Experiment design, reliability, uncertainty
Presentation
- Linear covariance models, multiple interactions, mixed models.
- Principle of randomized experiments and classical experiments design
- Factorial, fractional designs
- Examples with the SAS or JMP software
- Numerical design of experiments (quasi-Monte Carlo sequences, Latin Hypersquares)
- Response surfaces and metamodels (polynomials, kriging, links to statistical learning).
- Analysis of uncertainties for numerical simulations: propagation of uncertainties, reliability methods (FORM/SORM, order statistics ..) , sensitivity analysis
- Industrial applications: design with uncertainties, risk analysis.
Objectives
At the end of this module, the student will have understood and be able to explain:
- the main methods of experimental design,
- the analysis of uncertainties,
- the reliability methods,
- the probability estimation of of rare events.
The student will be able to:
- plan an experiment in the framework of a linear model,
- built a response surface
- perform a sensitivity analysis for the treatment of uncertainties in numerical simulation.
Needed prerequisite
Elements of statistical modelling [I4MMMS71]
Softwares and methods of statistical exploratory data analysis [4MMSP81]
Form of assessment
The evaluation of outcome prior learning is made as a continuous training during the semester. According ot the teaching, the assessment will be different: as a written exam, an oral exam, a record, a written report, peers review...