A new strategy for Phase I analysis in SPC

The Phase I analysis in statistical process control usually includes a task of filtering out out‐of‐control data in the historical data set via control charting. The conventional procedure for this is an iterative procedure that first uses all the samples to set up initial trial control limits and discards all the ‘out‐of‐control’ samples accordingly, and then iteratively repeats the screening step on the remaining samples until no more ‘out‐of‐control’ samples are detected. For simplicity, the ‘out‐of‐control’ samples here refer to the samples with their monitoring statistics exceeding the trial control limits. It is found in this study that this procedure throws away too many useful in‐control samples. To overcome this drawback, we propose and study a new iterative procedure that discards only one ‘out‐of‐control’ sample (i.e. the most extreme one) at each iteration. Our simulation study, using the Shewhart X Chart for illustration, demonstrates that the new one‐at‐a‐time procedure reduces dramatically the occurrences of false alarms. For cost‐saving, we further suggest a new strategy on when to stop and inspect the process to look for assignable causes for samples signaling out‐of‐control alarms. To determine the control limits, both the traditional method that controls the individual false‐alarm‐rate and the Bonferroni method that controls the overall false‐alarm‐rate are considered. The performances of the proposed schemes are evaluated and compared in terms of the false‐alarm rate and the detecting power via simulation studies. Copyright © 2009 John Wiley & Sons, Ltd.     

Statistical process monitoring using an empirical Bayes multivariate process control chart

In this paper, we describe the theory underlying an empirical Bayesian approach to monitoring two or more process characteristics simultaneously. If the data is continuous and multivariate in nature, often the multivariate normal distribution can be used to model the process. Then, using Bayesian theory, we develop techniques to implement empirical Bayes process monitoring of the multivariable process. Lastly, an example is given to illustrate the use of our techniques. Copyright © 2001 John Wiley & Sons, Ltd.     

Impact of battery weight and charging patterns on the economic and environmental benefits of plug-in hybrid vehicles

Plug-in hybrid electric vehicle (PHEV) technology is receiving attention as an approach to reducing US dependency on foreign oil and greenhouse gas (GHG) emissions from the transportation sector. PHEVs require large batteries for energy storage, which affect vehicle cost, weight, and performance. We construct PHEV simulation models to account for the effects of additional batteries on fuel consumption, cost, and GHG emissions over a range of charging frequencies (distance traveled between charges). We find that when charged frequently, every 20 miles or less, using average US electricity, small-capacity PHEVs are less expensive and release fewer GHGs than hybrid electric vehicles (HEVs) or conventional vehicles. For moderate charging intervals of 20–100 miles, PHEVs release fewer GHGs, but HEVs have lower lifetime costs. High fuel prices, low-cost batteries, or high carbon taxes combined with low-carbon electricity generation would make small-capacity PHEVs cost competitive for a wide range of drivers. In contrast, increased battery specific energy or carbon taxes without decarbonization of the electricity grid would have limited impact. Large-capacity PHEVs sized for 40 or more miles of electric-only travel do not offer the lowest lifetime cost in any scenario, although they could minimize GHG emissions for some drivers and provide potential to shift air pollutant emissions away from population centers. The tradeoffs identified in this analysis can provide a space for vehicle manufacturers, policymakers, and the public to identify optimal decisions for PHEV design, policy and use. Given the alignment of economic, environmental, and national security objectives, policies aimed at putting PHEVs on the road will likely be most effective if they focus on adoption of small-capacity PHEVs by urban drivers who can charge frequently.     

Highly stable strained layer leaky-mode diode laser arrays

A simple fabrication process for InGaAs strained quantum well leaky-mode laser arrays is demonstrated. The arrays are ten-element devices grown by two-step metal-organic chemical vapor deposition. The structure consists of a strained quantum well InGaAs graded index-separate confinement active region and a thin (0.12 μm), transparent GaAs waveguide region. The near-field pattern typical of leaky-mode phase-locked arrays was measured. Fundamental mode oscillation was observed up to 2 A (threshold was as low as 175 mA). The authors observed a 1 μs pulsed optical output power of 172 mW per facet and a far-field angle (full width at half maximum) of 1.6 times the diffraction limit at 1 A. This is the first reported operation of a strained quantum well leaky-mode laser utilizing a built-in index step     

p53 codon 72 polymorphism in Taiwanese lung cancer patients: association with lung cancer susceptibility and prognosis

Previous studies have indicated that milrinone, a specific type III phosphodiesterase inhibitor, may be able to induce chloride secretion in cystic fibrosis (CF) tissues. We have now assessed the effect of this agent in vivo on the nasal epithelium of CF mutant mice and also in the nose and lungs of human subjects with CF. Wild-type mice showed a small hyperpolarization of the nasal potential difference (PD) in response to milrinone (100 microM, 1.6 +/- 0.6 mV, n = 8, P < 0.05). In contrast, CF mice carrying either the most common human mutation of the gene for the CF transmembrane regulator (CFTR), DeltaF508 (protein mislocalized), or the G551D mutation (protein normally localized) failed to demonstrate this response. Milrinone perfused alone had no significant effect on the baseline nasal PD of human subjects without CF (14.7 +/- 4.0 mV preperfusion; 15.3 +/- 4.6 mV postperfusion), but significantly (P < 0.05) augmented the hyperpolarization induced by a subsequently perfused low-chloride solution (with milrinone, 36.8 +/- 3.0 mV, n = 6; without milrinone, 18.1 +/- 2.2 mV, n = 19). In contrast, in human subjects with CF (n = 6), milrinone alone significantly (P < 0. 05) altered the nasal baseline PD (52.2 +/- 3.3 mV preperfusion; 57. 4 +/- 4.2 mV, postperfusion) but not the subsequent responses to the low-chloride solution (with milrinone, 1.1 +/- 2.2 mV, n = 4; without milrinone, 0.6 +/- 0.5 mV, n = 28) or to isoproterenol (100 microM). In a separate study in subjects (n = 6) with the DeltaF508 mutation, nasal coadministration of milrinone with isoproterenol produced no effect in the presence of amiloride and a low-chloride solution (-0.8 +/- 0.5 mV). This was also the case in the nasal epithelium of CF subjects (n = 4) carrying at least one G551D allele (-0.3 +/- 0.8 mV). Similarly, milrinone did not hyperpolarize the PD of either the tracheal (n = 6) or segmental (n = 6) airways of CF subjects (DeltaF508) when applied topically in vivo in the presence of amiloride, isoproterenol, or adenosine triphosphate (all 100 microM) in a low-chloride solution. These data do not support the use of milrinone to induce chloride secretion in CF airways in vivo.     

Decomposition of singular large sparse matrix by adding dummy links and dummy degrees

Abstract

This paper proposes a simple scheme to decompose an n×n nonpositive definite matrix, A, associated with simultaneous equations, A X = B, into a triple‐factors (lower triangular, diagonal, and upper triangular matrices), i.e., Å = L D U, without interchanging rows or columns of A, but with A expanded with new rows and new columns to an m×m matrix Å. Whenever a near‐zero diagonal element, say ā_ii , is encountered and used as a pivoting element, an appropriate positive real number, say p, is added to this diagonal element, and a new term —px_k is also added to the i‐th equation, where x_k is a new variable called “dummy variable'’. If we also add a new equation —px_i + px_k = 0 to enforce the new added variable x_k equal to x_i then the modified i‐th equation has the same effect as the original equation. Therefore, the original solution X can be found directly from the expanded solution of the modified expanded equation. The method is very useful in solving the following problems: (1) nonlinear problems near the limit state, (2) postbuckling analysis, (3) system equations with constraint conditions, and (4) getting eigenvectors from eigenvalues.