CLUSTERING PROPERTIES OF FUZZY KOHONEN'S SELF-ORGANIZING FEATURE MAPS

A new clustering algorithm called fuzzy self-organizing feature maps is introduced. It can process not only the exact digital inputs, but also the inexact or fuzzy non-digital inputs, such as natural language inputs. Simulation results show that the new algorithm is superior to original Kohonen’s algorithm in clustering performance and learning rate.

Feature Extraction of Kernel Regress Reconstruction for Fault Diagnosis Based on Self-organizing Manifold Learning

The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension.Currently,nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddings,such as manifold learning.However,these methods are all based on manual intervention,which have some shortages in stability,and suppressing the disturbance noise.To extract features automatically,a manifold learning method with self-organization mapping is introduced for the first time.Under the non-uniform sample distribution reconstructed by the phase space,the expectation maximization(EM) iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention.After that,the local tangent space alignment(LTSA) algorithm is adopted to compress the high-dimensional phase space into a more truthful low-dimensional representation.Finally,the signal is reconstructed by the kernel regression.Several typical states include the Lorenz system,engine fault with piston pin defect,and bearing fault with outer-race defect are analyzed.Compared with the LTSA and continuous wavelet transform,the results show that the background noise can be fully restrained and the entire periodic repetition of impact components is well separated and identified.A new way to automatically and precisely extract the impulsive components from mechanical signals is proposed.

Pattern recognition of seismogenic nodes using Kohonen selforganizing map: example in west and south west of Alborz region in Iran

Pattern recognition of seismic and mor- phostructural nodes plays an important role in seismic hazard assessment. This is a known fact in seismology that tectonic nodes are prone areas to large earthquake and have this potential. They are identified by morphostructural analysis. In this study, the Alborz region has considered as studied case and locations of future events are forecast based on Kohonen Self-Organized Neural Network. It has been shown how it can predict the location of earthquake, and identifies seismogenic nodes which are prone to earthquake of M5.5＋ at the West of Alborz in Iran by using International Institute Earthquake Engineering and Seismology earthquake catalogs data. First, the main faults and tectonic lineaments have been identified based on MZ （land zoning method） method. After that, by using pattern recognition, we generalized past recorded events to future in order to show the region of probable future earthquakes. In other word, hazardous nodes have determined among all nodes by new catalog generated Self-organizing feature maps （SOFM）. Our input data are extracted from catalog, consists longitude and latitude of past event between 1980-2015 with magnitude larger or equal to 4.5. It has concluded node D1 is candidate for big earthquakes in comparison with other nodes and other nodes are in lower levels of this potential.

基于mRMR-SOM的异步电机轴承故障诊断研究

针对异步电机轴承故障诊断问题,提出了一种融合最大相关最小冗余特征选择算法(mRMR)和自组织映射神经网络(SOM)的故障诊断方法,并将其应用于轴承故障诊断的不同阶段。首先,在实验室环境下搭建了异步电机故障诊断试验平台,在不同电机状态下分别采集振动、电流和电压信号,利用统计学方法获取了高维混合特征集;然后,以互信息为背景,利用mRMR根据特征与状态标签间的相关性和特征间的冗余性,筛选了具备强区分能力的特征,以避免计算冗余和后验诊断性能下降;最后,采用SOM对异步电机健康和轴承故障状态进行了分类识别,验证了SOM对异步电机轴承故障诊断的有效性,以及mRMR对故障诊断结果的影响。研究结果表明:基于mRMR-SOM的异步电机轴承故障诊断方法能够准确地区分健康和故障状态,测试集分类准确率达到89%;使用mRMR特征筛选能够将154维特征降低至17维,缩短23.5%的网络收敛时间,并将分类准确率由89%提升至98%;试验结果验证了基于mRMR-SOM的异步电机轴承故障诊断方法对于异步电机轴承故障诊断问题的有效性,且证实其具备良好的诊断效果。

Self-organizing feature map neural network classification of the ASTER data based on wavelet fusion

Most methods for classification of remote sensing data are based on the statistical parameter evaluation with the assumption that the samples obey the normal distribution. How-ever, more accurate classification results can be obtained with the neural network method through getting knowledge from environments and adjusting the parameter (or weight) step by step by a specific measurement. This paper focuses on the double-layer structured Kohonen self-organizing feature map (SOFM), for which all neurons within the two layers are linked one another and those of the competition layers are linked as well along the sides. Therefore, the self-adapting learning ability is improved due to the effective competition and suppression in this method. The SOFM has become a hot topic in the research area of remote sensing data classi-fication. The Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) is a new satellite-borne remote sensing instrument with three 15-m resolution bands and three 30-m resolution bands at the near infrared. The ASTER data of Dagang district, Tianjin Munici-pality is used as the test data in this study. At first, the wavelet fusion is carried out to make the spatial resolutions of the ASTER data identical; then, the SOFM method is applied to classifying the land cover types. The classification results are compared with those of the maximum likeli-hood method (MLH). As a consequence, the classification accuracy of SOFM increases about by 7% in general and, in particular, it is almost as twice as that of the MLH method in the town.

Morphological self-organizing feature map neural network with applications to automatic target recognition

The rotation invariant feature of the target is obtained using the multi-direction feature extraction property of the steerable filter. Combining the morphological operation top-hat transform with the self-organizing feature map neural network, the adaptive topological region is selected. Using the erosion operation, the topological region shrinkage is achieved. The steerable filter based morphological self-organizing feature map neural network is applied to automatic target recognition of binary standard patterns and real world infrared sequence images. Compared with Hamming network and morphological shared-weight networks respectively, the higher recognition correct rate, robust adaptability, quick training, and better generalization of the proposed method are achieved.

Visualization of amino acid composition differences between processed protein from different animal species by self-organizing feature maps

Amino acids are the dominant organic components of processed animal proteins,however there has been limited investigation of differences in their composition between various protein sources.Information on these differences will not only be helpful for their further utilization but also provide fundamental information for developing species-specific identification methods.In this study,self-organizing feature maps(SOFM) were used to visualize amino acid composition of fish meal,and meat and bone meal(MBM) produced from poultry,ruminants and swine.SOFM display the similarities and differences in amino acid composition between protein sources and effectively improve data transparency.Amino acid composition was shown to be useful for distinguishing fish meal from MBM due to their large concentration differences between glycine,lysine and proline.However,the amino acid composition of the three MBMs was quite similar.The SOFM results were consistent with those obtained by analysis of variance and principal component analysis but more straightforward.SOFM was shown to have a robust sample linkage capacity and to be able to act as a powerful means to link different sample for further data mining.

VP型宽频带倾斜仪故障信号的BBA-SOM智能诊断

针对现有VP型倾斜仪故障诊断主要依靠人工经验和诊断流程较为复杂的问题,提出以互补集合经验模态分解(complete ensemble empirical mode decomposition,CEEMD)多尺度近似熵和二进制蝙蝠算法(binary bat algorithm,BBA)优化SOM神经网络参数的VP型倾斜仪故障诊断新方。首先,将归一化后的仪器故障信号进行CEEMD分解,对6阶本征模态函数(intrinsic mode function,IMF)求取多尺度近似熵值;然后将网络输入法按比例分为训练集和测试集,以训练集的识别率为适应度函数,应用二进制蝙蝠算法(binary bat algorithm,BBA)优化SOM神经网络的竞争层维数和网络训练次数;最后应用上述得到的BBA-SOM网络模型对倾斜仪故障特征数据进行辨识。实验表明:CEEMD多尺度近似熵判据对倾斜仪故障特征的区分效果符合预期;相对于朴素贝叶斯、AdaBoost集成学习与LDA等学习模型,BBA-SOM模型可以准确进行故障诊断;该方法对实现VP型倾斜仪故障的自动诊断有重要现实意义。

Vibration Feature Fusion for State Evaluation of Machinery

To overcome the problem that a single feature can not reflect the state of machinery in different stages,a method of vibration feature fusion based on self-organizing map(SOM) is presented.Minimum quantization error(MQE) is obtained unsupervised based on SOM network.And trend information of the MQE curve is extracted by the wavelet packet to enhance state differentiating.Experimental flat is designed for bearing accelerating fatigue.And experimental results show that the method of vibration feature fusion based on SOM can reflect the state of machinery in different stages effectively.

Pattern recognition of messily grown nanowire morphologies applying multi-layer connected self-organized feature maps

Multi-layer connected self-organizing feature maps(SOFMs) and the associated learning procedure were proposed to achieve efficient recognition and clustering of messily grown nanowire morphologies. The network is made up by several paratactic 2-D SOFMs with inter-layer connections. By means of Monte Carlo simulations, virtual morphologies were generated to be the training samples. With the unsupervised inner-layer and inter-layer learning, the neural network can cluster different morphologies of messily grown nanowires and build connections between the morphological microstructure and geometrical features of nanowires within. Then, the as-proposed networks were applied on recognitions and quantitative estimations of the experimental morphologies. Results show that the as-trained SOFMs are able to cluster the morphologies and recognize the average length and quantity of the messily grown nanowires within. The inter-layer connections between winning neurons on each competitive layer have significant influence on the relations between the microstructure of the morphology and physical parameters of the nanowires within.

基于多特征增强融合的交流接触器状态表征

准确掌握交流接触器的运行状态是实现交流接触器智能化的基础,为此提出了一种基于多特征增强融合的状态表征方法。首先针对交流接触器特征参数非线性、非平稳、随机变化、趋势性不明显但符合一定统计特性的特点,利用Wasserstein概率距离进行特征变换得到趋势性较强的初态特征;然后以多属性初态特征参数为驱动,考虑参数间强耦合的特点,利用自编码器神经网络进行特征压缩提取,剔除冗余信息,保留有用信息;在此基础上,以压缩提取特征为输入,通过自组织映射神经网络来实现多维特征的竞争性融合输出,得到交流接触器运行状态的综合健康指标,实现交流接触器状态的定量表征。最后,结合实测数据验证了所提方法的有效性,并与其他2种方法相比较,结果表明:所提方法得到的健康指标趋势性、单调性和鲁棒性相比其他2种方法分别至少提高了4%、24%和5%,研究可为下一步研究交流接触器的精准控制和智能化提供参考。

基于自组织映射神经网络的淮河流域生态系统服务簇时空变化特征

生态系统服务簇的识别是区域生态系统服务管理与优化的关键。量化了2000、2010、2020年淮河流域产水量(WY),水源涵养(WC),土壤保持(SC),生境质量(HQ),水质净化(WP),净初级生产力(NPP)和碳储量(CS)7种生态系统服务。并基于自组织映射神经网络(SOFM)识别了生态系统服务簇,探讨了生态系统服务簇的时空变化特征。结果表明:(1)2000—2020年,WP,NPP与WC呈上升趋势,WC的增幅最大;CS与HQ呈下降趋势。淮河流域各生态系统服务具有时空异质性,生态系统服务高值区多位于西南部山区与东北部丘陵山地地区。(2)识别了5个生态系统服务簇:核心生态服务簇,WP服务簇,WY服务簇,NPP服务簇与生态过渡服务簇。核心生态服务簇与生态过渡服务簇的面积总体增加,流域西南部山区与东北部丘陵山地地区生态系统服务提升,2000—2020年,WY服务簇与NPP服务簇间的转移面积较大,WY服务簇面积减少达60.09%,NPP服务簇面积显著增加,2020年占整个流域面积的57.02%。研究结果不仅有助于清晰认识淮河流域生态系统服务簇的空间分布格局及动态变化,也为探索淮河流域可持续的生态系统管理与规划决策奠定了基础。

基于自组织特征映射模型(SOFM)网络的中国自然资源生态安全区划

自然资源生态安全是国家安全的重要组成部分,自然资源生态安全区划对保障区域可持续发展提供了重要途径。基于自然资源数据、生态环境数据和相关区划资料,从生态敏感性与生态服务重要性角度构建了自然资源生态安全评价指标体系,进而揭示了中国自然资源生态安全的空间格局;通过建立区划的原则和指标,按照一级区主要反映自然资源空间分布格局,二级区主要揭示自然资源生态安全水平的差异,采用SOFM网络制订了中国自然资源生态安全区划方案。结果显示:(1)中国自然资源生态安全水平整体偏低,以中警与重警状态区域为主,安全和较安全状态的区域仅占24.22%,其中低安全等级区多分布于400mm等降水量线以西的干旱、半干旱区,高安全等级区则集中分布于水热资源与生物资源较为丰富的东南部地区;(2)中国自然资源生态安全区划方案包括8个一级区与27个二级区,总结归纳各大区自然资源的特征和威胁生态安全的问题,并针对二级区自然资源生态安全状况提出了对策建议。研究结果可为分区、分类推进全国自然资源可持续利用和国土空间优化提供理论支持与决策依据。

模糊SOFM-GIS空间聚类模型在农用地分等中的应用

针对目前农用地分等方法中的存在的不足之处,提出将模糊理论、自组织特征映射(Se lf-O rgan iz ing F eature M ap,SOFM)网络与G IS相结合,构造出一种新的农用地分等模型—模糊SOFM-G IS空间聚类模型。并利用此模型对广东省高要市农用地进行农用地分等评价,结果表明采用模糊SOFM-G IS空间聚类模型进行农用地分等评价具有稳定、结果可靠等特点。

基于自组织神经网络的生态敏感性分区--以北京市房山区为例

采用自组织神经网络(SOM)模型,以北京市房山区为例,对其进行生态敏感性分区.分别以土壤侵蚀、地表水环境、地下水环境和生境为生态敏感性因子,作为SOM模型的4个二维输入矩阵,通过多次迭代学习和自组织聚类,使结果在4维(4个生态因子)生态敏感性空间内最大限度地逼近房山区生态特征分布.结果表明,房山区西北部山区的敏感性最高;东部平原是地表、地下水非常丰富的地区,属中度敏感;二者之间的丘陵浅山区敏感性相对较弱.

基于SOFM与随机森林的大别山区水土保持空间管控分区

水土保持是国家生态文明建设的重要内容,水土保持空间管控分区是水土流失区域科学治理的前提与关键。然而,目前水土保持管控区域划分研究还未形成成熟的空间划定方法,且以小流域为单元的水土保持空间管控研究较少。为探索水土保持空间管控分区的方法,落实差别化保护治理措施,该研究利用通用土壤流失方程(universal soil loss equation,USLE)计算研究区潜在土壤侵蚀模数与实际土壤侵蚀模数,并通过随机森林确定了土壤侵蚀的主要影响因子,基于小流域单元的土壤侵蚀及其影响因子利用自组织映射神经网络(self-organizing feature map,SOFM)确定了大别山区的水土保持空间管控分区。结果显示:1)大别山区的平均潜在土壤侵蚀为84 415.7 t/(km^(2)·a),平均实际土壤侵蚀为210.25 t/(km^(2)·a)。小流域的实际土壤侵蚀主要分布于0~300 t/(km^(2)·a),小流域尺度上潜在土壤侵蚀与实际土壤侵蚀空间分布格局基本一致,高值区主要分布于研究区中部与东部海拔较高的山区腹地;2)植被覆盖度、坡度分别为小流域尺度上潜在土壤侵蚀与实际土壤侵蚀的主要影响因子,植被覆盖度、坡度与土壤侵蚀呈显著正相关(P<0.01)。高植被覆盖区主要分布于林地占比较高的大别山区腹地,坡度较大的区域沿大别山山脊线自西向东分布。3)SOFM结果显示,小流域尺度上的大别山水土保持空间管控区域划分为重点预防区、一般预防区与其他区域,其中重点预防区涉及小流域710个,面积15 287.4 km^(2)。一般预防区共890个小流域,面积18 874.4 km^(2)。两个预防区面积共占研究区61.2%。各区域间的实际土壤侵蚀、潜在土壤侵蚀与坡度差异明显,可作为大别山水土保持空间管控各区域的主要划分指标。研究结果为水土保持空间管控分区提供了思路,为分区域进行水土保持空间管控提供了理论支持与决策依据。

基于SOM-RBF算法的瓦斯涌出量动态预测模型研究

针对煤矿瓦斯涌出量的多影响因素预测问题,以多传感器的瓦斯监测系统采集处理后的数据作为样本,提出了一种自组织特征映射神经网络(Self-organizing Feature Maps,SOM)与多变量的径向基函数(Radial Basis Function,RBF)结合的组合人工神经网络的模型动态预测新方法。采用先聚类、再分类建模和预测的方法,解决了由于训练样本有限和训练样本点分散所导致的预测精度降低的问题,并通过矿井监测到的各项历史数据进行试验。结果表明,与其他预测模型相比较,该模型的预测精度更高,泛化能力更强。预测平均相对误差为2.16%,均相对变动值ARV为0.005 9,均方根误差RMSE为0.131 1,有效地实现了对煤矿绝对瓦斯涌出量的动态预测,有较高的实用价值。

多光谱卫星云图的SOFM-PNN网络耦合的云分类模型

针对单一类型的神经网络分类器难以正确区分和有效识别复杂云类特征的缺陷,本文基于静止气象卫星云图多光谱云类样本,通过计算、分析云图灰度、梯度与纹理特征,提取了云分类最佳判别因子,建立了自组织网络(SOFM)与概率神经网络(PNN)的综合云分类器优化模型.该分类器首先利用自组织网络对云类样本进行无监督初始分类,确定出相似样本子集;随后用概率神经网络对初始分类误差进行有监督修正和分类结果的二次优化判别.试验结果表明,该分类器可有效提高云类判别效果,分类结果的总正确率达到92.4%,Kappa系数为90.82,明显优于单一的统计分类器判别效果.

一种基于SOM和K-means的文档聚类算法

提出了一种把自组织特征映射SOM和K-means算法结合的聚类组合算法。先用SOM对文档聚类,然后以SOM的输出权值初始化K-means的聚类中心,再用K-means算法对文档聚类。实验结果表明,该聚类组合算法能改进文档聚类的性能。

一种协同半监督分类算法Co-S3OM

为了提高半监督分类的有效性,提出了一种基于SOM神经网络和协同训练的半监督分类算法CoS3OM(coordination semi-supervised SOM)。将有限的有标记样本分为无重复的三个均等的训练集,分别使用改进的监督SSOM算法(supervised SOM)训练三个单分类器,通过三个单分类器共同投票的方法挖掘未标记样本中的隐含信息,扩大有标记样本的数量,依次扩充单分类器训练集,生成最终的分类器。最后选取UCI数据集进行实验,结果表明Co-S3OM具有较高的标记率和分类率。