Prediction of Turbine Performance using Multilayer Feedforward Networks by Reducing Mapping Nonlinearity

2009 ◽  
Author(s):  
H. Lee ◽  
P. Hajela
Keyword(s):  
Feedforward Networks ◽  
Turbine Performance

Bi-modal derivative activation function for sigmoidal feedforward networks

2014 ◽  
Vol 143 ◽  
pp. 182-196 ◽  
Author(s):  
Sartaj Singh Sodhi ◽  
Pravin Chandra
Keyword(s):  
Activation Function ◽  
Feedforward Networks

scholarly journals Performance assessment and optimization of a helical Savonius wind turbine by modifying the Bach’s section

2021 ◽  
Vol 3 (8) ◽  
Author(s):  
M. Niyat Zadeh ◽  
M. Pourfallah ◽  
S. Safari Sabet ◽  
M. Gholinia ◽  
S. Mouloodi ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Performance Assessment ◽  
Turbulent Flows ◽  
Power Coefficient ◽  
Speed Ratio ◽  
Tip Speed Ratio ◽  
Basic Model ◽  
Turbine Performance ◽  
Primary Model ◽  
Savonius Wind Turbine

AbstractIn this paper, we attempted to measure the effect of Bach’s section, which presents a high-power coefficient in the standard Savonius model, on the performance of the helical Savonius wind turbine, by observing the parameters affecting turbine performance. Assessment methods based on the tip speed ratio, torque variation, flow field characterizations, and the power coefficient are performed. The present issue was stimulated using the turbulence model SST (k- ω) at 6, 8, and 10 m/s wind flow velocities via COMSOL software. Numerical simulation was validated employing previous articles. Outputs demonstrate that Bach-primary and Bach-developed wind turbine models have less flow separation at the spoke-end than the simple helical Savonius model, ultimately improving wind turbines’ total performance and reducing spoke-dynamic loads. Compared with the basic model, the Bach-developed model shows an 18.3% performance improvement in the maximum power coefficient. Bach’s primary model also offers a 12.4% increase in power production than the initial model’s best performance. Furthermore, the results indicate that changing the geometric parameters of the Bach model at high velocities (in turbulent flows) does not significantly affect improving performance.

scholarly journals Gas Turbine Performance Forecast and Assessment: GE LM2500 in Outlook

2021 ◽  
Vol 1107 (1) ◽  
pp. 012025
Author(s):  
A. El-Suleiman ◽  
O.D. Samuel ◽  
S.T. Amosun ◽  
I. Emovon ◽  
F. I. Ashiedu ◽  
...  
Keyword(s):  
Gas Turbine ◽  
Turbine Performance

scholarly journals Unsupervised learning by competing hidden units

2019 ◽  
Vol 116 (16) ◽  
pp. 7723-7731 ◽  
Author(s):  
Dmitry Krotov ◽  
John J. Hopfield
Keyword(s):  
Learning Algorithm ◽  
Lower Layer ◽  
Learning Rule ◽  
Backpropagation Algorithm ◽  
Feedforward Networks ◽  
Feature Detectors ◽  
End To End ◽  
Hidden Layer ◽  
Full Network ◽  
Global Inhibition

It is widely believed that end-to-end training with the backpropagation algorithm is essential for learning good feature detectors in early layers of artificial neural networks, so that these detectors are useful for the task performed by the higher layers of that neural network. At the same time, the traditional form of backpropagation is biologically implausible. In the present paper we propose an unusual learning rule, which has a degree of biological plausibility and which is motivated by Hebb’s idea that change of the synapse strength should be local—i.e., should depend only on the activities of the pre- and postsynaptic neurons. We design a learning algorithm that utilizes global inhibition in the hidden layer and is capable of learning early feature detectors in a completely unsupervised way. These learned lower-layer feature detectors can be used to train higher-layer weights in a usual supervised way so that the performance of the full network is comparable to the performance of standard feedforward networks trained end-to-end with a backpropagation algorithm on simple tasks.

Evolution of Gas Turbine Intake Air Filtration in a 420 MW Cogeneration Plant

2014 ◽  
Author(s):  
Steve Ingistov ◽  
Michael Milos ◽  
Rakesh K. Bhargava
Keyword(s):  
Gas Turbine ◽  
Gas Turbines ◽  
Economic Benefits ◽  
Cogeneration Plant ◽  
Air Filtration ◽  
Air Filter ◽  
Filter System ◽  
Turbine Performance ◽  
Filtration System ◽  
Operational Data

A suitable inlet air filter system is required for a gas turbine, depending on installation site and its environmental conditions, to minimize contaminants entering the compressor section in order to maintain gas turbine performance. This paper describes evolution of inlet air filter systems utilized at the 420 MW Watson Cogeneration Plant consisting of four GE 7EA gas turbines since commissioning of the plant in November 1987. Changes to the inlet air filtration system became necessary due to system limitations, a desire to reduce operational and maintenance costs, and enhance overall plant performance. Based on approximately 2 years of operational data with the latest filtration system combined with other operational experiences of more than 25 years, it is shown that implementation of the high efficiency particulate air filter system provides reduced number of crank washes, gas turbine performance improvement and significant economic benefits compared to the traditional synthetic media type filters. Reasons for improved gas turbine performance and associated economic benefits, observed via actual operational data, with use of the latest filter system are discussed in this paper.

scholarly journals Design Oriented Aerodynamic Modelling of Wind Turbine Performance

2007 ◽  
Vol 75 ◽  
pp. 012011 ◽  
Author(s):  
Luca Greco ◽  
Claudio Testa ◽  
Francesco Salvatore
Keyword(s):  
Wind Turbine ◽  
Turbine Performance ◽  
Aerodynamic Modelling
Sign in / Sign up

Export Citation Format

Share Document