Your Reliability Engineering Professional Development Site
Reliability testing is expensive, time-consuming, and fraught with errors. Is it worth the effort? Is it necessary? Let’s explore relegating testing to only a ‘when necessary’ status. Let’s explore what you and your team can do instead.
[Read more…]
Creating a reliable product that meets customer expectations is risky.
What is risk and how does one go about managing risk? The recent set of ISO standard updates elevates risk management.
A starting place is a definition. [Read more…]
This type of reliability may have different names. A quick search of a few references in my library and I didn’t find ongoing reliability testing, ORT, in any of them.
It does exist and you may have heard of it before or even use some form of ORT. Or not.
Ongoing reliability testing or ORT is the continued evaluation of your product typically using samples drawn from production. The testing evaluates the reliability performance of recent production units.
The focus is on finding anomalies or changes that may occur in the design, supply chain, or production process that significantly changes field reliability performance. [Read more…]
Chapter 7 Design for Reliability of the book Practical Reliability Engineering starts with:
The reliability of a product is strongly influenced by decisions made during the design process.
The key message here is reliability occurs at the point of decision. Each time someone makes a decision, selects a component, chooses a material, assumes a use profile, the eventual product reliability takes shape.
Design for Reliability, DfR, is about making good decisions across the organization concerning reliability. [Read more…]
A Bloomberg articles details the Takata airbag recall series of events. The line that caught my attention is:
…company documents suggesting that Takata executives discounted concerns from their own employees and hid the potential danger…
“Sixty Million Car Bombs: Inside Takata’s Airbag Crisis”, Susan Berfield, et.al. Bloomberg Business Week, posted June 2nd, 2016, https://www.bloomberg.com/news/features/2016-06-02/sixty-million-car-bombs-inside-takata-s-air-bag-crisis
There are other examples where management doesn’t seem to listen when engineers raise concerns. Have we cried wolf too often? Has management gotten used to taken risks as a good business practice?
At times reliability risks are real and need to be clearly communicated. Let’s talk about how you can effectively get the message across. [Read more…]
There are a few different reasons we explore differences in scale.
Keep in mind that the scale of a dataset is basically the spread of the data. For most datasets, we’re examining the variance.
Hypothesis tests comparing means vary depending on the assumption of equal variances. Thus testing that assumption requires methods to adequately test the homogeneity of variances. The F-test should come to mind as it is a common approach.
Some datasets do not lend themselves to using the F-test, which is applicable using real numbers. Some datasets gather information that is ordinal or interval data, thus we need another approach to test for differences in scale. [Read more…]
The Hartley test is an extension of the F distribution-based hypothesis test checking if two samples have different variances.
The F test works with two samples allowing us to compare two population variances based on the two samples. This test does not work for three or more populations. We could conduct multiple pairwise comparisons, yet the probability of an erroneous result is significant.
Bartlett’s Test and Levene’s Test are non-parametric checks for homogeneity of variances. Bartlett’s Test pretty much expects the underlying data to be normally distributed.
Levene’s Test is a better choice when you’re not sure the data is normal. Both are conservative and time-consuming to calculate.
We need another way to check for equal variances. [Read more…]
Sigma, σ, is the Greek character we use to represent standard deviation. 6 σ represents the spread of data about the mean. For data with a normal distribution, 6 σ includes 99.7% of the data.
The 6 σ design approach incorporates knowledge of the variation that will occur within the design such that the design has is unlikely to fail.
According to Mikel J. Harry, the foundation of excellence in product quality rests on achieving six sigma product quality. [1] [Read more…]
The data analysis course professor tended to focus on the practical application of statistics.
Avoiding statistical theory was fine with me. Learning statistics for me was on how to solve problems, optimize designs, and understanding data.
Then one lecture started with the question, “Why do we sum squares regression analysis, ANOVA calculations, and with other statistical methods?” He paused waiting for one us to answer.
We didn’t. I feared the upcoming lecture would include arcane derivations and burdensome theoretical annotations. It didn’t. [Read more…]
In a single meeting, you may need to structure a reliability model, create estimates, outline test plans, and discuss a field failure. The breadth of tools and knowledge to be effective is staggering.
No two problems, questions, situations, or industries are the same. Thus, the solutions you provide must differ as well. If you enjoy a complete set of reliability engineering tools at your disposal, you are well situated to address any question.
Your team may understand the system reliability goal, yet they should know the goal for the element they are addressing. Let’s discuss why you must do reliability apportionment. Plus, let’s explore how it benefits your team.
[Read more…]
A common assumption when comparing three or more normal population means is they have similar (the same) population variances.
ANOVA and some DOE analysis results rely on the underlying data having similar variances. If this assumption is not true, the conclusions suggested by the ANOVA or DOE may be misleading.
It doesn’t take long to check. [Read more…]
The concept of derating is similar to the mechanical engineering concept of a stress–strength analysis.
The intent is to ensure that the selected component or the mechanical design has sufficient strength to withstand the expected applied stresses.
Components operating at or near their rated values have short lives. Consequently, the general practice is to use components for materials well below their rated values to extend the operating life of the items.
This is where derating comes into play. [Read more…]
Here the 2016 survey results as reported by the TypeForm survey tool. [Read more…]
Confidence intervals (CIs)provide a means to judge point estimates based on a sample from the population.
If that statement excites you, you may well have the makings of a fine statistician.
CIs are a form of internal estimate and specify a range within which a parameter may reside. CIs helps us evaluate the trustworthiness of point estimates. [Read more…]