Abstract
Superheater corrosion causes vast annual losses to the power companies. If the corrosion could be reliably predicted, new power plants could be designed accordingly, and knowledge of fuel selection and determination of process conditions could be utilized to minimize superheater corrosion. If relations between inputs and the output are poorly known, conventional models depending on corrosion theories will fail. A prediction model based on a neural network is capable of learning from errors and improving its performance as the amount of data increases. The neural network developed during this study predicts superheater corrosion with 80 % accuracy at early stage of the project. (orig.) 10 refs.
Makkonen, P
[1]
- Foster Wheeler Energia Oy, Karhula R and D Center, Karhula (Finland)
Citation Formats
Makkonen, P.
Neural network for prediction of superheater fireside corrosion.
Finland: N. p.,
1998.
Web.
Makkonen, P.
Neural network for prediction of superheater fireside corrosion.
Finland.
Makkonen, P.
1998.
"Neural network for prediction of superheater fireside corrosion."
Finland.
@misc{etde_324967,
title = {Neural network for prediction of superheater fireside corrosion}
author = {Makkonen, P}
abstractNote = {Superheater corrosion causes vast annual losses to the power companies. If the corrosion could be reliably predicted, new power plants could be designed accordingly, and knowledge of fuel selection and determination of process conditions could be utilized to minimize superheater corrosion. If relations between inputs and the output are poorly known, conventional models depending on corrosion theories will fail. A prediction model based on a neural network is capable of learning from errors and improving its performance as the amount of data increases. The neural network developed during this study predicts superheater corrosion with 80 % accuracy at early stage of the project. (orig.) 10 refs.}
place = {Finland}
year = {1998}
month = {Dec}
}
title = {Neural network for prediction of superheater fireside corrosion}
author = {Makkonen, P}
abstractNote = {Superheater corrosion causes vast annual losses to the power companies. If the corrosion could be reliably predicted, new power plants could be designed accordingly, and knowledge of fuel selection and determination of process conditions could be utilized to minimize superheater corrosion. If relations between inputs and the output are poorly known, conventional models depending on corrosion theories will fail. A prediction model based on a neural network is capable of learning from errors and improving its performance as the amount of data increases. The neural network developed during this study predicts superheater corrosion with 80 % accuracy at early stage of the project. (orig.) 10 refs.}
place = {Finland}
year = {1998}
month = {Dec}
}