Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors
The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-07-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2075-4701/8/8/593 |
| id |
doaj-art-0ab65b5158b2488e8a632b645cdd5d8e |
|---|---|
| recordtype |
oai_dc |
| spelling |
doaj-art-0ab65b5158b2488e8a632b645cdd5d8e2018-08-22T08:03:03ZengMDPI AGMetals2075-47012018-07-018859310.3390/met8080593met8080593Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence FactorsQiangjian Gao0Yingyi Zhang1Xin Jiang2Haiyan Zheng3Fengman Shen4School of Metallurgy, Northeastern University, Shenyang 110819, ChinaSchool of Metallurgical Engineering, Anhui University of Technology, Ma’anshan 243002, ChinaSchool of Metallurgy, Northeastern University, Shenyang 110819, ChinaSchool of Metallurgy, Northeastern University, Shenyang 110819, ChinaSchool of Metallurgy, Northeastern University, Shenyang 110819, ChinaThe Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.http://www.mdpi.com/2075-4701/8/8/593iron ore pelletscompressive strength (CS)prediction modelartificial neural networkprincipal component analysis |
| institution |
Open Data Bank |
| collection |
Open Access Journals |
| building |
Directory of Open Access Journals |
| language |
English |
| format |
Article |
| author |
Qiangjian Gao Yingyi Zhang Xin Jiang Haiyan Zheng Fengman Shen |
| spellingShingle |
Qiangjian Gao Yingyi Zhang Xin Jiang Haiyan Zheng Fengman Shen Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors Metals iron ore pellets compressive strength (CS) prediction model artificial neural network principal component analysis |
| author_facet |
Qiangjian Gao Yingyi Zhang Xin Jiang Haiyan Zheng Fengman Shen |
| author_sort |
Qiangjian Gao |
| title |
Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors |
| title_short |
Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors |
| title_full |
Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors |
| title_fullStr |
Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors |
| title_full_unstemmed |
Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors |
| title_sort |
prediction model of iron ore pellet ambient strength and sensitivity analysis on the influence factors |
| publisher |
MDPI AG |
| series |
Metals |
| issn |
2075-4701 |
| publishDate |
2018-07-01 |
| description |
The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process. |
| topic |
iron ore pellets compressive strength (CS) prediction model artificial neural network principal component analysis |
| url |
http://www.mdpi.com/2075-4701/8/8/593 |
| _version_ |
1612679433887416320 |