reliability-engineering

Weibull fitting to right-censored failure-time data estimates parameters to compute MTTF, hazard rate, and B-life metrics. The analysis uses Python with numpy, scipy, pandas, and the reliability library to process datasets and generate survival curve outputs.

FMEA RPN prioritization evaluates failure modes by calculating Risk Priority Number as Severity multiplied by Occurrence multiplied by Detection. This ranks failure modes to highlight those requiring corrective action for engineering risk mitigation.

Fault tree analysis computes top event probability by building AND and OR logic structures from basic events. It also derives importance measures like Birnbaum structural importance to quantify individual component engineering risk contributions.

Reliability block diagrams model system reliability using series, parallel, and k-of-n voting logic structures. This evaluates overall system availability and computes combined reliability metrics for complex engineering architectures.

Accelerated life testing applies stress models like Arrhenius or power-law equations to extrapolate failure behavior to use conditions. It projects high-stress failure data into normal operating reliability metrics.

Reliability engineering analysis requires Python with numpy, scipy, matplotlib, pandas, and the reliability library. These dependencies support Weibull fitting, fault tree evaluation, and risk output generation.