Kernel Generalization of Multi-Rate Probabilistic Principal Component Analysis for Fault Detection in Nonlinear Process

In practical process industries,a variety of online and offline sensors and measuring instruments have been used for process control and monitoring purposes,which indicates that the measurements coming from different sources are collected at different sampling rates.To build a complete process monitoring strategy,all these multi-rate measurements should be considered for data-based modeling and monitoring.In this paper,a novel kernel multi-rate probabilistic principal component analysis(K-MPPCA)model is proposed to extract the nonlinear correlations among different sampling rates.In the proposed model,the model parameters are calibrated using the kernel trick and the expectation-maximum(EM)algorithm.Also,the corresponding fault detection methods based on the nonlinear features are developed.Finally,a simulated nonlinear case and an actual pre-decarburization unit in the ammonia synthesis process are tested to demonstrate the efficiency of the proposed method.

FUZZY PRINCIPAL COMPONENT ANALYSIS AND ITS KERNEL-BASED MODEL

Principal Component Analysis(PCA)is one of the most important feature extraction methods,and Kernel Principal Component Analysis(KPCA)is a nonlinear extension of PCA based on kernel methods.In real world,each input data may not be fully assigned to one class and it may partially belong to other classes.Based on the theory of fuzzy sets,this paper presents Fuzzy Principal Component Analysis(FPCA)and its nonlinear extension model,i.e.,Kernel-based Fuzzy Principal Component Analysis(KFPCA).The experimental results indicate that the proposed algorithms have good performances.

Application of Particle Swarm Optimization to Fault Condition Recognition Based on Kernel Principal Component Analysis

Panicle swarm optimization （PSO） is an optimization algorithm based on the swarm intelligent principle. In this paper the modified PSO is applied to a kernel principal component analysis （ KPCA ） for an optimal kernel function parameter. We first comprehensively considered within-class scatter and between-class scatter of the sample features. Then, the fitness function of an optimized kernel function parameter is constructed, and the particle swarm optimization algorithm with adaptive acceleration （CPSO） is applied to optimizing it. It is used for gearbox condi- tion recognition, and the result is compared with the recognized results based on principal component analysis （PCA）. The results show that KPCA optimized by CPSO can effectively recognize fault conditions of the gearbox by reducing bind set-up of the kernel function parameter, and its results of fault recognition outperform those of PCA. We draw the conclusion that KPCA based on CPSO has an advantage in nonlinear feature extraction of mechanical failure, and is helpful for fault condition recognition of complicated machines.

A deep kernel method for lithofacies identification using conventional well logs

How to fit a properly nonlinear classification model from conventional well logs to lithofacies is a key problem for machine learning methods.Kernel methods(e.g.,KFD,SVM,MSVM)are effective attempts to solve this issue due to abilities of handling nonlinear features by kernel functions.Deep mining of log features indicating lithofacies still needs to be improved for kernel methods.Hence,this work employs deep neural networks to enhance the kernel principal component analysis(KPCA)method and proposes a deep kernel method(DKM)for lithofacies identification using well logs.DKM includes a feature extractor and a classifier.The feature extractor consists of a series of KPCA models arranged according to residual network structure.A gradient-free optimization method is introduced to automatically optimize parameters and structure in DKM,which can avoid complex tuning of parameters in models.To test the validation of the proposed DKM for lithofacies identification,an open-sourced dataset with seven con-ventional logs(GR,CAL,AC,DEN,CNL,LLD,and LLS)and lithofacies labels from the Daniudi Gas Field in China is used.There are eight lithofacies,namely clastic rocks(pebbly,coarse,medium,and fine sand-stone,siltstone,mudstone),coal,and carbonate rocks.The comparisons between DKM and three commonly used kernel methods(KFD,SVM,MSVM)show that(1)DKM(85.7%)outperforms SVM(77%),KFD(79.5%),and MSVM(82.8%)in accuracy of lithofacies identification;(2)DKM is about twice faster than the multi-kernel method(MSVM)with good accuracy.The blind well test in Well D13 indicates that compared with the other three methods DKM improves about 24%in accuracy,35%in precision,41%in recall,and 40%in F1 score,respectively.In general,DKM is an effective method for complex lithofacies identification.This work also discussed the optimal structure and classifier for DKM.Experimental re-sults show that(m_(1),m_(2),O)is the optimal model structure and linear svM is the optimal classifier.(m_(1),m_(2),O)means there are m KPCAs,and then m2 residual units.A workflow to determine an optimal classifier in DKM for lithofacies identification is proposed,too.

基于String Kernel和KPCA的负实例语法特征提取算法

提出通过String Kernel方法把负实例语法数据库中的负实例转化成核矩阵,再用Kernel Principal Component Analysis(KPCA)对转换的核矩阵进行特征提取,进而可将原始负实例数据库按照这些特征分成多个容量较小的特征表。通过构造负实例特征索引表设计了一个分类器,待检查的句子通过此分类器被分配到某个负实例特征表里进行匹配搜索,而此特征表的特征属性数和记录数要远远小于原始负实例数据库中的相应数目,从而大大提高了检查的速度,同时不影响语法检查的精度。通过比较测试,可看出提出的方法在保证语法检查精确度的同时有更快的速度。

Adaptive WNN aerodynamic modeling based on subset KPCA feature extraction

In order to accurately describe the dynamic characteristics of flight vehicles through aerodynamic modeling, an adaptive wavelet neural network (AWNN) aerodynamic modeling method is proposed, based on subset kernel principal components analysis (SKPCA) feature extraction. Firstly, by fuzzy C-means clustering, some samples are selected from the training sample set to constitute a sample subset. Then, the obtained samples subset is used to execute SKPCA for extracting basic features of the training samples. Finally, using the extracted basic features, the AWNN aerodynamic model is established. The experimental results show that, in 50 times repetitive modeling, the modeling ability of the method proposed is better than that of other six methods. It only needs about half the modeling time of KPCA-AWNN under a close prediction accuracy, and can easily determine the model parameters. This enables it to be effective and feasible to construct the aerodynamic modeling for flight vehicles.

Multi-response optimization of Ti-6A1-4V turning operations using Taguchi-based grey relational analysis coupled with kernel principal component analysis

Ti-6A1-4V has a wide range of applications, especially in the aerospace field;however, it is a difficultto- cut material. In order to achieve sustainable machining of Ti?6A1-4V, multiple objectives considering not only economic and technical requirements but also the environmental requirement need to be optimized simultaneously. In this work, the optimization design of process parameters such as type of inserts, feed rate, and depth of cut for Ti-6A1-4V turning under dry condition was investigated experimentally. The major performance indexes chosen to evaluate this sustainable process were radial thrust, cutting power, and coefficient of friction at the toolchip interface. Considering the nonlinearity between the various objectives, grey relational analysis (GRA) was first performed to transform these indexes into the corresponding grey relational coefficients, and then kernel principal component analysis (KPCA) was applied to extract the kernel principal components and determine the corresponding weights which showed their relative importance. Eventually, kernel grey relational grade (KGRG) was proposed as the optimization criterion to identify the optimal combination of process parameters. The results of the range analysis show that the depth of cut has the most significant effect, followed by the feed rate and type of inserts. Confirmation tests clearly show that the modified method combining GRA with KPCA outperforms the traditional GRA method with equal weights and the hybrid method based on GRA and PCA.

Kernel feature extraction methods observed from the viewpoint of generating-kernels

This paper introduces an idea of generating a kernel from an arbitrary function by embedding the training samples into the function.Based on this idea,we present two nonlinear feature extraction methods:generating kernel principal component analysis(GKPCA)and generating kernel Fisher discriminant(GKFD).These two methods are shown to be equivalent to the function-mapping-space PCA(FMS-PCA)and the function-mapping-space linear discriminant analysis(FMS-LDA)methods,respectively.This equivalence reveals that the generating kernel is actually determined by the corresponding function map.From the generating kernel point of view,we can classify the current kernel Fisher discriminant(KFD)algorithms into two categories:KPCA+LDA based algorithms and straightforward KFD(SKFD)algorithms.The KPCA+LDA based algorithms directly work on the given kernel and are not suitable for non-kernel functions,while the SKFD algorithms essentially work on the generating kernel from a given symmetric function and are therefore suitable for non-kernels as well as kernels.Finally,we outline the tensor-based feature extraction methods and discuss ways of extending tensor-based methods to their generating kernel versions.

基于双滑模的飞机燃油油量传感器故障监测方法

飞机燃油油量传感器故障监测由于输出信号的不稳定性,导致故障正确识别率低、残差监测值与标准残差间误差大,提出基于双滑模的飞机燃油油量传感器故障监测方法。以故障产生原因分析结果为基础,引入双滑膜,利用等效输出误差注入原理建立双滑膜观测器,结合李雅普诺夫矩阵关系优化双滑膜观测器测量矩阵,采集故障信息;通过小波包分解法分解采集的信息,提取特征;引入核主成分分析法,建立标准主成分信息模型,利用采集信息在主成分模型上的投影,对比传感器信息与核主成分信息的偏移,实现飞机燃油油量传感器故障监测。仿真结果表明,所提方法的故障正确识别率为100%,且残差监测值与标准残差间最大仅存在0.02的误差,该方法能够有效监测飞机燃油油量传感器故障。

时间特征与空间特征融合的轻量网络故障诊断方法

为了解决多传感器数据间存在信息交叉、特征重复,导致模型训练精度低的问题,对滚动轴承在声辐射信号下的故障诊断进行了研究,提出了一种时间特征与空间特征融合的轻量网络故障诊断(SF-TFNet)方法。首先,利用卷积神经网络提取了原始轴承声阵列信号的空间特征(SFs),使用长短时记忆网络(LSTM)提取了声阵列信号中的时域特征(TFs),并对提取的SFs和TFs进行了特征融合,生成了新的特征矩阵;然后,为了消除融合特征带来的重叠特征和信息冗余问题,引入了基于核的主成分分析(KPCA)方法对新生成的特征矩阵进行了非线性降维,去除了特征中的冗余成分,构建了滚动轴承新的时空特征数据集;最后,采用AdaBoost算法对新生成的数据集进行了故障分类,并得到了滚动轴承的最终故障诊断结果。研究结果表明:在半消声室滚动轴承故障实验台测试中,SF-TFNet方法的故障分类精度可以达到99.75%,其分类精度较高、聚类效果明显。在强背景噪声环境下与ResNet、ICNN和AlexNet三种方法进行比较,SF-TFNet方法不仅收敛速度快,而且故障识别精度高,诊断精度最高可达99.25%。为基于多通道的滚动轴承声辐射信号故障诊断提供了理论依据。

基于相关性分析和生成对抗网络的电网缺失数据填补方法

城市电网新型电力系统中多元资源增多,数据采集难度加大,导致数据随机缺失率升高,难以满足精细化分析决策需求。为解决新型电力系统中配网量测数据在采集与传输过程中频发的缺失问题,文中提出一种基于波动互相关分析(fluctuation cross-correlation analysis,FCCA)算法和生成对抗网络(generative adversarial network,GAN)的电网缺失数据填补方法。首先,融合FCCA算法提出强相关性电网数据多维特征提取方法;其次,基于核主成分分析(kernel principal component analysis,KPCA)对多维特征数据集进行降维处理;最后,设计改进型GAN结构,融合电网数据多维特征对低维向量进行重构,实现缺失数据填补。算例采用真实电网数据进行算法验证,并在某城市电网试运行。结果表明,所提方法比传统数据填补方法具有更高填补精度。因此,在新型电力系统中量测数据连续缺失和缺失量较大的情况下,融合强相关性特征进行数据填补,对提升量测数据的完整性和可用性有明显优势。

基于超声辅助的汽车微小零部件内部缺陷无损检测方法

为了更准确、全面地分析汽车微小零部件缺陷,基于超声辅助的方式,设计了内部缺陷无损检测方法。根据超声波传播反射情况及声场变化,采集微小零部件图像;通过融合边缘信息消除图像中噪声,分割图像主体并完成边缘识别,确定存在内部缺陷的区域;利用核主成分分析技术,通过降维处理方式确定缺陷区域特征,进而完成无损检测。结果表明:利用所提方法获取的零部件图像清晰,缺陷检测准确率始终高于95%,对气泡和气孔缺陷的检测时间小于6 s,对裂纹缺陷的检测时间小于8 s,说明所提方法对内部缺陷的定位准确度和识别效率均较高。

基于多域特征与信息融合的叶片裂纹故障诊断

针对离心风机叶片裂纹故障诊断问题,提出了一种基于多域特征与信息融合的叶片裂纹故障特征提取方法.首先,在时域、频域和时频域特征的基础上,针对叶片裂纹故障信号的幅值调制特点,采用一系列循环域特征,构建多域特征集.其次,使用Laplacian分数、随机森林、ReliefF算法、互信息和信息增益等多种特征选择方法对多域特征集的所有特征进行评分;然后,提出了改进的Dempster-Shafer证据理论方法,并融合多准则下的特征分数向量,得到敏感特征子集;最后,提出了基于蜉蝣算法优化的核主成分分析方法,充分利用多传感器信息,完成叶片裂纹故障敏感特征的提取,实现叶片的裂纹故障诊断.结果表明:所提方法的平均测试准确率达到99.70%,优于其他对比方法,可用于叶片裂纹的故障诊断.

GLCM Based Extraction of Flame Image Texture Features and KPCA-GLVQ Recognition Method for Rotary Kiln Combustion Working Conditions

According to the pulverized coal combustion flame image texture features of the rotary-kiln oxide pellets sintering process,a combustion working condition recognition method based on the generalized learning vector(GLVQ) neural network is proposed.Firstly,the numerical flame image is analyzed to extract texture features,such as energy,entropy and inertia,based on grey-level co-occurrence matrix(GLCM) to provide qualitative information on the changes in the visual appearance of the flame.Then the kernel principal component analysis(KPCA) method is adopted to deduct the input vector with high dimensionality so as to reduce the GLVQ target dimension and network scale greatly.Finally,the GLVQ neural network is trained by using the normalized texture feature data.The test results show that the proposed KPCA-GLVQ classifer has an excellent performance on training speed and correct recognition rate,and it meets the requirement for real-time combustion working condition recognition for the rotary kiln process.

基于KPCA和数据处理组合方法神经网络的半球谐振陀螺温度建模补偿方法

针对半球谐振陀螺(HRG)的温度建模与补偿问题,提出基于核主成分分析(KPCA)和数据处理组合方法(GMDH)神经网络的建模补偿方法.通过分析HRG的温度特性和大数据特征,初步确定网络模型的特征向量.为了去除HRG输出数据的相关性和冗余性,引入KPCA并降低特征向量维度.将特征向量代入GMDH神经网络训练,区分训练集和验证集以确定网络权值和网络结构,实现HRG温度漂移的建模与补偿.实验结果表明,单一样本预测时,所提方法预测效果明显好于传统多项式模型;多样本预测时,在4种不同训练样本下,所提方法相比传统多项式模型精度分别提升了48.5%、54.0%、56.3%、68.4%,相比GMDH模型分别提升了3.6%、5.1%、3.8%、8.8%.所提方法能够有效提高HRG在变温工况下的测量精度.

联合循环发电站电力输出预测

为了使联合循环发电站利润最大化,准确预测其满负载电力输出非常重要。联合循环发电站运行时,前一级产生的废气被用来驱动下一级热机,以此来推动发电机,其满负载电力输出受到环境温度、大气压强、相对湿度和废气气压的影响。为此,首先,采用核主成分分析(kernel principle component analysis,KPCA)对电站发电相关的特征进行特征组合降维完成特征提取;然后,采用极端梯度提升(extreme gradient boosting,XGBoost)算法进行特征重要性评分,并结合序列前向选择法(forward selection,FS)获取最优特征子集;最后,构建了KPCA-XGB-FS模型用于联合循环发电站满负载下小时电力输出预测。通过对某联合发电站的真实数据进行实验,并与使用相同数据的已有研究方法进行对比,结果表明,所提出方法能够有效对电力输出进行预测,预测结果优于已有的研究方法。

基于IPSO-SVM的动态汽车衡故障诊断方法研究

针对服役状态下,不易对轴重式动态汽车衡的灵敏度漂移等故障进行在线检测这一问题,提出了一种特征降维下结合莱维飞行改进粒子群算法优化支持向量机(IPSO-SVM)模型,以及信号特征提取与降维的动态汽车衡故障诊断方法。首先,提取了输出信号的时域与频域特征,利用核主成分分析(KPCA),将非线性映射函数输入空间变换到高维空间,实现对特征向量的降维与筛选目的;然后,利用了莱维飞行改进粒子群优化算法(PSO)的寻优能力,并采用改进后的算法对支持向量机(SVM)进行了优化,得到了最优的参数组合,以此构建了全局最优的IPSO-SVM诊断模型;最后,采用建立的诊断模型,对不同车重、不同车速、不同轴型载荷工况下的动态汽车衡进行了故障诊断验证。研究结果表明:采用该动态汽车衡故障诊断方法,其诊断准确率可达98%,证实了引入莱维飞行后的改进粒子群算法可显著改进优化的效率和效果。相比现有诊断方法,IPSO-SVM诊断模型可有效解决PSO算法易陷入局部最优解的问题,准确率得到了较大提升,可实现对汽车衡系统动态故障工况下的全类型高精度诊断。

基于iPLS-KPCA的高温燃气红外光谱特征提取方法研究

高温燃气红外光谱特征是判断燃气成分和浓度的有效途径。针对高温燃气红外辐射特性复杂、建模难度高的问题,研究了一种基于间隔偏最小二乘(interval Partial Least Squares,iPLS)和核主成分分析(Kernel Principal Component Analysis,KPCA)的特征提取算法。首先通过iPLS进行预筛选,确定具有最优预测能力的特征光谱波段,避免单个子区间建模过程中有用吸收峰信息的遗失;其次,利用KPCA降低数据维度,保留贡献率高的关键特征,降低成分预测模型的复杂度。仿真结果表明,经过iPLS-KPCA方法特征提取后,预测模型的复杂度大幅下降,且预测能力显著提升。

基于PSO-GBDT的基桩缺陷智能识别与定位

低应变反射波法是实现基桩缺陷诊断与健康评估的重要手段。然而,目前该方法检测结果的判断仍采用人工方式进行,而人工进行结果的判断又不可避免会因缺陷波形不明显等因素导致误判或判断不准确等问题。为了解决这一问题,利用梯度提升决策树(GBDT)建立低应变反射波法检测结果与桩身缺陷位置的非线性关系,实现桩身缺陷的快速识别与定位,引入粒子群优化算法(PSO)优化模型关键参数,提高模型的精度与泛化能力。此外,利用核主成分分析(KPCA)算法对低应变反射波的多域特征降维,以此降低模型训练难度。最后,通过大量实测数据验证了该模型的可行性与准确性,结果表明,该模型具备基桩缺陷的快速识别与定位的能力。