浅谈汽车塑料件用油漆色差的防治

介绍汽车塑料件用油漆产生色差的原因、检测方法和在生产过程中的防治方法。     

Comparative studies on color preference in Japan and other Asian regions,with special emphasis on the preference for white

The results of three surveys are presented. The first survey was carried out in four large cities in Japan, and the findings were analyzed by factor analysis and cluster analysis. The second survey was carried out in Seoul, Korea and Tokyo, Japan to determine color preference in the two countries, focusing on the preference for white. The last survey compared color preference in Taipei and Tokyo, also with emphasis on the preference for white. In these successive studies on color preference in Japan and other Asian cities, the subjects were mainly asked to choose from a color chart the three colors they liked most and the three they liked least, and to state the reasons for their choices. The results of Survey 1 showed that color preference could be influenced by differences in age, sex, and geographical region. Also factor analysis and cluster analysis indicated some relation between color preference and the subjects' life styles. Dual scaling analysis of the results of Surveys 2 and 3 indicated that each Asian area has unique color preference tendencies and that there are statistically significant differences in the frequency of selection of colors of certain hues and tones. However, a high preference for white was common to all areas, along with preferences for some other colors. These results thus demonstrated a common strong preference for white in three neighboring Asian areas. The reasons given for the choices suggested that besides the factors of age and sex, associative images based on environmental and cultural aspects may be an important factor influencing color preference. © 1996 John Wiley & Sons, Inc.     

MPCA在间歇反应过程故障诊断中的应用

将多方向主元分析(MPCA)理论应用到一个实际的PVC间歇反应过程的性能监测与故障诊断中。由于间歇反应的特点,数据具有多维性,应用传统的主元分析将使过程的统计建模与故障诊断难以实现。MPCA可将间歇过程的多维数据沿时间轨迹分割,使得多批次的数据可以在各时间序列轨迹上建立相应的PCA模型,从而完成对间歇过程的实时监视及故障诊断。     

基于部分DPCA的动态系统故障隔离

Principal component analysis （PCA） is a useful tool in process fault detection, but offers little support on fault isolation. In this article, structured residual with strong isolation property is introduced. Although it is easy to get the residual by transformation matrix in static process, unfortunately, it becomes hard in dynamic process under control loop. Therefore, partial dynamic PCA（PDPCA） is proposed to obtain structured residual and enhance the isolation ability of dynamic process monitoring, and a compound statistic is introduced to resolve the problem resulting from independent variables in every variable subset. Simulations on continuous stirred tank reactor （CSTR） show the effectiveness of the proposed method.     

Principal hue curves and color difference

The size of perceptual difference of colors (j, k) is scaled as d_jk by selecting a pair of Munsell grays in which the lightness difference matches in size with the color difference. Hence, d is given in terms of Munsell V. The degree of principal hue component α in a color j is scaled as ξ_α(j) by making marks on a line segment and the range of ξ_α is from 0 to 10. By plotting ξ_α(H V/C) on Munsell H‐circle, principal hue curves ξ¯_α(H V/C) are defined, where α = R, Y, G, B, V = 4–7, and C = 2–10. In this process, similar plots of NCS codes (cϕ_α) are used as references. The curves ξ¯_α(H V/C) tell us the appearance of Munsell colors (H V/C) and also enable us to predict color differences. The relationship between d_jk and ΔV = |V_j − V_k|, Δξ¯_α = |ξ¯_α(H_j V_j/C_j) − ξ¯_α(H_k V_k/C_k)| is tested in various ways, e.g., logarithmic, power, Minkowski‐type functions. The best predictor d̃ is given by a simple linear form, d̃ = a_VΔV + {d₀ + Σa_αΔξ¯_α}. For 899 pairs (j, k), 706 differing in H, C and 193 differing in H, V, C, a_V = 0.459, d₀ = 0.610, a_R = 0.199, a_Y = 0.031, a_G = 0.098, a_B = 0.136, and the root‐mean‐squares of (d_jk − d̃_jk) is 0.338 in the matched V‐unit. © 1999 John Wiley & Sons, Inc. Col Res Appl, 24, 266–279, 1999     

主成分分析法(PCA)在藻类生长影响分析中的应用

水华的发生、发展是一个相当复杂的过程,众多影响因素共同导致藻类生长、水华爆发。常用的分析工具难以分析、预测实际情况下藻类的生长。该文利用当今世界上最大型的统计与图表分析软件之一STATISTICA对2008年和2009年奥运森林公园主湖的监测数据进行主成分分析。结果表明STATISTICA软件中的主成分分析适用于藻类生长分析,并发现除了已知的藻类生长影响因素(营养盐、温度等)之外,景观湖中底泥的累积效应也应纳入分析之内。     

基于导函数层序聚类的光谱成分预测方法研究

多光谱成像技术通过增加颜色通道的维数,成功的实现了基于光谱的颜色复制。然而,由于其颜色信息维数较高,此方法在提高色度精度的同时引入了较大的计算及存储压力。为此,最常用的方法就是通过对光谱数据进行分组,并利用每组光谱数据集中的主成分向量来对各个光谱曲线进行线性表示,从而实现数据的降维处理。提出了1种新的针对光谱数据导函数曲线的聚类分析方法,并利用伪逆算法进行光谱重建;本研究采用孟塞尔光泽色卡及无光泽色卡作为实验数据集,并将提出的导函数聚类分析法与现有的主成分分析法、聚类分析法以及色相角分类法相比较,实验结果证明其颜色预测精度在色度匹配及光谱匹配方面均优于现有方法。     

Experimental determination of the laws of color harmony. Part 4: Color preference and the color harmony content

In 1956, we decided at the Budapest University of Technology and Economics to start a large‐scale experiment on color harmony. The experiments and the processing of the experimental results have been completed in 2006. These experiments, described in this article, form a study of how much are people, participating in the experiment, influenced by their own personal color preference in judging the harmony content of a composition. These experiments have utilized the results of former (1958–1969) color preference experiments and the system of color preference indexes, which were developed by the generalization of those results. Within the framework of these experiments, conducted between 1998 and 2006 there were 24 compositions, shown to the participants, at first one by one, then in pairs and at last in groups of six. They had to assess the harmony content of the compositions and award a score on a scale between 0 and 10. Each composition possessed a specific amount of harmony content according to the rules of color space, based on the Coloroid harmony threshold and verified by former experiments. In these experiments the number of elementary observations were 135 568. The people participating in the experiment were approximately equal number of men and women, from the age group between 10 and 70 years. During processing, by using the color preference numerical indexing system, we compared the results of those experiments with the color preference of a similar age group, by using color compositions, identical to the ones used in the present experiment. We have found that the sensation of the color harmony and its intensity have a strong relation to how the observers relate to colors and also their color preferences. The sensation of color harmony is also influenced by the gender and the age of the observer. © 2009 Wiley Periodicals, Inc. Col Res Appl, 34, 210–224, 2009     

基于辅助变量KNN分析的软测量建模方法

提出一种基于辅助变量最近邻（KNN）分析的软测量建模方法,该方法将KNN算法应用于辅助变量分类,根据分类结果,应用核主成分分析（KPCA）和支持向量回归机（SVR）相结合进行软测量建模。KNN分析独立于后继回归模型,却又直接影响模型结构,KPCA作为中间层,在KNN分类结果指导下提取不同类别包含辅助变量高阶信息的特征主元,然后使用SVR建立特征主元和主导变量之间的回归模型。用该方法建立粗汽油干点软测量模型,结果表明KNN-KPCA-SVR（KKS）模型的预测精度和泛化能力优于线性PLS、RBF核函数SVR和KPCA-SVM模型。     

间歇生产过程鲁棒统计监控及其应用

In order to reduce the variations of the product quality in batch processes, multivariate statistical process control methods according to multi-way principal component analysis (MPCA) or multi-way projection to latent structure (MPLS) were proposed for on-line batch process monitoring. However, they are based on the decomposition of relative covariance matrix and strongly affected by outlying observations. In this paper, in view of an efficient projection pursuit algorithm, a robust statistical batch process monitoring (RSBPM) framework, which is resistant to outliers, is proposed to reduce the high demand for modeling data. The construction of robust normal operating condition model and robust control limits are discussed in detail. It is evaluated on monitoring an industrial streptomycin fermentation process and compared with the conventional MPCA. The results show that the RSBPM framework is resistant to possible outliers and the robustness is confirmed.