Biomedical subjects
Publications and source records attributed to R Russell Rhinehart.
A simple procedure is developed that uses concepts from statistical process control to filter noise from a process variable. Code is presented for the algorithm, and it is experimentally demonstrated on a pilot-scale process for which both noise and level change significantly and frequently.
A group of feed-forward neural networks (NNs), each providing the prediction of an individual process output at a future step, is used as the dynamic prediction model for the model-based predictive control (MPC) scheme in the proposed work. These NNs are parallel (independent) rather than cascaded--they are trained and implemented in parallel. Therefore, the complexity and effort in the training stage is decreased and compounded error propagation is eliminated from the prediction. A new strategy of compensating for the process-model mismatch under this grouped-NN model structure is also developed. Effectiveness of the scheme as a general nonlinear MPC is demonstrated by simulation results.