Research on Prediction of Ash Content in Flotation-Recovered Clean Coal Based on NRBO-CNN-LSTM
Abstract
:1. Introduction
2. Experiments
3. Collection and Processing of Flotation Image Data
3.1. Image Preprocessing
3.1.1. Histogram Equalization
3.1.2. Filtering Enhancement
3.1.3. Fractional-Order Differentiation
3.2. Bubble Diameter
3.3. Bubble Count
3.4. Bubble Color
3.5. Bubble Grayscale Histogram Features
3.6. Bubble Velocity
4. Model Construction
4.1. CNN and LSTM Models
4.2. NRBO Optimized CNN-LSTM
5. Results
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Chen, S.; Li, L.; Qu, J.; Liu, Q.; Tang, L.; Tao, X.; Fan, H. Oily bubble flotation technology combining modeling and optimization of parameters for enhancement of flotation of low-flame coal. Powder Technol. 2018, 335, 171–185. [Google Scholar] [CrossRef]
- Wen, Z.; Zhou, C.; Pan, J.; Nie, T.; Jia, R.; Yang, F. Froth image feature engineering-based prediction method for concentrate ash content of coal flotation. Miner. Eng. 2021, 170, 107023. [Google Scholar] [CrossRef]
- Shean, B.J.; Cilliers, J.J. A review of froth flotation control. Int. J. Miner. Process. 2011, 100, 57–71. [Google Scholar] [CrossRef]
- Richaud, R.; Herod, A.A.; Kandiyoti, R. Comparison of trace element contents in low-temperature and high-temperature ash from coals and biomass. Fuel 2004, 83, 2001–2012. [Google Scholar] [CrossRef]
- Pak, Y.; Pak, D.; Ponomaryova, M.; Imanov, M.; Balbekova, B. Express measurement of solid fuel ash content by nuclear gamma-method. Appl. Radiat. Isot. 2019, 147, 54–58. [Google Scholar] [CrossRef] [PubMed]
- Rizk, R.A.M.; El-Kateb, A.H.; Abdul-Kader, A.M. On-line nuclear ash gauge for coal based on gamma-ray transmission techniques. J. Radioanal. Nucl. Chem. 1999, 242, 139–145. [Google Scholar] [CrossRef]
- Lv, W.; Wang, Y.; Li, L.; Jin, L.; Wang, C. Mechanism of measuring ash with low-energy gamma rays for equal coal seam thickness. Int. J. Coal Prep. Util. 2024, 44, 1–14. [Google Scholar] [CrossRef]
- Yu, A.; Liu, H.; Wang, C.; Lv, J.; Wang, F.; He, S.; Wang, L. Online Ash Content Monitor by Automatic Composition Identification and Dynamic Parameter Adjustment Method in Multicoal Preparation. Processes 2022, 10, 1432. [Google Scholar] [CrossRef]
- Morar, S.H.; Harris, M.C.; Bradshaw, D.J. The use of machine vision to predict flotation performance. Miner. Eng. 2012, 36–38, 31–36. [Google Scholar] [CrossRef]
- Aldrich, C.; Avelar, E.; Liu, X. Recent advances in flotation froth image analysis. Miner. Eng. 2022, 188, 107823. [Google Scholar] [CrossRef]
- Bai, Y. 5G Industrial IoT and Edge Computing Based Coal Slime Flotation Foam Image Processing System. IEEE Access 2020, 8, 137606–137615. [Google Scholar] [CrossRef]
- Tan, J.; Liang, L.; Peng, Y.; Xie, G. The concentrate ash content analysis of coal flotation based on froth images. Miner. Eng. 2016, 92, 9–20. [Google Scholar] [CrossRef]
- Qiu, Z.; Dou, D.; Zhou, D.; Yang, J. On-line prediction of clean coal ash content based on image analysis. Measurement 2021, 173, 108663. [Google Scholar] [CrossRef]
- Zarie, M.; Jahedsaravani, A.; Massinaei, M. Flotation froth image classification using convolutional neural networks. Miner. Eng. 2020, 155, 106443. [Google Scholar] [CrossRef]
- Chaurasia, R.C.; Sahu, D.; Suresh, N. Prediction of ash content and yield percent of clean coal in multi gravity separator using artificial neural networks. Int. J. Coal Prep. Util. 2021, 41, 362–369. [Google Scholar] [CrossRef]
- Tang, M.; Zhou, C.; Zhang, N.; Liu, C.; Pan, J.; Cao, S. Prediction of the Ash Content of Flotation Concentrate Based on Froth Image Processing and BP Neural Network Modeling. Int. J. Coal Prep. Util. 2021, 41, 191–202. [Google Scholar] [CrossRef]
- Massinaei, M.; Jahedsaravani, A.; Mohseni, H. Recognition of process conditions of a coal column flotation circuit using computer vision and machine learning. Int. J. Coal Prep. Util. 2022, 42, 2204–2218. [Google Scholar] [CrossRef]
- Wen, Z.; Jia, R.; Liu, H.; Zhou, C. Transfer learning using small-sized dataset for concentrate ash content prediction of coal flotation. Int. J. Coal Prep. Util. 2023, 43, 1358–1375. [Google Scholar] [CrossRef]
- Lu, F.; Liu, H.; Lv, W. Deep correlation and precise prediction between static features of froth images and clean coal ash content in coal flotation: An investigation based on deep learning and maximum likelihood estimation. Measurement 2024, 224, 113843. [Google Scholar] [CrossRef]
- Gers, F.A.; Schmidhuber, J.; Cummins, F. Learning to Forget: Continual Prediction with LSTM. Neural Comput. 2000, 12, 2451–2471. [Google Scholar] [CrossRef]
- Da Silva, D.G.; Meneses, A.A. Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction. Energy Rep. 2023, 10, 3315–3334. [Google Scholar] [CrossRef]
- Gogineni, A.; Rout, M.K.D.; Shubham, K. Evaluating machine learning algorithms for predicting compressive strength of concrete with mineral admixture using long short-term memory (LSTM) Technique. Asian J. Civ. Eng. 2024, 25, 1921–1933. [Google Scholar] [CrossRef]
- Li, W.; Ren, B.; Zhang, X.; Liu, Y.; Yao, J. Prediction of Multiple Components of Secondary Ash in Blast Furnace Based on Firefly Algorithm Optimized LSTM. In Proceedings of the 2023 5th International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China, 21–24 August 2023; pp. 1–6. [Google Scholar] [CrossRef]
- Gong, X.; Jiang, W.; Hu, S.; Yang, Z.; Liu, X.; Fan, Z. Comprehensive utilization of foundry dust: Coal powder and clay minerals separation by ultrasonic-assisted flotation. J. Hazard. Mater. 2021, 402, 124124. [Google Scholar] [CrossRef]
- Khan, M.F.; Goyal, D.; Nofal, M.M.; Khan, E.; Al-Hmouz, R.; Herrera-Viedma, E. Fuzzy-Based Histogram Partitioning for Bi-Histogram Equalisation of Low Contrast Images. IEEE Access 2020, 8, 11595–11614. [Google Scholar] [CrossRef]
- Singh, K.; Vishwakarma, D.K.; Walia, G.S.; Kapoor, R. Contrast enhancement via texture region based histogram equalization. J. Mod. Optic 2016, 63, 1444–1450. [Google Scholar] [CrossRef]
- Xiong, J.; Yu, D.; Wang, Q.; Shu, L.; Cen, J.; Liang, Q.; Chen, H.; Sun, B. Application of Histogram Equalization for Image Enhancement in Corrosion Areas. Shock. Vib. 2021, 2021, 8883571. [Google Scholar] [CrossRef]
- Wang, Z.; Zhao, H.; Zeng, X. Constrained Least Mean M-Estimation Adaptive Filtering Algorithm. IEEE Trans. Circuits Syst. II Express Briefs 2021, 68, 1507–1511. [Google Scholar] [CrossRef]
- Xiao, H.; Guo, B.; Zhang, H.; Li, C. A Parallel Algorithm of Image Mean Filtering Based on OpenCL. IEEE Access 2021, 9, 65001–65016. [Google Scholar] [CrossRef]
- Zhang, Y.-S.; Zhang, F.; Li, B.-Z. Image restoration method based on fractional variable order differential. Multidimens. Syst. Signal Process. 2018, 29, 999–1024. [Google Scholar] [CrossRef]
- Hemalatha, S.; Margret Anouncia, S. G-L fractional differential operator modified using auto-correlation function: Texture enhancement in images. Ain Shams Eng. J. 2018, 9, 1689–1704. [Google Scholar] [CrossRef]
- El Hamidi, A.; Tfayli, A. Identification of the derivative order in fractional differential equations. Math. Method Appl. Sci. 2021, 44, 8397–8413. [Google Scholar] [CrossRef]
- Zhang, W.; Liu, D.; Wang, C.; Liu, R.; Wang, D.; Yu, L.; Wen, S. An Improved Python-Based Image Processing Algorithm for Flotation Foam Analysis. Minerals 2022, 12, 1126. [Google Scholar] [CrossRef]
- Roerdink, J.B.T.M.; Meijster, A. The Watershed Transform: Definitions, Algorithms and Parallelization Strategies. Fund. Inform. 2000, 41, 187–228. [Google Scholar] [CrossRef]
- Nie, Y.; Wang, H.; Qin, Y.; Sun, Z. Distributed and morphological operation-based data collection algorithm. Int. J. Distrib. Sens. Netw. 2017, 13, 1550147717717593. [Google Scholar] [CrossRef]
- Yianatos, J.; Vallejos, P. Limiting conditions in large flotation cells: Froth recovery and bubble loading. Miner. Eng. 2022, 185, 107695. [Google Scholar] [CrossRef]
- Tian, R.; Sun, G.; Liu, X.; Zheng, B. Sobel Edge Detection Based on Weighted Nuclear Norm Minimization Image Denoising. Electronics 2021, 10, 655. [Google Scholar] [CrossRef]
- Zhang, K.; Wang, W.; Cui, Y.; Lv, Z.; Fan, Y.; Zhao, X. Deep learning-based estimation of ash content in coal: Unveiling the contributions of color and texture features. Measurement 2024, 233, 114632. [Google Scholar] [CrossRef]
- Lhermitte, E.; Hilal, M.; Furlong, R.; O’Brien, V.; Humeau-Heurtier, A. Deep Learning and Entropy-Based Texture Features for Color Image Classification. Entropy 2022, 24, 1577. [Google Scholar] [CrossRef]
- Bonifazi, G.; Serranti, S.; Volpe, F.; Zuco, R. Characterisation of flotation froth colour and structure by machine vision. Comput. Geosci. 2001, 27, 1111–1117. [Google Scholar] [CrossRef]
- Lu, F.; Liu, H.; Lv, W. Prediction of Clean Coal Ash Content in Coal Flotation through a Convergent Model Unifying Deep Learning and Likelihood Function, Incorporating Froth Velocity and Reagent Dosage Parameters. Processes 2023, 11, 3425. [Google Scholar] [CrossRef]
- Huang, Q.; Xiang, T.; Zhao, Z.; Wu, K.; Li, H.; Cheng, R.; Zhang, L.; Cheng, Z. Directional region-based feature point matching algorithm based on SURF. J. Opt. Soc. Am. A 2024, 41, 157–164. [Google Scholar] [CrossRef] [PubMed]
- Li, X.; Zhu, J.; Ruan, Y. Vehicle Seat Detection Based on Improved RANSAC-SURF Algorithm. Int. J. Pattern Recogn. 2021, 35, 2155004. [Google Scholar] [CrossRef]
- Al-Qudah, S.; Yang, M. Large Displacement Detection Using Improved Lucas–Kanade Optical Flow. Sensors 2023, 23, 3152. [Google Scholar] [CrossRef] [PubMed]
- Chen, L.; Li, S.; Bai, Q.; Yang, J.; Jiang, S.; Miao, Y. Review of Image Classification Algorithms Based on Convolutional Neural Networks. Remote Sens. 2021, 13, 4712. [Google Scholar] [CrossRef]
- You, W.; Shen, C.; Wang, D.; Chen, L.; Jiang, X.; Zhu, Z. An Intelligent Deep Feature Learning Method with Improved Activation Functions for Machine Fault Diagnosis. IEEE Access 2020, 8, 1975–1985. [Google Scholar] [CrossRef]
- Xiao, F.; Xue, W.; Shen, Y.; Gao, X. A New Attention-Based LSTM for Image Captioning. Neural Process Lett. 2022, 54, 3157–3171. [Google Scholar] [CrossRef]
- Landi, F.; Baraldi, L.; Cornia, M.; Cucchiara, R. Working Memory Connections for LSTM. Neural Netw. 2021, 144, 334–341. [Google Scholar] [CrossRef]
- Sowmya, R.; Premkumar, M.; Jangir, P. Newton-Raphson-based optimizer: A new population-based metaheuristic algorithm for continuous optimization problems. Eng. Appl. Artif. Intel. 2024, 128, 107532. [Google Scholar] [CrossRef]
Frother (μL) | Collector (μL) |
---|---|
28.98 | 110.63 |
33.12 | 119.85 |
37.26 | 129.07 |
41.41 | 138.29 |
45.55 | 147.51 |
Parameters | Set Values |
---|---|
MiniBatchSize | 128 |
Optimal L2 Regularization Coefficient | 1 × 10−6 |
Optimal Number of Hidden Nodes | 70 |
Optimal Initial Learning Rate | 0.1 |
Dropout | 0.25 |
Epoch | 500 |
Time | 13 |
Evaluation Metrics | R2 | MSE | RMSE | MAPE | MAE | RPD |
---|---|---|---|---|---|---|
Training Set | 0.992 | 0.002 | 0.044 | 0.003 | 0.025 | 10.972 |
Test Set | 0.946 | 0.013 | 0.116 | 0.008 | 0.061 | 4.316 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, Y.; Liu, H.; Lu, F. Research on Prediction of Ash Content in Flotation-Recovered Clean Coal Based on NRBO-CNN-LSTM. Minerals 2024, 14, 894. https://doi.org/10.3390/min14090894
Li Y, Liu H, Lu F. Research on Prediction of Ash Content in Flotation-Recovered Clean Coal Based on NRBO-CNN-LSTM. Minerals. 2024; 14(9):894. https://doi.org/10.3390/min14090894
Chicago/Turabian StyleLi, Yujiao, Haizeng Liu, and Fucheng Lu. 2024. "Research on Prediction of Ash Content in Flotation-Recovered Clean Coal Based on NRBO-CNN-LSTM" Minerals 14, no. 9: 894. https://doi.org/10.3390/min14090894