Bio-inspired multi-agent systems for reconfigurable manufacturing systems

Abstract

The current market's demand for customization and responsiveness is a major challenge for producing intelligent, adaptive manufacturing systems. The Multi-Agent System (MAS) paradigm offers an alternative way to design this kind of system based on decentralized control using distributed, autonomous agents, thus replacing the traditional centralized control approach. The MAS solutions provide modularity, flexibility and robustness, thus addressing the responsiveness property, but usually do not consider true adaptation and re-configuration. Understanding how, in nature, complex things are performed in a simple and effective way allows us to mimic nature's insights and develop powerful adaptive systems that able to evolve, thus dealing with the current challenges imposed on manufacturing systems. The paper provides an overview of some of the principles found in nature and biology and analyses the effectiveness of bio-inspired methods, which are used to enhance multi-agent systems to solve complex engineering problems, especially in the manufacturing field. An industrial automation case study is used to illustrate a bio-inspired method based on potential fields to dynamically route pallets.

Dynamic self-organization in holonic multi-agent manufacturing systems: The ADACOR evolution

“…Drawing inspiration from the social behaviour of schools of fishes and flocks of birds, it is concluded that they work very well as a group, maintaining the system equilibrium and, e.g., avoiding predators [24], which in this case are external system perturbations. The inexistence of any central authority regulating this global behaviour makes this mechanism even more robust and powerful.…”

“…Biology and nature, as well as chaos and evolutionary theories are suitable sources of inspiration to design and develop solutions for solving complex, large-scale problems aimed at increasing their potential by embedding emergent concepts such as self-organization [24]. One example is the use of self-organization principles, which can be described as the ability of a system to arrange itself autonomously and spontaneously, mainly due to internal interactions, and without the need to use a central authority [25].…”

Improving the ADACOR2 supervisor holon scheduling mechanism with genetic algorithms

“…Of particular interest are the bio-inspired algorithms that are being widely used as the optimization mechanisms to solve problems in diverse branches of society, namely in Engineering or Mathematics [3].…”

Measures of reconfigurability and its key characteristics in intelligent manufacturing systems

“…Some of this work includes modular machine tools and material handlers (Heilala and Voho 2001;Landers et al 2001;Shirinzadeh 2002;Müller et al 2013) and distributed automation (Brennan and Norrie 2001;Vyatkin 2007;Lepuschitz et al 2010;Vallee et al 2011). Additionally, a wide set of artificially intelligent paradigms such as multi-agent systems (Shen and Norrie 1999;Shen et al 2000;Leitao 2009; Leitao and Restivo 2006;Leitao et al 2012;Ribeiro and Barata 2013;Lin et al 2013;Trappey et al 2013), and Holonic manufacturing systems (Babiceanu and Chen 2006;Marik et al 2002;McFarlane and Bussmann 2000;McFarlane et al 2003) have emerged. This work is particularly concerned with the integration of these intelligent control techniques within manufacturing systems.…”