taguchi s / n ratios
Six Sigma – iSixSigma › Forums › Old Forums › General › taguchi s / n ratios
 This topic has 6 replies, 6 voices, and was last updated 16 years, 6 months ago by Kev.

AuthorPosts

April 18, 2003 at 4:20 am #32020
arun.s.kumarParticipant@arun.s.kumar Include @arun.s.kumar in your post and this person will
be notified via email.I am a trainee in an automotive parts supplier company. I require guidance for calculation of S/N ratios in the taguchi method. Also recommend a good software for this. Please give a basic overview of the calculations (detailed version also invited) and guide me to any specific links that you would know. The significance of the S / N ratios and the log transormation is also awaited.
0April 23, 2003 at 12:44 am #85153You can use rdExpert software for Taguchi experiments
Manee0April 23, 2003 at 1:08 pm #85163If you want to understand Taguchi’s S/N read his book on Quality Engineering.
Minitab does a good job with S/N although it is easy to prove that traditional analysis of mean and Box Myers analysis of variability done separately will allow you to learn much more.0February 13, 2006 at 4:41 pm #133722There are 3 SignaltoNoise ratios of common interest; (I) SMALLERTHEBETTER : n = 10 Log10 [ mean of sum of squares of measured data ] This is usually chosen for all undesirable characteristics like ” defects ” etc for which the ideal value is zero. Also, when an ideal value is finite and its maximum or minimum value is defined (like maximum purity is 100% or maximum Tc is 92K or minimum time for making a telephone connection is 1 sec) then the difference between measured data and ideal value is expected to be as small as possible. The generic form of S/N ratio then becomes, n = 10 Log10 [ mean of sum of sqaures of {measured – ideal} ] (II) LARGERTHEBETTER : n = 10 Log10 [mean of sum squares of reciprocal of measured data] This case has been converted to SMALLERTHEBETTER by taking the reciprocals of measured data and then taking the S/N ratio as in the smallerthebetter case.(III) NOMINALTHEBEST : n = 10 Log10 (square of mean / variance )This case arises when a specified value is MOST desired, meaning that neither a smaller nor a larger value is desirable. Examples are; (i) most parts in mechanical fittings have dimensions which are nominalthebest type. (ii) Ratios of chemicals or mixtures are nominally the best type. e.g. Aqua regia 1:3 of HNO3:HCL Ratio of Sulphur, KNO3 and Carbon in gun powder (iii) Uniformity in deposition /growth /plating /etching thickness.
0February 13, 2006 at 4:41 pm #133723There are 3 SignaltoNoise ratios of common interest; (I) SMALLERTHEBETTER : n = 10 Log10 [ mean of sum of squares of measured data ] This is usually chosen for all undesirable characteristics like ” defects ” etc for which the ideal value is zero. Also, when an ideal value is finite and its maximum or minimum value is defined (like maximum purity is 100% or maximum Tc is 92K or minimum time for making a telephone connection is 1 sec) then the difference between measured data and ideal value is expected to be as small as possible. The generic form of S/N ratio then becomes, n = 10 Log10 [ mean of sum of sqaures of {measured – ideal} ] (II) LARGERTHEBETTER : n = 10 Log10 [mean of sum squares of reciprocal of measured data] This case has been converted to SMALLERTHEBETTER by taking the reciprocals of measured data and then taking the S/N ratio as in the smallerthebetter case.(III) NOMINALTHEBEST : n = 10 Log10 (square of mean / variance )This case arises when a specified value is MOST desired, meaning that neither a smaller nor a larger value is desirable. Examples are; (i) most parts in mechanical fittings have dimensions which are nominalthebest type. (ii) Ratios of chemicals or mixtures are nominally the best type. e.g. Aqua regia 1:3 of HNO3:HCL Ratio of Sulphur, KNO3 and Carbon in gun powder (iii) Uniformity in deposition /growth /plating /etching thickness.
0February 13, 2006 at 5:39 pm #133728These links provide a good explanation for the Taguchi Methods:
http://www.ee.iitb.ac.in/~apte/CV_PRA_TAGUCHI_INTRO.htm
http://www.sixsigmafirst.com/taguchi2.htm
http://www.itl.nist.gov/div898/handbook/pri/section5/pri56.htm
Hope this will help
0February 13, 2006 at 6:32 pm #133729One of office BB is doing a Tuguchi DOE.
What about the P values to keep?0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.