Abstract
Modelling plays a major role in predicting the behaviour of any system. It is also one of the crucial parts in the design of the control system and tuning of the controller. Tuning parameters are developed based on the transfer function obtained from the modelling process. The primary goal of this paper is to model and simulate a research grade Electric Resistance Furnace (ERF) under transient conditions and derive the transfer function using simulation data. Using this transfer function the gain parameters (PID, Proportional, Integral and Derivative) of the controller will be derived using conventional tuning approaches. The secondary goal is to provide an optimized model for future development of a Neural Network based controller for the furnace. The controller will be equipped with an auto tuning algorithm based on Model Predictive Control (MPC) which will have a Recurrent Neural Network (RNN) as a system model. The training data set for the RNN will be obtained by using the PID parameters derived in this paper. This would enable precise control of the furnace with lower rise and settling time, reduced or no overshoot, maximum stability and ramp hold ability.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Materials Science and Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
