International Journal of Quality Engineering and Technology http://www.inderscience.com/browse/index.php?journalID=339&year=2011&vol=2&issue=4 Inderscience Publishers Ltd en-uk International Journal of Quality Engineering and Technology 1757-2177 1757-2185 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijqet_scoverijqet.jpg http://www.inderscience.com/browse/index.php?journalID=339&year=2011&vol=2&issue=4 http://www.inderscience.com/link.php?id=43168 Robust parameter design (RPD) can be implemented in systems in which a user, through the setting of the levels of controllable factors, seeks to minimise the variability of a system response influenced by uncontrollable factors while obtaining a consistent and reliable system response over time. RPD is conducted under the assumption that the relationship between the system response and controllable and uncontrollable variables does not change over time. Since performance degradation in real-world systems will almost certainly occur; this assumption will inevitably be violated. We propose a methodology to find new levels of controllable factor settings that will be robust to moderate system degradation while remaining robust to noise variables within the system. A gradient-search algorithm is presented for this enhanced RPD analysis utilising quadratic regression. A gradient-based method to guard against system degradation in robust parameter design
Bernard Jacob Loeffelholz; Kenneth W. Bauer
International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 277 - 290
Robust parameter design (RPD) can be implemented in systems in which a user, through the setting of the levels of controllable factors, seeks to minimise the variability of a system response influenced by uncontrollable factors while obtaining a consistent and reliable system response over time. RPD is conducted under the assumption that the relationship between the system response and controllable and uncontrollable variables does not change over time. Since performance degradation in real-world systems will almost certainly occur; this assumption will inevitably be violated. We propose a methodology to find new levels of controllable factor settings that will be robust to moderate system degradation while remaining robust to noise variables within the system. A gradient-search algorithm is presented for this enhanced RPD analysis utilising quadratic regression.

]]> 10.1504/IJQET.2011.043168 International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 277 - 290 Bernard Jacob Loeffelholz; Kenneth W. Bauer Sensors Directorate, Air Force Research Laboratory (AFRL), WPAFB, OH 45433-7765, USA. ' Department of Operational Sciences, Air Force Institute of Technology, WPAFB, OH 45433-7765, USA gradient search quadratic regression robust design parameter design RPD system degradation noise variables. 2011-10-18T23:20:50-05:00 2 4 277 290 2011-10-18T23:20:50-05:00 http://www.inderscience.com/link.php?id=43169 The families of process capability indices C<SUB align=right>p<SUP align=right>u</SUP> (u, v) and C<SUB align=right>p<SUP align=right>l</SUP>(u, v) provide measurements of process performance for one-sided processes. In this work we deal with the problem of gauge measurement errors effects on the performance of these indices. We show that using a lower confidence bound without taking these errors into account, severely underestimates the true capability. In order to improve the results, we suggest using an adjusted lower confidence bound, and we give a Maple program to obtain this bound. We finally present a real study on a polymer granulates manufacturing process to illustrate how to make use of our suggestion. Lower confidence bound for capability indices with one-sided tolerance processes and measurement errors
Daniel Grau
International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 291 - 305
The families of process capability indices C<SUB align=right>p<SUP align=right>u</SUP> (u, v) and C<SUB align=right>p<SUP align=right>l</SUP>(u, v) provide measurements of process performance for one-sided processes. In this work we deal with the problem of gauge measurement errors effects on the performance of these indices. We show that using a lower confidence bound without taking these errors into account, severely underestimates the true capability. In order to improve the results, we suggest using an adjusted lower confidence bound, and we give a Maple program to obtain this bound. We finally present a real study on a polymer granulates manufacturing process to illustrate how to make use of our suggestion.

]]> 10.1504/IJQET.2011.043169 International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 291 - 305 Daniel Grau Laboratory of Applied Mathematics, CNRS UMR 5142, IUT de Bayonne, Université de Pau et des Pays de l'Adour, 17 Place Paul Bert, 64100 Bayonne, France quality technology process capability indices gauge measurement errors one-sided tolerance processes lower confidence bound polymer granulates manufacturing. 2011-10-18T23:20:50-05:00 2 4 291 305 2011-10-18T23:20:50-05:00 http://www.inderscience.com/link.php?id=43170 The desire to accelerate inspection procedures and reduce inspection costs often results in tests being curtailed. Even though every item is meant to undergo a number of independent/dependent tests, once an item, e.g., item #XXX fails to pass a test, further tests/inspections are terminated. Thus, the empirical data existing at the end of the inspection procedure does not contain information about item #XXX's ability to pass the cancelled tests. Information mining statistical tools can be used to uncover the latent quality information hidden within these data. This paper proposes altering curtailed testing procedures (e.g., changing the order of the tests or detectability levels), in order to estimate the theoretical joint probabilities (latent quality information) concerning an item's ability to pass a part of, or the entire sequence of tests. The effectiveness of the proposed procedures is then evaluated using simulated data. Revealing latent quality information hidden within inspection reports of curtailed tests
Tamar Gadrich; Emil Bashkansky
International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 306 - 327
The desire to accelerate inspection procedures and reduce inspection costs often results in tests being curtailed. Even though every item is meant to undergo a number of independent/dependent tests, once an item, e.g., item #XXX fails to pass a test, further tests/inspections are terminated. Thus, the empirical data existing at the end of the inspection procedure does not contain information about item #XXX's ability to pass the cancelled tests. Information mining statistical tools can be used to uncover the latent quality information hidden within these data. This paper proposes altering curtailed testing procedures (e.g., changing the order of the tests or detectability levels), in order to estimate the theoretical joint probabilities (latent quality information) concerning an item's ability to pass a part of, or the entire sequence of tests. The effectiveness of the proposed procedures is then evaluated using simulated data.

]]> 10.1504/IJQET.2011.043170 International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 306 - 327 Tamar Gadrich; Emil Bashkansky Department of Industrial Engineering and Management, Ort Braude College, P.O. Box 78, Karmiel, Israel. ' Department of Industrial Engineering and Management, Ort Braude College, P.O. Box 78, Karmiel, Israel quality categories latent quality information curtailed inspection information mining defects detection inspection reports test results. 2011-10-18T23:20:50-05:00 2 4 306 327 2011-10-18T23:20:50-05:00 http://www.inderscience.com/link.php?id=43171 Serially dependent multi-stage processes are monitored by cause selecting control charts based on regression models. In production processes, we come across instances where dependent stages have data modelled by the Poisson distribution. In such situations, the condition of homoscedasticity (constant variance) is not satisfied, as the process mean equals its variance. Pedagogy suggests remedying such cases by transforming a response variable with a square root transform and regressing it against independent variable(s). This work shows that transforming both the regressor and the response variable lends itself to a better regression model fit. A new power transform which is superior to the conventional square root transform has been proposed for improving the run length performance of the residuals control chart for response processes. Further, a run rule has been proposed to sensitise this control chart to enhance its average run length and detect data patterns. Monitoring Poisson data of bivariate serially dependent response process
S. Lakshminarasimhan; S.M. Kannan
International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 328 - 343
Serially dependent multi-stage processes are monitored by cause selecting control charts based on regression models. In production processes, we come across instances where dependent stages have data modelled by the Poisson distribution. In such situations, the condition of homoscedasticity (constant variance) is not satisfied, as the process mean equals its variance. Pedagogy suggests remedying such cases by transforming a response variable with a square root transform and regressing it against independent variable(s). This work shows that transforming both the regressor and the response variable lends itself to a better regression model fit. A new power transform which is superior to the conventional square root transform has been proposed for improving the run length performance of the residuals control chart for response processes. Further, a run rule has been proposed to sensitise this control chart to enhance its average run length and detect data patterns.

]]> 10.1504/IJQET.2011.043171 International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 328 - 343 S. Lakshminarasimhan; S.M. Kannan ULTRA College of Engineering and Technology for Women, Madurai, 625104, India. ' ULTRA College of Engineering and Technology for Women, Madurai, 625104, India average run length cause selecting control charts homoscedasticity power transform regression models residuals response variables run rules square root transform constant variance data patterns. 2011-10-18T23:20:50-05:00 2 4 328 343 2011-10-18T23:20:50-05:00 http://www.inderscience.com/link.php?id=43172 A new formulation to the tolerance allocation based on minimum sensitivity is given. Several synthesis methodologies are reviewed to highlight their importance in details. A brief but complete literature review is given and conclusions are drawn. Objectives such as minimum cost functions, minimum sensitivity functions and minimum variance functions are formulated and a heuristic approach is used for optimisation. An example problem is given to illustrate the concept and results indicate that there are alternatives for tolerance allocation problems. Besides, there are margins of tolerance for which the measure of objective functions are least sensitive. Least sensitive tolerance allocation
Mohamed H. Gadallah
International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 344 - 356
A new formulation to the tolerance allocation based on minimum sensitivity is given. Several synthesis methodologies are reviewed to highlight their importance in details. A brief but complete literature review is given and conclusions are drawn. Objectives such as minimum cost functions, minimum sensitivity functions and minimum variance functions are formulated and a heuristic approach is used for optimisation. An example problem is given to illustrate the concept and results indicate that there are alternatives for tolerance allocation problems. Besides, there are margins of tolerance for which the measure of objective functions are least sensitive.

]]> 10.1504/IJQET.2011.043172 International Journal of Quality Engineering and Technology, Vol. 2, No. 4 (2011) pp. 344 - 356 Mohamed H. Gadallah Department of Mechanical Design and Production, Faculty of Engineering, Cairo University, Giza, 12613, Cairo, Egypt tolerance allocation minimum sensitivity heuristics objective functions. 2011-10-18T23:20:50-05:00 2 4 344 356 2011-10-18T23:20:50-05:00