Your Reliability Engineering Professional Development Site
Find all articles across all article series listed in reverse chronological order.
Failures happen. Sometimes product failures happen quickly.
You just bought a new feature rich computer and discover it doesn’t work. Right out of the box, it will not power up. Conversations with the tech support and it’s a trip back to the store.
The failures that occur early the in the life of a product tend —
this ‘tend’ really is just a vague ‘in general’
…tend to occur because of manufacturing errors or shipping/installation damage.
Not always, though. [Read more…]
First off, switches are not perfect, so this situation includes the reliability of the switch. Switch reliability may be a factor of storage time, probability of actually working when called on to work, or number of switching cycles. Each switch technology may be slightly different. For this equation, you need the reliability or probability of success given the primary unit has failed. Although we are assume the switch reliability is independent of the primary unit reliability and subsequent failure.
[Read more…]
This is not the same as a confidence interval. For a mean or standard deviation, we can calculate the likelihood that the true parameter is within a range of values — confidence interval concerning a parameter.
A tolerance interval applies to the individual readings, not the statistics. The interval contains a certain proportion of the values within the distribution of individual data points. The endpoints are tolerance limits. [Read more…]
Your customers are your best testers for your next product. They will explore the features. Expose the product to use conditions in unconscious ways. And, they will let you what they consider failures without needing the specification document.
During the development process, you and team may work to understand what customer may want or expect for the new product. You may even conduct focus groups or review past product field failures and call center records. [Read more…]
First off, switches are not perfect, so this situation is hypothetical. Yet, when you are exploring adding standby redundancy and haven’t sorted out the switching mechanism, you may be purely curious about the benefits of the redundancy. [Read more…]
Mechanical systems wear out and fail eventually. The ability of a structure to support a load, move through the specified range of motion, or spin degrades with use and time. Even our joints eventually wear out.
Accelerated life testing (ALT) has plenty of literature concerning the failure mechanisms unique to electronic components and materials. This is partially due to the limited number of unique electronic components compared to the often custom mechanical designs. ALT also has value as it provides information about a system’s reliability performance in the future.
Let’s explore an example of mechanical reliability testing (an ALT) in order to outline a basic approach to ALT design and analysis. [Read more…]
Most statistics books and the CRE Primer have tables that permit you to avoid calculating the probability for common distributions. The normal distribution requires numerical methods to conduct the calculations and would not be feasible during the CRE exam. [Read more…]
Suppliers often include reliability information along with performance specifications.
We look for reliability statements as one part of the selection process to ascertain if the component is likely to have sufficient reliability.
When the vendor’s data is clearly stated and meaningful, that information saves us from potentially having to conduct our own reliability evaluations. [Read more…]
There are a number of different methods to calculate confidence intervals for a proportion. The normal approximation method is easy to use and is appropriate in most cases.
Clopper and Pearson describe the Clopper-Pearson method also called the exact confidence interval and we’ll describe it in a separate article.
There are other methods, which again will find a description in separate articles. [Read more…]
If you buy more than one of an item used in your product, you will have to deal with variability. In general, the variability from part to part is minimal and expected. Occasionally, the variability is large and causes reliability problems. [Read more…]
As with other point estimates, we often want to calculate the confidence interval about the estimate. The intent is to determine the range of reasonable values for the true and unknown population parameter. For MTBF, this no different.
It was late Friday afternoon and the phone rang. Which is rarely a good thing.
There seems to a significant spike in field failures due to one component. The initial failure analysis work reveals the issue started with a batch of parts received about two months ago and the flaw continues to appear in subsequent batches. [Read more…]
When using a sample to calculate a statistic we are estimating a population parameter. It is just an estimate and the sample due to the nature of drawing a sample may not create a value (statistic) that is close to the actual value (parameter). [Read more…]
The communication between suppliers or vendors and their customers is often using a mix of specifications and requirements.
Customers set requirements and suppliers offer specifications. When they match, or when a supplier component specifications meet the customer’s requirements, we have the potential for a transaction. [Read more…]
Control charts help us monitor and stabilize a process. A little graphics along with statistics provides a tool to identify when something has changed. Some changes are abrupt and obvious, other a little more subtle, yet the out of control signals each have approximately the same chance of alerting us to a change.
A little graphics along with statistics provides a tool to identify when something has changed. Some changes are abrupt and obvious, other a little more subtle, yet the out of control signals each have approximately the same chance of alerting us to a change. [Read more…]