Your Reliability Engineering Professional Development Site
A listing in reverse chronological order of articles by:
Statistical distribution – it has important role in general life and of course in engineering specifically. So, what is all about?
During morning commute either by bus or vehicle, you take some budget of time. From your daily routine experience, you with very high probability, can predict arrival time. You also know how much time it will take, in less ordinary cases, like slippery roads, or cars accident along you route.
[Read more…]
A short introduction to accelerated life testing or ALT. It is a method used to enhance product reliability by subjecting prototypes to stress levels significantly higher than those encountered in actual use. The idea is to rapidly induce failures which is equivalent to speeding up time.
[Read more…]
Anybody who did some hardware test in they life, eventually will face the question of sample size.
Probably it will be a tradeoff between the test duration and amount of samples to test.
So how much is enough? One, three, ten?
[Read more…]
In this article, I want to show you why Weibull, lognormal, and exponential distributions are more appropriate than others for modeling failure distributions. Instead of starting from the explanation of the most used fitting distributions in reliability engineering, I will begin with the analysis of artificial datasets created assuming specific failure behaviors. In other words, I will start from the data and not from the statistical distributions. I think that this approach can help those who deal with this topic for the first time.
[Read more…]
Many of us like to think that we can, at least sometimes, be objective. Which is the opposite of being subjective.
What does this mean? Something is ‘objective’ if it only depends on the world around it, and nothing else. Like the ‘perfect juror’ who is only swayed by facts and evidence when determining if he or she thinks someone is guilty of murder. Something is ‘subjective’ if it can be influenced … by itself. Like the ‘imperfect juror’ who decides to acquit a murder suspect regardless of the evidence … because the suspect is his or her brother. This is called bias.
Boeing has somehow managed to make the bad public relations created by those pesky onboard batteries catching fire in 2013 practically disappear. Not through good management. But through a never-ending series of disasters and catastrophes that shows no sign of letting up which is dominating Boeing’s news cycle that there is no remaining airtime for missteps like those battery fires.
Apple recently did something that it isn’t in the habit of doing. And that is – admitting failure. After spending $ 10 billion on ‘Project Titan’ whose aim was to produce a ‘really cool car,’ Apple decided to pull the pin and cancel it.
Simplifying Apple’s Project Titan ambitions to something as pithy as creating a ‘really cool car’ might seem a little condescending. The problem for Apple was that unfortunately, this was the practical truth. And that is why it failed.
If I must date myself, I cut my teeth as a product development engineer in the automotive industry in the bad old days when warranty terms were shockingly poor. Let’s examine this through the lens of my first new car which I purchased in 1984. Why was my warranty coverage so bad, what drove the significant improvements seen in the industry since that time, and how do we now validate our products to keep it that way?
We like to think we make decisions based on information. We don’t. We make decisions based on emotions. And the most important emotion we rely upon for decision-making is confidence. We can be provided all the information in the world, but if we can’t understand it, trust it or believe it, we look for confidence in other ways. Often to disastrous outcomes.
The number of ‘well-funded’ production efforts full of ‘very smart people’ that routinely generate expensive but unreliable products is sadly, very high. And it all comes down to the wrong types of confidence that well-paid decision-makers chase.
In the current century, data is ubiquitous but how to make use of it to drive product decisions can take time and effort. Data visualization is a useful technique to identify patterns in a dataset and derive exploratory statistics to analyze trends.
[Read more…]
Let’s say that you and your team have done well. Your products or systems are reliable. They work, customers are happy, and the cost of unreliability is low. That’s the goal, right? Congratulations are in order.
However, enjoying great reliability performance was the goal. It is what we expected. It’s what we worked to achieve. Now what?
[Read more…]Since I published my first contribution about reliability, I’ve received a number of emails asking where the stress and strength distributions come from (Figure 1).
[Read more…]What does it mean to be a ‘visionary leader’? It starts with being different to most people. You can’t just become a visionary leader by completing a leadership course, being mentored by someone awesome, or by compiling an impressive curriculum vitae (although these can help people with the potential to become visionary leaders get there).
One of the first things that the then United States Army Chief of Staff (General George C. Marshall) did at the outbreak of World War II was to fire the majority of his officers who had climbed the ladder of military ranks throughout the previous 20 years of relative peace.
Boeing is really having a bad stretch. Or more specifically, the passengers flying in its 737 MAX aircraft are.
Most recently a ‘plug’ flew off the side of Boeing 737 MAX 9 plane in flight, leaving a refrigerator sized hole next to startled (but mercifully still living) passengers. A ‘plug’ is a panel that seals up a hole in the fuselage that is included during manufacture to allow an optional emergency exit to be installed.
This failure is not a good look … especially for a three-month-old plane. Lots of manufacturers of different machines throughout history have been able to successfully bolt panels to cover holes of a similar size to that of an aircraft emergency exit. It is not hard to do. Nor is it hard to have systems in place to make sure it is done right.
A month ago, I received a question, “Why the castles for the artwork?” It was not the first time someone wondered why we use line drawings of old stone building features or sketches of castle layouts. It is safe to say it was and remains a purposeful artwork selection to promote community around Accendo Reliability.
[Read more…]