Prediction Model of Burning Through Point Based on JITL-XGBoost

doi:10.12068/j.issn.1005-3026.2025.20230256

Abstract

Abstract:

The burning through point （BTP） is an important parameter in the sintering process， which directly affects the efficiency of the sintering machine. Due to the multi-working conditions and time-varying characteristics of the sintering production process， the prediction performance of the global model is insufficient. Therefore， a burning through point prediction model using XGBoost as a local model in the just-in-time learning framework is proposed， namely JITL-XGBoost. Firstly， the KL divergence similarity measurement method is used to extract the characteristics of the sample to be tested， and the most relevant data set of the sample to be tested is selected. Secondly， this dataset is used as input to the XGBoost model to predict the location of the burning through point. In addition， the impact of related dataset numbers on model prediction accuracy and model computation time is considered. Finally， by comparing with other models， the results show that the model built has the best prediction accuracy within a reasonable time， providing new guidance for improving the efficiency of sintering machines.

Key words: sintering ore, burning through point, prediction model, just-in-time learning, extreme gradient boosting

CLC Number:

TF 046.4

Jin-yang WANG, Zhao-xia WU, Zhong-zheng LI, Zeng-xin KANG. Prediction Model of Burning Through Point Based on JITL-XGBoost[J]. Journal of Northeastern University(Natural Science), 2025, 46(2): 28-34.

Figures/Tables 9

Table 1 Main parameters of sintering process

焦粉/(t·h^-1)

燃料/(t·h^-1)

烧结返矿/(t·h^-1)

除尘灰/（t·h^-1）

铁粉/(t·h^-1)

高炉返矿/(t·h^-1)

混合料参数

混合料TFe质量分数%

混合料CaO质量分数/%

混合料水分质量分数/%

混合料V₂O₅质量分数/%

混合料SiO₂质量分数/%

操作参数

圆辊转速/(r·h^-1)

烧结机速度/(m·min^-1)

煤气流量/(m³·h^-1)

助燃风流量/(m³·h^-1)

九辊转速/(r·h^-1)

点火温度/℃

风机风量/(m³·h^-1)

助燃风压力/kPa

状态参数

24~37

南烟道温度/℃

北烟道温度/℃

14个风箱废气温度/℃

38~51

南烟道负压/kPa

北烟道负压/kPa

14个风箱负压/kPa

输出参数

BTP

—

Fig.1 Box plot

Fig. 2 Results of box plot method for identifying abnormal data points

Table 2 Calculation results of CMI

过程参数	C_MI值	过程参数	C_MI值
20号风箱废气温度	0.517 500	焦粉	0.419 891
1号风箱废气温度	0.366 053	7号风箱真空度	0.355 897
2号风机风量	0.353 517	11号风箱真空度	0.276 374
7号风箱废气温度	0.273 018	22号风箱废气温度	0.233 880
3号风箱废气温度	0.174 285	混合料CaO质量分数	0.172 590
混合料V₂O₅质量分数	0.148 207	TFe	0.145 821
9号风箱真空度	0.143 866	2号风箱废气温度	0.141 890
混合料SiO₂硅质量分数	0.134 581	烧结机速度	0.133 350
2号风箱真空度	0.129 686	混合料除尘灰质量分数	0.127 677
13号风箱废气温度	0.126 931	混合料水分质量分数	0.125 018
5号风箱真空度	0.121 172	15号风箱废气温度	0.113 292
5号风箱废气温度	0.105 676	11号风箱废气温度	0.105 623
烟道温度	0.103 928	3号风箱真空度	0.093 048

Fig. 3 Flowchart of the JITL-XGBoost model

Fig. 4 Influence of the numbers of relevant data sets on prediction accuracy of the model

Fig. 5 BTP prediction results before the change of process state

Fig.6 BTP prediction results after the change of process state

Table 3 Comparison of prediction performance of different prediction models

模型	$e M A$	$e M S$	$e R M S$
JITL-GPR	0.064 9	0.013 8	0.117 4
JITL-SVR	0.057 5	0.006 9	0.083 3
XGBoost	0.034 2	0.027 3	0.165 2
JITL-XGBoost	0.029 9	0.003 8	0.061 6

Table 3 Comparison of prediction performance of different prediction models

模型	$e M A$	$e M S$	$e R M S$
JITL-GPR	0.064 9	0.013 8	0.117 4
JITL-SVR	0.057 5	0.006 9	0.083 3
XGBoost	0.034 2	0.027 3	0.165 2
JITL-XGBoost	0.029 9	0.003 8	0.061 6

References 15

1	Du S， Wu M， Chen L F， et al. A fuzzy control strategy of burn-through point based on the feature extraction of time-series trend for iron ore sintering process［J］. IEEE Transactions on Industrial Informatics， 2020， 16（4）： 2357-2368.
2	Patisson F， Bellot J P， Ablitzer D， et al. Mathematical modelling of iron ore sintering process［J］. Ironmaking & Steelmaking， 1991， 18（2）： 89-95.
3	Cumming M J， Thurlby J A. Developments in modelling and simulation of iron ore sintering［J］. Ironmaking & Steelmaking， 1990， 17（4）： 245-254.
4	Chen X X， Shi X H， Tong C D. Multi-time-scale TFe prediction for iron ore sintering process with complex time delay［J］. Control Engineering Practice， 2019， 89： 84-93.
5	Du S， Wu M， Chen L F， et al. Prediction model of burn-through point with fuzzy time series for iron ore sintering process［J］. Engineering Applications of Artificial Intelligence， 2021， 102： 104259.
6	Chen X， Hu J， Wu M， et al. T–S fuzzy logic based modeling and robust control for burning-through point in sintering process［J］. IEEE Transactions on Industrial Electronics， 2017， 64（12）： 9378-9388.
7	Liu S， Lyu Q， Liu X J， et al. A prediction system of burn through point based on gradient boosting decision tree and decision rules［J］. ISIJ International， 2019， 59（12）： 2156-2164.
8	Wang D D， Yang K， He Z J， et al. Application research based on GA-FWA in prediction of sintering burning through point［C］//Proceedings of 2018 International Conference on Computer， Communications and Mechatronics Engineering. Shanghai，2018： 378-385.
9	赵济民，何杨，刘建华，等. 基于即时学习算法的铸坯质量预测方法［J］. 连铸， 2022， 47（6）： 54-60， 67.
	Zhao Ji-min， He Yang， Liu Jian-hua， et al. Predictive method of casting slab quality based on just-in-time learning algorithm［J］. Continuous Casting， 2022， 47（6）： 54-60， 67.
10	任明仑，宋月丽，褚伟. 灰铸铁抗拉强度预测的局部加权线性回归建模［J］. 电子测量与仪器学报， 2019， 33（3）： 65-71.
	Ren Ming-lun， Song Yue-li， Chu Wei. Locally weighted linear regression modeling for tensile strength prediction of gray cast iron［J］. Journal of Electronic Measurement and Instrumentation， 2019， 33（3）： 65-71.
11	王通，高宪文，刘文芳. 基于改进即时学习算法的动液面软测量建模［J］. 东北大学学报（自然科学版）， 2015， 36（7）： 918-922.
	Wang Tong， Gao Xian-wen， Liu Wen-fang. Soft sensor for determination of dynamic fluid levels based on enhanced just-in-time learning algorithm［J］. Journal of Northeastern University （Natural Science）， 2015，36（7）： 918-922.
12	Xia G L， Wu Z X， Liu M Y， et al. Prediction interval estimation of sinter drum index based on light gradient boosting machine and kernel density estimation［J］. Ironmaking & Steelmaking， 2023， 50（8）： 909-920.
13	Li D C， Huang W T， Chen C C， et al. Employing box plots to build high-dimensional manufacturing models for new products in TFT-LCD plants［J］. Neurocomputing， 2014， 142： 73-85.
14	Simon N， Tibshirani R. Comment on “detecting novel associations in large data sets” by reshef et Al， science dec 16， 2011［EB/OL］.（2014-06-14）［2023-05-15］. 2014： 1401.7645. .
15	Li G Y， Li W， Tian X L， et al. Short-term electricity load forecasting based on the XGBoost algorithm［J］. Smart Grid， 2017， 7（4）： 274-285.

[1]	Guang-lei XIA, Zhao-xia WU, Meng-yuan LIU, Yu-shan JIANG. Prediction of Sinter Chemical Indexes Based on GMM-KNN-LSTM [J]. Journal of Northeastern University(Natural Science), 2024, 45(3): 314-322.
[2]	Meng CHEN, Yu HONG. Test Study on Drying Shrinkage Properties of Engineered Cementitious Composites with RTP‐PVA Hybrid Fibre [J]. Journal of Northeastern University(Natural Science), 2024, 45(3): 407-414.
[3]	Xiu-mei CAO, Wen ZHAO, Zhi-guo WANG, Peng HE. Prediction of Soil Conditioners for Sandy Soil Shield Based on Optuna-XGBoost [J]. Journal of Northeastern University(Natural Science), 2024, 45(12): 1769-1777.
[4]	Meng-yuan LIU, Zhao-xia WU, Jin-yang WANG, Guang-lei XIA. Air Permeability Prediction of Sinter Layer Based on TST-LSTM Model [J]. Journal of Northeastern University(Natural Science), 2024, 45(10): 1379-1385.
[5]	HUANG Chuan-qi， REN Yu-qian， WU Zhao-xia. A Stacked Generalization Ensemble-based Hybrid LGBM-RF-XGB Model for Sintering Moisture Prediction [J]. Journal of Northeastern University(Natural Science), 2023, 44(9): 1245-1250.
[6]	LIU Ke-qi， DU Dian-chun， ZHAO Wen， DING Wan-tao. Machine Learning-Based Prediction and Optimization of Slurry Shield’s Key Tunneling Parameters [J]. Journal of Northeastern University(Natural Science), 2023, 44(11): 1621-1630.
[7]	JIAO Zhi-jie， WANG Zhi-qiang， LUO Jun-yi， XU Zhi-peng. Study on Plate Angular Rolling Process Using Pattern Prediction Model [J]. Journal of Northeastern University(Natural Science), 2022, 43(6): 815-820.
[8]	CHEN Bing， HAN Jin-yang， TANG Xiao-lei， XIA Bo-ran. Prediction Model for Elongation of Tension Leveling Based on Machine Learning Algorithm and Numerical Analysis [J]. Journal of Northeastern University(Natural Science), 2022, 43(2): 236-242.
[9]	GONG Qi， CHEN Bing-zhi， LI Yong-hua， XIA Qing. Fault Analysis of Metro Power Supply Module and Prediction Method [J]. Journal of Northeastern University(Natural Science), 2022, 43(1): 8-16.
[10]	GUO Yong-chun， ZHENG Hai-yan， HU Xin-guang， SHENG Feng-man. Prediction Model of Al₂O₃ Activity in CaO-SiO₂-Al₂O₃-MgO Quaternary Slag System [J]. Journal of Northeastern University(Natural Science), 2021, 42(5): 652-657.
[11]	ZHU Zi-zong， XIE Yang-yang， WU Qiang， SHI Guo-jing. Coke-Making with Modified Xinjiang Kubai Coals and Prediction the Cold Strength of Coke [J]. Journal of Northeastern University Natural Science, 2017, 38(12): 1726-1730.
[12]	LI Xiao-peng， WANG Xue， YUN Hai-meng， AN Lian-chui. Static Friction Coefficient Fractal Model of Joint Surfaces with Elastic-Plastic Beformation Considered [J]. Journal of Northeastern University Natural Science, 2016, 37(5): 673-677.
[13]	LIU Qing， YUAN Wei， WANG Bao， PENG Liang-zhen. Concentrate Grade Prediction of Gold Ore Based on GA-BP Neural Network [J]. Journal of Northeastern University Natural Science, 2015, 36(2): 237-240.
[14]	LYU Wu， MAO Zhizhong， YUAN Ping， JIA Mingxing. Ladle Furnace End Point Sulphur Content Prediction Model Based on Model Migration Method〓 [J]. Journal of Northeastern University Natural Science, 2014, 35(3): 314-317.