Use of On-Demand Cloud Services to Model the Optimization of an Austenitization Furnace

Abstract

This article describes a smart manufacturing framework, comprising an on-demand, cloud-based deployment of a modeling application in a manufacturing operation. A specific use case, the optimization of the austenitization of steel parts, is presented. The framework uses a Kepler workflow as a cloud service to orchestrate and manage the data and computations required to implement a run-time model-based control and optimization approach on Amazon Web Services (AWS) resources. Austenitization is an energy intensive heat treating process commonly employed to harden and strengthen ferrous metals, such as steel. Pre-finished steel parts are heated to a specific temperature in a continuously operating industrial austenitization furnace without oxidizing the surface. The steel parts are then rapidly cooled or quenched in an oil bath. There is significant potential to optimize energy productivity by managing the energy usage needed to achieve the properties of the metal part instead of managing to operational process settings. Models of this process, which predict the furnace energy consumption and temperatures of parts as a function of time and position in the furnace and map temperatures to properties, have been previously developed; however, for operational use, the data and models need to be orchestrated for run-time operation, access to infrastructure, scalability, security, and support. A cloud-based approach is an alternative to the on-premise approach, in which an infrastructure for data, computational, and security needs to be built and maintained to support the application. A workflow service makes it possible to combine and sequence simulation and optimization software applications developed in several distinct MATLAB (The Mathworks Inc., Natick, MA) model configurations that are needed for various data-based calculations. The final output of the computation is the optimal operating condition of the furnace that minimizes the fuel consumption without violating the part target specifications. The workflow can be triggered on demand by an operator of the furnace or run at periodic intervals. All the computational resources required are instantiated and run at the start of the workflow and shutdown at the end of the workflow.