|Auto-tuning PID controller using neural network
Neural networks (Computer science)
Hong Kong Polytechnic University -- Dissertations
|1 v. (various pagings) : ill. ; 30 cm
|PID auto-tuning controllers based on neural network model are described in this dissertation. There are a number of papers describing the auto-tuning PID controller using neural network. However, they are mainly realised in discrete time. Moreover, the neural network used directly identifies the process and is acted as a tool to determine the Jacobian of the process, hence to tune the parameters of the discrete time PID controller. Therefore, the neural network used requires a prior knowledge of the process such as the order and the deadtime of the process in order to have a good identification of the process. In this dissertation, a methodology is proposed which does not require a priori information on the process. In fact, the process is first on-line identified by a neural network accompanied with a first order plus deadtime (FPD) model generator based on the input and output response of the process. The parameters of the model are then used to tune a PID controller with reference to the ziegler and nichols tuning formula. The controller is realized by a continuous time implementation; i.e. a numerical solution of differential equation rather than a transformation to the Z-domain. Hence, the structure of the neural network does not depend on the order of the process. In addition, a PID auto-tuning controller with a single neuron structure is described. The single neuron used has three input connections that have associated weights. Each gain parameter corresponds to each weight of the single neuron. The performance of the PID controllers are simulated with three general types of process.
|All rights reserved
Files in This Item:
|For All Users (off-campus access for PolyU Staff & Students only)
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: