别提升了 37. 3% 、8% 和 2. 8% ,ADC-GPR 算法的选择效率更高。