Go
New
Find
Notify
Tools
Reply
  
-star Rating Rate It!  Login/Join 
Posted
I ask for your opinion about the best software or utility to do weibull analysis (please do not forget the relation quality / price). I am referring to estimate the lyfe time from historical data of failures or substituions or suspensions. Which experience do you have to implement the results from this analysis as checking period for Pdm technologies, as vibration?

Regards,

Allen
 
Posts: 46 | Location: Spain | Registered: 29 August 2006Reply With QuoteEdit or Delete MessageReport This Post
Vee
Posted Hide Post
Allen,
Your question
quote:
implement the results from this analysis as checking period for Pdm technologies, as vibration?

intrigues me. Weibull analysis is a statistical process. PdM is based on physical degradation rates. They are in different domains, so how do you plan to use to check the other? Degradation can commence randomly, and in these cases the Weibull shape factor will be 1. With Weibull parameters you dont know time of start of degradation of any individual failure.

Some years ag, I used WinSmith software and it was very good. I guess there are many out there of similar capability. As to price, it is best you do a check yourself, as they change all the time.


Regards,
V.Narayan (Vee)
Lead Author, 100 Years of Maintenance: Practical Lessons from Three Lifetimes, Industrial Press.NY ISBN-13: 978-0831133238
Author, Effective Maintenance Management: Risk and Reliability Strategies for Optimizing Performance, 2004, Industrial Press NY ISBN-13: 978-0831131784
 
Posts: 770 | Location: Scotland, UK. | Registered: 16 May 2004Reply With QuoteEdit or Delete MessageReport This Post
Posted Hide Post
I used a program called Reliability Analyst which was good but I think Excel also has a lot of capability. See for example the following link. http://www.qualitydigest.com/jan99/html/weibull.html
 
Posts: 71 | Location: Netherlands | Registered: 12 January 2006Reply With QuoteEdit or Delete MessageReport This Post
<Rui Assis>
Posted
Be careful. The use of a two or a three-parameter Weibull distribution can be misleading. In the example given in the link, you get:

Location parameter = 0; Shape parameter = 4.25; Scale parameter = 693,380

If you consider the three-parameter Weibull distribution, then you get:

Location parameter = 180,000; Shape parameter = 2.89; Scale parameter = 508,880

The results seem to be more realistic in the second situation as it is reasonable to think that some time (cycles) has to elapse before any spring fails - so the location parameter cannot be zero. Differences might not be negligible. Further, no suspensions are considered.

Nevertheless, I agree with Rogier, EXCEL can be programmed to deal with this matter at no cost and still getting some pleasure in return.

Rui

This message has been edited. Last edited by: <Rui Assis>,
 
Reply With QuoteEdit or Delete MessageReport This Post
Posted Hide Post
Weibull++ is also available for life data (weibull) analysis with many features and capabilities. Additional information on Weibull++ can be found at http://www.reliasoft.com/Weibull/index.htm.

I hope this helps.
 
Posts: 15 | Location: Tucson | Registered: 14 August 2006Reply With QuoteEdit or Delete MessageReport This Post
 Previous Topic | Next Topic powered by eve community  
 


Copyright © 2004-2008 NetexpressUSA Inc. All rights reserved.