### Refine

#### Institute

#### Keywords

- Architektur <Informatik> (1)
- CAD (1)
- Computerunterstütztes Verfahren (1)
- Ingenieurbau (1)
- Internet (1)
- Modellierung (1)
- Planungsprozess (1)
- Verteiltes System (1)

Interval analysis extends the concept of computing with real numbers to computing with real intervals. As a consequence, some interesting properties appear, such as the delivery of guaranteed results or confirmed global values. The former property is given in the sense that unknown numerical values are in known to lie in a computed interval. The latter property states that the global minimum value, for example, of a given function is also known to be contained in a interval (or a finite set of intervals). Depending upon the amount computation effort invested in the calculation, we can often find tight bounds on these enclosing intervals. The downside of interval analysis, however, is the mathematically correct, but often very pessimistic size of the interval result. This is in particularly due to the so-called dependency effect, where a single variable is used multiple times in one calculation. Applying interval analysis to structural analysis problems, the dependency has a great influence on the quality of numerical results. In this paper, a brief background of interval analysis is presented and shown how it can be applied to the solution of structural analysis problems. A discussion of possible improvements as well as an outlook to parallel computing is also given.

Although there are some good reasons to design engineering software as a stand-alone application for a single computer, there are also numerous possibilities for creating distributed engineering applications, in particular using the Internet. This paper presents some typical scenarios how engineering applications can benefit from including network capabilities. Also, some examples of Internet-based engineering applications are discussed to show how the concepts presented can be implemented.