Effect of Two Kinds of Similarity Factors on Principal Component Analysis Fault Detection in Air Conditioning Systems

Screening similar historical fault-free candidate data would greatly affect the effectiveness of fault detection results based on principal component analysis(PCA).In order to find out the candidate data,this study compares unweighted and weighted similarity factors(SFs),which measure the similarity of the principal component subspace corresponding to the first k main components of two datasets.The fault detection employs the principal component subspace corresponding to the current measured data and the historical fault-free data.From the historical fault-free database,the load parameters are employed to locate the candidate data similar to the current operating data.Fault detection method for air conditioning systems is based on principal component.The results show that the weighted principal component SF can improve the effects of the fault-free detection and the fault detection.Compared with the unweighted SF,the average fault-free detection rate of the weighted SF is 17.33%higher than that of the unweighted,and the average fault detection rate is 7.51%higher than unweighted.

Multimode Process Fault Detection Using Local Neighborhood Similarity Analysis

Traditional data driven fault detection methods assume unimodal distribution of process data so that they often perform not well in chemical process with multiple operating modes. In order to monitor the multimode chemical process effectively, this paper presents a novel fault detection method based on local neighborhood similarity analysis(LNSA). In the proposed method, prior process knowledge is not required and only the multimode normal operation data are used to construct a reference dataset. For online monitoring of process state, LNSA applies moving window technique to obtain a current snapshot data window. Then neighborhood searching technique is used to acquire the corresponding local neighborhood data window from the reference dataset. Similarity analysis between snapshot and neighborhood data windows is performed, which includes the calculation of principal component analysis(PCA) similarity factor and distance similarity factor. The PCA similarity factor is to capture the change of data direction while the distance similarity factor is used for monitoring the shift of data center position. Based on these similarity factors, two monitoring statistics are built for multimode process fault detection. Finally a simulated continuous stirred tank system is used to demonstrate the effectiveness of the proposed method. The simulation results show that LNSA can detect multimode process changes effectively and performs better than traditional fault detection methods.

Modeling and monitoring of nonlinear multi-mode processes based on similarity measure-KPCA

A new modeling and monitoring approach for multi-mode processes is proposed.The method of similarity measure(SM) and kernel principal component analysis(KPCA) are integrated to construct SM-KPCA monitoring scheme,where SM method serves as the separation of common subspace and specific subspace.Compared with the traditional methods,the main contributions of this work are:1) SM consisted of two measures of distance and angle to accommodate process characters.The different monitoring effect involves putting on the different weight,which would simplify the monitoring model structure and enhance its reliability and robustness.2) The proposed method can be used to find faults by the common space and judge which mode the fault belongs to by the specific subspace.Results of algorithm analysis and fault detection experiments indicate the validity and practicability of the presented method.

Polarimetric Meteorological Satellite Data Processing Software Classification Based on Principal Component Analysis and Improved K-Means Algorithm

With the increasing variety of application software of meteorological satellite ground system, how to provide reasonable hardware resources and improve the efficiency of software is paid more and more attention. In this paper, a set of software classification method based on software operating characteristics is proposed. The method uses software run-time resource consumption to describe the software running characteristics. Firstly, principal component analysis (PCA) is used to reduce the dimension of software running feature data and to interpret software characteristic information. Then the modified K-means algorithm was used to classify the meteorological data processing software. Finally, it combined with the results of principal component analysis to explain the significance of various types of integrated software operating characteristics. And it is used as the basis for optimizing the allocation of software hardware resources and improving the efficiency of software operation.

Study on GC-MS fingerprint of petroleum ether fraction of Shenqi Jiangtang Granules

Objective To establish gas chromatography-mass spectrometry(GC-MS)fingerprint method for the petroleum ether fraction of Shenqi Jiangtang Granules(SQJTG)and evaluate the product quality.Methods The GC-MS fingerprint of petroleum ether fraction of SQJTG was established by GC-MS,and the chemical components corresponding to the fingerprint peaks were structurally identified on NIST2014.The batch consistency of SQJTG products was evaluated based on the chemical composition of petroleum ether parts by using fingerprint similarity evaluation and Principal components analysis(PCA)technology.At the same time,Hotelling's T2 and DMODX statistics are used to set the control range for the quality of different batches of products.Results Twenty-two components were identified from the petroleum ether part of SQJTG,accounting for 60.94%of the total components separated.The similarity of fingerprints of petroleum ether parts of 24 batches of SQJTG was greater than 0.95.The PCA of 24 batches of samples were all under the control limits of Hotellin’s T2 and DMODX statistics,indicating that the petroleum ether parts of different batches of SQJTG were consistent.Conclusion The developed GC-MS fingerprint method can be used to evaluate the quality of SQJTG.

Similarity Analysis-based Component Standardization for Product Family Design

During the product family design, it is necessary to reduce the variety of components and share common components among many products. The major benefits are lessened design efforts and reduced costs. Therefore, this paper presents an approach to standardize components of a product family. Form feature modeling for components is discussed. Based on the similarity analysis, a step by step method to standardize the feature architectures of components is described. The algorithms for standardization are identified as well. A case for standardizing components of an auto-body family is used to demonstrate the validity of this approach.

Relationship between Tropical Forest Distribution and Soils on Different Types of Mother Rocks in the Republic of Congo

The factors influencing the distribution of forests and their development are important in order to better understand the bio-functioning of tropicals ecosystems forests. The Republic of the Congo has an important forest area of 23.5 million ha subdivided into three large massifs with different forest units from the north until the south of the country. The present study proposes to highlight the relationship between the edaphic and pedological factors and the distribution of the floristic species of some tropical forests of the Congo. To achieve this aim, a principal component analysis (PCA) was to identify similarities or oppositions between variables and to locate the most correlated variables. Also, the indices of biodiversities were used to assess the biodiversity between forest plot and forest sites. A total of 238 species distributed in 46 families were counted. We noted a CS similarity between Mbomo-Kellé and FMU Mokabi-Dzanga of 50%. However, there was considerable variability between the forests of the Impfondo-Dongou axis and of the forest of other localities. The main component analysis carried out showed that the distribution of floristic species in the studied forests is determined by the edaphic factors.

基于UPLC-Q-TOF MS的水栀子药材指纹图谱建立及其与栀子药材成分差异分析

建立水栀子药材超高效液相—质谱联用指纹图谱,分析水栀子与栀子药材指纹图谱的差异.采用80%甲醇超声提取,超高效液相色谱法测定指纹图谱,结合质谱、保留指数和相关文献对部分色谱峰定性鉴别;并通过相似度评价和主成分分析水栀子与栀子药材所含主要指标性成分的差异.结果显示,水栀子指纹图谱共有24个共有峰,确定了其中的14个成分.水栀子与栀子药材相似度较为一致,主成分分析可以准确区分水栀子与栀子药材.所建立的指纹图谱测定方法可以用于水栀子与栀子药材的鉴别,研究结果为水栀子与栀子药材真伪品鉴定提供了实验依据.

An HPLC Fingerprint Identification of Dried Barks of Ilex rotunda and Ilex godajam

[Objectives] A simple and reliable HPLC fingerprint method was developed for the identification of dried barks of Ilex rotunda and I. godajam. [Methods] Nine batches of dried barks of I. rotunda,and seven batches of dried barks of I. godajam collected from different pharmacies and arboretums in different regions of China were used to establish fingerprints. The software Similarity Evaluation System of Chromatographic Fingerprints of Traditional Chinese Medicine( 2004 A Edition) was used to evaluate the fingerprints. [Results]The fingerprints of dried barks of I. rotunda and I. godajam were established. Methodological study met the technical requirements of fingerprints. The similarities of the fingerprints of dried barks of I. rotunda and I. godajam were all more than 0. 8 and 0. 9 respectively. There were 31 and 28 common peaks in I. rotunda and I. godajam,which could be classified into two clusters by principal component analysis( PCA) and hierarchical cluster analysis. [Conclusions] The feasibility and advantages of used HPLC fingerprints were verified,and the results indicated that the HPLC fingerprint as a characteristic distinguishing method combining similarity evaluation,principal component analysis and hierarchical cluster analysis can be successfully used to identify the authenticity of dried barks of I. rotunda and I. godajam.

林芝市引进梨品种果实品质的综合分析与评价模型构建

【目的】在西藏引入不同优良梨品种,以调整区内梨果树种植结构,为推动西藏特色林果业发展提供理论依据。【方法】以西藏林芝市引入的9个梨品种作为试验材料,成熟后测定其12项果实品质指标。通过相关性分析和因子分析,建立基于因子分析、主成分分析、线性回归分析以及相似性分析的综合品质评价模型,并根据综合品质得分进行优良度排序,筛选出适宜林芝市种植的优良梨品种。【结果】9个梨品种的果实品质性状变异系数有所不同,其中果形指数的变异系数较大,单果质量、果实硬度、可滴定酸含量、固酸比和石细胞含量的变异系数均中等,果实横径、果实纵径、果心横径、果心比、可溶性固形物和维生素C含量的变异系数均相对较小。对9个梨品种的12项果实品质性状的因子分析,得知前4个公因子的累积方差贡献率达89.120%,其中,第1个公因子的贡献率为37.240%,主要反映果实大小和酸甜口感品质,第2个公因子的贡献率为20.658%,主要反映了梨果实的软硬程度,第3个公因子的贡献率为17.760%,主要反映了果实形状和维生素C含量,第4个公因子的贡献率为13.642%,主要反映了果实可食部分大小和果实糖含量。各品种间存在显著的统计差异(R=0.768,p=0.001),新梨七号与晚秋黄品种显示出最大的差异性。品种间在多维性状上的分布特点表明质量和横径被识别为分类的关键因素。经综合品质评价模型,得出9个梨品种在林芝种植后的果实综合品质得分高低排序为圆黄、华山、翠冠、中梨1号、初夏绿、新梨七号、翠玉、红太阳和晚秋黄。【结论】研究结果对指导西藏自治区内特色梨品种的选育和促进梨产业的可持续发展具有重要意义。

一测多评法测定法制半夏曲中11种成分含量及其GRA、EW-TOPSIS质量评价

目的采用一测多评(QAMS)法同时测定法制半夏曲中肌苷、鸟苷、腺苷等11种成分含量,并建立其灰色关联度分析(GRA)联合熵权逼近理想解排序分析法(EW-TOPSIS)综合质量评价方法。方法采用Shimadzu C 18色谱柱;乙腈-0.5%醋酸为流动相,梯度洗脱,流速1.0 mL·min-1;检测波长254和290 nm。以对甲氧基肉桂酸乙酯为内参比物质,计算其他10个成分的相对校正因子(RCF),测定各成分含量。采用GRA联合EW-TOPSIS模型对法制半夏曲进行综合质量评价。结果法制半夏曲中11种成分在一定浓度范围内线性关系良好,相关系数均>0.999;平均加样回收率96.94%~100.12%(RSD<2.0%,n=9);QAMS与外标法(ESM)实测值无明显差异。GRA模型相对关联度0.2903~0.6187,EW-TOPSIS模型相对接近度0.2114~0.6343;GRA和EW-TOPSIS模型综合评价结果基本一致。结论QAMS法便捷、准确,可用于法制半夏曲多指标成分定量控制,GRA联合EW-TOPSIS模型可用于法制半夏曲综合质量评价。

解郁安神颗粒一测多评多组分定量检测法建立及综合质量评价模型构建

目的建立一测多评(QAMS)法同时测定解郁安神颗粒中13种成分含量,并构建其综合质量评价模型。方法以乙腈-0.1%磷酸为流动相,同时测定解郁安神颗粒中王百合苷C、王百合苷E、王百合苷B、羟异栀子苷、栀子苷、斯皮诺素、酸枣仁皂苷A、酸枣仁皂苷B、柴胡皂苷a、柴胡皂苷d、双去甲氧基姜黄素、去甲氧基姜黄素和姜黄素的含量,采用正交偏最小二乘法-判别分析(OPLS-DA)和熵权逼近理想解排序(EW-TOPSIS)法对其整体质量进行综合评价。结果高效液相色谱(HPLC)方法学验证均符合《中华人民共和国药典》要求。OPLS-DA显示栀子苷、柴胡皂苷d、王百合苷B、姜黄素、斯皮诺素和柴胡皂苷a为解郁安神颗粒质量差异的主要因子。EW-TOPSIS显示14批解郁安神颗粒最优解欧氏贴近度0.2849~0.6407。结论所建立的方法可用于解郁安神颗粒的质量控制和整体评价。

基于HPLC指纹图谱结合多元统计分析九制女贞子炮制过程中成分变化

目的建立3个不同批次九制女贞子样品的高效液相色谱(HPLC)指纹图谱及多成分含量测定方法,结合化学模式识别分析评价九制女贞子的质量差异。方法采用HPLC法建立不同批次九制女贞子的指纹图谱并进行5种成分的含量测定,通过相似度分析、主成分分析(PCA)和最小偏二乘法-判别分析(PLS-DA)评价不同批次九制女贞子质量差异,找寻炮制过程中成分含量的动态变化情况。结果建立了九制女贞子的HPLC指纹图谱,标定了26个共有峰,指认了其中5个成分,分别是羟基酪醇(峰9)、红景天苷(峰10)、特女贞苷(峰19)、女贞苷G13(峰24)、Oleonuezhenide(峰25),含量变化明显。方法学考察结果显示,各成分的线性关系良好(r≥0.990),平均回收率为99.90%~103.19%。27批样品的指纹图谱与对照指纹图谱相似度均>0.953。PCA结果提取了4个主成分,PLS-DA能将3批不同批次九制女贞子明显区分,并根据变量重要性投影值(VIP)>1的原则筛选出了7个主要差异成分,并指认了Oleonuezhenide、女贞苷G13、特女贞苷这3个是与九制女贞子相关性较强的化学成分。不同批次之间九制女贞子质量差异较大。结论建立的九制女贞子HPLC指纹图谱方法简便,与模式识别方法相结合可为九制女贞子药材质量评价提供参考,炮制过程中含量呈现动态变化,羟基酪醇整体呈现不变趋势,红景天苷整体呈现增加趋势、特女贞苷、女贞苷G13、Oleonuezhenide整体呈现减少趋势,在炮制过程中,特女贞苷、女贞苷G13、Oleonuezhenide发生了转化,但具体转化机制有待后续研究发现,九制女贞子的指纹图谱结合化学模式识别方法,不仅为九制女贞子质量提供参考也可继续深入探讨九制女贞子潜在的质量标志物。

基于结构相似度和鲁棒主成分分析的运动目标检测

运动目标传统检测方法只考虑图像的亮度或纹理等某一种特性,受特异值影响较大,对噪声比较敏感,鲁棒性也不够好,而且背景恢复精度不高。针对以上局限性,提出一种融合结构相似度(structural similarity,SSIM)全参考模型和鲁棒主成分分析(robust principal component analysis,RPCA)的运动目标检测方法。此方法综合考虑图像的亮度、对比度和结构三种特性,不采用传统的背景减除法,而是把图像像素点的结构相似度作为度量来实现运动对象与背景的分离。实验结果表明,此方法准确率可达0.95,且F度量较传统运动目标检测算法平均提升0.15,总体上比传统方法更具优势。

海上三相重力分离器晃荡试验研究

海上浮式生产储卸油装置FPSO摇摆导致油气水三相重力分离器液面发生晃荡,减弱了油水分离效果,在分离器内布置防晃板可抑制晃荡,但防晃板间距的确定目前尚无明确设计方法。为此,基于相似性理论,通过1∶9模型分离器试验,研究了防晃板及内构件对分离器晃荡的抑制与影响过程。研究结果表明:防晃板、聚结板、均流板、堰板等内构件之间的间距发生变化时,可削弱FPSO外部激励形成的界面共振;油水界面与外部激励之间的共振是分离器内部液体晃荡主要形式;各种开孔结构的内构件与聚结板可削弱界面晃荡的振幅;聚结板、均流板、防晃板和堰板之间液体区域界面固有周期可用基于线性理论的圆筒形容器计算公式估算。研究结果可为海上生产现场分离器的防晃设计提供技术参考。

不同综合评价法对大豆综合农艺性状的分析及比较研究

为科学合理地评价大豆综合农艺性状,采用DTOPSIS法、灰色关联度分析法、模糊评价法、同异分析法和主成分分析法5种常用综合评价法对2020年河南省夏大豆区域试验的14个品种进行综合分析,比较不同方法在大豆农艺性状综合评价方面的优劣。结果表明:5种分析方法计算出的参试品种综合得分之间存在极显著正相关关系,其中DTOPSIS法对品种综合性状优劣的区分度最好,其次为灰色关联度法、同异分析法、主成分分析法和模糊函数法;同异分析法对综合性状的评价准确度最高,其次为模糊函数法、灰色关联度法、主成分分析和DTOPSIS法;5种分析方法的综合得分与产量的灰色关联度最大的为灰色关联度法,其次为DTOPSIS法、同异分析法、模糊函数法和主成分分析。综上,灰色关联度分析法对大量大豆材料农艺性状的综合评价具有较高的准确度和区分度,并且分析结果与产量联系密切,能够为大豆品系鉴定和筛选提供有效的决策参考。

槲寄生UPLC指纹图谱研究

目的:建立槲寄生超高效液相色谱(ultra performance liquid chromatography,UPLC)指纹图谱并进行相似度评价,结合聚类分析(cluster analysis,CA)和主成分分析(principal component analysis,PCA)化学计量学分析方法,为槲寄生药材质量一致性评价提供参考。方法:色谱柱为Waters ACQUITY UPLC HSS T3(2.1×100 mm,1.8μm);流动相为乙腈(A)-0.5%乙酸水(B),梯度洗脱;检测波长254 nm;柱温30℃;进样量3μL。采用《中药色谱指纹图谱相似度评价系统软件(2012版)》建立槲寄生指纹图谱,标定其共有峰,并进行相似度评价;采用SPSS 26.0对14批不同产地的槲寄生进行聚类分析和主成分分析。结果:槲寄生指纹图谱的方法学考察结果良好,确定了14个共有峰,通过与对照品比对,指认了其中4号峰为紫丁香苷、9号峰为高圣草素-7-O-β-D-葡萄糖苷。相似度评价结果显示,11批样品的相似度在0.950以上,其余3批相似度小于0.950;通过聚类分析将样品聚为3类,S5单独为一类,S12,S7,S9为一类,其余样品聚为一类;主成分分析得到的4个主成分因子的累计方差贡献率为88.732%,其中S5、S10、S3、S11样品的主成分因子在综合得分位于前四位,整体质量良好。结论:该研究所建立的指纹图谱方法分离度、精密度、稳定性良好,分析时间短,并且结合相似度评价、聚类分析和主成分分析,为槲寄生药材的质量控制提供理论基础。

基于多距离融合的场次降雨时空相似性比较

【目的】降雨相似性分析是一种用于比较和评估不同降雨事件之间相似性的一种方法,可用于降雨径流过程的预测。针对降雨时空分布特征,以北京市中心城区2008—2021年为数据样本,提出了一种基于多距离融合的场次降雨时空相似性比较方法。【方法】首先通过设置雨量占比阈值,进行降雨场次划分,共划分位于汛期(6—9月)降雨225场。随后提取降雨量、降雨历时、降雨强度、降雨中心范围等特征要素,并计算3个方面的降雨特征距离:降雨要素距离、降雨中心距离、降雨总量距离。同时为了更好综合特征距离,采用主成分分析方法进行距离融合计算权重,得出最终的距离,并根据计算结果进行相似度排序。【结果】通过对33号和120号两场降雨的比较,从降雨量分布图、降雨中心范围图及降雨特征要素的直观对比,展示了较高的相似度,经过计算的综合相似度为78.46%。【结论】结果表明:该方法综合考虑了降雨的强度、空间范围和降雨总量等方面的差异,能够提供准确可靠的场次降雨相似性分析结果,并为城市洪涝预警和灾害防治提供有益工具。

三维荧光结合区域积分鉴别酸枣仁及其掺伪品

目的:研究建立酸枣仁三维荧光光谱鉴别方法,为酸枣仁真伪鉴别提供依据。方法:建立6批不同产地酸枣仁三维荧光光谱,并利用三维荧光技术对2批酸枣仁伪品、3批掺伪品鉴别分析,采用荧光区域积分法对不同产地酸枣仁、酸枣仁伪品及掺伪品三维荧光图谱进行区域积分,将区域积分值进行相似度评价、聚类分析和主成分分析。结果:相似度结果显示,不同产地酸枣仁三维荧光图谱相似性均为1,相似性极高;聚类结果与主成分分析结果一致,明确将样品分为3类,均能通过区域积分值实现酸枣仁正品、伪品、掺伪品的区分。结论:利用三维荧光技术可以对不同产地酸枣仁质量进行一致性评价,实现酸枣仁真伪的快速鉴别,为酸枣仁的质量评价提供参考。

汾河流域水文相似度时空特征分析

水文相似度是度量两流域相似程度的指标,常用于相似流域的识别和选择,传统研究通常只对流域间是否具有相似性进行判别,而较少关注流域水文相似度的时空特征。为探究汾河流域水文相似度的时空变化特征,根据流域水文特征相似理论,以年、月、日不同气象要素设置计算时间尺度,按汾河嵌套一、二、三级不同河流等级设置子流域尺度,对研究区内5种气象要素、17种下垫面指标进行主成分分析,最终建立以平均年降水量、平均年气温、地形湿度指数、表土PH、平均高程和地表粗糙度为特征指标的汾河流域水文相似度评价体系,并采用变异系数法确定流域水文相似权重系数,对汾河干、支流流域的水文相似度时空特征进行定量研究。结果表明:①年、月、日尺度下,汾河嵌套一级流域相对于汾河干流流域的水文相似度均大于0.750。3种时间尺度下,樊王河干流相对于汾河流域的水文相似度均为最高,依次为0.908、0.927、0.910;年尺度下,大川河干流相对于汾河流域的水文相似度最低,为0.773;月尺度下,昌源河相对于汾河流域的水文相似度最低,为0.818;日尺度下,中马坊河相对于汾河流域的水文相似度最低,为0.791。②在不同子流域尺度下,水文相似度随汾河嵌套支流流域级数的降低呈现逐渐减小的特征。岚河、昌源河、文峪河和樊王河一至三级支流相对于汾河流域的水文相似度依次为0.845、0.814、0.736、0.800、0.891、0.794、0.811、0.772、0.722、0.908、0.738、0.725。③水文相似度与特征指标呈正相关,地形湿度指数、表土PH与水文相似度回归方程的决定系数分别为0.5733和0.8946,分别呈现显著和高度相关关系,其余特征指标与水文相似度呈弱相关关系。研究成果对汾河流域无资料地区水文预报和参数移植具有重要意义。