J. Bert Keats

Integrating Statistical Process Control and Engineering Process Control

Statistical process control (SPC) is traditionally applied to processes that vary about a fixed mean, and where successive observations are viewed as statistically independent. Engineering process control (EPC) is usually applied to processes in which ..

D-Optimal Sequential Experiments for Generating a Simulation-Based Cycle Time-Throughput Curve

A cycle time-throughput curve quantifies the relationship of average cycle time to throughput rates in a manufacturing system. Moreover, it indicates the asymptotic capacity of a system. Such a curve is used to characterize system performance over a range of start rates. Simulation is a fundamental method for generating such curves since simulation can handle the complexity of real systems with acceptable precision and accuracy. A simulation-based cycle time-throughput curve requires a large amount of simulation output data; the precision and accuracy of a simulated curve may be poor if there is insufficient simulation data. To overcome these problems, sequential simulation experiments based on a nonlinear D-optimal design are suggested. Using the nonlinear shape of the curve, such a design pinpointsp starting design points, and then sequentially ranks the remainingn --p candidate design points, wheren is the total number of possible design points being considered. A model of a semiconductor wafer fabrication facility is used to validate the approach. The sequences of experimental runs generated can be used as references for simulation experimenters.

Robustness of the time between events CUSUM

Many companies have set Parts per Million (PPM) or Parts per Million Opportunities (PPMO) goals in their quest for continuous improvement. The time-between-events (TBE) CUSUM has been suggested for monitoring the number of good units or the number of opportunities that occurred between discoveries of consecutive bad units. We focus on the robustness of the TBE CUSUM. Robustness, in this case, refers to sensitivity of the procedure to make the proper decisions regarding a shift in the mean defect rate when, in fact, the time between events is not exponential. We examine and report average run lengths (ARLs) under both a Weibull and a lognormal time between events distribution. Our results indicate that the TBE CUSUM is extremely robust for a wide variety of parameter values for both the Weibull and lognormal distributions. The implications of these results in practice imply that users of the TBE CUSUM procedure need not be concerned about departures from the exponential TBE distribution. Practical implementation of the TBE CUSUM procedure is also discussed.

Screening stochastic Life Cycle assessment inventory models

A screening methodology is presented that utilizes the linear structure within the deterministic life cycle inventory (LCI) model. The methodology ranks each input data element based upon the amount it contributes toward the final output. The identified data elements along with their position in the deterministic model are then sorted into descending order based upon their individual contributions. This enables practitioners and model users to identify those input data elements that contribute the most in the inventory stage. Percentages of the top ranked data elements are then selected, and their corresponding data quality index (DQI) value is upgraded in the stochastic LCI model. Monte Carlo computer simulations are obtained and used to compare the output variance of the original stochastic model with modified stochastic model. The methodology is applied to four real-world beverage delivery system LCA inventory models for verification. This research assists LCA practitioners by streamlining the conversion process when converting a deterministic LCI model to a stochastic model form. Model users and decision-makers can benefit from the reduction in output variance and the increase in ability to discriminate between product system alternatives.

Combining SPC and EPC in a Hybrid Industry

Integration of statistical process control (SPC) and engineering process control (EPC) is finding wide recognition and is successfully used in continuous process industries. However, application of this technique to parts or hybrid industries involving ..

COST OF SOFTWARE QUALITY: A MEANS OF PROMOTING SOFTWARE PROCESS IMPROVEMENT

Cost of quality (COQ) is well understood conceptually and quantitatively in manufacturing and service industries. In software production, however, this concept has only recently been applied. This article explores COQ as applied to software and as publi..

POISSON CUSLTM VERSUS c CHART FOR DEFECT DATA

The Poisson CUSUM and the c chart are compared with respect to average run length properties and in use through an example. Important properties of the Poisson CUSUM are given. The Poisson CUSUM is recommended for use rather than the c chart when attrib..

Using statistically designed experiments for process development and improvement: an application in electronics manufacturing

Abstract The last 20 years have seen important advances on statistical experimental design. These advances have been both in methodology and in the scope of applications. Of particular interest is the application of designed experiments for process and product design, development and improvement. We present a three-phase methodology for process development and improvement based on statistically designed experiments, along with a comprehensive example for a surface mount technology process in the electronics industry.

Improving the performance of the multivariate exponentially weighted moving average control chart

Multivariate statistical process control (SPC) procedures are useful in cases where several process variables are monitored simultaneously. A significant disadvantage of these techniques is that the time required to detect a process shift increases with the number of variables being monitored. We show how the shift detection capability of one popular multivariate SPC scheme, the multivariate analogue of the exponentially weighted moving average control chart, can be significantly improved by transforming the original process variables to a lower-dimensional subspace through the use of a U-transformation.

ARLS AND HIGHER-ORDER RUN-LENGTH MOMENTS FOR THE POISSON CUSUM

We present a Microsoft Quick BASIC program which uses the Markov chain approach to calculate average run length (ARL) values for a Poisson CUSUM control scheme. Using a recursive formula, the progr...