Process structure-based recurrent neural network modeling for model predictive control of nonlinear processes

TL;DR: In this paper, a review of hybrid modeling techniques, associated system identification methodologies and model assessment criteria for chemical and biochemical processes is presented, with a focus on the use of big data and machine learning frameworks.

TL;DR: An overview of the recent developments of time-series neural network modeling along with its use in model predictive control (MPC) is presented in this paper , where a tutorial on the construction of a neural network-based model is provided and key practical implementation issues are discussed.

TL;DR: In this article , the authors provide a comprehensive comparison of the hybridization techniques with respect to their differences and similarities, as well as advantages and limitations and future perspectives and apply and illustrate hybrid modeling, physics-informed ML and model calibration via a chemical reactor case study.

TL;DR: An artificial neural network (ANN) model was adopted instead of using the existing linearized model in order to increase the speed of optimization and accuracy of the model.

TL;DR: In this article, the authors present essential flow diagrams for understanding processes, including the structure of Chemical Process Flow Diagrams, and tools for evaluating system performance and performance curves for individual unit operations.

TL;DR: In this article, the existence of a smooth control-Lyapunov function implies smooth stabilizability, and the result is extended to real-analytic and rational cases as well.

TL;DR: Responding to a shortage of literature dedicated to ensemble learning, this volume offers comprehensive coverage of state-of-the-art ensemble learning techniques, including the random forest skeleton tracking algorithm in the Xbox Kinect sensor, which bypasses the need for game controllers.

TL;DR: In this article, a hybrid neural network-first principles modeling scheme is developed and used to model a fedbatch bioreactor, which combines a partial first principles model, which incorporates the available prior knowledge about the process being modeled, with a neural network which serves as an estimator of unmeasuredprocess parameters that are difficult to model from first principles.