Neural Network Based Sensorless Maximum Wind Energ

Uploaded from authorPOINTLite
Views:
 
Category: Entertainment
     
 

Presentation Description

No description available.

Comments

By: allammy (31 month(s) ago)

hi plz allow me to download

By: allammy (31 month(s) ago)

thank you its agreat works

By: meetujain (33 month(s) ago)

hi plz allow me to download

By: nishu69 (38 month(s) ago)

can u pls send me the detail report on this to nischith10@gmail.com

Presentation Transcript

Neural Network Based Sensorless Maximum Wind Energy Control with Compensated Power Coefficient: 

Neural Network Based Sensorless Maximum Wind Energy Control with Compensated Power Coefficient Hui Li Dept. of ECE FAMU-FSU College of Engineering Tallahassee, FL32310

Current Mechanical Sensorless Peak Power Tracking Control: 

Current Mechanical Sensorless Peak Power Tracking Control

Proposed work : 

Proposed work

Variable Wind Speed System: 

Variable Wind Speed System (a) PMSG wind Generator (b) SCIG wind Generator

Analysis of Wind Turbine Maximum Power: 

Pm output mechanical power of the wind turbine,  air density,  tip speed ratio, Cp the power coefficient, rm adius of the rotor,  wind turbine rotor swept area, Vw wind velocity, r rotor speed of the turbine Analysis of Wind Turbine Maximum Power

Wind velocity estimation by ANN (I): 

Wind velocity estimation by ANN (I)

Wind velocity estimation by ANN (II): 

Wind velocity estimation by ANN (II)

Peak Control strategy with compensation of power coefficient drift: 

Peak Control strategy with compensation of power coefficient drift

Derivation of Pseudo-power curve: 

Derivation of Pseudo-power curve (a) (b)

Peak Control strategy with compensation of power coefficient drift: 

Peak Control strategy with compensation of power coefficient drift

Simulation Study of PMSG Wind Generator: 

Simulation Study of PMSG Wind Generator

SCIG Wind Generator: 

SCIG Wind Generator

Experimental Setup: 

Experimental Setup

Experimental Results: 

Experimental Results

Conclusion: 

Conclusion A maximum mechanical power of the wind turbine can be well tracked at both dynamic and steady states; A neural network based wind velocity estimator is developed to provide fast and accurate velocity information to avoid using anemometers; A neural network based scheme is presented to compensate the potential drift of wind turbine power coefficient curve without extra sensors A maximum mechanical The simulation study and experimental results of PMSG wind generator and SCIG wind generator proves the validity of the method.