Neural Network Based Model Predictive Control Of Maglev System Using Particle Swarm Optimiztion With Control Radom Exploration Velocity
By: Periyasamy, D.
Contributor(s): Keerthana, K.
Publisher: New Delhi Journals Pub 2019Edition: Vol.5(2), Jul-Dec.Description: 1-12p.Subject(s): EXTC EngineeringOnline resources: Click here In: International journal of VLSI design and technologySummary: This paper deals to create a mathematical exemplification of Maglev system using the model of artificial neural network and cost function minimization using particle swarm optimization with control random exploration velocity. An effective application of Model Predictive Control using a neural network as the Maglev system model is presented in this paper. The two concerns in model predictive controller one is prediction and another one is optimization of cost function. Then artificial neural network models turned the consideration of MPC users due to their ability to absolutely identify complex nonlinear relationships between dependent and independent variables with less effort. The other concern in model predictive controller is computational cost, as it does prediction and optimization at each sampling instant. The main cost in the usage of non-linear programming as the optimization algorithm is in the calculation of the Hessian matrix (second derivatives) and its inverse which is difficult and costly. There is a class of evolutionary algorithms, which are derivative free techniques that uses some tools motivated by biological evolution. Simulation consequences show convergence to a virtuous solution within minimum number of iterations and hence real time control of fast-sampling system like the Maglev system is possible.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2020-2021181 |
This paper deals to create a mathematical exemplification of Maglev system using the model of artificial neural network and cost function minimization using particle swarm optimization with control random exploration velocity. An effective application of Model Predictive Control using a neural network as the Maglev system model is presented in this paper. The two concerns in model predictive controller one is prediction and another one is optimization of cost function. Then artificial neural network models turned the consideration of MPC users due to their ability to absolutely identify complex nonlinear relationships between dependent and independent variables with less effort. The other concern in model predictive controller is computational cost, as it does prediction and optimization at each sampling instant. The main cost in the usage of non-linear programming as the optimization algorithm is in the calculation of the Hessian matrix (second derivatives) and its inverse which is difficult and costly. There is a class of evolutionary algorithms, which are derivative free techniques that uses some tools motivated by biological evolution. Simulation consequences show convergence to a virtuous solution within minimum number of iterations and hence real time control of fast-sampling system like the Maglev system is possible.
There are no comments for this item.