Your Reliability Engineering Professional Development Site
Environmental testing is the evaluation of a product or system in one or more stress conditions. Environmental as in that which surrounds and affects a product. Consider temperature. Is the product going to experience outdoor temperatures as found in Fargo, North Dakota or Belmopan, Belize?
The weather is one way to describe external stresses, yet it is so much more. Environmental testing may include fungus, insect, and animal exposure. The document MIL-STD-810G lists and describes testing methods for a wide range of environmental conditions. [Read more…]
Before computers and statistical software, we relied on tables to determine values for common integration problems – the normal distribution in particular. There is no closed form solution for the integral of the normal distribution probability density function, it requires advanced numerical methods to estimate the area under the curve. [Read more…]
Stop testing when the testing provides no value.
If no one is going to review the results or use the information to make a decision, those are good signs that the testing provides no value. Of course, this may be difficult to recognize.
Some time ago while working with a product development team, one of the tasks assigned was to create an ongoing reliability test plan. This was just prior to the final milestone before starting production. During development, we learned quite a bit about the product design, supply chain, and manufacturing process. Each of which included a few salient risks to reliable performance.
There are two basic ways to consider the central limit theorem. First consider a random variable, X, which has a mean, μ, and variance σ2. If we take a random sample from f(X) of size n and calculate the sample mean, X̄, then as n increases the distribution of the sample means, X̄’s approaches a normal distribution with mean, μ, and variance σ2/√n̄. The original data, X, may have any distribution and when n is suitably large the distribution of the averages will approach a normal distribution. [Read more…]
In the Monte Carlo method, one uses the idea that not all parts have the same dimensions, yet a normal distribution describing the variation of the part dimensions is not assumed.
Although the normal distribution does commonly apply, if the process includes sorting or regular adjustments or if the distribution is either clipped or skewed then the normal distribution may not be the best way to summarize the data.
As with any tolerance setting, getting it right is key for the proper functioning of a product. Monte Carlo method allows you to consider and use the appropriate models for the variations that will exist across your components. [Read more…]
A continuous distribution is useful in many statistical applications such as process capability, control charts, and confidence intervals about point estimates. On occasion time to failure, data may exhibit behavior that a normal distribution models well. [Read more…]
The root sum squared (RSS) method is a statistical tolerance analysis method. In many cases, the actual individual part dimensions fall near the center of the tolerance range with very few parts with actual dimensions near the tolerance limits.
This, of course, assumes the part dimensions are tightly grouped and within the tolerance range.
Setting tolerances well, using the best available data about the part(s) variation, allows creating designs that function well given the expected part variation. This is better for reliable performance. Also, the same method can be applied when the loads and stresses are normally distributed.
Check that assumption with you data first, of course. [Read more…]
Learn more and register for the CRE Prep course here. (registration is closed at this time)
The course is 16 two hour sessions – a mix of lecture, discussion and Q&A that focused on what you need to know to pass the ASQ CRE exam. Sure, beyond the course you will need to study. This involved practicing sample exam questions, using your references and calculator, and practicing finding answers quickly.
We discuss ways to study along with any issues or ideas you have as you prepare for the exam.
*Note: These online classes will be Archived and you will be able to access them later even if you cannot make it to the Live class session! This means you may watch them again in case you forget something, miss a class, or can’t make it one day. Saturdays may be scheduled with the instructor for extra sessions or make-up classes if needed.
Mondays, July 13 – August 17, 2015 (3:00PM-5:00PM PDT)
Last Session for questions, September 21 and 28, 2015 (3:00PM-5:00PM PDT)
This class ends prior to the semi-annual ASQ Section testing, where everyone may sign-up through their local Section to take their test. Be sure to check out the ASQ website to get the early-bird rate before the end of this course!
Looking forward to seeing you in the course. And, of course, at any time, feel free to ask questions here, or in the CRE Preparation LinkedIn group.
Learn more and register for the CRE Prep course here.
Similar to the Weibull distribution yet with slightly heavier tails. While not as easy to interpret if the data shows early life or wear out features, the lognormal distribution often fits time to repair data accurately.
Transform the data by taking the natural log of each data point. The resulting values tend to be normally distributed if the original data fits a lognormal distribution.
You can use base 10 or base 2 or any base and the results will still tend to be normally distributed. It is common to use natural log, ln(). [Read more…]
Worst-case tolerance analysis is the starting point when creating a tolerance specification.
It is a conservative approach as it only considers the maximum or minimum values of part variation—whichever leads to the worst situation. Setting tolerances such that the system will function given the expected variation of manufactured components improves that ability of the system to perform reliably.
In the worst-case method, you simply add the dimensions using the extreme values for those dimensions. Thus, if a part is specified at 25 ± 0.1 mm, then use either 25.1 or 24.9 mm, whichever leads to the most unfavorable situation.
The actual range of variation should be the measured values from a stable process. It may be based on vendor claims for process variation, industry standards, or engineering judgment. [Read more…]
A discreet distribution useful when counting events within a time period.
It models rates, such as the number of gophers in your garden, paint scratches on your car, or the number of shopping carts that arrive in the 5 minutes before you in line. Essentially it’s the count of something over a time period or defined area. [Read more…]
The exponential distribution is a model for items with a constant failure rate (which very rarely occurs).
If the chance of failure is the same each hour (or cycle, etc.), including the first hour, 100th hour, and 1 millionth hour or use, then the exponential distribution is suitable.
Many practitioners assume the failure rate either is constant or changes so little as to be essential constant in order to make reliability calculations simpler. [Read more…]
And, being encouraged to write a paper or two on drone reliability. Now that Amazon has a delivery drone patent, and industrial applications continue to announced daily, there is a need for serious reliability in these devices.
The early adopters and explorers in any nascent industry generally discover the many design faults including reliability issues. That is common.
As the drone industry develops, improving product reliability becomes a business necessity. For industrial application it is essential. [Read more…]
It is not enough to simply state your organization has a proactive stance concerning reliability. It more than running a few tests or thinking about reliability before the product ships or the equipment is installed.
It is a way of doing business.
