JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Ayenew, Yenesew | |
| dc.date.accessioned | 2025-03-03T07:51:08Z | |
| dc.date.available | 2025-03-03T07:51:08Z | |
| dc.date.issued | 2023-12 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/16518 | |
| dc.description.abstract | This paper describes a model predictive control of a 4 × 3 Multiple-Input Multiple-Output (MIMO) biomass control system that improves control performance by using radial basis function (RBF) as an activation function. By gathering measured input and output data from the 31.5 MW Tana Beles sugar mill and applying a black box modeling technique to the data analysis, the biomass boiler model is created from the system identification box in MATLAB. The main objective of this work is to use Radial Basis Function Neural Networks (RBFNN) to increase model accuracy, which in turn improves the overall control system, in order to improve the MIMO control performance of a biomass boiler. Three outputs and four inputs are present in biomass boilers. The temperature, pressure, and drum level are the outputs, and the inputs are airflow 1, airflow 2, water flow, and stocker speed(the speed of the motor that feeds bagasse or sugarcane pulp). The MATLAB R2021a software with system identification toolbox was used to program the RBFNN model. The suggested model predictive controller using RBFNN model produced shorter settling times of 0.286 s, 1.873 s, and 0.637 s, as well as tolerable overshoots of 0.505%, 1.5%, and 15.698% for temperature, pressure, and level, respectively. On the other hand, the settling times with the same controller and state space model are 2.318 s, 5.461 s, and 6.147 s, respectively, with overshoots of 4.737%, 8.152%, and 38.194% for the three variables. The model predictive control and the recommended approach were contrasted. This is because, the state space model is always constant, in contrast to the neural network’s active monitoring of boiler dynamics. This will be done by finding the nonlinear neural network model for the biomass boiler and then linearized by using linearization method because of the variables in Biomass Boiler are nonlinear and time varying. The measured input output data will be gathered from Tana Beles sugar factory for neural network training data. Finally using radial basis function artificial neural network of the plant model there is good system performance than that of boiler model without RBFANN. Key Words: Radial Basis Function, neural network Modelling, Model Predictive Controller, Artificial Neural Network | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | Electrical and Computer Engineering | en_US |
| dc.title | Radial Basis Function Artificial Neural Network Based Model Predictive Controller For Biomass Boiler System (Case study in Tana Beles Sugar Factory) | en_US |
| dc.type | Thesis | en_US |
