Preliminary design using the Bees Algorithm D.T.Pham, M. Castellani, A.Ghanbarzadeh Manufacturing Engineering Centre, Cardiff University, CF24 3AA, U.K. Abstract Computer aided preliminary design can be regarded as a special case of optimisation, where the goal is to generate as many solutions as possible above a pre-defined performance threshold. The higher the number of solutions satisfying the preliminary selection criteria, the greater is the chance to produce a good final solution. The Bees Algorithm was recently developed by the authors for function and combinatorial optimisation. The algorithm mimics the food foraging behaviour of honey bees to combine exploitative neighbourhood search with random explorative search. An improved version of the Bees Algorithm is proposed for computer-aided preliminary design. The algorithm has been adapted for discrete function optimisation and tested on a simple machine design task, preliminary gearbox design. The test consists of finding as many alternative gearbox configurations as possible that approximately produce the required output speed using one of the available input speeds. Experimental results show that the proposed Bees Algorithm outperforms random search and a genetic optimisation algorithm. 1 Introduction Until now, research efforts in computer aided design (CAD) have mainly focused on detailed design. Effective computing tools have been developed for tedious and time consuming tasks such as finite element analysis (FEA), simulation, and draughting for the later design phases. The initial creative part of the design process is still carried out almost exclusively by humans.