基于排列熵和VPMCD的滚动轴承故障诊断方法

VPMCD(Variable Predictive Model Based Class Discriminate)是一种新的模式识别方法,它充分利用从原始数据中所提取的特征值之间的相互内在关系建立数学模型,从而进行模式识别。论文将VPMCD结合排列熵(Permutation Entropy,简称PE)方法应用于滚动轴承故障诊断。首先采用ITD(Intrinsic Time-scale Decomposition,简称ITD)对滚动轴承振动信号进行分解,得到若干个固有旋转(Proper Rotation)分量,并对包含主要故障信息的PR分量提取排列熵作为故障特征值;然后,对VPMCD分类器进行训练;最后,采用VPMCD分类器进行故障识别和分类。实验数据的分析结果表明该方法能够有效地应用于滚动轴承故障诊断。     

基于流形学习和改进VPMCD的滚动轴承故障诊断方法*

提出一种基于拉普拉斯特征映射流形学习算法(Laplacian Eigenmaps,简称LE)和改进多变量预测模型(Variable predictive model based class discriminate,简称VPMCD)的滚动轴承故障诊断方法,首先对振动信号进行局部特征尺度分解(Local characteristic scale decomposition,简称LCD),并提取各内禀尺度分量(Intrinsic scale component,简称ISC)的特征构造高维特征向量,接着采用LE算法挖掘出高维数据中包含有效信息且具有内在规律性的低维特征,然后输入到基于Kriging的改进多变量预测模型(Kriging-variable predictive model based class discriminate,简称KVPMCD)分类器中进行模式识别。该方法充分利用并有效结合了LCD在信号处理、LE在挖掘特征信息和KVPMCD在模式识别方面的优势,实现了滚动轴承故障特征提取到故障识别的全程诊断。实验分析结果表明:基于LE算法和KVPMCD的分类方法可以有效地对滚动轴承的工作状态和故障类型进行识别。     

基于VPMELM的滚动轴承劣化状态辨识方法

针对变量预测模型模式识别方法(VPMCD)仅仅包含几种简单数学模型的问题,所建立的预测模型不足以反映特征值之间的复杂关系;极限学习机(ELM)回归模型是一种复杂且被广泛应用的模型,其模型可以反映特征之间的相互关系。结合极限学习机回归模型和VPMCD方法的优点,提出了一种基于极限学习机的变量预测模型(VPMELM)模式识别方法,并将该方法应用于滚动轴承劣化状态实验中。实验表明,基于VPMELM的辨识方法可以有效地对滚动轴承的劣化状态进行识别。     

Xgboost在滚动轴承故障诊断中的应用

针对不同轴承数据特征选择困难和单个分类器方法在滚动轴承故障诊断中精度较低的问题,提出一种基于分类与回归树的Xgboost(e Xtreme Gradient Boosting)轴承故障诊断算法。Xgboost是包含多个分类器的集成学习方法。通过Xgboost的"提升"思想来提高滚动轴承故障诊断的精度。首先,从滚动轴承的振动信号中提取时域特征参数;然后利用Xgboost算法对滚动轴承故障进行诊断。将SQI-MFS实验平台的轴承振动数据,与传统分类器(支持向量机、邻近算法和人工神经网络)以及单个分类回归树的诊断结果相比,结果表明Xgboost在轴承故障诊断率上优于上述几种算法,且计算时间比传统提升决策树算法短。     

基于部分集成局部特征尺度分解与拉普拉斯分值的滚动轴承故障诊断模型

提出了一种基于部分集成局部特征尺度分解(Partly ensemble local characteristic-scale decomposition,PELCD)、拉普拉斯分值(Laplacian score,LS)特征选择和基于变量预测模型模式分类(Variable predictive model based class discrimination,VPMCD)的滚动轴承故障诊断模型。PELCD是新提出的一种基于噪声辅助数据分析方法,克服了局部特征尺度分解的模态混淆问题,与传统的基于噪声辅助数据分析方法相比有一定的优越性,论文将其应用于滚动轴承振动信号的预处理。之后提取振动信号PELCD分量的时域和频域统计特征及振动信号的时频联合域特征;同时为了降低特征向量维数,提高诊断效率,采用LS优化特征向量。再将优化的特征向量输入到VPMCD分类器进行训练和测试。滚动轴承实验数据分析结果表明该模型能够有效地诊断故障程度和故障类型。     

基于改进多项式响应面的VPMCD方法及其在滚动轴承故障诊断中的应用

基于变量预测模型的模式识别(Variable predictive model based class discriminate,简称VPMCD)方法在训练过程中是用多项式响应面(Polynomial Response Surface,简称PRS)法来建立预测模型的,然而PRS法的模型拟合精度不能随训练样本容量的增加而显著提高。针对这一缺陷,将原方法中的PRS方法进行了改进,提出了基于改进多项式响应面(Improved Polynomial Response Surface,简称IPRS)的VPMCD方法,并将其应用于滚动轴承故障诊断。通过实验,将原方法和改进方法在训练样本容量不同情况下的模式分类精度进行对比,结果表明,相对于原VPMCD方法,改进的VPMCD方法不仅具有更好的模式分类效果,而且其分类精度随训练样本容量的增加提高得更明显。     

全参数动态学习深度信念网络在滚动轴承寿命预测中的应用

相对于传统的"对信号进行特征提取+人工选择对数据敏感的特征值+预测模型"的滚动轴承寿命预测方法,深度信念网络(DBN)有显著的优势:DBN可以直接处理原始数据,让机器自动学习信号特征,从而免去了特征提取和选择的过程,提高了预测的智能性。但是传统的DBN采用固定学习率进行网络学习,不利于寻找最优结果;基于此,提出了一种改进的深度信念网络——全参数动态学习深度信念网络(GPDLDBN),并将其应用于滚动轴承寿命预测中。GPDLDBN预测模型由多层受限玻尔兹曼机(RBM)单元组成,采用自下而上的逐层无监督贪婪算法训练参数;接着采用自上而下的监督学习算法微调整个网络参数,两个过程均采用新的全参数动态学习策略设置各参数;采用GPDLDBN预测模型对实测的滚动轴承寿命数据进行了预测,并与传统的固定学习率的DBN预测模型进行了对比分析。结果表明,GPDLDBN预测模型能够有效加快收敛速度,减少模型的训练时间,且具有更高的预测精度。     

基于互信息的滚动轴承故障特征选择方法

信号特征提取与优化选择是实现滚动轴承故障模式快速有效分类的关键.针对滚动轴承故障信号特征提取,采用小波分解和奇异值分解得到信号的能谱和奇异谱,并计算Shannon熵和Renyi熵两种测度下的能谱熵和奇异熵;针对特征参数集的优化选择,提出利用基于互信息的最大相关最小冗余准则(mRMR)对特征参数集进行评价,通过贪婪搜索得到特征子集序列,利用LS-SVM交叉验证各特征子集的性能,提出确定最优特征子集所包含特征数目的准则.从信号处理、特征提取、特征选择和故障分类等方面构建了滚动轴承故障诊断的完整体系,实际故障诊断表明所提出方法的有效性和优越性.     

基于本征时间尺度分解和变量预测模型模式识别的机械故障诊断

基于变量预测模型的模式识别(variable predictive model based class discriminate,VPMCD)方法是一种充分利用特征值之间相互内在关系进行多分类模式识别的新方法。对VPMCD算法进行了研究,并采用交叉验证法来选择VPMCD模型。针对机械故障振动信号的特征值之间的相互内在关系,结合本征时间尺度分解(intrinsic time-scale decom-position,ITD),提出了一种基于本征时间尺度分解和VPMCD的机械故障诊断方法。该方法首先利用ITD方法将原始信号分解若干个PR(proper rotation,PR)分量,然后提取第一个PR分量的无量纲时域统计参数组成特征向量,最后采用VPMCD方法进行机械故障诊断。通过滚动轴承故障诊断实验验证了该方法能有效地应用于小样本多分类机械故障诊断。     

基于特征评价的ADMOW模式识别方法及其应用

针对以往模式识别方法的不足及特征数据存在“异常值”导致的模型失真问题,提出了基于特征评价的优化加权代理判别模型（Agent discriminate model based optimization weighted,ADMOW）模式识别方法。该方法根据同一状态类别中各特征值之间的对应关系（不同类别有不同的对应关系）建立数学预测模型,然后计算各特征值的类相似度评价指标,根据评价指标对特征值进行加权处理,从而削弱“异常值”对模型的影响,建立更加准确的代理判别模型,提高分类准确度。实验结果表明,经过特征加权处理的ADMOW方法对滚动轴承的状态识别具有更高的识别率。     

The Research of Anti-Wear Properties of Organomolybdenum Compounds in the Engine Oils

A four-ball tester was used to evaluate the anti-wear performance of three kinds of organomolybdemun compounds in the engine oils, i. e., molybdenum dialkyldithiophosphate (MoDDP), molybdenum dialkyldithiocarbamate ( MoDTC), and sulphur and phosphorus freeorganomolybdeum (Molybdate). The results indicate that a low concentration of MoDDP doesn' t improve the anti-wear properties of the commercial engine oils, but a high concentration of MoDDP can obviously improve the anti-wear properties and the load-carrying capacity of the engine oils. MoDTC doesn' t improve the antiwear properties of the engine oils, but worsens the anti-wear properties of the oils. Signifi can timprove ment of frictional and wear characteristics is obtained with Molybdate added in the commercial engine oils and the formulated oils.     

Certification Institutions Expected to Update and Transfer Information on Present Standards

Standards are the basis for production enterprises to organize production, ex-factory inspection, trade (delivery) and technical exchanges, product certification, quality arbitration and supervision.……     

Certification Becomes Important for the I Quality; and Safety Supervision of the Chinese Liquor Sector

The end of 2007, over 200 unit products of more than 80 Chinese firms have passed the quality grade certification for liquor products. These products involve distilled spirits, beer, wine, yellow wine, fruit syrup wine and others, and cover over 80% of the national top-branded liquor products.……     

Deposition and Coating Properties on CVD Tungsten

Surface characterization and microstructure studies are performed on chemical vapor deposited (CVD) tungsten coating. There is about 2 μm thickness diffusion layer of tungsten in the molybdenum substrate. The thermal shock test shows tungsten coating has good adhesion with molybdenum substrate, but the elements of oxygen and carbon in the tungsten coating have the bad affection to the adhesion. The result of high-temperature diffusion experiment is the diffusion rate from molybdenum substrate to tungsten coating is faster.     

Analysis of marine hydrobiont lipid extracts as possible cryoprotective agents

We studied a combined effect of the cryoprotectants both of lipid and carbohydrate origin at the presence of DMSO or without it on cell viability and the RNA synthesis in the embryonic mollusc and echinoderm cell cultures obtained at different developmental stages. Cryoprotective properties of exogenous lipids correlated with their thermotropic behavior. Lipid extracts from marine hydrobiontes, which thermal transitions are characterized by relatively small part of calorimetric thermogram area lying at temperatures above 0 °C (6–18%), were found to possess a considerable cryoprotective activity. The results are discussed in relation to the prediction of the cryoprotective activity of lipid extracts for marine animal cells. In addition, it was found that marine invertebrate cells can be cryopreserved without DMSO at the presence of trehalose and lipid extracts of some marine hydrobiontes.     

Low-Temperature Properties of Silver

Pure silver is used extensively in the preparation of high-temperature superconductor wires, tapes, films, and other configurations in which the silver not only shields the superconducting material from the surrounding materials, but also provides a degree of flexibility and strain relief, as well as stabilization and low-resistance electrical contact. Silver is relatively expensive, but at this stage of superconductor development, its unique combination of properties seems to offer the only reasonable means of achieving usable lengths of conductor. In this role, the low-temperature physical (electrical, thermal, magnetic, optical) and mechanical properties of the silver all become important. Here we present a collection of properties data extracted from the cryogenic literature and, to the extent possible, selected for reliability.     

Early ironwork in Biscay: Survey,excavation, experimentation and materials characterization. An integral study of the mountainside ironworks (ferrerías de monte or “haizeolak”)

ABSTRACT

The production of iron in Biscay (Basque Country, Spain) has been a hallmark of this territory of the North of the Iberian Peninsula throughout its history. The Archaeology team of the Basque Country Mining Museum has spent 13 years, so far, studying the origins of this activity through the evidences left at the old pre-hydraulic iron production workshops known as mountainside ironworks (ferrerías de monte) or haizeolak. It has catalogued 170 archaeometallurgical sites of this type in Biscay, and the archeological excavation of some of them has led to the knowledge of the different stages of the production process that took place in these workshops. The team has also experimentally reproduced the work carried out in a mountainside ironworks from the High Middle Ages, and it has currently started the characterization process of this type of activity through the study of the collected materials.     

Optimum-Simulation von Ernteprozessen

Zusammenfassung Bei der Gestaltung von Ernteprozessen — beispielsweise des Prozesses Mähdrusch, Körnertransport und -abnahme — als transportverbundene Fließarbeitsverfahren mit mindestens zwei verschiedenen Arbeitsmitteln gibt es einen großen Optimierungsspielraum. Solche Prozesse sind mehrstufige Bedienungsprozesse mit gemischter Anordnung der Bedienungseinrichtungen. Außerdem besitzen sie stark ausgeprägte räumliche Aspekte. Es wird vor allem gezeigt, welche Merkmale solcher Prozesse in Simulationsmodellen abgebildet sein müssen, welche Zielgrößen in Abhängigkeit von welchen Einflußgrößen unter Berücksichtigung welcher Prozeßbedingungen ermittelt werden sollten und wie der Bewertungsprozeß zur Ermittlung der gewünschten Informationen gestaltet werden muß.     

Mechanism Study on the Wear of CrAlTiN Coated High-Speed Steel Twist Drills Under Dry Cutting Conditions

As demands about environment protection are growing up, dry cutting technology is getting more and more concerns from all over the world. Main works performed here are study on dry cutting performances and wear mechanisms of M2high-speed steel (HSS) twist drills with CrAlTiN multicomponent coatings, which was deposited using magnetron sputter ion plating system, in drilling 45 and 30CrMnSiA steel, and their comparisons to those in drilling the same steel but using monolayer CrN and commercial TiN coated drills. Drilling performances of drills are evaluated mainly through the measurements of width on outer corner flank land and the cutting forces. Results show that performances of CrAlTiN coated drills are better than those of monolayer CrN and TiN coated drills. In drilling 45 and 30CrMnSiA steel, the average tool life of the CrAlTiN coated drills are 17.2 and 11.8 times higher than those of the uncoated drills. Observing wear of the drill with scanning electronic microscope, results show that there is no crack or spallation of the CrAlTiN coatings in wear zones. Main mechanism of the wear here is adhesion.     

Structural Characteristics of TiO2 Ceramic Coating by Micro-Plasma Oxidation

TiO2 ceramic coatings with thickness of 20 μm were formed on the surface of pure titanium by micro-plasma oxidation. Their micro-structures were investigated by by using X-ray diffraction and their surface images were detected by using scan electronic microscope. There were three kinds of TiO2 coatings, pure anatase type TiO2 phase, mixed phases consisted of rutile type TiO2 phase and anatase type TiO2 phase, pure rutile type TiO2 phase. The coating surface with the pure anatase type TiO2 phase is rough, while the coating surface with the pure rutile type TiO2phase is smooth. The upper coating surface with the mixed type TiO2 phases is anatase type TiO2 structure and the subsurface of the TiO2 coating is rutile type TiO2structure.