A variety of discussion and resources that I’ve found related to No MTBF.

Papers

While researching reliability predictions I ran across this paper that critically examines a few common reliability prediction methods.

Jais, C., Werner, B. & Das, D., 2013, Reliability and Maintainability Symposium (RAMS), 2013 Proceedings-Annual, Reliability predictions-continued reliance on a misleading approach. pp. 1-6.

A draft version of the paper that was eventually published as  “J.A.Jones & J.A.Hayes, ”A comparison of electronic-reliability prediction models”, IEEE Transactions on reliability, June 1999, Volume 48, Number 2, pp 127-134” A nice comparison and illustration of the variability to expect when using a parts count prediction method. Graciously provided by Jeff  – and it’s in draft form, so please pardon the odd typo’s etc. 

Draft Comparison of Electronic Reliability Prediction Methodologies [slideshare id=11756810&doc=draftcomparisonofelectronicreliabilitypredictionmethodologies-120226115557-phpapp01&type=d]

Bowles, J. B. and J. G. Dobbins (2004). “Approximate Reliability and Availability Models for High Availability and Fault-tolerant Systems with Repair.” Quality and Reliability Engineering International 20(7): 679-697.

Systems designed for high availability and fault tolerance are often configured as a series combination of redundant subsystems. When a unit of a subsystem fails, the system remains operational while the failed unit is repaired; however, if too many units in a subsystem fail concurrently, the system fails.

Under conditions usually met in practical situations, we show that the reliability and availability of such systems can be accurately modeled by representing each redundant subsystem with a constant, lsquoeffectiversquo failure rate equal to the inverse of the subsystem mean-time-to-failure (MTTF). The approximation model is surprisingly accurate, with an error on the order of the square of the ratio mean-time-to-repair to mean-time-to-failure (MTTR/MTTF), and it has wide applicability for commercial, high-availability and fault-tolerant computer systems.

The effective subsystem failure rates can be used to: (1) evaluate the system and subsystem reliability and availability; (2) estimate the system MTTF; and (3) provide a basis for the iterative analysis of large complex systems. Some observations from renewal theory suggest that the approximate models can be used even when the unit failure rates are not constant and when the redundant units are not homogeneous. Copyright © 2004 John Wiley & Sons, Ltd. Bowles, J. B. (2002).

“Commentary-caution: constant failure-rate models may be hazardous to your design.” Reliability, IEEE Transactions on 51(3): 375-377. This commentary examines the consequences, from a system perspective, of modeling system components using only their failure-rates, viz, the inverse of their MTTF, when, in actuality, they have a lifetime distribution with either an increasing or a decreasing hazard function.

Such models are often used because: they are tractable; they are thought to be “robust;” they depend only on average values; or only small amounts of data are available for calculations. However, the results of such models can greatly understate the system-reliability for some time periods and overstate it for others. Using MTTF as a figure of merit for system-reliability can be especially misleading. Furthermore, the redundancy in a redundant system might provide very little of the reliability improvement predicted by the constant failure-rate model, and series systems might, in fact, be much more reliable than predicted. The overall result is that a constant failure-rate model can give very misleading guidance for system-design

If you have a paper that you’d like to add to this list, please let me know.

Fred: One example I use when lecturing is the life time of a wine glass (or ceramic coffee mug). The probability of failure in the next day is independent of the age. Failure will occur when there is an accident (dropped on the floor or something in the dishwasher hitting it). Bill (email from William Q. Meeker Jr., Oct 26th, 2011)

Presentations

Learn about MTBF

One of the advantages of learning about MTBF is the same understanding applies to the many variations. Rather than engage in endless debates over what is or is not counted – shift the conversation to how to use the  information for decisions. What is in service to the decision?

The Perils page provides some information about MTBF and the web provides a wealth of information about this common metric. A basic understanding of this inverse of a failure rate goes a long way to determine if the data is being well represented.

Alternative Metrics

MTBF is often used to represent product life. It is not complete nor sufficient. Product life or reliability has four elements: function, probability, duration and environment. MTBF is only the probability and assumes (in most cases) the duration does not matter, or worse is not even stated.

As an alternative, use reliability directly. State the probability of success over a specified time frame, along with the functions (leads to understanding of product failure definition) and environment. The function and environment are often abbreviated, i.e. a respirator provides life support breathing in North American intensive care facilities. The details of the functions and environment are often well stated in product development and marketing documents.

The probability and duration may include multiple statements. One for important elements of the product life. For example, since products that failure during first use damage the product brand significantly, we may want to have a very high probability of success during the first 3 months of product use. Say, 99.99% reliability over first 3 months of use.

The warranty period may be another duration of interest. 98% reliability over the 1 year warranty period. And, the design life (how long the product should last and provide value to the customer) might be stated as 90% reliability over 5 years.

The early failures focus on component, assembly, shipping and installation sources of product failure. The warrant period and reliability is of interest as a business liability. The design life focuses on the longer term failure mechanisms.

Therefore, move away from a partial statement concerning product reliability. Make full use of clear statements of expectations (goals) and measures.

Teach Others

This one is easy – with your understanding of MTBF and the various pitfalls and misunderstandings. Do not permit those around you (peers, management, vendors, suppliers, and customers) continue to misunderstand and use incorrectly MTBF. Verify understanding and convey the actual meaning of the term.

Ask Questions

Besides asking about understanding and definitions, ask about the use of reliability statements.

• Where did this come from?
• How and when is this measure?
• What decisions does this metric support?
• How does the data support this measure?

Challenge Assumptions

There are two principle assumptions made related to MTBF – both require your challenge.

First, what is the evidence that the underlying time to failure data supports the use of the exponential distribution? Or, the concept of a constant failure rate over the product life?

And, if the data supports the assumption you still benefit by using reliability as the metric, rather than MTBF. As it avoids the common misunderstandings surrounding the metric.

Second, challenge the assumption based on ‘this is what our industry and customers always use’. A full statement of reliability can always be converted to an MTBF statement if required. To make decisions use the data and appropriate and accurate summaries and measures. To assist your vendors and customers fully understand the reliability requirements or claims, use a complete reliability statement.

In conclusion

Years ago while conducting factory assessments we often asked about and inspected a suppliers application of statistical process control (SPC). Often these programs were little more than a show of a few very poorly management and applied SPC charts that resulted in no process improvements. One factory even used a locked display cabinet to display the charts, convenient for customer inspection. Two years later the same charts were still on display. Worthless to them and us.

The point is MTBF and similar measures can have real value across the entire supply chain and product life cycle. Only when the measure accurately describes the data, if well or easily understood, and permits appropriate assessment of risks and tradeoffs. MTBF often fails these simple criteria.

What can you do? Do not use MTBF.