Optimizing Furnace efficiency for Factory of Future using Cooperative Games

Abstract

Approximately 65 to 90 percent of energy used in petrochemical and refining industries is consumed by furnaces. Operating furnaces at optimal conditions results in huge amounts of savings in energy consumption. In this paper, we model the furnace efficiency optimization as a multi-objective problem involving multiple interactions among the controlled variables and propose a cooperative game based formulation for the factory of future. The controlled variables are Absorbed Duty and Coil Outlet Temperature. We propose a comprehensive solution to select the best combination of manipulated variables (fired duty, throughput and coil inlet temperature) satisfying multiple criteria using a cooperative game theory approach. We compare this approach with the standard multi-objective optimization using NSGA-II and RNSGA-II algorithms. The new approach provides a single optimum solution, instead of a set of equally efficient configurations, as in the case of NSGA-II and RNSGA-II algorithms.