Nonlinear predictive control based on artificial neural network model for industrial crystallization

Integral feedback compensation control of sugar precipitation for Chinese medicine solution

“…The following main result is reached under the above analysis. Theorem: Given the control system (12), if the following condition is satisfied…”

“…However, strong nonlinearity of most chemical process shows the limitation of linear MPC, due to the limited validity of the linear model. Of late, relative algorithms are mainly iterative learning control [9,10] and nonlinear model-based predictive control [11,12].…”

Flame Failures and Recovery in Industrial Furnaces: A Neural Network Steady-State Model for the Firing Rate Setpoint Rearrangement

“…e capability of characterizing the behaviors of complicated systems without prior knowledge, low computational costs, and good interpolating performances is the main advantage of neural network models [28]. Different structures of artificial neural networks have been used for optimizing the operation of industrial processes; however, in general, two distinct categories can be identified in their applications: static neural network models are more common in real-time optimization (RTO) applications, whereas steady-state models are required for optimizing the operational conditions at the upper control layers; (2) dynamic neural models are used as the core of model predictive control at the lower control levels [29][30][31].…”

Soft-sensor for Mother Liquor Purity in The Industrial Cane Sugar Crystallization Based on Extreme Learning Machine and Particle Swarm Optimization

“…However, it's nearly impossible to build a precise model for sugar crystallization process due to its complex physical mechanism, nonlinearity, great inertia and strong coupling links, where lots of uncertain factors are involved [3][4]. In the sugar crystallization process monitoring field, the vast majority of researchers focus on the advanced control techniques [3][4][5][6][7][8][9][10][11][12][13][14][15][16] like nonlinear control, fuzzy predictive control, neural network with PID and robust control. However, the detection sensor devices for process parameters like supersaturation, concentration, purity, crystal content and crystal size uniformity etc., are hard to be measured in the real world, which makes the application of all those advanced control techniques stay at theoretical stage but not an actual one [17].…”