Rensselaer Polytechnic Institute

Raj Subbu

Arthur C Sanderson

Robert J Graves

Cem Hocaoglu

A method and architecture for efficiently solving complex distributed problems uses coevolutionary agents incorporating evolutionary algorithms located at different nodes in a distributed network. The coevolutionary agents conduct localized database searches and evolve at their respective nodes while sharing information with other coevolutionary agents working the same problem. Results or solutions to the problem posed are available at each network node containing a coevolutionary agent working the problem.

System and method for time-efficient distributed search and decision-making using cooperative co-evolutionary algorithms executing in a distributed multi-agent architecture

A Virtual Design Module (VDM) used in a networked design environment generates manufactured product designs that are near optimal in terms of cost and production cycle time by using design data files containing alternative parts and manufacturers information. Numerous product design alternatives are considered and evaluated in terms of design-manufacturing-parts-supplier feasibility and real-time information on cost and production cycle time for realization. The VDM generates a population of new designs with appropriate board design information to allow for design-manufacturer-supplier decision making and determines the feasibility of each member of the current generation of designs and rejects designs that are not feasible. The VDM triggers Mobile Software Agents (MSA) that obtain data for parts availability, cost, lead time and manufacturer data for manufacturing availability, cost and lead time for each feasible member of the current generation of designs and return the data. In one application for printed circuit board design, the VDM evaluates each member of the current generation of designs by calculating cost, lead-time and value using a J function. The VDM then improves board designs through selection and use of board design modifiers. The process continues until optimized designs are obtained. Optimized board designs are output as results to an operator.

Growing community of inventors

Troy, NY, United States of America

Raj Subbu