Home / Maintenance / Reliability
Paste from Excel the hours (or cycles, km) to failure of each unit and those still running, and see the failure pattern, B10 life with confidence interval, mission reliability, warranty cost and how many units to test to prove the goal. You only need a column of times and another saying F (failed) or C (still running); 5 to 10 failures already give a first estimate, with wide ranges.
Pre-sizing and estimating tool: results do not replace design, calculations or reports signed by a licensed professional, nor verification against the applicable codes and standards.
Each point is a failure at its modified Kaplan-Meier position; censored units enter the position calculation. Line = fitted distribution; band = CI of the percentiles. Points on the line: the distribution describes the data well.
How to read: horizontal axis = time to failure (log scale); vertical axis = cumulative % failed, on a scale where the distribution becomes a straight line. Points = real failures; line = fitted model; band = confidence interval. To read B10, follow the 10% line to the fit and drop to the time axis. A steep line (high β) = failures bunched together, predictable wear-out; a flat line = scattered failures.
The same data on four scales. Pick the one with the straightest points: lowest adjusted Anderson-Darling and highest correlation.
How to read: each panel shows the same times on one distribution’s scale (Weibull, lognormal, exponential, normal). The one that lines the points up best describes the data; in the table that is the lowest Anderson-Darling and the highest correlation. If two tie, prefer the one with a physical explanation: Weibull for fatigue and wear, lognormal for corrosion and cracks.
Parameters with standard error and confidence interval, mean and quartiles of the fitted distribution and the percentile table (Bx life).
Steps = Kaplan-Meier (data, no distribution assumed; + = censored); curve = fitted distribution with CI. Agreement confirms the fit.
How to read: horizontal axis = time; vertical axis = % of units still working. The steps come straight from the data (Kaplan-Meier, + marks censored units) and the smooth curve is the model, with its band. Steps and curve together = good fit. To know how many survive to a given time, go up from that time to the curve.
Instantaneous failure risk of units still running. Rising = wear-out (preventive replacement pays); constant = random; falling = infant mortality (improve assembly and start-up).
How to read: horizontal axis = time; vertical axis = risk of failing now, among units still working. Rising curve = wear-out (preventive replacement before the rise pays off); flat line = random failures (preventive does not help, only redundancy or spares); falling curve = infant mortality (run-in or burn-in and improve assembly).
Where failures concentrate in time. Ticks on the axis = observed failures.
How to read: horizontal axis = time; the curve shows when failures happen; the peak is the most likely moment. The ticks on the axis are the observed failures. A narrow curve = predictable failures (good for planning replacement); a wide or long-tailed curve = hard-to-predict failures.
Each group fitted separately, tests for equal parameters (likelihood ratio) and equal survival curves (log-rank and Wilcoxon).
Parallel lines = same shape (same failure mode); the one shifted right lasts longer. Crossing lines = different failure modes.
How to read: one line per group (supplier, lot, design) on the same probability paper. Parallel lines = same failure mode; the one further right lasts longer. Lines with different slopes or that cross = different failure modes: investigate the cause before picking the "best" group.
Kaplan-Meier for each group (steps) and fitted distribution (dashed). The B10 life difference between groups shows directly on the chart.
How to read: one survival curve per group: steps = data, dashed = model. The highest, right-most curve belongs to the group that lasts longest. The horizontal gap between curves at the 90% height is the B10 life difference between groups.
Expected cumulative failures in the units sold over time, with CI; the vertical line is the end of the warranty.
How to read: horizontal axis = time in the field; vertical axis = cumulative number of sold units expected to have failed, with the uncertainty band. The vertical line marks the end of warranty: where it crosses the curve is the total expected claims. If the curve climbs fast after the line, extending the warranty is expensive.
How many units and how much test time to prove the goal at the chosen confidence (Weibull with known β).
x axis = how much the true life (η) exceeds the goal. A design just at the goal passes with probability 1 − C; allowing failures (m > 0) protects a design slightly better than the goal.
How to read: horizontal axis = how many times the design’s real life exceeds the goal (1× = exactly at the goal); vertical axis = chance of passing the test. One curve per number of failures allowed. A design "right at the limit" almost always fails; the further right the curve rises, the more margin the design needs to pass safely.
Each curve is an equally valid plan: pick the combination that fits your test rig and schedule.
How to read: each curve joins combinations of number of units (horizontal axis) and test time per unit (vertical axis, as a multiple of the goal time) that give the same proof. More units = shorter test. Pick the point that fits your bench and your deadline.
Take this page’s results to another calculator with the fields already filled in.
The calculation report gathers this page's inputs, results, equations, assumptions and references, with fields for project, engineer and revision. The full report also includes the charts and interpretations, in color. In the print dialog, choose Save as PDF.
It fits a life distribution to a component’s times to failure. The shape β tells whether failures are early (β < 1), random (β ≈ 1) or wear-out (β > 1), and the scale η is the age by which 63.2% have failed. From that you estimate B10 life, mission reliability, preventive replacement interval and warranty cost.
Include them all, marked with status C (right-censored). Dropping them or treating them as failures underestimates life: in the bearing example, 12 of Supplier A’s 26 units were still running. Maximum likelihood uses the fact that they lasted at least that long.
Use maximum likelihood by default, especially with heavy censoring: it handles censoring exactly and gives confidence intervals. LSXY, the line on the probability plot, often does better with few failures (fewer than 10 to 15) and little censoring.
Compare the adjusted Anderson-Darling and correlation in the distribution identification: the lowest AD and highest correlation win. If two tie, choose by physics: Weibull for fatigue, wear and bearings; lognormal for cracks, corrosion and repairs; exponential only when the failure rate is constant, as in electronics after burn-in.
It is the time by which 10% of units fail. Bearings are rated by L10 life (= B10), and warranties are usually set below B1 or B5. Use the lower bound of the confidence interval for conservative decisions, since the estimate comes from a sample.
Paste the group column. The page fits each group, tests whether the parameters are equal (likelihood ratio) and whether the survival curves differ (log-rank and Wilcoxon). In the example, Supplier A has a much higher B10 than B, with log-rank p ≈ 0.03: the difference is real.
Use the demonstration test plan: enter the goal (for example, 90% at 4,000 h), the confidence, the known β and how many failures you accept. The page returns the test time per unit for a given number of parts, or the number of parts for a given time, and shows the chance that a good design passes.
Important notice: Indus Metrics tools produce estimates and pre-sizing results from the data you enter and from published engineering methods. They do not replace design, calculations or reports signed by a licensed professional engineer (PE), nor verification against the applicable codes, standards and regulations, such as OSHA rules and the ASME codes. Material and fuel properties vary: check manufacturer data or your own process analyses before deciding. By using this site you agree to the Terms of Use.
© 2026 Indus Metrics. Found an error? Write to contato@seudominio.com.