A vast majority of engineering problems are inverse problems, while the mathematically based engineering problem solving methods and computational mechanics are primarily capable of solving forward problems. Nature has evolved highly effective, robust and imprecision tolerant problem solving strategies for very difficult inverse problems. Biologically inspired soft computing methods such as neural network, genetic algorithm and fuzzy logic inherit the basic characteristics of nature’s problem solving methods and, as such, they are suitable for inverse problems in engineering. In this chapter we start by discussing the fundamental differences between the mathematically based engineering problem solving methods and biologically inspired soft computing methods. Bulk of the rest of the chapter is devoted to applications of neural networks in computational mechanics and several difficult inverse engineering problems.
CITATION STYLE
Ghaboussi, J. (2010). Advances in neural networks in computational mechanics and engineering. In CISM International Centre for Mechanical Sciences, Courses and Lectures (Vol. 512, pp. 191–236). Springer International Publishing. https://doi.org/10.1007/978-3-211-99768-0_4
Mendeley helps you to discover research relevant for your work.