|
|
|
| Data��Driven Prediction of Sintering Burn-Through Point Based on Novel Genetic Programming |
| SHANG Xiu��qin, LU Jian��gang, SUN You��xian, et al |
|
|
|
|
Abstract The paper presents an empirical dynamic model of burn-through point (BTP) in sintering process. The model combines two stages of sintering process, cold processing stage and sintering stage. Fist, cold bed permeability measured by Gas velocity is introduced in the cold stage. Then, K-Means clustering is applied to partition the feed according to the permeability. Besides, for each clustering, a novel genetic programming (NGP) is proposed to construct the empirical model of the waste gas temperature and pressure drop through the bed in sintering stage. NGP adopts least square method (LSM) and M-estimator to improve the ability to compute and resist disturbance. Therefore, the paper constructs a model base of burn-through point and the simulation proves that the model base has a good performance.
|
|
Received: 09 November 2009
|
|
Corresponding Authors:
Shang Xiu-Qin
|
|
|
|
|
|
|
2010, Vol. 17 
