Statistics
AuraScore 81/100

Accelerated Degradation and Reliability Test Protocol Plan

Formulate a Weibull-based accelerated life test and failure analysis plan for industrial components under combined stress.

Deploy this template when designing life-data testing programs, ALT matrices, and survival models to estimate component reliability and B-life targets before full-scale manufacturing release.

Template

Role: Senior Reliability Engineering Statistician specializing in industrial asset lifecycle modeling and survival analysis.

Context

  • Target component under test: {{component_name}}
  • Applied environmental stress variables: {{stress_variables}}
  • Nominal design life expectation: {{expected_lifetime_hours}}
  • Target statistical confidence level: {{confidence_level}}
  • Test time truncation & censoring scheme: {{censoring_scheme}}
  • Target unreliability threshold: {{target_b10_life}}

Task

Author an accelerated degradation and life-testing (ALT) protocol plan for {{component_name}} to statistically validate reliability targets against {{target_b10_life}} under combined {{stress_variables}}.

Method

  1. Select the physics-of-failure stress acceleration model (e.g., Arrhenius, Inverse Power Law, generalized Eyring) matching {{stress_variables}}.
  2. Design the stress level matrix (nominal, elevated, destructive) ensuring uniform failure mechanism activation without inducing non-representative failure modes.
  3. Calculate required sample sizes and allocation across stress cells to achieve {{confidence_level}} confidence on the life parameter estimates.
  4. Define the right-censored or interval-censored data logging protocol matching {{censoring_scheme}} across the test duration.
  5. Formulate maximum likelihood estimation (MLE) and rank regression routines for 2-parameter and 3-parameter Weibull distribution fitting.
  6. Structure acceleration factor (AF) extrapolations to map accelerated time-to-failure distributions back to nominal {{expected_lifetime_hours}}.
  7. Detail goodness-of-fit diagnostic criteria (Kolmogorov-Smirnov, Anderson-Darling, log-likelihood ratios) for parametric distribution validation.
  8. Establish corrective engineering feedback triggers if the projected B10 life fails to satisfy {{target_b10_life}}.

Constraints

  • MUST specify the exact mathematical form of the acceleration transfer function.
  • MUST NOT allow untested extrapolation beyond substantiated thermal/mechanical stress limits.
  • Confidence bounds MUST use Fisher Information Matrix or likelihood ratio approximations.
  • Total testing protocol MUST clearly state sample size per stress tier.

Output format

Deliver the test protocol plan structured as follows:

  1. Reliability Target Definition & Stress Physics Profile
  2. Experimental Stress Allocation Matrix (table: Stress Level, Sample Count, Temp/Vib Setpoints, Duration)
  3. Statistical Estimation Methodology (Weibull/Lognormal MLE Equations & Censoring Handling)
  4. Acceleration Factor & Lifetime Extrapolation Framework
  5. Model Diagnostic & Goodness-of-Fit Verification Plan
  6. Risk Mitigation & Protocol Execution Timeline

Self-review

  • Confirm that the acceleration models match the physical characteristics of {{stress_variables}}.
  • Verify sample size calculations mathematically support the requested {{confidence_level}}.
  • Check that the censoring rules correctly align with {{censoring_scheme}}.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-statistics
manufacturing-industrial
reliability
weibull-analysis
alt-testing