Narrow Results

In some industrial situations, the classical assumption used in the batch process monitoring that all batches have equal durations and are synchronized does not hold. A batch process is carried out in sequential phases and a significant variability generally occurs in the duration of the phases such that events signifying the beginning or the end of a phase are generally misaligned in time within the various batches. The consequence is that the variable trajectories, in the different runs of the same batch process, are unsynchronized. In this case, data analysis from process for performing the multivariate statistical process control can be difficult. In this paper, we propose several innovative methods for the off-line and on-line monitoring of batch processes with varying durations, all based on the Hausdorff distance. These methods have been successfully tested on a simulated example and on an industrial case example. The conclusion is that these methods are able to efficiently discriminate between nominal and non-nominal batches.

Inspection is widely believed to be one of the most cost-effective methods for detection of defects in the work products produced during software development. However, the inspection process, by its very nature, is labor intensive and for delivering value, they have to be properly executed and controlled. While controlling the inspection process, the inspection module size is a key control parameter. Larger module size can lead to an increased leakage of defects which increases the cost since rework in the subsequent phases is more expensive. Small module size reduces the defect leakage but increases the number of inspections. In this paper, we formulate a cost model for an inspection process using which the total cost can be minimized. We then use the technique of Design of Experiments to study how the optimum module size varies with some of the key parameters of the inspection process, and determine the optimum module size for different situations.

In the industrial setting characterized by short run processes, adaptive Bayesian control charts have been demonstrated to be an efficient means to perform the on-line process monitoring. Up to now, Bayesian charts have been implemented on manufacturing processes to monitor attribute variables and the sample mean. In this paper the Bayesian approach is extended to the control of the process data dispersion: several adaptive schemes of one-sided Bayesian charts monitoring the sample variance S² have been designed. The design of each Bayesian S² chart is performed to achieve an economic goal: the minimization of the total quality cost incurred during the production run. The quality economic performance of the Bayesian S² charts is compared with that of a static Shewhart S² chart and two other strategies which do not require sampling from the process. A comprehensive sensitivity analysis has been carried out to investigate the positive effects on costs deriving from the adoption of the different adaptive policies. Finally, some practical guidelines are suggested to help decision makers to select the best performing strategy to be employed within their own industrial environment.

This paper develops a wavelet control chart for monitoring autocorrelated processes. The procedure uses the discrete wavelet transform of the original series, and traditional control charts are applied to the stream of wavelet coefficients. Unlike other control charts for monitoring autocorrelated processes found in the literature, the wavelet control chart does not require that a model be specified for the process data. The wavelet-based control chart is simple enough that it can be easily automated. Real and simulated data are used to illustrate the effectiveness of the proposed wavelet control chart.

Availability of data in different forms is a boon or bane as it may require different approaches to deal with. In fact, while the construction of control charts is straightforward if the data are real-valued, in many practical situations data are essentially interval-valued with observations often represented by minimum and maximum values. While there are only fewer attempts to develop control charts for interval-valued data, no simple-to-use approaches have been proposed to deal with such type of data. In this paper, considering the idea of the development of control limits for multi-stream processes, we propose to make use of the mixture probability distributions approach to determine control limits for the interval-valued data. The resulting control limits are flexible in nature as they are linked to the control limits of the overall distribution that is based on the average of the means of two upper and lower populations along with their respective standard deviations. We have studied and numerically evaluated the average run length (ARL) properties of the proposed control chart to demonstrate the ways of determining the control chart coefficients. The proposed control chart is then illustrated using a dataset and conclusions are drawn based on the results.

The rapid growth of air traffic density has long demanded the Federal Aviation Administration (FAA) to design an effective safety inspection system. Well defined thresholds are essential to such an inspection system since they provide standards for both monitoring and regulating purposes. In this paper, we use control chart techniques to derive thresholds and standards for inspection measures, and to provide charts for monitoring them continuously. These thresholds charts play the same role as control charts do in statistical quality control for the monitoring of manufacturing processes. In quality control, the centerline of the chart indicates the target value and the control limits determine whether the process is out of control. In safety inspections, we view the centerline as the safety standard, and justify some properly chosen levels of control limits as meaningful thresholds. For FAA safety inspection surveillance results concerning air carriers, these thresholds are termed alert, advisory, expected, and informational. They provide a concrete measure of the inspection results in terms of the severity of potential flaws, and serve as a guideline for the general rating of the safety performance of each carrier. Furthermore, we can now use the so-called average run length to measure the effectiveness of the inspection system with the proposed thresholds. This approach is implemented on a dataset of an operational performance measure collected from ten air carriers over a period of 6 months. The results are very supportive.

In this paper we derive sequential procedures for monitoring the structure of the tangency portfolio. A new measure of the distance between the estimated weights and the weights of the holding portfolio is suggested which is used in the derivation of the control schemes. The results are applied in a situation that is practically relevant.

Monitoring processes with data collected from spatial systems is a common need in industry. This paper outlines an approach commonly used in geostatistics, namely Universal Kriging (Cressie, 1993), for modelling spatial trends. The fitted spatial models together with their standard errors are then used to establish control limits for monitoring changes in spatial trends. Also the QQ-plot and related tests are used to signal processes that are out-of-control. These methods are applied to the process of constructing concrete road pavements.