A novel algorithm combined X-ray fluorescence and Neural Network (XRF-NN) for coal ash content prediction: Algorithm design and performance evaluation

• Autorzy: Wang Chuanzhen , Lv Jintao , Wang Xinyi , Khumalo Andile , Yu Anghong

Identyfikatory

DOI

10.37190/ppmp/193187

• Języki publikacji: EN

Abstrakty

EN

This study investigated a precise algorithm combining X-ray Fluorescence and Neural Network (XRF-NN) for predicting ash content. The 261 sets of XRF tests show that the 34 elements in the chosen Guqiao coal can be categorized as major, secondary, and tiny elements, whose cumulative ratios were ~95%, 4-5%, and <1%, respectively. Referring to the machine learning theory, the construction strategy of the Element-Ash dataset was determined viz. value determination → standardization → division → optimization of generalization ability. Then, the hyperparameters optimization displays that the XRF-NN model with 34 inputs and 1 output was suitable to predict coal ash content, where the activation function, loss function, and optimizer were ReLU, MAE, and Momentum, respectively. After iterative training, the new XRF-NN model provides the precise prediction of coal ash content with absolute errors between -2.0% and 2%. Moreover, the prediction accuracy rose from 57.69% to 100%, as the expected relative error increased from 1% to 5%. Furthermore, the comparisons between different prediction methods reveal that the minimum MRE of 1.22% can be obtained by XRF-NN with total elements, which was only half of those given by the conventional Multiple Linear Regression and Partial Least Squares Regression. Besides, the XRF-NN model presents the root mean squared error of 0.797%, a mean absolute error of 0.625%, and the coefficient of determination of 0.999, which were significantly superior to those calculated by Dual-Energy Gammaray Transmission, Ploy, RFR, XGBoost, and DNN model. The results of this study suggest the excellent performance of the new XRF-NN model in predicting ash content.

Słowa kluczowe

EN

ash content prediction; X-ray fluorescence; neural network; machine learning; mineral processing

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Physicochemical Problems of Mineral Processing
• Rocznik: 2024
• Tom: Vol. 60, iss. 5
• Strony: art. no. 193187
• Opis fizyczny: Bibliogr. 41 poz., fot., rys., tab., wykr.

Twórcy

autor

Wang Chuanzhen

• Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China

autor

Lv Jintao

• Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China

autor

Wang Xinyi

• Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China

autor

Khumalo Andile

• Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China

autor

Yu Anghong

• Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China

Bibliografia

• BAI, F., FAN, M., YANG, H., DONG, L., 2021. Rapid ash content determination method for coal particles through images captured under multiple ring light sources with various incident angles. Fuel. 271, 117557.
• BEGUM, N., MAITI, A., CHAKRAVARTY, D., DAS, BS., 2020. Reflectance spectroscopy based rapid determination of coal quality parameters. Fuel. 280, 118676.
• BHAKTA, S., NANDI, U., SI, T., GHOSAL, SK., CHANGDAR, C., PAL, RK., 2023. DiffMoment: an adaptive optimization technique for convolutional neural network. Appl. Intell. 13, 16844-16858.
• BORSARU, M., BIGGS, M., NICHOLS, W., BOS, F., 2001. The application of prompt-gamma neutron activation analysis to borehole logging for coal. Appl. Radiat. Isot. 54, 335-343.
• CAO, A., LIU, Y., YANG, X., LI, S., LIU, Y., 2022. FDNet: Knowledge and Data Fusion-Driven Deep Neural Network for Coal Burst Prediction. Sensors. 22, 3088.
• CHEN, T-C., ILIYASU, AM., ALIZADEH, SM., SALAMA, AS., EFTEKHARI-ZADEH, E., HIROTA, K., 2023. The use of artificial intelligence and time characteristics in the optimization of the structure of the volumetric percentage detection system independent of the scale value inside the pipe. Applied Artificial Intelligence. 37, 2166225
• CHENYANG, Z., XIBO, L., YUEMIN, Z., XULIANG, Y., YANJIAO, L., LIANG, D., CHENLONG, D., ZHONGHAO, R., 2021. Recent progress and potential challenges in coal upgrading via gravity dry separation technologies. Fuel. 305, 121430.
• CTVRTNICKOVA, T., MATEO, MP., YAñEZ, A., NICOLAS, G., 2010. Laser Induced Breakdown Spectroscopy application for ash characterisation for a coal fired power plant. Spectrochim. Acta, Part B. 8, 734-737
• CYBENKO, G., 1989. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems. 4, 303-314
• DJORK-ARNE, C., THOMAS, U., SEPP, H., 2015. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv - CS - Machine Learning. 1511, 07289.
• FEIYAN, B., MINQIANG, F., HONGLI, Y., LIANPING, D., 2021. Fast recognition using convolutional neural network for the coal particle density range based on images captured under multiple light sources. Int. J. Min. Sci. Technol. 31, 1053-1061.
• GAFT, M., DVIR, E., MODIANO, H., SCHONE, U., 2008. Laser Induced Breakdown Spectroscopy machine for online ash analyses in coal. Spectrochim. Acta, Part B. 63, 1177-1182.
• GAO, R., LI, J., WANG, S., ZHANG, Y., ZHANG, L., YE, Z., ZHU, Z., YIN, W., JIA, S., 2023. Ultra-repeatability measurement of calorific value of coal by NIRS-XRF. Anal. Methods. 13, 1674-1680.
• GEISSER, S. 1975., The Predictive Sample Reuse Method with Applications. J. Am. Stat. Assoc. 70, 320-328.
• GOODFELLOW, I., BENGIO, Y., COURVILLE, A., 2016. Deep Learning. MIT Press.
• HORNIK, K. 1991., Approximation capabilities of multilayer feedforward networks. Neural Networks. 2, 251-257.
• HOWER, JC., FINKELMAN, RB., EBLE, CF., ARNOLD, BJ., 2022. Understanding coal quality and the critical importance of comprehensive coal analyses. Int. J. Coal Geol. 263, 104120.
• KHOONTHIWONG, C., SAENGKAEW, P., CHANKOW, N., 2020. Determination of the ash content of coal samples by nuclear techniques with bismuth germanate detectors. Int. J. Coal Prep. Util. 4, 1-10.
• KORKMAZ, M. 2019., A study over the Formulation of the Parameters 5 or Less Independent Variables of Multiple Linear Regression. J. Funct. Spaces. 2019, 1-14.
• LIU, J., LIU, X., LIU, C., LE, BT., XIAO, D., 2019. Random Search Enhancement of Incremental Regularized Multiple Hidden Layers ELM. IEEE Access. 7, 36866-36878.
• LIU, Z., DENG, Z., DAVIS, S., CIAIS, P., 2023. Monitoring global carbon emissions in 2022. Nature Reviews Earth & Environment. 4, 205-206.
• LU, H-J., ZOU, N., JACOBS, R., AFFLERBACH, B., LU, X-G., MORGAN, D., 2019. Error assessment and optimal crossvalidation approaches in machine learning applied to impurity diffusion. Comput. Mater. Sci. 169, 109075-109075.
• OUADAH., ABDELFETTAH., ZEMMOUCHI, G., LEILA., SALHI., NEDJMA., 2022. Selecting an appropriate supervised machine learning algorithm for predictive maintenance. The International Journal of Advanced Manufacturing Technology. 119, 1-25.
• PARKES, EJ., DUFFY, BR., 1996. An automated tanh-function method for finding solitary wave solutions to non-linear evolution equations. Comput. Phys. Commun. 98, 288-300.
• REBIERE, H., KERMAïDIC, A., GHYSELINCK, C., BRENIER, C., 2018. Inorganic analysis of falsified medical products using X-ray fluorescence spectroscopy and chemometrics. Talanta. 195, 490-496.
• SHEELA, KG., DEEPA, SN., 2013. Review on Methods to Fix Number of Hidden Neurons in Neural Networks. Math. Probl. Eng. 2013, 1-11.
• SHEN, L., QIAO, E., LIU, L., XUE, C., LIU, B., MIN, F-F., 2022. Utilization of coal slime: Coal and kaolinite separation by classification, forward and reverse flotation method. Physicochem. Probl. Miner. Process. 3, 58.
• STONE, M. 1974., Cross-Validatory Choice and Assessment of Statistical Predictions. Journal of the Royal Statistical Society: Series B (Methodological). 2, 111-133
• TEMENG, VA., ZIGGAH, YY., ARTHUR, CK., 2020. A novel artificial intelligent model for predicting air overpressure using brain inspired emotional neural network. Int. J. Min. Sci. Technol. 5, 683-689
• TRAN, TTK., LEE, T., KIM, JS., 2020. Increasing Neurons or Deepening Layers in Forecasting Maximum Temperature Time Series? Atmosphere. 11, 1072-1072.
• VINCZE., SOMOGYI., OSAN., VEKEMANS., TOROK., JANSSENS., ADAMS., 2002. Quantitative trace element analysis of individual fly ash particles by means of X-ray microfluorescence. Anal. Chem. 74, 1128-1135.
• WANG, C., LV, J., LIU, H., WANG, G., YU, A., 2023. Research of GM(1,N) dynamic network based on the metabolic algorithm optimization for ash fitting. Journal of China Coal Society. 12, 4549-4558
• WANG, C., LV, W., 2023. Intelligent control of heavy media separation. Int. J. Global Energy Issues. 45, 86-100.
• WANG, G., HE, T., KUANG, Y-L., LIN, Z., 2020. Optimization of soft-sensing model for ash content prediction of flotation tailings by image features tailings based on GA-SVMR. Physicochem. Probl. Miner. Process. 4, 56.
• WEN, Z., LIU, H., ZHOU, M., LIU, C., ZHOU, C., 2023. Explainable machine learning rapid approach to evaluate coal ash content based on X-ray fluorescence. Fuel. 332, 125991.
• YANG, M., XIE, Q., WANG, X., DONG, H., ZHANG, H., LI, C., 2018. Lowering ash slagging and fouling tendency of high-alkali coal by hydrothermal pretreatment. Int. J. Min. Sci. Technol. 29, 521-525.
• YANG, X., ALDRICH, C., 2013. Optimizing control of coal flotation by neuro-immune algorithm. Int. J. Min. Sci. Technol. 23, 407-413.
• YU, A., LIU, H., WANG, C., LV, J., WANG, F., HE, S., WANG, L., 2022. Online Ash Content Monitor by Automatic Composition Identification and Dynamic Parameter Adjustment Method in Multicoal Preparation. Processes. 10, 1432.
• ZHANG, C., BENGIO, S., HARDT, M., RECHT, B., VINYALS, O., 2021. Understanding deep learning (still) requires rethinking generalization. Commun. ACM. 64, 107-115.
• ZHANG, N., LIU, C., 2018. Radiation characteristics of natural gamma-ray from coal and gangue for recognition in top coal caving. Sci. Rep. 8, 190
• ZHOU, Y., LI, D., HUO, S., KUNG, S-Y., 2020. Shape autotuning activation function. Expert Syst. Appl. 171, 114534.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).