Reliability HotWire: eMagazine for the Reliability Professional
In this issue:

Issue 16, June 2002

*Hot Topics
*Reliability Basics
*Tool Tips
*Latest Software Updates
*Hot News
*From the Edge
*Contribute to HotWire

Reliability HotWire is a service of ReliaSoft Corporation

To subscribe or update your e-mail preferences, go to

Hot Topics  
Verifying the Assumption of a Constant Shape Parameter in Accelerated Life Testing Data
It is a generally accepted practice to assume a constant shape parameter across the different stress levels (independent of stress) when analyzing data from an accelerated life test. For the Weibull distribution, the shape parameter is Beta and for the lognormal distribution, the shape parameter is the log-std. This implies that the unit/component will fail in the same manner across different stress levels. But how can you validate this assumption? Does the unit/component actually behave in this manner? There are multiple ways that you could test the validity of this assumption, such as a likelihood ratio test or a maximum ratio test. However, this article will employ a graphical method utilizing ReliaSoft's ALTA 6 and Weibull++ 6 software.

To read more, see 

Reliability Basics  
The purpose of this section is to offer background and advice to the novice reliability engineer.

Comparison of MLE and Rank Regression Analysis When the Data Set Contains Suspensions
In previous issues of the HotWire, we have discussed the maximum likelihood estimation (MLE) and rank regression methods for parameter estimation. We have also mentioned that when your data set contains a large number of suspensions, it is suggested that you use MLE for parameter estimation. But why? In this month's Reliability Basics, we will take a closer look at this "rule of thumb" and illustrate how rank regression does not take into account the characteristics of the entered data when there are a large number of suspensions.

To read more, see 

Tool Tips  

The Tool Tips section addresses helpful hints and frequently asked questions about ReliaSoft software products.

  • How do I set the properties of an existing block to match the properties of another block within BlockSim?

  • How can I import the results from a data set analyzed in Weibull++ 6 to a block in BlockSim?

To read more, see 

Latest Software Updates

This section will present the latest software update information for ReliaSoft software products. To determine the compile revision of the application on your computer, from the Help menu, click About. In the About window, click the Details button.

Application Date Created Version
Weibull++ 6 4/25/02 6.0.8
Weibull++ 6 Service Pack 4/25/02 SP3 CRV 8
Weibull++ 6 MT 4/25/02 Weibull++ 6.0.8 - MT 6.1.5
Weibull++ 6 MT Service Pack 4/25/02 SP3 CRV 8 - 5
Weibull++ 6 Developer Edition 12/13/01 1.0.1
ALTA 6 4/16/02 6.0.8
ALTA 6 Service Pack 4/16/02 SP3 CRV 8
BlockSim 1.5 4/11/02 1.5.2
BlockSim 1.5 Service Pack 4/16/02 SP1 CRV 2
MPC 3 4/15/02 3.0.4
MPC 3 Service Pack 4/15/02 SP1 CRV 4
Hot News
* Reliability Training Seminars - Upcoming ReliaSoft public reliability training seminars include: 


QALT Boot Camp intensive three day course on advanced topics, concepts and applications of quantitative accelerated life testing (QALT), such as time-varying stress, multiple stress testing and ReliaSoft's ALTA PRO software: June 26-28, 2002 in Tucson, Arizona. For more information, see


Master the Subject, Master the Tools training seminar for life data analysis, accelerated life data analysis and system reliability: August 19 - 23, 2002 in San Diego, California. For more information, see


New Resources on - Recent additions to the reliability resource Web site include iTools and Rank Tables for Probability Plotting. The new iTools section provides a collection of quick Web-based reliability analysis tools, including a simple Weibull analysis, a rank calculator and more. The site's popular probability plotting papers reference has been expanded to include rank tables for probability plotting. Whenever you have reliability related questions, be sure to turn to for the answers!
* ReliaSoft at AQC - ReliaSoft would like to thank those of you who stopped by the ReliaSoft booth in the vendors area during the recent Annual Quality Congress in Denver, Colorado. We hope that we helped to make this a productive and interesting conference for you.


Reliability Training at GM Knowledge Center - We are pleased to announce that once again ReliaSoft will be providing training classes for GM employees at the General Motors Knowledge Center in Warren, Michigan. The courses offered will cover three diverse disciplines of reliability engineering and include life data analysis, accelerated life testing analysis and system reliability, maintainability and availability analysis. For more information, visit the GMU Knowledge Center Web site at or contact ReliaSoft at +1.520.886.0410. Class size is limited. GM suppliers should check with GM for class availability. The remaining 2002 class schedule is as follows:


August 5 - 7, 2002 - Life Data Analysis


August 8, 2002 - Accelerated Life Testing
- October 14 - 16, 2002 - Life Data Analysis
- October 17, 2002 - System Reliability
From The Edge  
In addition to the monthly Reliability HotWire, ReliaSoft publishes Reliability Edge, a printed journal that includes articles and information related to the field of reliability engineering. Articles of interest in the current edition:
  • Predicting Warranty Returns Based on Customer Usage Data - In recent years, there has been a lot of research in understanding how the customer is using the product. Despite the significant investment into these efforts, much of this customer usage information is being underutilized, or is not being used at all, because the proper analysis method is unknown. This article presents a methodology for utilizing customer usage data in order to perform reliability predictions. The approach presented here is based on a combination of quantitative accelerated life testing (QALT) data analysis methodologies and stress-strength interference analysis, a method used in probabilistic design. See
  • Implementing an Automated Reliability/Quality System: What You Can Expect - The benefits of automated analysis and reporting systems for reliability and quality data are abundant and well-understood within the product manufacturing community. The rewards to companies that invest in automated reliability analysis systems range from improved product design to increased customer satisfaction. When deciding to make the commitment to implementing such a system, the company must also carefully consider the investment of time and money as well as the risks of undertaking a project of this nature. This article is intended to provide some insight into what can be expected when an organization undertakes the implementation of an automated analysis system for reliability and quality data. See
Contribute to HotWire
Contributions Welcomed
As always, your feedback and contributions are appreciated. ReliaSoft is able to provide the most user-friendly reliability software packages and support because we listen to our customers. This applies to our newsletters and publications as well. We welcome any suggestions or contributions you may have for Reliability HotWire. If you have a topic or article that you think would be useful to the readers of Reliability HotWire, feel free to contact us.
ReliaSoft Logo

Copyright 2002 ReliaSoft Corporation, ALL RIGHTS RESERVED