Reliability
Definition
The probability that an item will perform its required function under stated conditions for a specified period of time. Reliability is a quantitative measure expressed as a probability (0 to 1) or percentage. It is a function of the failure rate and time: for constant failure rate systems, R(t) = e^(-lambda*t). Higher reliability means lower probability of failure over the same period.
Context
The foundational concept in reliability engineering. Reliability quantifies how trustworthy a piece of equipment is over time. In Reliatic, reliability metrics (MTBF, MTTF, failure rate) are calculated from reliability event data and displayed in the reliability analytics module with Weibull analysis and trend visualization.
Formula
R(t) = e^(-lambda*t) for constant failure rate; R(t) = e^(-(t/eta)^beta) for Weibull
Examples
- A pump with a failure rate of 0.002 failures/hour has a reliability of R(1000) = e^(-0.002*1000) = 0.135, meaning a 13.5% probability of surviving 1000 hours without failure.
- The reliability dashboard shows that process pumps across the facility have an average reliability of 95% over a 12-month period, with centrifugal pumps outperforming reciprocating pumps.
Applicable Standards
- IEC 60300-3-1
- ISO 14224:2016
- MIL-HDBK-217
Related Terms
The proportion of time that an item is in a state to perform its required function under given conditions, assuming that the required external resources are provided. Availability combines reliability (how often it fails) and maintainability (how quickly it can be restored). Inherent availability considers only corrective maintenance; operational availability includes all downtime including preventive maintenance and logistics.
MaintainabilityThe probability that a failed item can be restored to operational condition within a specified period of time when maintenance is performed under stated conditions using prescribed procedures and resources. Maintainability is a design characteristic that reflects how easy, fast, and cost-effective it is to diagnose, access, repair, and verify the restoration of a failed item.
Failure Rate(Lambda)The average number of failures per unit of time for a population of items, typically expressed as failures per hour, per year, or per million hours. Failure rate (lambda) is the reciprocal of MTBF for constant-failure-rate systems. It is a statistical average measure, distinct from the instantaneous hazard rate, and is most accurate when the failure rate is approximately constant (beta near 1).
Mean Time Between Failures(MTBF)The average time between consecutive failures of a repairable system or component, calculated as the total operating time divided by the number of failures during that period. MTBF is the primary reliability metric for repairable systems and represents the expected time of continuous operation between failure events. Higher MTBF indicates better reliability.
Mean Time To Failure(MTTF)The average time from the start of operation until the first failure of a non-repairable item, or the average time between replacement and next failure for items that are replaced rather than repaired. MTTF is technically correct for non-repairable components (bearings, seals, filters, lamps) while MTBF applies to repairable systems. In practice, the terms are often used interchangeably.
Weibull DistributionA continuous probability distribution widely used in reliability engineering to model the time-to-failure of components and systems. The two-parameter Weibull distribution is defined by the shape parameter (beta) and scale parameter (eta). Its versatility lies in its ability to model increasing, constant, or decreasing failure rates depending on the shape parameter value, making it suitable for all phases of the bathtub curve.
Where this appears in Reliatic
This concept is used in the Reliability Analytics module.