An Integrated Quality Systems Approach to Quality and Productivity Improvement in Continuous Manufacturing Processes

1986 ◽  
Vol 108 (4) ◽  
pp. 322-327 ◽  
Author(s):  
K. J. Dooley ◽  
S. G. Kapoor ◽  
M. I. Dessouky ◽  
R. E. DeVor

An integrated quality systems methodology is presented as a framework within which the concepts of process control can be used to improve quality and productivity. The process is mathematically described by stochastic time series models which statistically describe how inputs and outputs interact. Several different methods for fault identification, including autocorrelation checks of the model residuals, forecasting prediction intervals, and the cusum chart are compared in terms of relative performance. A helix cable manufacturing process is simulated and analyzed by the methodology and faults are identified and suggestions are made for process improvement. Through the simulation these time series control chart methods are shown to be much more effective than conventional methods such as Shewhart control charts.

1986 ◽  
Vol 108 (3) ◽  
pp. 219-226 ◽  
Author(s):  
B. D. Notohardjono ◽  
D. S. Ermer

This paper discusses the development of control charts for correlated and contaminated data. For illustration the charts were applied to a set of maximum principal-stress data at two locations on a blast furnace shell. The Dynamic Data System (DDS) approach was used to model the correlated data which contained several types of discrepancies. After the standard DDS models were found, control charts for the averages and variances of the model residuals were constructed for two data sets. For more effective analysis, two methods for calculating the control limits for both charts are given. With this approach, dynamic process change, such as an increase in the production rate or the wearing out of the sacrificial lining, can be detected and separated from data with collection errors from instrument malfunctions. Furthermore, the tap hole opening timing is identified from the DDS model parameters, to help verify the time series model.


Author(s):  
SANDY D. BALKIN ◽  
DENNIS K. J. LIN

Sensitizing Rules are commonly applied to Shewhart Charts to increase their effectiveness in detecting shifts in the mean that may otherwise go unnoticed by the usual "out-of-control" signals. The purpose of this paper is to demonstrate how well these rules actually perform when the data exhibit autocorrelation compared to non-correlated data. Since most control chart data are collected as time series, it is of interest to examine the performance of Shewhart's [Formula: see text] Chart using data generated from typical time series models. In this paper, measurements arising from autoregressive (AR), moving average (MA) and autoregressive moving average (ARMA) processes are examined using Shewhart Control Charts in conjunction with several sensitizing rules. The results indicate that the rules work well when there are strong autocorrelative relationships, but are not as effective in recognizing small to moderate levels of correlation. We conclude with the recommendation to practitioners that they use a more definitive measure of autocorrelation such as the Sample Autocorrelation Function correlogram to detect dependency.


2014 ◽  
Vol 31 (8) ◽  
pp. 1565-1574 ◽  
Author(s):  
Alireza Faraz ◽  
Erwin M. Saniga ◽  
Cedric Heuchenne

2021 ◽  
Vol 69 ◽  
pp. 273-289
Author(s):  
Kim Duc Tran ◽  
Qurat-Ul-Ain Khaliq ◽  
Adel Ahmadi Nadi ◽  
Thi Hien Nguyen ◽  
Kim Phuc Tran

Sign in / Sign up

Export Citation Format

Share Document