2020/02/14 by Srikanth Chandar, Chandar, Srikanth, Harsha Sunder +1
Computer Science · Engineering · Physics and Astronomy · #FOS: Computer and information sciences #FOS: Electrical engineering #Fault Detection and Control Systems #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2002.10228
openalex publication_date 2020/02/14 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this paper, we introduce a novel architecture to connecting adaptive\nlearning and neural networks into an arbitrary machine's control system\nparadigm. Two consecutive Recurrent Neural Networks (RNNs) are used together to\naccurately model the dynamic characteristics of electromechanical systems that\ninclude controllers, actuators and motors. The age-old method of achieving\ncontrol with the use of the- Proportional, Integral and Derivative constants is\nwell understood as a simplified method that does not capture the complexities\nof the inherent nonlinearities of complex control systems. In the context of\ncontrolling and simulating electromechanical systems, we propose an alternative\nto PID controllers, employing a sequence of two Recurrent Neural Networks. The\nfirst RNN emulates the behavior of the controller, and the second the\nactuator/motor. The second RNN when used in isolation, potentially serves as an\nadvantageous alternative to extant testing methods of electromechanical\nsystems.\n