1 / 5

Real Time Nonlinear Model Predictive Control Strategy for Multivariable Coupled Tank System

Real Time Nonlinear Model Predictive Control Strategy for Multivariable Coupled Tank System. Kayode Owa Supervisor - Sanjay Sharma University of Plymouth. Introduction. Most chemical processes are multivariable and have strong nonlinear dynamics.

lynda
Download Presentation

Real Time Nonlinear Model Predictive Control Strategy for Multivariable Coupled Tank System

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Real Time Nonlinear Model Predictive Control Strategy forMultivariable Coupled Tank System Kayode Owa Supervisor - Sanjay Sharma University of Plymouth UKACC PhD Presentation Showcase

  2. Introduction • Most chemical processes are multivariable and have strong nonlinear dynamics. • Linear models and conventional controllers are not sufficient to handle these processes. • This creates challenges in developing nonlinear multi input multi output (MIMO) models and advance control strategies. • Background and motivation for research • Process dynamics change over time, equipment degrade and valves do wear out. • Original mathematical models tend to mismatch with the real plant. • Models are limited to small range of operations. UKACC PhD Presentation Showcase

  3. Research methodology • System identification – use raw data for modelling • Wavelet activated neural network nonlinear model • Online real time optimisation using genetic algorithm (GA) • Nonlinear model predictive control (NMPC) strategy • Simulation and Real time practical implementation • Current status • Real time practical implementation stage for abnormal conditions • Contribution to knowledge • Novel approach using WNN-NMPC for coupled tank system (CTS) UKACC PhD Presentation Showcase

  4. NMPC Strategy Results mse=0.0049 ace=82.41 mse=0.0036 ace=55.01 mse=0.0046 ace=78.26 mse=0.0022 ace=65.92 (a) ANN (a) ANN (b) WNN (b) WNN sReal time Results sSimulation Results UKACC PhD Presentation Showcase mse=mean squared error, unit is m2 ace=average controller energy, unit is v2

  5. Conclusion • The proposed wavelet neural network (WNN) NMPC strategy is more efficient than ANN in MIMO case. • Real time optimisation (RTO) of the controller actions is achieved using GA. • Future works will check the robustness of this approach for abnormal conditions of plants dynamic. UKACC PhD Presentation Showcase

More Related