Hemant Urdhwareshe, Director of Institute of Quality and Reliability presents case study to maximize fatigue strength of crankshaft using design of experiments using SigmaXL Template of Full Factorial Design with three factors each at two levels.

Hemant is Fellow of ASQ and possesses five certifications from ASQ including Six Sigma Master Black Belt and Reliability Engineer. It is recommended that viewers first watch the previous videos DOE-1, DOE-2 and DOE-3 before watching this video. SigmaXL trial version can be downloaded from www.sigmaxl.com.

[Read more…]

by Hemant Urdhwareshe Leave a Comment

DOE-3: Coded and Uncoded Values & Establishing Regression Equation

I am happy to share my third video on Design of Experiments (DOE-3). This is the third video in our series on Design of Experiments. It is recommended that viewers should watch the first two videos (doe-1-introduction-to-design-of-experiments and DOE-2: DOE Case Study of Spot Welding) before watching this video for better learning and understanding.

In this video, we have explained how to convert uncoded values of factor-levels to coded values and vice versa. We have also explained how to create a linear regression equation from the results of a full factorial two-level experiment.

[Read more…]

by Ray Harkins Leave a Comment

Student Questions from My Root Cause Analysis Class, Part 1

Since launching my Root Cause Analysis class just over 5 years ago, I count myself remarkably fortunate to have been a part of the learning journeys of the 14,000+ students who have taken it. And a welcomed part of teaching courses online is fielding questions that come from students. In addition to clarifying for them various technical points of the course, I also get a “behind the curtains” look at the general training gaps in the quality profession. Afterall, that one student’s question may be in lingering in the minds of countless other quality professionals as well.

[Read more…]

by Hemant Urdhwareshe Leave a Comment

DOE-2: Application of Design of Experiments for Spot Welding Process

Dear Friends, we hope you have seen our first video on Introduction to Design of Experiments DOE)! Here is my second video on DOE! I have illustrated a case study of DOE application to Spot Welding process! The Case study is about application of Full Factorial Design with three factors, each at two levels. The video assumes that viewers have seen our first video on Introduction to DOE.

[Read more…]

by Ray Harkins Leave a Comment

A Primer on Acceptance Sampling Plans

In modern manufacturing, ensuring product quality is paramount. One of the fundamental tools employed to maintain quality standards is sampling plans. These plans provide a systematic approach to inspecting a subset of items from a larger batch, allowing for efficient and reliable decision-making regarding the acceptability of the entire lot.

In this primer, we probe the essentials of sampling plans, their types, and the trade-offs between sampling and 100% inspection. Because of their ubiquitous use in manufacturing, we will more closely examine attribute sampling plans, including single, double, and multiple sampling plans, and their applicable industry standards.

[Read more…]

by Hemant Urdhwareshe Leave a Comment

DOE-1: Introduction to Design of Experiments

Dear Friends, this video is created to provide a simple introduction to Design of Experiments (DOE). DOE is a proven statistical tool and is known to be superior to the conventional approach of One-Factor-at-a-Time of OFAT! In OFAT, one tries to optimize the settings of various factors one by one. But this has a major limitation of not getting information about interaction of the factors! DOE helps us to estimate effects of various factors along with their interactions! This is the first in the series of videos that we wish to create and share in near future. Our future videos on DOE will include practical application examples of DOE, analysis and interpretation, optimization using DOE, Fractional Factorial Designs. We will also introduce later to Response Surface Designs.

[Read more…]

by Carl S. Carlson Leave a Comment

Key Teaching Principle # 4: Questioning

As covered in the first article in this series, Principles of Effective Teaching, reliability engineers, FMEA team leaders, and other quality and reliability professionals are often called upon to teach the principles of reliability or FMEA. Whether you are a student who wants to enhance your learning experience, an instructor who wants to improve teaching results, or an engineer who wishes to convey knowledge to another person, this series will offer practical knowledge and advice.

The Importance of Questioning

“No one can teach, if by teaching we mean the transmission of knowledge, in any mechanical fashion, from one person to another. The most that can be done is that one person who is more knowledgeable than another can, by asking a series of questions, stimulate the other to think, and so cause him to learn for himself.” Socrates

Questioning is important for transferring knowledge and building relationships. It is an essential part of effective teaching.

[Read more…]

by Hemant Urdhwareshe Leave a Comment

Warranty Data Analysis on Minitab

I am happy to share my next video on ‘Warranty Data Analysis using Minitab Software’. The video explains the popular Nevada format of warranty data collection and how to convert it in to suitable tabular format so that the same can be analysed using Minitab or other software. In this video, we explain the various types of failure data when Nevada format is used. In some of our previous videos, we have already discussed various types of life data i.e. complete, right censored, left censored and interval censored. When all these types of data are present at the same time, we call such data as multiply censored. Such type of data can be analysed on Minitab using the commands for arbitrarily censored data.

[Read more…]

by Larry George Leave a Comment

Do the Best You Can With Available Data?

Lifetime data is nice to have, but lifetime data is not necessary! Generally Accepted Accounting Principles require statistically sufficient data to estimate nonparametric reliability and failure rate functions. Some work is required!

ISO 14224 “Petroleum, Petrochemical and Natural Gas Industries—Collection and Exchange of Reliability and Maintenance Data for Equipment” requires lifetime data to estimate exponential or Weibull reliability functions! Sales or ships and returns or failure counts are statistically sufficient to make nonparametric estimates of reliability and failure rate functions, without unwarranted distribution assumptions or lifetime data!

[Read more…]

by Hemant Urdhwareshe Leave a Comment

Case Study in Tolerance Design of a Spring using Monte Carlo Simulation

One of the weak areas in designing parts is deciding tolerances of various parts. We have shared a video of statistical tolerancing for assembly of parts. Many viewers have expressed that we should also post a video of application of Monte Carlo Simulation for tolerance design when there is a transfer function that relates the input parameters to an output variable. We therefore present in this video an application example of designing tolerance for a helical spring using Monte Carlo Simulation. The video explains this procedure step-by-step using Simular software. I have used Simular software to demonstrate this with a practical example of spring. Simular is a free software (emailware) which can be downloaded from https://www.simularsoft.com.ar/. However, one can use other software such as Crystal Ball, @Risk etc. for such analysis. Tolerance design is usually an essential step in Design for Six Sigma (DFSS) projects.

[Read more…]

by Ray Harkins Leave a Comment

Machine Run-Off’s: What Are They and Why Do Them

A machine run-off, refers to the process of testing and adjusting a new or modified machine or piece of equipment before it is put into regular use. When a run-off is performed prior to shipping to the customer, it is called a Factory Acceptance Test (FAT), and when it is performed after installation at the customer’s facility it is called a Site Acceptance Test (SAT).

Both types of machine run-offs are common with large, complex, and/or expensive equipment. And both have the same goal of ensuring the equipment is safe and reliable, and meets the customer’s requirements and functional criteria before it is launched into production where repairs and corrections become much more expensive. The SAT is largely a repeat of the FAT expect it additionally verifies that no damage was incurred during shipment and that the unit is correctly installed.

[Read more…]

by Hemant Urdhwareshe Leave a Comment

Life Data Analysis of Right Censored data using Minitab Software

I am happy to share my next video on ‘Life Data Analysis of Right Censored Data using Minitab Software’ as many viewers had requested! In this video, we revisit the types of failure data and explain procedure to analyse right censored data in Minitab software with an example.

The procedure is predominantly in three steps:

1. Identify the distribution that best fits our data
2. Estimate parameters of the selected distribution
3. Estimate reliability or probability of failure at specified time(s)

The procedure is explained in detail using an application example of camshaft failure data. In the video, I have also explained how to estimate expected number of failures by 100000 Kilometres and also the 95% upper bound which is the worst-case scenario. I am sure, you will find this video interesting and useful for practical application of Life Data Analysis! Your feedback on the video is welcome!

[Read more…]

by Larry George Leave a Comment

Why Use Nonparametric Reliability Statistics?

Fred asked me to explain why use nonparametric statistics? The answer is reality. Reality trumps opinion, mathematical convenience, and tradition. Reality is more interesting, but quantifying reality takes work, especially if you track lifetimes. Using field reliability reality provides credibility and could reduce uncertainty due to tradition and unwarranted, unverified assumptions.

Data is inherently nonparametric. Cardinal numbers are used for period counts: cohorts, cases, failures, etc. Accounting data is numerical; it is derived from data or from dollars required by GAAP (Generally Accepted Accounting Principles); e.g., revenue = price*(products sold), service cost = (Cost per service)*(Number of services), or numbers of spare parts sold. Why not do nonparametric reliability estimation, with or without lifetime data?

[Read more…]

by Hemant Urdhwareshe 2 Comments

Statistical Tolerancing using Monte Carlo Simulation

One of the weak areas in designing parts is deciding tolerances of various parts. Most engineers are familiar with Arithmetic Tolerance stack up analysis wherein they check impact of maximum and minimum values of various tolerances on assembly of parts. However, this can often result in high manufacturing cost. Thus, it may be more appropriate to analyse tolerances using statistical tolerance stack up approach. This can be performed using Monte Carlo Simulation. In one of the previous videos, I had shown how to predict reliability using Monte Carlo simulation. In this video, I will explain how to perform statistical tolerance stack up analysis using Monte Carlo Simulation. I have used Simular software to demonstrate this with a practical example. Simular is a free software (emailware) which can be downloaded from https://www.simularsoft.com.ar/. However, one can use other software such as Crystal Ball, @Risk etc. for such analysis. Statistical tolerance stack up is usually an integral part of Design for Six Sigma (DFSS) projects. I hope viewers will find this video useful. Feedback is welcome!

[Read more…]