Improved Principal Component Monitoring of Large-Scale Processes

This is the first paper that shows and theoretically analyses that the presence of auto-correlation can produce considerable alterations in the Type I and Type II errors in univariate and multivariate statistical control charts. To remove this undesired effect, linear inverse ARMA filter are employed and the application studies in this paper show that false alarms (increased Type I errors) and an insensitive monitoring statistics (increased Type II errors) were eliminated.

Kv1.5 is a major component underlying the A-type potassium current in retinal arteriolar smooth muscle.

Little is known about the molecular characteristics of the voltage-activated K(+) (K(v)) channels that underlie the A-type K(+) current in vascular smooth muscle cells of the systemic circulation. We investigated the molecular identity of the A-type K(+) current in retinal arteriolar myocytes using patch-clamp techniques, RT-PCR, immunohistochemistry, and neutralizing antibody studies. The A-type K(+) current was resistant to the actions of specific inhibitors for K(v)3 and K(v)4 channels but was blocked by the K(v)1 antagonist correolide. No effects were observed with pharmacological agents against K(v)1.1/2/3/6 and 7 channels, but the current was partially blocked by riluzole, a K(v)1.4 and K(v)1.5 inhibitor. The current was not altered by the removal of extracellular K(+) but was abolished by flecainide, indicative of K(v)1.5 rather than K(v)1.4 channels. Transcripts encoding K(v)1.5 and not K(v)1.4 were identified in freshly isolated retinal arterioles. Immunofluorescence labeling confirmed a lack of K(v)1.4 expression and revealed K(v)1.5 to be localized to the plasma membrane of the arteriolar smooth muscle cells. Anti-K(v)1.5 antibody applied intracellularly inhibited the A-type K(+) current, whereas anti-K(v)1.4 antibody had no effect. Co-expression of K(v)1.5 with K(v)beta1 or K(v)beta3 accessory subunits is known to transform K(v)1.5 currents from delayed rectifers into A-type currents. K(v)beta1 mRNA expression was detected in retinal arterioles, but K(v)beta3 was not observed. K(v)beta1 immunofluorescence was detected on the plasma membrane of retinal arteriolar myocytes. The findings of this study suggest that K(v)1.5, most likely co-assembled with K(v)beta1 subunits, comprises a major component underlying the A-type K(+) current in retinal arteriolar smooth muscle cells

Improved Process Monitoring Using Nonlinear Principal Component Models

This paper presents two new approaches for use in complete process monitoring. The firstconcerns the identification of nonlinear principal component models. This involves the application of linear
principal component analysis (PCA), prior to the identification of a modified autoassociative neural network (AAN) as the required nonlinear PCA (NLPCA) model. The benefits are that (i) the number of the reduced set of linear principal components (PCs) is smaller than the number of recorded process variables, and (ii) the set of PCs is better conditioned as redundant information is removed. The result is a new set of input data for a modified neural representation, referred to as a T2T network. The T2T NLPCA model is then used for complete process monitoring, involving fault detection, identification and isolation. The second approach introduces a new variable reconstruction algorithm, developed from the T2T NLPCA model. Variable reconstruction can enhance the findings of the contribution charts still widely used in industry by reconstructing the outputs from faulty sensors to produce more accurate fault isolation. These ideas are illustrated using recorded industrial data relating to developing cracks in an industrial glass melter process. A comparison of linear and nonlinear models, together with the combined use of contribution charts and variable reconstruction, is presented.