基于MPCA-LSSVM的生产制造过程异常监控模型

针对PCA方法在生产过程质量异常监控中存在阈值设置过于主观、特征提取效果不高等问题,文章提出一种将多主元分析方法（MPCA）与最小二乘支持向量机算法（LSSVM）相结合的生产制造过程质量异常模式智能监控模型。首先,利用不同阈值设置方法对观测数据进行PCA特征提取。其次,将不同的主元特征作为LSSVM分类器的输入对监控模型进行训练。然后,将识别效率最高的主元特征对应的模型参数与MSVM相结合,构建出基于MPCA-LSSVM的监控模型对生产过程的质量异常模式进行识别。仿真实验表明,基于MP-CA-LSSVM识别模型的识别精度比基于传统的主元分析方法以及其他特征提取方法的监控模型有显著提高。

Multivariate Regression Analysis on Correlated Characters about Fresh Pod Yield of Fresh Edible Soybean

Objective] The alm was to survey 10 characters of 8 fresh edibIe soy-bean varieties, analyze maln Ioading factors using principal component analysis, and estabIish muItipIe regression equation on fresh pod yield. [Methods] Through princi-pal component analysis on 10 characters of 8 fresh edibIe soybean varieties, char-acters reIated to fresh pod yield of fresh edibIe soybean were cIarified. [Results] Af-ter the principal components analysis, pod weight per pIant, 100-seed weight and pod number per pIant of fresh edibIe soybean were chosen to study their reIation with the yield of fresh edibIe soybean, moreover, it was demonstrated that the reIa-tion was Iinear reIation, thus it was suitabIe for muItivariate regression analysis. Fi-nal y, the mathematical expression formuIa about fresh pod yield was estabIished. [Conclusions] There were three characters affecting fresh pod yield, nameIy, pod weight per pIant, 100-seed weight and pod number per pIant, the mathematical equation was y=816.732＋4.145X6-0.718X8-0.985X9 （X6： pod weight per pIant; X8： 100-seed weight; X9： pod number per pIant）.

Melt Index Prediction by Neural Soft-Sensor Based on Multi-Scale Analysis and Principal Component Analysis

Prediction of melt index （MI）, the most important parameter in determining the product＇s grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model with principal component analysis （PCA）, radial basis function （RBF） networks, and multi-scale analysis （MSA） is proposed to infer the MI of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, MSA is introduced to a^quire much more information and to reduce the uncertainty of the system, and RBF networks are used to characterize the nonlinearity of the process. The research results show that the proposed method provides promising prediction reliability and accuracy, and supposed to have extensive application prospects in propylene polymerization processes.

Soft sensor design for hydrodesulfurization process using support vector regression based on WT and PCA

A novel method for developing a reliable data driven soft sensor to improve the prediction accuracy of sulfur content in hydrodesulfurization(HDS) process was proposed. Therefore, an integrated approach using support vector regression(SVR) based on wavelet transform(WT) and principal component analysis(PCA) was used. Experimental data from the HDS setup were employed to validate the proposed model. The results reveal that the integrated WT-PCA with SVR model was able to increase the prediction accuracy of SVR model. Implementation of the proposed model delivers the best satisfactory predicting performance(EAARE=0.058 and R2=0.97) in comparison with SVR. The obtained results indicate that the proposed model is more reliable and more precise than the multiple linear regression(MLR), SVR and PCA-SVR.

Biomass estimation of Shorea robusta with principal component analysis of satellite data

Spatio-temporal assessment of the above ground biomass （AGB） is a cumbersome task due to the difficulties associated with the measurement of different tree parameters such as girth at breast height and height of trees. The present research was conducted in the campus of Birla Institute of Technology, Mesra, Ranchi, India, which is predomi- nantly covered by Sal （Shorea robusta C. F. Gaertn）. Two methods of regression analysis was employed to determine the potential of remote sensing parameters with the AGB measured in the field such as linear regression analysis between the AGB and the individual bands, principal components （PCs） of the bands, vegetation indices （VI）, and the PCs of the VIs respectively and multiple linear regression （MLR） analysis be- tween the AGB and all the variables in each category of data. From the linear regression analysis, it was found that only the NDVI exhibited regression coefficient value above 0.80 with the remaining parameters showing very low values. On the other hand, the MLR based analysis revealed significantly improved results as evidenced by the occurrence of very high correlation coefficient values of greater than 0.90 determined between the computed AGB from the MLR equations and field-estimated AGB thereby ascertaining their superiority in providing reliable estimates of AGB. The highest correlation coefficient of 0.99 is found with the MLR involving PCs of VIs.

Principal Component Analysis （PCA） on Multivariate Data of Lard Analysis in Cooking Oil

Discrimination of fatty acids （FAs） of lard in used cooking oil is important in halal determination. The aim of this study was to find the information related to the changes FAs of lard when frying in cooking oil. Quantitative analysis of FAs composition extracted from a series of experiments which involving frying cooking oil spiked with lard at three different parameters; concentration of spiked lard, heating temperatures and period of frying. The samples were analyzed using Gas Chromatography （GC） and Principal Components Analysis （PCA） technique. Multivariate data from chromatograms of FAs were standardized and computed using Unscrambler X10 into covariance matrix and eigenvectors correspond to Principal Components （PCs）. Results have shown that the first and second PCs contribute to the FAs mapping which can be visualized by scores and loading plots to discriminate FAs of lard in used cooking oil

Study On the Influencing Factors of Energy-Saving and Environmental Protection Industries in Shanghai

By using principal component analysis, this paper selected some appropriate influencing indicators, and constructed multiple linear regression models to predict the development of energy-saving environmental protection industry（ESEPl） in Shanghai. The Influencing Factors can be categorized into comprehensive economic factors and environmental factors, and GDP of the second industries and the total industries GDP in comprehensive economic factors have the strongest correlation, while in the environmental index factors, the total discharge of waste water has the strongest correlation. On the basis of influencing factors study, the regression model shows that by the end of 2020, the industry investment will reach 89.788 billion RMB, which proves that the development of ESEPI in Shanghai would grow continuously and dramatically.

Source Apportionment of Heavy Metals in Soils Using Multivariate Statistics and Geostatistics

The main objectives of this study were to introduce an integrated method for effectively identifying soil heavy metal pollution sources and apportioning their contributions, and apply it to a case study. The method combines the principal component analysis/absolute principal component scores (PCA/APCS) receptor model and geostatistics. The case study was conducted in an area of 31 km2 in the urban-rural transition zone of Wuhan, a metropolis of central China. 124 topsoil samples were collected for measuring the concentrations of eight heavy metal elements (Mn, Cu, Zn, Pb, Cd, Cr, Ni and Co). PCA results revealed that three major factors were responsible for soil heavy metal pollution, which were initially identified as "steel production", "agronomic input" and "coal consumption". The APCS technique, combined with multiple linear regression analysis, was then applied for source apportionment. Steel production appeared to be the main source for Ni, Co, Cd, Zn and Mn, agronomic input for Cu, and coal consumption for Pb and Cr. Geostatistical interpolation using ordinary kriging was finally used to map the spatial distributions of the contributions of pollution sources and further confirm the result interpretations. The introduced method appears to be an effective tool in soil pollution source apportionment and identification, and might provide valuable reference information for pollution control and environmental management.

PROJECTION-PURSUIT BASED PRINCIPAL COMPONENT ANALYSIS:A LARGE SAMPLE THEORY

The principal component analysis （PCA） is one of the most celebrated methods in analysing multivariate data. An effort of extending PCA is projection pursuit （PP）, a more general class of dimension-reduction techniques. However, the application of this extended procedure is often hampered by its complexity in computation and by lack of some appropriate theory. In this paper, by use of the empirical processes we established a large sample theory for the robust PP estimators of the principal components and dispersion matrix.