Please use this identifier to cite or link to this item:
https://doi.org/10.1109/TIE.2007.909064
Title: | Neural controller for UPS inverters based on B-spline network | Authors: | Deng, H. Oruganti, R. Srinivasan, D. |
Keywords: | Digital control Inverters Iterative methods Neurocontrollers Spline functions Uninterruptible power systems |
Issue Date: | Feb-2008 | Citation: | Deng, H., Oruganti, R., Srinivasan, D. (2008-02). Neural controller for UPS inverters based on B-spline network. IEEE Transactions on Industrial Electronics 55 (2) : 899-909. ScholarBank@NUS Repository. https://doi.org/10.1109/TIE.2007.909064 | Abstract: | This paper proposes a controller for uninterruptible power supply inverters based on a particular type of online-trained neural network, which is called the B-spline network (BSN). Due to its linear nature and local weight updating, the BSN controller is more suitable for real-time implementation than conventional multilayer feedforward neural controllers. Based on a frequency-domain stability analysis, a design methodology for determining the two main parameters of the BSN are presented. The model is found to be similar to that of an iterative learning control (ILC) scheme. However, unlike ILC, which requires a complex digital filter design that involves both causal and noncausal parts, the design procedure of the proposed BSN controller is straightforward and simple. Experimental results under various conditions show that the proposed controller can achieve excellent performance, comparable to that of a high-performance ILC scheme developed earlier. The proposed controller is an attractive alternative to both the multilayer feedforward neural controller and iterative learning controller in this and similar applications. © 2008 IEEE. | Source Title: | IEEE Transactions on Industrial Electronics | URI: | http://scholarbank.nus.edu.sg/handle/10635/56780 | ISSN: | 02780046 | DOI: | 10.1109/TIE.2007.909064 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.