An Accendo Reliability recorded webinar event

NoWe like to think that we make decisions based on the information we have available to us. We don’t. We instead make decisions based on emotions. And the most dominant emotion we rely upon when making a decision is confidence. You can have all the information in the world, but if you don’t understand it, don’t trust it, or otherwise don’t believe in it, then you won’t have the confidence to make the right decision. And we often try and generate ‘false’ confidence by having lots of clauses in contracts, schedule lots of tests, and demand people comply with standards. But the confidence these things create is a façade that quickly gets broken down when our products don’t meet our expectations. Want to understand the only way you should be generating confidence when it comes to reliability engineering? Join us for this webinar!

An Accendo Reliability recorded webinar event

NSome of you might have heard of the ‘bell curve.’ Some of you might have heard that the ‘bell curve’ is sometimes called the ‘normal distribution.’ There is a reason it is called normal … but that is not always obvious. But then there is the ‘lognormal distribution.’ What is this? … and how does it relate back to the ‘bell curve?’ There is a really good reason for this link. And the good thing is that all you need is just a little bit of knowledge about how something breaks (and is repaired) to help use the lognormal distribution to help you make lots of important decisions … easily!

An Accendo Reliability recorded webinar event

Some of you might have heard of the Weibull distribution. It is an uncannily accurate way of describing many of the ways components fail. It can model things that wear-in where failure is caused by pre-existing damage and defects in a fraction of products. The Weibull distribution can also model things that wear-out we failure is caused once enough damage has accumulated. And some of you might have heard of the ‘3 Parameter Weibull distribution.’ But what makes this different and (sometimes) helpful? We are always wanting to improve the way we model things, including failure processes. So to see if the ‘3 Parameter Weibull Distribution’ can help you … join this webinar!

An Accendo Reliability recorded webinar event

We often use probability distributions to help us characterize the likely values a random variable will have. This includes the random variable we call ‘time to failure’ or TTF, which is how long something works before it fails. Failure is a random process, but just because it is random, doesn’t mean it’s unpredictable. Products that wear-in will have vastly different probability distributions for TTF when compare do products that wear-out. So you need to have a good idea of the probability distribution of the TTF of your product when it comes to reliability engineering. But we often see in textbooks and standards the ‘exponential distribution’ simply being assumed as a ‘good’ TTF probability distribution. But is it? And what happens when it isn’t … but you use it anyway? Join this webinar to find out!

An Accendo Reliability recorded webinar event

Let’s make a comparison. Let’s check our product’s key characteristics against specifications, compare vendor life data, or compare the newest design changes to prior performance. We can and should do comparisons well using the appropriate statistical approach.

Let’s examine a handful of parametric and non-parametric comparison tools, including various hypothesis tests. Plus how to best use these tools and when to set them aside and explore another approach.

An Accendo Reliability recorded webinar event

Everyone has heard of the ‘bell curve.’ Sports show hosts, teachers, scientists, and a bunch of other people routinely use the term ‘bell curve’ to describe uncertainty. But do you know where it comes from? It is not just a ‘pretty shape’ that seems to work, It comes from a really cool physical phenomena that we find everywhere. So, the ‘bell curve’ naturally aligns with how our primitive human brain often tries to characterize or visualize uncertainty. The other really cool thing about the bell curve (and lots of other curves that look like bells) is that if we find it in our reliability data, it automatically tells us where to look in order to improve reliability. If you want a basic introduction to one of the most common statistical concepts with NO EQUATIONS … this is the webinar for you!

An Accendo Reliability recorded webinar event

Whether new to reliability or a veteran, you have probably heard about the Weibull distribution. It has almost mythical status amongst those who conduct reliability data analysis … or in other words – turning a jumble of dots (data points) into information that actually means something. So why do we ‘worship’ the Weibull distribution? What is so special about it? Whether you have been doing this for a long time or five minutes, you will get something out of this webinar that looks at one of the most popular tools for reliability analysis.

An Accendo Reliability recorded webinar event

Gage R&R – this is mainly a quality tool, where 10% is a pass and 10-30% is “marginal.” What does that mean, or even better yet, how can I use gage R&R to provide meaningful results in a design environment without specifications? In 30 minutes, we will discuss how you can calculate Gage discrimination – the more useful result for a design situation, and even how to use it for destructive reliability tests.

An Accendo Reliability recorded webinar event

Reliability is a measure of your product or system. Confidence is a measure of you. But we often forget this. We often subject our new product, system, or service to test after test until it reaches this thing called ‘required statistical confidence.’ But this is often an illusion, which is great! Because if statistical confidence is often not ‘real’ confidence, then we don’t always have to resort to statistics to get confidence. In fact, those of us who exclusively rely on statistics are usually those who lack confidence in the product, system or service and need a security blanket to make them feel OK. This webinar talks about confidence from the perspective of the ‘process owner.’ The design team lead. The CTO. The junior engineer. And how you can get a much healthier version of confidence through the way we design and produce our ‘things’ so that when it comes time to test … we are (justifiably) supremely confident that we will absolutely dominate whatever statistical testing hurdle can be thrown our way. And this sometimes means we don’t need to deal with statistics at all!

An Accendo Reliability recorded webinar event

OK … we have all been there. We have all sat in some statistical presentation or read a document containing mathematical symbols and statistical hieroglyphics we don’t understand. And we pretend we do understand so that we don’t embarrass ourselves. The people we don’t want to embarrass ourselves in front of usually also pretend to understand those symbols and hieroglyphics. This webinar is a light (re)introduction to common mathematical symbols used in many engineering scenarios … including reliability.

An Accendo Reliability recorded webinar event

When fitting a line or curve to data, it’s a model. When modeling, it is worth remembering the George Box quote, “Essentially all models are wrong, but some are useful.” Yet, how do we separate a useful model from one that isn’t useful? One step in finding a helpful regression model is to consider the residuals. BTW: Weibull analysis is another term for regression analysis.

An Accendo Reliability recorded webinar event

You may fondly, or most likely not fondly, remember your undergraduate course on probability and statistics. The calculations of various winning hands with card games were interesting and connected to the early ‘invention’ of probability and statistical methods. Yet, the jar with colored beads was rather boring.

An Accendo Reliability recorded webinar event

Once we have made something really reliable (or really available) … then comes the part where we have to work out how many of them we need (if they make up a fleet) or how many spare parts we need to keep them running. That is where discrete distributions are really helpful. They assign probabilities to ‘discrete’ random variables. These are random variables that can only have certain specified values. Like whole numbers. For example … the number of failures you expect to see in a mission. Or the number of available systems out of a given fleet size. If this sounds like something that could help you out … see you for this webinar!

An Accendo Reliability recorded webinar event

Ok. They say there are lies, damn lies, and statistics. At the heart of statistics are these intimidating functions like ‘probability density functions’ and ‘cumulative distribution functions.’

They mean something – but are practically useless unless they help inform a decision. And we, as engineers, are supposed to know what these functions mean. But have you ever sat in a meeting or presentation where you realized some gaps in your knowledge? … or perhaps you felt like you were given too many charts but not enough help to make your decision?

If you want a really easy introduction or review of these functions – then check out this webinar!