A System of Systems (SoS) design amplifier

This paper takes a System of Systems (SoS) approach to the realization of machine intelligence. It is a case study pertaining to the symbolic design of a Freon refrigeration device, which is subsequently transformed using a knowledge base into a thermoelectric refrigerator. The process first explores the design of two-stage refrigeration and inherent differences between fluid mechanics and thermoelectric devices. These random differences are learned by the system, generalized, and made available for subsequent replay in design transformations. It is empirically demonstrated that cross-domain symmetries can play a major role in design generation in particular and in the design of SoS in general. The fundamental theory of randomization is the science, which underpins the practice.