On the Use of the Expected ARL Metric for Control Charts Based on Estimated Parameters

At the origination of the Shewhart control chart, it was assumed that the process parameters were known. The in‐control Average Run Length (ARL) and the probability of having a false alarm (P) were introduced as metrics to indicate the in‐control performance. These two metrics are related when the process data are i.i.d. normally distributed: the ARL equals 1/P. When the process parameters are unknown and have to be estimated, a similar relation holds for each estimated control chart, but the relation between the expected ARL (the average of the ARLs of all possible estimated charts) and the expectedP is different. Control charts based on estimates are often designed such that the in‐control ARL equals a predefined value. This paper shows that the expected in‐control ARL is a less suitable design criterion. Copyright © 2016 John Wiley & Sons, Ltd.     

The performance of control charts for large non‐normally distributed datasets

Because of digitalization, many organizations possess large datasets. Furthermore, measurement data are often not normally distributed. However, when samples are sufficiently large, the central limit theorem may be used for the sample means. In this article, we evaluate the use of the central limit theorem for various distributions and sample sizes, as well as its effects on the performance of a Shewhart control chart for these large non‐normally distributed datasets. To this end, we use the sample means as individual observations and a Shewhart control chart for individual observations to monitor processes. We study the unconditional performance, expressed as the expectation of the in‐control average run length (ARL), as well as the conditional performance, expressed as the probability that the control chart based on estimated parameters will have a lower in‐control ARL than a specified desired in‐control ARL. We use recently developed factors to correct the control limits to obtain a specified conditional or unconditional in‐control performance. The results in this paper indicate that the control chart should be applied with caution, even with large sample sizes.     

Quality criteria of powder coated HDG steel in corrosive environment

The performance of powder coatings on hot-dip galvanized steel has been studied by testing in 5 years field exposure in marine and industrial atmospheres, as well as in accelerated tests. The aim was to assess the quality of such coating systems in corrosive environments and to establish criteria for how to obtain good quality. The test data demonstrates that polyester powder coatings are a good alternative to wet paint as top coat on hot-dip galvanized steel. The phosphate layer is identified as the most crucial step to ensure high quality. Recommendations for how to obtain good quality are provided.     

Evaluating distance-based clustering for user (browse and click) sessions in a domain-specific collection

We seek to improve information retrieval in a domain-specific collection by clustering user sessions from a click log and then classifying later user sessions in real time. As a preliminary step, we explore the main assumption of this approach: whether user sessions in such a site are related to the question that they are answering. Since a large class of machine learning algorithms use a distance measure at the core, we evaluate the suitability of common machine learning distance measures to distinguish sessions of users searching for the answer to same or different questions. We found that two distance measures work very well for our task and three others do not. As a further step, we then investigate how effective the distance measures are when used in clustering. For our dataset, we conducted a user study where we had multiple users answer the same set of questions. This data, grouped by question, was used as our gold standard for evaluating the clusters produced by the clustering algorithms. We found that the observed difference between the two classes of distance measures affected the quality of the clusterings, as expected. We also found that one of the two distance measures that worked well to differentiate sessions, worked significantly better than the other when clustering. Finally, we discuss why some distance metrics performed better than others in the two parts of our work.     

Stability of SrFeO3 based materials in the presence of SiOx species in humid atmosphere at high temperatures and pressures

Strontium silicate was found on the surface of La_0.2Sr_0.8Fe_0.79Cr_0.2Mg_0.01O₃ exposed to hydrogen containing humid atmospheres at 1000 °C and 30 bars. Silica originated from the furnace tube material and was transported via the gas phase as a gaseous silica hydrate. Fe and Sr were initially preferentially expelled from the perovskite grain boundaries to give Sr₂SiO₄ at the surface, along with a secondary Fe-rich phase and a LaCrO₃-rich grain boundary region. Eventually, Fe and Sr were drawn from the grains, leaving a porous structure. This investigation highlights the importance of avoiding Si sources near Sr-rich membranes in humid atmospheres at high temperatures.     

Stability of SrFeO3-Based Materials in H2O/CO2-Containing Atmospheres at High Temperatures and Pressures

The chemical stability of SrFeO₃-based perovskites in H₂O- and CO₂-containing atmospheres at high temperatures and pressures has been examined. The extent of reaction as a function of p CO₂, p H₂O, temperature, and time has been determined. Either strontium carbonate or Sr(OH)₂·H₂O was observed on sample surfaces after exposure. Observation of two different reaction-rate behaviors could be explained by the formation of different products. The stability of the perovskite has been found to increase when the activity of Sr is decreased. Chemical stability in H₂O/CO₂ is important to understand in order to use these membrane materials for syngas production.     

Protein content in aqueous humor from patients with pseudoexfoliation (PEX) investigated by capillary LC MALDI‐TOF/TOF MS

Analysis of proteins in human body fluids is challenging since the composition of the sample often is rather complex. Here we present a method for analysis of proteins in aqueous humor from two groups of cataract patients, with and without pseudoexfoliation (PEX). Aqueous humor is an extracellular fluid contained in the anterior chamber of the eye between the cornea and iris. The limited volume of sample requires sophisticated analysis techniques. Our method is based on a total tryptic digestion of the sample followed by capillary LC‐MALDI MS and MS/MS analysis of the peptides. The method is rapid, efficient and suitable as a complement or alternative to more commonly used methods based on gel electrophoretic experiments. With this method we found and unambiguously identified 30 nonredundant proteins. Proteins found include general transport proteins such as albumin and apolipoprotein A1 but also specific proteins involved in immune response, such as complement factors. Cystatin C, clusterin, and crystallins were also found. Although the number of proteins was roughly the same in both groups there was a significant difference in their identities. These findings may give some new insights into the pathophysiology of the PEX syndrome.     

Prediction of optimal CO2 emitter capacity developed for modified atmosphere packaging of fresh salmon fillets (Salmo salar L.)

Pieces of pre‐rigor filleted Atlantic salmon were modified atmosphere (MA)‐packaged (60% CO₂ and 40% N₂) in eight different ways according to tray sizes (ml), gas/product ratios (g/p ratios), number of fillet layers and capacities of the CO₂ emitters being used (based on the fish weight or on the surface area of the fish). All the samples were stored at 2°C for 21 days. Gas measurement showed that the CO₂ emitter based on fish weight developed too much CO₂, and the emitters based on surface area developed too less during storage. Samples with the lowest CO₂ level in the headspace (emitter based on surface area), and also probably the lowest amount of absorbed CO₂, had the highest bacterial growth after 17 days of storage for some of the samples. Both the pH and the bacterial growth were similar between the top layer and the bottom layer within the packages of more than one layer in each tray. This indicates that the CO₂ was also available for the bottom layers. The liquid loss was similar for the trays with the different emitter types, but it differed between the tray sizes. A model based on the weight and surface area of the fish, and g/p ratio and capacity (ml) of the tray was made in order to more precisely calculate an optimal amount of the CO₂ emitter ingredients because of a predefined CO₂ level in the headspace. Copyright © 2008 John Wiley & Sons, Ltd.