A Simple Model of a Variance Stable Process

	Bookmark This Page Email This Page Format for Printing Cite This Article Submit an Article Read More Articles
	Related Tools & Articles What Is A Stable Process? Variation - The Root Of All Process Evil More About Variation and Statistics
	Discussion Forum "Low Volume production is not the issue. It is process volume not product. Your idea is along the correct track. You want to understand the process dynamics and it may or maynot behave independently of the product. You can make a decision on the product design dependency using Hypothesis testing or DOE..." Low Volume Process Variation

By J

New from iSixSigma NEW VERSION! Process Management Training Slides Business Process Management E-book Wave Solder Process Improvement Project Example

ohn J. Hickey

Most fairly accurate descriptions of equipment and/or process lifetimes assume that failure rates follow a three period I II III "bath tub curve pattern" where failures / errors:

I - Decrease during the debugging or improvement time period.

II - Remain relatively constant and at their lowest levels during the normal equipment or process operating period.

III- Increase during the wearout time period.

Scientific studies of limit based natural or complex growth patterns also suggest that many processes are inherently non linear and subject to chaotic tendencies. The Logistics Map(3) or Parabola Xt+1 = R Xt(1-Xt) where Xt+1 the measure of the next generation is a function of the present measure Xt, R is the growth factor and t is a discrete time variable is a simple model for these processes. When the growth factor R falls within the range of 1< R < 3 the process is stable. For R=2, the time series iterates Xt = X1 X2 X3… converge to the constant value Xc =.5 which can be easily demonstrated(see Table I) through the use of an Excel spreadsheet or pocket calculator:

The critical growth factor value Rcr = 3.24(5^1/2 +1 ) in Table I signals the start of chaotic instability in this model process and for R = 3.8 the instability is clearly evident.

Process Variance Stability
If we assume that Variance Vt of a process during its lifetime varies between zero and some maximum acceptable value Vm, the application of the logistics parabola model to the process results in the iterate expression Vt+1=RVt(Vm-Vt). In this case the process is stable (1) within the growth factor R range of 1/Vm < R < 3/Vm . Also , the process attains super- stability or constancy when its variance equals one half of the maximum acceptable value( Vt =Vm/2) and when R = 2/Vm. This is illustrated for a process with a maximum allowed Variance of Vm= 9 (standard deviation =3) in Table II.

The values of R in Table II are obtained by scaling the R values of Table I by 1/Vm=1/9. For example , R = 2/9= .222 is the super-stable growth factor and Rcr = 3.24/9 =.36 is the critical factor. In the case of Poisson distributed processes, the expected number of occurrences C =NP(large N , small fraction P of occurrence) is both the variance and mean of the distribution. A conditional Poisson process that conformed to this simple non linear model has the variance Ct+1= RCt(Cm -Ct) and would be stable in growth rate range 1/Cm < R < 3/Cm where Cm is the specified maximum number of occurrences. When Ct = Cm/2 and R = 2/Cm the process is super-stable(1) and ideally Poisson because the expected number of occurrences Co = C1= C2….= Ct =Ct+1 remain constant and are time independent over the operating lifetime of the process. This condition of super-stability is analogous to "States of Equilibrium" in Statistical Mechanics(2) and is illustrated by the Ct+1 = Ct intersecting line of above Figure I quadratic map.

The hypothetical model is suggestive of an ideal , super-stable six sigma process with an expected Poisson failure no of C = 1.7 PPM (N= 10⁶ P=1.7x 10^-6), maximum failure no. of Cm =3.4 PPM and growth factor that has the value R= .60.

A real world stable process would of course exhibit random fluctuations in variance which would not be strictly deterministic. However, as it ages or deteriorates and becomes unstable some deterministic chaos may be present and evident by an oscillatory pattern of variance(ex: machine tool wear). If a process is stable with a relatively constant variance and it meets requirements, in my opinion, it does not need to be fixed.

Notes and References

1. |F'(Vt)| < 1 is the first derivative criteria for the stability of the fixed points Vt =0, Vt = Vm-1/R in the Variance quadratic map Vt+1 =R Vt (Vm-Vt). Since F'(Vt)= R(Vm-2Vt), the stability ranges for the fixed points Vt=0, Vt =Vm-1/R calculate as R < 1/Vm and 1/Vm < R < 3/Vm respectively. Vt =Vm/2 is the value of the non zero fixed point at the growth rate R = 2 /Vm and F'(Vt) =0 when this occurs. Therefore, a super-stable Poisson process Variance Ct would be "ideally Poisson" because its expected number of occurrences Ct = Ct+1…remain constant during successive time periods. The oscillatory behavior of the logistic parabola iterates in the unstable growth rate region R >= 3 is known as 2ⁿ period doubling. It is represented mathematically by the composite function expression Fⁿ (X0)=X0 where n is the number of cycles or iterations required for a repetition of the point X0. The cycles or "splittings" increase as the associated growth rates R1 ..R2.. become larger. Chaos and infinite period doubling occurs with R > 3.6/Vm. For the 2-cycle period F² (X0)=X0 and super-stable fixed point X0 =.5, the growth rate for Vm=1 is Rc = 5^1/2 +1.
2. E.C. Andrews, Equilibrium Statistical Mechanics , John Wiley & Sons Inc., 1975 defines a state of equilibrium as one in which the information we have about the system it has reached a time -independent minimum. In the Chapter 7 section on ensembles with minimum information he proves that a maximum ignorance( lack of assigned causes) about the system exists when the state probabilities are equal.
3. The technical literature on non linear dynamics, Logistic Equations, Quadratic Maps, Fixed Point Stability, Period Doubling and Chaos is quite extensive and only a Web site sampling is provided:
   * Non Linear Dynamics and Chaos
   * Interval Self Mappings
   * Logistic Maps

About The Author
John J. Hickey is a Chemist and Quality professional with extensive experience in the areas of Analytical Chemistry, QA, Safety, Regulatory Affairs, Management and Training.

"The Bottom Line" Links

BMG Upgrade Your Skills Master Black Belt Certification Get the industry's most Flexible, Robust Program for Professionals >> Find out more

VILLANOVA UNIVERSITY   Earn Your Lean, Green or Black Belt Six Sigma Master Certificate Online BOOST YOUR SALARY! *$38k more than uncertified counterparts. Learn From Industry Leaders!   START NOW

SIGMAPRO MBB, Lean Sigma, & DFSS   when experience matters most...

M O T O R O L A U N I V E R S I T Y Learn from the most experienced practitioners of Six Sigma in the world Public Training & Certification Click here to take a free Six Sigma Lesson

J URΛN   Lean Six Sigma Public Workshops Atlanta, GA - Sept 2008 Become one of your organization's 'vital few'. Get Juran Certified.

LSI Knowledge & Experience Get Your Lean Black Belt Certification -  in Denver         Register Now   -   Starts August 11!                                                     >>Learn about LodeStar Institute specials..

HOWARD UNIVERSITY Now offering Process Simulation ! 4 weeks + 1 cost saving project + 1 mentor + 1 caring instructor = 1 Marketable Certified Lean Six Sigma Black Belt

WINSTON SALEM STATE UNIVERSITY Now offering Process Simulation ! 4 weeks + 1 cost saving project + 1 mentor + 1 caring instructor = 1 Marketable Certified Lean Six Sigma Black Belt

THE UNIVERSITY OF TEXAS AT AUSTIN 2 weeks + 1 project = Black Belt Certification

. Find us on LinkedIn Join the iSixSigma Network and Connect with Other Six Sigma Pros .

. iSixSigma Live! Summit & Awards Jan 13-16, 2009 • Miami, FL Save up to $700 • Click Here! Register by August 14 .

Download the iSixSigma Toolbar for 1-Click access. Search Your Way. Everyday. Without Delay.

BEST SELLING PRODUCTS (iSixSigma Publications) 2008 VERSION! Six Sigma DMAIC Training Slides The complete Lean Six Sigma DMAIC course prepares participants to perform the role of a LSS Black Belt; covering what’s ... NEW VERSION! Process Management Training Slides The OSSS Process Management course is designed in two phases comprised of:352 Powerpoint slidesInstructor notesSlide exp... Certified Lean Six Sigma Black Belt Assessment Exam Interested in assessing your knowledge of Lean Six Sigma? Preparing for certifications? Testing your students and traine... Gage R&R Excel Template Gage Repeatability and Reproducibility (R&R) studies measure the amount of measurement variation that is attributabl... E6 Sigma DMAIC EZ: Black Belt for Service E6 Sigma is THE Six Sigma Holy Grail. The first-ever Six Sigma training and implementation software, REAL Six Sigma is a... FMEA Excel Template Need to be more preventative, prioritize risks, or brainstorm possible failures in a process or product? Use the FMEA to... NEW VERSION! Six Sigma Black Belt (DMAIC) Training Slides The OSSS Six Sigma Black Belt course is comprised of: 1,176 PowerPoint slides, Instructor notes, Slide explanations, 37 ... Sell Your Products