Expand description
Monte Carlo dispersion, sensitivity analysis, optimization and challenge specifications.
Monte Carlo dispersion shows a run and how far to trust it. Sensitivity analysis ranks which inputs matter. Optimization finds the design that hits a target. Start here says what works today and what is planned.
montecarlo: one rocket flown many times with its uncertain inputs drawn afresh each time. It’s seeded and reproducible sample by sample, and runs in parallel with theparallelfeature.statistics: the spread of what the samples gave, with the failed ones counted.ellipse: where the landings scatter, as an ellipse holding a chosen share of them.sensitivity: which uncertain inputs move a result most, by Morris’s screening and Sobol’ indices.optimize: the design variables that make a result as small as it can be, to hit a target apogee, say. It uses CMA-ES, NSGA-II for two or more goals at once, or EGO for a slow model.
Status: dispersion, the apogee’s spread, landing ellipses and sensitivity analysis work. So does optimization over continuous and discrete variables, with constraints and with one goal or several. Optimizing a Monte Carlo statistic (a robust mode) and challenge specifications are planned (the roadmap).
Modules§
- ellipse
- Landing ellipses: where a rocket’s landings scatter on the ground, as an ellipse that holds a chosen share of them.
- montecarlo
- Monte Carlo dispersion: one rocket flown many times, each time with its uncertain inputs drawn afresh, to see how far its apogee and landing spread.
- optimize
- Optimization: the design variables that make a model’s output as small as it can be.
- sensitivity
- Sensitivity analysis: which of a model’s uncertain inputs move its output most.
- statistics
- Summaries of a sample of numbers: the spread of a Monte Carlo run’s apogees, say.
- table
- A Monte Carlo
Runas a table: one row a sample, in index order, and one column an input it drew or a number its flight came to.hpr mcwrites it as CSV (RunTable::csv), each number in the shortest form that reads back to the same bits, so a program reading the file gets the run’s own numbers.
Enums§
- Analysis
Error - What an analysis refuses or can’t do.