Optimization of correlated multi-response quality engineering by the upside-down normal loss function

Most of the published literature on robust design is basically concerned with a single response. However, the reality is that common industrial problems usually involve several quality characteristics, which are often correlated. Traditional approaches to multidimensional quality do not offer much information on how much better or worse a process is when finding optimal settings. Köksoy and Fan [Engineering Optimization 44 (8): 935–945] pointed out that the upside-down normal loss function provides a more reasonable risk assessment to the losses of being off-target in product engineering research. However, they only consider the single-response case. This article generalizes their idea to more than one response under possible correlations and co-movement effects of responses on the process loss. The response surface methodology has been adapted, estimating the expected multivariate upside-down normal loss function of a multidimensional system to find the optimal control factor settings of a given problem. The procedure and its merits are illustrated through an example.     

The influence of bile salts on the distribution of simvastatin in the octanol/buffer system

Abstract

Introduction: Distribution coefficient (D) is useful parameter for evaluating drugs permeability properties across biological membranes, which are of importance for drugs bioavailability. Given that bile acids are intensively studied as drug permeation-modifying and -solubilizing agents, the aim of this study was to estimate the influence of sodium salts of cholic (CA), deoxycholic (DCA) and 12-monoketocholic acids (MKC) on distribution coefficient of simvastatin (SV) (lactone [SVL] and acid form [SVA]) which is a highly lipophilic compound with extremely low water solubility and bioavailability.

Methods: LogD values of SVA and SVL with or without bile salts were measured by liquid–liquid extraction in n-octanol/buffer systems at pH 5 and 7.4. SV concentrations in aqueous phase were determined by HPLC-DAD. Chem3D Ultra program was applied for computation of physico-chemical properties of analyzed compounds and their complexes.

Results: Statistically significant decrease in both SVA and SVL logD was observed for all three studied bile salts at both selected pH. MKC exerted the most pronounced effect in the case of SVA while there were no statistically significant differences between observed bile salts for SVL. The calculated physico-chemical properties of analyzed compounds and their complexes supported experimental results.

Conclusions: Our data indicate that the addition of bile salts into the n-octanol/buffer system decreases the values of SV distribution coefficient at both studied pH values. This may be the result of the formation of hydrophilic complexes increasing the solubility of SV that could consequently impact the pharmacokinetic parameters of SV and the final drug response in patients.     

Monitoring the Ratio of Two Normal Variables Using EWMA Type Control Charts

In many fields, there is the need to monitor quality characteristics defined as the ratio of two random variables. The design and implementation of control charts directly monitoring the ratio stability is required for the continuous surveillance of these quality characteristics. In this paper, we propose two one‐sided exponentially weighted moving average (EWMA) charts with subgroups having sample size n > 1 to monitor the ratio of two normal random variables. The optimal EWMA smoothing constants, control limits, and ARLs have been computed for different values of the in‐control ratio and correlation between the variables and are shown in several figures and tables to discuss the statistical performance of the proposed one‐sided EWMA charts. Both deterministic and random shift sizes have been considered to test the two one‐sided EWMA charts' sensitivity. The obtained results show that the proposed one‐sided EWMA control charts are more sensitive to process shifts than other charts already proposed in the literature. The practical application of the proposed control schemes is discussed with an illustrative example. Copyright © 2015 John Wiley & Sons, Ltd.     

Bootstrapping Analysis of Lifetime Data with Subsampling

Because of cost and time limitations, reliability experiments frequently contain subsampling, which is a restriction on randomization. A two‐stage approach can analyze right censored Weibull distributed reliability data with subsampling. However, in implementing such a method, we found that it did not address the problems of how to perform confidence intervals of low percentiles and reduce the bias of estimates. In this paper, we present a two‐stage bootstrapping approach and an unbiasing factor approach to solve the aforementioned problems. An example is provided to illustrate the proposed method. In addition, the proposed method is compared with existing methods through simulation. The resulting simulations show that the proposed method performs well in low percentiles. Copyright © 2015 John Wiley & Sons, Ltd.     

On the Modelling and Monitoring of General Inflated Poisson Processes

In this work, we propose and study general inflated probability distributions that can be used for modelling and monitoring unusual count data. The considered models extend the well‐known zero‐inflated Poisson distribution because they allow the excess of values, other than zero. Four simple upper‐sided control schemes are considered for the monitoring of count data based on the proposed general inflated Poisson distributions, and their performance is evaluated under various out‐of‐control situations. The usefulness of the considered models and techniques is illustrated via two real‐data examples, while practical guidelines are provided as well. Copyright © 2015 John Wiley & Sons, Ltd.     

Effective Control Charts for Monitoring the NGINAR(1) Process

In recent years, there has been a growing interest in the control of autocorrelated count data. Existing results focus on the Poisson integer‐valued autoregressive (INAR) process, but this process cannot deal with overdispersion (variance is greater than mean), which is a common phenomenon in count data. We propose to control the autocorrelated count data based on a new geometric INAR (NGINAR) process, which is an alternative to the Poisson one. In this paper, we use the combined jumps chart, the cumulative sum chart, and the combined exponentially weighted moving average chart to detect the shift of parameters in the process. We compare the performance of these charts for the case of an underlying NGINAR(1) process in terms of the average run lengths. One real example is presented to demonstrate good performances of the charts. Copyright © 2015 John Wiley & Sons, Ltd.     

On the Efficiency of Runs Rules Schemes for Process Monitoring

There are two main types of variations, namely, common and special causes leading to in‐control and out‐of‐control states, respectively. Control charts are popular tools used to differentiate between these two states of a process. Implementation of runs rules schemes with control charts is an attractive approach for process monitoring. This study is designed to describe the methodology of runs rules schemes and discuss their implementation for different types of control charts. We have considered memory‐less charts, namely, , S, and R charts for our study purposes. It is examined that the efficiency gain depends on the number of decision points utilized to implement a given rule. Moreover, superiority of runs rules schemes may vary for different types of location and dispersion charts. An application example using a dataset is also included in the study for practical considerations. Copyright © 2015 John Wiley & Sons, Ltd.     

Control Charts for the Lognormal Mean

Among a set of tools that form the core of statistical process control, statistical control charts are most commonly used for controlling, monitoring, and improving processes. The conventional control charts are based on the assumption that the distribution of the quality characteristic to be monitored follows the normal distribution. However, in real applications, many process distributions may follow a positively skewed distribution such as the lognormal distribution. In this study, we discuss the construction of several control charts for monitoring the mean of the lognormal distribution. A real example is used to demonstrate how these charts can be applied in practice. Copyright © 2015 John Wiley & Sons, Ltd.     

Modelling and Thermal Analysis of Tray‐layered Fruits inside Ventilated Packages during Forced‐air Precooling

Ventilated packaging is widely used in the forced‐air precooling practice for horticultural produce. Fresh fruits are living organisms which are sensitive to temperature in turn related to airflow and heat transfer inside package. In this study, a transient mathematical model considering heat of respiration and evaporation is developed to predict the thermal response of tray‐layered fruits in ventilated packages during forced‐air precooling. Specifically, the heat source is combined with the energy conservation equation and loaded into numerical solution by User Defined Function (UDF). Temperature profiles of three variously distributed circular and oblong vents in three different patterns (spaced, paralleled and crossed stacking) are simulated, separately. The results show that the heat source affects fruit cooling process, and the layered fruit in paralleled stacking pattern tends to be cooled better than others. Furthermore, the results indicate that vertical oblong vent could improve the longitudinal and lateral airflow, while non‐central vent design could greatly improve the overall cooling performance. Definitely a triangular distribution of three circular vents was superior to laterally distributed centre vents with 66.5% higher uniformity and 2.5°C lower of the highest temperature. Compared with the three identical vertical oblong vent conditions, vent design with one hand hole and two side vertical oblong vents can be cooled more uniformly with an increase of 6.5%. It is revealed that vents with large major‐to‐minor axis ratio could be applied to balance airflow and ease cooling differences for a rapid but uniform cooling. Experimental validations were performed for Sim2, Sim4 and Sim6, Sim8, Sim9, and good agreement was obtained considering the five vent conditions with the error less than 3.5°C but coordinated later (within the limits of the experimental uncertainty).Thus the numerical model can be used to predict and optimize temperature distribution within precooling packages. Copyright © 2016 John Wiley & Sons, Ltd.     

对无临近点信息干涉条纹的参数估计

用广义radon变换可以从运动目标产生的干涉条纹中估计出目标的运动参数和波导不变量。但是当干涉条纹中没有出现临近点时,用此方法估计不出真实值。为了解决此问题,提出了一种新的估计方法。主要过程是先从时频图中提取出干涉条纹轨迹,再去搜索与此轨迹误差最小的最优曲线,此曲线的参数值代表目标的运动参数和波导不变量。仿真和海试结果表明,在干涉条纹无临近点信息情况下,用广义radon变换估计的参数值与真实值偏差很大,但是文中提出的方法仍能估计出较准确的结果。