Fundamentals of Reliability Engineering (Accredited)

Differentiate repairable and non-repairable items and measure reliability using MTTF for non-repairables and MTBF for repairables, with light bulbs and cars as examples.

Understand mean time to failure (mttf) as the average life of non-repairable items, shown by bulb lifetimes, and relate lambda = 1/mttf to mean time between failures.

Explore how mean time between failures (MTBF) applies to repairable items, differentiating MTBF from MTTF and MTTR, with a 5000-hour example yielding about 1.75 failures per year.

Assess availability as uptime divided by total time. Learn how mean time to repair shapes the availability of repairable items.

Explore how reliability data can be complete or censored, including right, left, and interval censored data, and how this affects estimating mean time to failure and reliability predictions.

Explore right censored data in reliability calculations, distinguishing type one (time-based stopping) from type two (stop after a predefined number of failures), noting that type one is most common.

Explore censored data in reliability to estimate mean time to failure (MTTF). Learn why simple averages fail when many items survive, and how distribution fitting and Minitab aid estimation.

Learn how to handle censored data in reliability analysis using Minitab, avoid simple averages for mean time to failure, and apply a Weibull-based parametric approach to estimate MTTF.

Explore three failure patterns in reliability engineering: failure of weaker items, constant failure, and wear-out, and see how their combined bath-tub curve shapes product reliability over time.

Explore the bathtub curve in reliability engineering, with three phases—early failure, constant failure, and wear out—and how predictions assume a constant failure rate during the useful life.

Explore the hazard function as the instantaneous rate of failure, computed year by year from reliability data, linking it to bathtub curve's infant mortality, constant failure rate, and wear-out phases.

Explore the bathtub curve and its early failure, constant failure, and wear-out phases, and apply accelerated life testing, preventive maintenance, and reducing the load on components.

Explore reliability improvement by distinguishing quantitative and qualitative tests, focusing on the useful life phase of the bathtub curve, and examining ALT, HALT, HASS, ESS, and burn-in.

accelerated life testing uses higher temperatures to accelerate failures, then interprets results to estimate product life at the normal operating temperature, as a quantitative reliability method.

Identify the product's weak points and failure modes through HALT, a qualitative stress test using temperature and vibration that reveals how it fails rather than when.

Use accelerated stress screening to screen out bad products, reveal defects, and enable corrective action before shipment by testing within upper and lower operating limits to prevent early failures.

Explore environmental stress screening (ess) and burn-in as short-term reliability checks that reveal latent defects before shipment, contrasting with halt and hass and aiming to prevent infant mortality.

Define reliability as the probability of a system performing without failure over time and introduce reliability block diagrams for computing overall reliability from component data.

Compute system reliability from component reliabilities using serial and parallel connections. Use serial to multiply reliabilities; use parallel to compute one minus the product of (1 minus r).

Explore system reliability by solving two examples of reliability block diagrams with serial and parallel configurations, including nested cases, to compute a final overall reliability.

Explore reliability block diagrams, serial versus parallel configurations, and redundancy types—hot, standby, and k-out-of-m—using pump examples to boost overall system reliability.

Understand the Weibull distribution, a versatile continuous distribution used in reliability calculations; with shape, scale, and location parameters, it includes exponential behavior when the shape factor equals one.

Examine how the exponential distribution models reliability during the constant failure phase of the bathtub curve, using R(t) = e^{-lambda t} with lambda = 1/MTBF to predict reliability.

Explore why a constant failure rate leads to the exponential distribution. Use hazard rate concepts and e^-lambda t to estimate life and mean time to failure.

Apply the exponential distribution with a constant failure rate to compute reliability, using MTBF and lambda to estimate the probability of no failure over time.

Apply exponential distribution to reliability calculations for non-repairable products using meantime to failure, illustrating survival at 1500 hours and the 36%/63% rule.