Calculate Equipment Reliability
Abstract
Chris and Fred discuss how we can go about calculating equipment reliability … when you only have a small amount of information. Help!
Key Points
Join Chris and Fred as they discuss how you can calculate equipment reliability when you have a little bit of information. This comes from a listener who asked us to calculate the reliability of their equipment that failed four times in one month (with 400 hours of operation). How do we find this system’s reliability?
Topics include:
- So what is the number? If we assume a constant hazard rate (yuck) then we can use the exponential distribution to work out that the reliability at one month (400 hours) is 1.8 %.
- Is this helpful? Our listener didn’t tell us why they wanted a reliability number … but 1.8 % is almost certainly useless in terms of making better decisions. Why? Well we don’t know if our equipment is wearing in or wearing out. We don’t know if we have 10 pieces of equipment working at the same time over this month, with only 4 of them failing. So what do we do?
- What is the DECISION? This is a common question (refrain). What are you deciding to do with this number? We can’t think of a single decision that this 1.8 % estimate will help. Again, we don’t know if the equipment is wearing in or wearing out … which would affect our estimate. Knowing the precise times of failure would be really helpful as well. But is the decision more useful if it is based on availability? It sounds like the equipment is being repaired, so how long does it spend being repaired? What is the DECISION!
- Don’t just stick with numbers … look for WHY? Are you doing root cause analysis (RCA)? If you can (for example) quickly identify that the four failures were caused by incorrect startup procedures, and a quick change to those procedures would make the problems go away … fix it! Stop doing statistics on numbers you can make go away.
Enjoy an episode of Speaking of Reliability. Where you can join friends as they discuss reliability topics. Join us as we discuss topics ranging from design for reliability techniques to field data analysis approaches.
- Social:
- Link:
- Embed:
Leave a Reply