Developing a data-driven soft sensor to predict silicate impurity in iron ore flotation concentrate

• Autorzy: Pural Yusuf Enes

Identyfikatory

DOI

10.37190/ppmp/169823

• Języki publikacji: EN

Abstrakty

EN

Soft sensors are mathematical models that estimate the value of a process variable that is difficult or expensive to measure directly. They can be based on first principle models, data-based models, or a combination of both. These models are increasingly used in mineral processing to estimate and optimize important performance parameters such as mill load, mineral grades, and particle size. This study investigates the development of a data-driven soft sensor to predict the silicate content in iron ore reverse flotation concentrate, a crucial indicator of plant performance. The proposed soft sensor model employs a dataset obtained from Kaggle, which includes measurements of iron and silicate content in the feed to the plant, reagent dosages, weight and pH of pulp, as well as the amount of air and froth levels in the flotation units. To reduce the dimensionality of the dataset, Principal Component Analysis, an unsupervised machine learning method, was applied. The soft sensor model was developed using three machine learning algorithms, namely, Ridge Regression, Multi-Layer Perceptron, and Random Forest. The Random Forest model, created with non-reduced data, demonstrated superior performance, with an R-squared value of 96.5% and a mean absolute error of 0.089. The results suggest that the proposed soft sensor model can accurately predict the silicate content in the iron ore flotation concentrate using machine learning algorithms. Moreover, the study highlights the importance of selecting appropriate algorithms for soft sensor developments in mineral processing plants.

Słowa kluczowe

EN

soft sensor; machine learning; random forest; multi-layer perceptron; flotation; grade estimation

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Physicochemical Problems of Mineral Processing
• Rocznik: 2023
• Tom: Vol. 59, iss. 5
• Strony: art. no. 169823
• Opis fizyczny: Bibliogr. 19 poz., rys., tab., wykr.

Twórcy

autor

Pural Yusuf Enes

• Istanbul Technical University, Faculty of Mines, Mineral Processing Engineering Department, Maslak, Istanbul, Turkey

• https://orcid.org/0000-0002-0676-3805

Bibliografia

• ABUSNİNA, A., 2014. Gaussian Process Adaptive Soft Sensors and their Applications in Inferential Control Systems. EngD. Thesis.
• AHSAN, M. M., MAHMUD, M. A. P., SAHA, P. K., GUPTA, K. D., & SİDDİQUE, Z., 2021. Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance. Technologies. 9(3), 5–9.
• DAOUD, JAMAL I., 2019. Multicollinearity and Regression Analysis. Journal of Physics: Conference Series, vol. 949, p. 012009.
• FAN, GUİXİA, LİGUANG WANG, YİJUN CAO, AND CHAO Lİ., 2020. Collecting Agent–Mineral Interactions in the Reverse Flotation of Iron Ore: A Brief Review. Minerals. 10, no. 8: 681.
• FERNÁNDEZ, Á., BELLA, J., & DORRONSORO, J. R., 2022. Supervised outlier detection for classification and regression. Neurocomputing. 486, 77–92.
• GE, Z., 2017. Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemometrics and Intelligent Laboratory Systems, 171(September), 16–25.
• GOMEZ-FLORES, A., HEYES, G. W., ILYAS, S., & KİM, H., 2022. Prediction of grade and recovery in flotation from physicochemical and operational aspects using machine learning models. Minerals Engineering. 183(March), 107627.
• JİAN, H., LİHUİ, C., & XİE, Y., 2020. Design of Soft Sensor for Industrial Antimony Flotation Based on Deep CNN. Proceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020, 2492–2496.
• Lİ, Z. MEİ, GUİ, W. HUA, & ZHU, J. YONG., 2019. Fault detection in flotation processes based on deep learning and support vector machine. Journal of Central South University, 26(9), 2504–2515.
• MCCOY, J. T., & AURET, L., 2019. Machine learning applications in minerals processing: A review. In Minerals Engineering (Vol. 132, pp. 95–109). Elsevier Ltd.
• MONTANARES, M., GUAJARDO, S., AGUİLERA, I., & RİSSO, N., 2021. Assessing machine learning-based approaches for silica concentration estimation in iron froth flotation. 2021 IEEE International Conference on Automation/24th Congress of the Chilean Association of Automatic Control, ICA-ACCA 2021.
• OLİVEİRA, E. M., 2017. Quality Prediction in a Mining Process. Retrieved September 7, 2019, from Kaggle.com website: https://www.kaggle.com/edumagalhaes/quality-prediction-in-a-mining-process
• POPLİ, K., AFACAN, A., LİU, Q., & PRASAD, V., 2018. Development of online soft sensors and dynamic fundamental model-based process monitoring for complex sulfide ore flotation. Minerals Engineering, 124(May), 10–27.
• REN, L., WANG, T., LAİLİ, Y., & ZHANG, L., 2022. A Data-Driven Self-Supervised LSTM-DeepFM Model for Industrial Soft Sensor. IEEE Transactions on Industrial Informatics, 18(9), 5859–5869.
• WEN, Z., ZHOU, C., PAN, J., NİE, T., ZHOU, C., & LU, Z., 2021. Deep learning-based ash content prediction of coal flotation concentrate using convolutional neural network. Minerals Engineering, 174, 107251
• ZHANG, D., & GAO, X., 2021. Soft sensor of flotation froth grade classification based on hybrid deep neural network. International Journal of Production Research, 59(16), 4794–4810.
• ZHANG, D., & GAO, X., 2022. A digital twin dosing system for iron reverse flotation. Journal of Manufacturing Systems, 63(March), 238–249. https://doi.org/10.1016/j.jmsy.2022.03.006
• ZHANG, D., GAO, X., & Qİ, W., 2022. Soft sensor of iron tailings grade based on froth image features for reverse flotation. Transactions of the Institute of Measurement and Control, 44(15), 2928–2940.
• ZHAO, B., HU, S., ZHAO, X., ZHOU, B., Lİ, J., HUANG, W., CHEN, G., WU, C., & LİU, K., 2022. The application of machine learning models based on particles characteristics during coal slime flotation. Advanced Powder Technology, 33(1), 103363.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).