การออกแบบสำหรับชิ้นส่วนเชิงกลโดยใช้วิธีการหาค่าเหมาะสมที่สุดแบบกลุ่มอนุภาค

Abstract

This research focuses on the development and application of the Particle Swarm Optimization (PSO) method to solve commercial mechanical design problems used in various mechanical industries such as a pressure vessel, a spring, a disc brake in order to simplify the calculation of objective functions with many complex constraints and help to decide the most optimal choice for mechanical component designs. The research contains single-objective and multi-objective mechanical component design problems which the algorithm is improved by using the Re-initial and the Migration methods for single-objective while the GLN-PSO and the Re-initial methods for multi-objective. The researcher used 8 equations from previous research to test. The results show that the improved PSO and MOPSO provide better solution sets than other methods from previous research. This research also provides guidelines for improving the efficiency of PSO and MOPSO in future research.