A global optimization algorithm based on plant growth is used to perform the dimensional synthesis of a slider-crank mechanism. The PGO is based on the plant growth characteristics in which an artificial plant growth model is built including leaf growth, branching, phototropism, and spatial occupancy. The plant growth process is that a plant grows a trunk from its root; some branches will grow from the nodes on the trunk; and then some new branches will grow from the nodes on the branches. Such process is repeated, until a plant is formed. This process is simulated in this algorithm by producing new points (branch points) from initial points (roots). After producing the new points (branch points), the algorithm searches the optimum solution around these points through the operation called leaf growth (for local search). This is used to improve the accuracy of the solution.
In this algorithm, Nelder-Mead Simplex method is used for local search for a case. For the synthesis of Slider-crank mechanism, pattern search method is used as the local search method. Initially the PGO is applied to a test function and the results are in good agreement to the analytical solution. Then it is applied to the slider-crank mechanism to perform the dimensional synthesis such that for a given set of crank angles, the slider occupies specified positions. The results obtained here are in agreement with the results obtained from the other synthesis procedures described in the literature. It is concluded that the PGO algorithm presented here can be applied to solve such problems.