Dealing with uncertainties in engineering problems using only available data

• We show how difficult is to find data about a real engineering problem.
• Due to lack of data we have to use different theories to model the uncertainties.
• We combine all types of uncertainties and propagate them through the model.
• We show different ways to represent the uncertainty in the quantity of interest.

This paper is the second in the series of three addressing the problem of how to deal with uncertainties in the modelings of engineering problems using only available data. The problem of the heat exchanger was selected as the example because it is sufficiently complex but still simple so that the difficulties and ideas will be apparent. There are various theories on how to treat the uncertainties in the first paper. In the series we use only the fuzzy set, respectively the possibility theory. In this paper we use the fuzzy approach for some model parameters and the probability approach for the others. The third paper will use the Bayesian theory.