Deep Generative Model-Based Synthesis of Four-Bar Linkage Mechanisms Considering Both Kinematic and Dynamic Conditions

Abstract Mechanisms are essential components designed to perform specific tasks in various mechanical systems. However, designing a mechanism that satisfies both kinematic and dynamic requirements is a challenging task. The kinematic requirements may include the workspace of a mechanism, where the maximum scalar displacement of the mechanism can be derived from this region. On the other hand, the dynamic requirements of a mechanism may include its torque transmission, which refers to the ability of the mechanism to transfer power and torque effectively. In this paper, we propose a deep generative model that can generate multiple crank-rocker four-bar linkage mechanism samples that satisfy both the kinematic and dynamic requirements aforementioned. The proposed model is based on a conditional generative adversarial network (cGAN) with some modifications for mechanism synthesis, which is trained to learn the relationship between the requirements of a mechanism with respect to linkage lengths, and generates multiple mechanism samples that satisfy given requirements. The results demonstrate that our proposed method can successfully generate multiple mechanisms that satisfy specific requirements. Our approach has several advantages over traditional design methods. It enables designers to explore a larger design space and efficiently generate multiple diverse and feasible designs. Also, the proposed method considers both the kinematic and dynamic requirements, which can lead to more efficient and effective mechanisms for real-world use, making it a promising tool for linkage mechanism design.