NN-based Prediction Interval for Nonlinear Processes Controller

Neural networks (NNs) are extensively used in modelling, optimization, and control of nonlinear plants. NN-based inverse type point prediction models are commonly used for nonlinear process control. However, prediction errors (root mean square error (RMSE), mean absolute percentage error (MAPE) etc.) significantly increase in the presence of disturbances and uncertainties. In contrast to point forecast, prediction interval (PI)-based forecast bears extra information such as the prediction accuracy. The PI provides tighter upper and lower bounds with considering uncertainties due to the model mismatch and time dependent or time independent noises for a given confidence level. The use of PIs in the NN controller (NNC) as additional inputs can improve the controller performance. In the present work, the PIs are utilized in control applications, in particular PIs are integrated in the NN internal model-based control framework. A PI-based model that developed using lower upper bound estimation method (LUBE) is used as an online estimator of PIs for the proposed PI-based controller (PIC). PIs along with other inputs for a traditional NN are used to train the PIC to predict the control signal. The proposed controller is tested for two case studies. These include, a chemical reactor, which is a continuous stirred tank reactor (case 1) and a numerical nonlinear plant model (case 2). Simulation results reveal that the tracking performance of the proposed controller is superior to the traditional NNC in terms of setpoint tracking and disturbance rejections. More precisely, 36% and 15% improvements can be achieved using the proposed PIC over the NNC in terms of IAE for case 1 and case 2, respectively for setpoint tracking with step changes.