Deep Neural Controller: a Neural Network for Model-free Predictive Control and its Application to Viscosity Control in Chemical Process

摘要

This' paper suggests Deep Neural Controller (DNC), a network architecture for sequential decision making based on high order Markovian state-space model. DNC is composed of two components, one for modeling system dynamics and another for constructing decision making policy. In this architecture, deriving control policy is conducted by training DNC network. We first employ a deep neural network to model the dynamic behavior of a complex dynamic system that has high-order Markovian property By integrating the complex neural state-space model with controller network, we can solve high-order Markovian, non-convex control problem with neural network. As a particular example, we employ the suggested method that controls viscosity level in a chemical process.