Computationally Efficient Neural Predictive Control Based on a Feedforward Architecture

Abstract

A new strategy for integrating system identification and predictive control is proposed. A novel feedforward neural-network architecture is developed to model the system. The network structure is designed so that the nonlinearity can be mapped onto a linear time-varying term. The linear time-varying model is augmented with a Kalman filter to provide disturbance rejection and compensation for model uncertainty. The structure of the model developed lends itself naturally to a neural predictive control formulation. The computational requirements of this strategy are significantly lower than those using the nonlinear neural network, with comparable control performance, as illustrated on a challenging nonlinear chemical reactor and a multivariable process, each with both nonminimum and minimum phase behavior. PreludeWarren Seider has been a pioneer in the use of nonlinear models for optimization and control. While model predictive control (MPC), as initially applied in the oil and petrochemical industries, was based on linear convolution coefficient-based models, Warren recognized that there was no inherent limitation to linear models. His publications with David Brengel were among the first to use nonlinear models as the basis for control computations in a model predictive control framework. He also used nonlinear MPC as a basis for integrating design and control, recognizing that the limitations to linear controller performance could impose unnecessary limitations to the process design. One of the most impressive attributes of Professor Seider is his ability to bring novel design and control concepts directly into the undergraduate classroom. His process design textbook with Professors Seader and Lewin makes these research results accessible to undergraduate students, many of whom will have the chance to implement these techniques early in their industrial career. It is with pleasure that we contribute a paper on a new technique to incorporate a neural-network-based model into a model predictive control strategy to this special issue dedicated to Professor Seider. IntroductionThere has been a trend toward specialty chemicals manufacturing, with production plants that frequently change operating conditions to meet varying product requirements for different consumers. Linear control strategies, which work quite well in maintaining a plant at a given steady state, may fail when required to operate over a wide range of conditions. To develop appropriate control strategies, accurate nonlinear models of the processes must first be developed. The use of fundamental firstprinciples models has been applied to control specialty and batch chemical processes. 1,2 First-principles models can give physical insights into the system. This physical insight allows for more meaningful interpretation of control system behavior, and a first principle's basis often means the model is accurate over a wider range of input/output space. However, not all systems lend themselves to fundamental models without considerable time and effort. Thou...

Continuous Glucose Monitoring: Real-Time Algorithms for Calibration, Filtering, and Alarms

“…A number of different structures and training procedures can be used for artificial neural networks. Kuure-Kinsey and associates 60 presented a process application of a feed-forward ANN, while Kuure-Kinsey and Bequette 61 showed that a recurrent ANN yields better future predictions. A major disadvantage to nonlinear techniques, such as ANN, is that much training data are needed (for model parameter estimation).…”

Offset-free neural network-based nonlinear model predictive controller design using parameter adaptation

“…This approach is known to be computationally efficient, however, it is sensitive to approximation error. In Kuure-Kinsey [11,12], a linear time-varying neural network model is augmented with a disturbance model, this disturbance is subsequently estimated using a Kalman filter and used to update prediction model in the predictive controller thus, compensating for unmeasured disturbances and model uncertainty. Jazayeri and Fatehi, [13] proposed the use of a disturbance model to model the effects of external disturbances and plant-model mismatches.…”

Neural Network Predictive Control Based Power System Stabilizer

“…The Neural Network Model Predictive Control (NN-MPC) is another typical and straightforward application of neural networks to nonlinear control. When a neural network is combined with MPC approach, it is used as a forward process model for the prediction of process output [14,15]. Neural network model predictive control has been applied on the process control as chemical, industry applications.…”