Research on the NNARX Model Identification of Hydroelectric Unit Based on Improved L-M Algorithm

Zhi Huai Xiao; Zhou Peng An; Shu Qing Wang; Shi Qi Zeng

doi:10.4028/www.scientific.net/AMR.871.304

Paper Titles

Design Optimization of an Industrial Muffler by Taguchi Method
p.277

Artificial Immune Systems with Negative Selection Applied to Health Monitoring of Aeronautical Structures
p.283

Research on Dynamic Characteristics of Anti-Reverse Valve for Hydraulic Excavator Rotary Motor
p.290

The Unsteady Flow and Forced Response for a Variable Nozzle Turbine
p.296

Research on the NNARX Model Identification of Hydroelectric Unit Based on Improved L-M Algorithm
p.304

3D Simulation Training Systems on Ship Lift of Hydropower Station
p.310

A Spiral Actuated Micro In-Pipe Robot for Pipes Diameter 15mm
p.315

A Study on Analysis Method Considering Camber for the Carbody Deflection of the Urban Transit Vehicles
p.323

Algorithm of Marriage in Honey Bees Optimization Coperate with Linear Method
p.330

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 871Research on the NNARX Model Identification of...

Research on the NNARX Model Identification of Hydroelectric Unit Based on Improved L-M Algorithm

Abstract:

Its hard to use traditional ways to set up a hydroelectric power plant model due to its complex, time-varying and nonlinear characteristics. This article uses the neural network autoregressive with exogenous input (NNARX) to identify and model hydro-turbine generating unit which is the key in the hydroelectric power plant modeling. The random guide vain signal is used to train NNARX in this paper and the other two working conditions are used to check its generalization ability. In order to improve identification accuracy, generalization performance and training speeds, an improved Levenberg-Marquardt algorithm is proposed in this article which is based on the L-M algorithm that widely used in artificial neural network weights adjustment. Simulation results indicate that NNARX model with improved L-M algorithm can reach high recognition accuracy and have good generalization ability. It can provide a good simulation model for intelligent controller design in the future.

You might also be interested in these eBooks

Applied Mechanics, Fluid and Solid Mechanics

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 871)

Pages:

304-309

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.871.304

Citation:

Cite this paper

Online since:

December 2013

Authors:

Zhi Huai Xiao*, Zhou Peng An, Shu Qing Wang, Shi Qi Zeng

Keywords:

Artificial Neural Network (ANN) Identification, Hydroelectric Unit Modeling, Improved L-M Algorithm, NNARX Modeling

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Jing Lei, Yei Luqing, and Zhou Jianzhong, Study of Neural Network Identificability for Hydroelectric Generating Unit, International Journal. Hydroelectric Energy. China, vol. 15, p.17–23, Jun (1997).

Google Scholar

[2] Guo Jun and Dong Zhaoxia, Modeling and Analysis for Hydroelectric Generating Unit based on Neural Networks, Proceeding of the EPSA. China, vol. 15, p.37–40, Dec (2003).

Google Scholar

[3] Wang Shuqing and Li Zhaohui, Research on identification of Hydraulic Turbine Model based on Adapting Fuzzy Neural Network, Engineering Journal of Wuhan University. China, vol. 39, No. 2, p.24–27, Apr (2006).

Google Scholar

[4] Nand. Kishor, S. P. Singh and A. S. Raghuvanshi, Adaptive Intelligent Hydro Turbine Speed Identification with Water and Random Load Disturbances, Engineering Applications of Artificial Intelligent. vol. 20, p.795.

DOI: 10.1016/j.engappai.2006.11.014

Google Scholar

[5] Nand. Kishor, P. R. Sharma, A. S. Raghuvanshi, An Investigation on Pruned NNARX identification model of Hydropower Plant, Engineering with Computers, vol. 21, p.272–281. doi: 10. 1007/s00366-006-0016-z.

DOI: 10.1007/s00366-006-0016-z

Google Scholar