STOCHASTIC FIELD MODELS FOR APPROXIMATING HIGHLY NONLINEAR RANDOM RESPONSES

Abstract eng:
The paper discusses different stochastic field models for approximating highly nonlinear responses. A key requirement for a good stochastic modeling is to be intimately related to the physics of the problem. Simple approximation procedures that have been popular in the past, may not work for many real-life problems. Classical Response Surface Method (RSM) is often insufficiently accurate for applications that involve highly nonlinear relationships. The paper describes different stochastic field modeling techniques that based on the author’s experience are adequate for high-complexity applications. These techniques are: (i) stochastic field expansion techniques, (ii) stochastic field interpolation techniques and (iii) stochastic localaveraging expansion techniques. Each category of these stochastic techniques has advantages and disadvantages that the analyst should understand before using them for a real application.

• Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks
• Add to your basket