Neural network based automatic modeling and coke quality prediction of stamp charge batteries at tata steel  

Oleh:

Maharana, Sulata ; Biswas, B ; Ganguly, Adity ; Kumar, Ashok

Jenis: Article from Proceeding
Dalam koleksi: ANQ Congress 19-22 October 2010 New Delhi, page 1-7.
Topik: Artificial Neural Networks; Coke Strength after Reaction; back Propagation.
Fulltext: S_Maharana_Tata_steel_Neural_Network_Based.pdf (296.88KB)

Isi artikel

Coke CSR has a strong effect on the performance indices of blast furnaces and hence any deviation in CSR has to be quickly arrested. CSR is closely interrelated to coal property and coke making process parameters. ANN models have been incrementally developed for each of the above mentioned categories. The aim is to quickly identify the group or a combination of groups which is causing the deviation of CSR. The uniqueness of the model lies in the fact that very less published work can be found for Stamp charge coke making which consists of the majority of coke in Tata Steel. This model has been a useful tool for process experts to adjust the control parameters in case of coke quality deviations.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali