Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit
Prediction of metallurgical responses during the flotation process is extremely vital to increase the process efficiency using a proper modeling approach. In this study, two new variants of the recurrent neural network (RNN) method were used to predict the copper ore flotation indices, i.e., grade a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/12/7/857 |
| _version_ | 1797444918144139264 |
|---|---|
| author | Alireza Gholami Meysam Movahedifar Hamid Khoshdast Ahmad Hassanzadeh |
| author_facet | Alireza Gholami Meysam Movahedifar Hamid Khoshdast Ahmad Hassanzadeh |
| author_sort | Alireza Gholami |
| collection | DOAJ |
| description | Prediction of metallurgical responses during the flotation process is extremely vital to increase the process efficiency using a proper modeling approach. In this study, two new variants of the recurrent neural network (RNN) method were used to predict the copper ore flotation indices, i.e., grade and recovery within different operating conditions. The model input parameters including pulp pH and solid content as well as frother and collector dosages were first analysed and then optimized using a two-step factorial approach. The statistical analysis showed a reliable correlation between operating parameters and copper grade and recovery with coefficients of 99.86% and 94.50%, respectively. The main effect plots indicated that pulp pH and solid content positively affect copper grade while increasing the frother and collector dosages negatively influenced the quality of the final concentrate. Despite the same effect from pulp pH, reverse effects from other variables were observed for copper recovery. Process optimization revealed that maximum copper recovery of 44.39% with a grade of 11.48% could be achieved under the optimal condition as pulp pH of 10, solid content of 20%, and frother and collector concentrations of 25 g/t and 9.9 g/t, respectively. Then, the predictive efficiency of long short-term memory (LSTM) and gated recurrent unit (GRU) networks with proper structure were evaluated using mean square error (<i>MSE</i>), root mean square error (<i>RMSE</i>), mean absolute percentage error (<i>MAPE</i>), and correlation coefficient (<i>R</i><sup>2</sup>). The simulation results showed that the LSTM network with higher <i>R</i><sup>2</sup> of 0.963 and 0.934 for copper grade and recovery, respectively, was more effective than the GRU algorithm with the corresponding values of 0.956 and 0.919, respectively. The results show that the LSTM model could be useful in predicting the copper flotation behaviour in response to changes in the operating parameters. |
| first_indexed | 2024-03-09T13:19:22Z |
| format | Article |
| id | doaj.art-55049cbf7ee441c188546dad9600ffe0 |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-09T13:19:22Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-55049cbf7ee441c188546dad9600ffe02023-11-30T21:32:02ZengMDPI AGMinerals2075-163X2022-07-0112785710.3390/min12070857Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation CircuitAlireza Gholami0Meysam Movahedifar1Hamid Khoshdast2Ahmad Hassanzadeh3Department of Mineral Processing, Faculty of Engineering, Tarbiat Modares University, Tehran 14117-13116, IranMineral Processing Division, Mining Engineering Department, Islamic Azad University, Sirjan, IranDepartment of Mining Engineering, Higher Education Complex of Zarand, Zarand 77611-56391, IranDepartment of Geoscience and Petroleum, Faculty of Engineering, Norwegian University of Science and Technology, 7031 Trondheim, NorwayPrediction of metallurgical responses during the flotation process is extremely vital to increase the process efficiency using a proper modeling approach. In this study, two new variants of the recurrent neural network (RNN) method were used to predict the copper ore flotation indices, i.e., grade and recovery within different operating conditions. The model input parameters including pulp pH and solid content as well as frother and collector dosages were first analysed and then optimized using a two-step factorial approach. The statistical analysis showed a reliable correlation between operating parameters and copper grade and recovery with coefficients of 99.86% and 94.50%, respectively. The main effect plots indicated that pulp pH and solid content positively affect copper grade while increasing the frother and collector dosages negatively influenced the quality of the final concentrate. Despite the same effect from pulp pH, reverse effects from other variables were observed for copper recovery. Process optimization revealed that maximum copper recovery of 44.39% with a grade of 11.48% could be achieved under the optimal condition as pulp pH of 10, solid content of 20%, and frother and collector concentrations of 25 g/t and 9.9 g/t, respectively. Then, the predictive efficiency of long short-term memory (LSTM) and gated recurrent unit (GRU) networks with proper structure were evaluated using mean square error (<i>MSE</i>), root mean square error (<i>RMSE</i>), mean absolute percentage error (<i>MAPE</i>), and correlation coefficient (<i>R</i><sup>2</sup>). The simulation results showed that the LSTM network with higher <i>R</i><sup>2</sup> of 0.963 and 0.934 for copper grade and recovery, respectively, was more effective than the GRU algorithm with the corresponding values of 0.956 and 0.919, respectively. The results show that the LSTM model could be useful in predicting the copper flotation behaviour in response to changes in the operating parameters.https://www.mdpi.com/2075-163X/12/7/857copper ore flotationrecurrent neural networkpredictive geometallurgylong short-term memory (LSTM)gated recurrent unit (GRU) |
| spellingShingle | Alireza Gholami Meysam Movahedifar Hamid Khoshdast Ahmad Hassanzadeh Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit Minerals copper ore flotation recurrent neural network predictive geometallurgy long short-term memory (LSTM) gated recurrent unit (GRU) |
| title | Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit |
| title_full | Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit |
| title_fullStr | Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit |
| title_full_unstemmed | Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit |
| title_short | Hybrid Serving of DOE and RNN-Based Methods to Optimize and Simulate a Copper Flotation Circuit |
| title_sort | hybrid serving of doe and rnn based methods to optimize and simulate a copper flotation circuit |
| topic | copper ore flotation recurrent neural network predictive geometallurgy long short-term memory (LSTM) gated recurrent unit (GRU) |
| url | https://www.mdpi.com/2075-163X/12/7/857 |
| work_keys_str_mv | AT alirezagholami hybridservingofdoeandrnnbasedmethodstooptimizeandsimulateacopperflotationcircuit AT meysammovahedifar hybridservingofdoeandrnnbasedmethodstooptimizeandsimulateacopperflotationcircuit AT hamidkhoshdast hybridservingofdoeandrnnbasedmethodstooptimizeandsimulateacopperflotationcircuit AT ahmadhassanzadeh hybridservingofdoeandrnnbasedmethodstooptimizeandsimulateacopperflotationcircuit |