Artificial neural networks and evolutionary algorithms in engineering design

Purpose: Purpose of this paper is investigation of optimization strategies eligible for solving complex engineering design problems. An aim is to develop numerical algorithms for solving optimal design problems which may contain real and integer variables, a number of local extremes, linear- and non-linear constraints and multiple optimality criteria. Design/methodology/approach: The methodology proposed for solving optimal design problems is based on integrated use of meta-modeling techniques and global optimization algorithms. Design of the complex and safety critical products is validated experimentally. Findings: Hierarchically decomposed multistage optimization strategy for solving complex engineering design problems is developed. A number of different non-gradient methods and meta-modeling techniques has been evaluated and compared for certain class of engineering design problems. The developed optimization algorithms allows to predict the performance of the product (structure) for different design and configurations parameters as well as loading conditions. Research limitations/implications: The results obtained can be applied for solving certain class of engineering design problems. The nano- and microstructure design of materials is not considered in current approach. Practical implications: The methodology proposed is employed successfully for solving a number of practical problems arising from Estonian industry: design of car frontal protection system, double-curved surface forming process modeling, fixings for frameless glazed structures, optimal design of composite bathtub (large composite plastics), etc. Originality/value: Developed numerical algorithms can be utilised for solving a wide class of complex optimization problems.