Precise and non-destructive approach for identifying the real concentration based on cured cemented paste backfill using hyperspectral imaging

Abstract

Cemented paste backfill (CPB) is a technology that achieves safe mining by filling the goaf with waste rocks, tailings, and other materials. It is an inevitable choice to deal with the development of deep and highly difficult mines and meet the requirements of environmental protection and safety regulations. It promotes the development of a circular economy in mines through the development of low-grade resources and the resource utilization of waste, and extends the service life of mines. The mass concentration of solid content (abbreviated as “concentration”) is a critical parameter for CPB. However, discrepancies often arise between the on-site measurements and the pre-designed values due to factors such as groundwater inflow and segregation within the goaf, which cannot be evaluated after the solidification of CPB. This paper innovatively provides an in-situ non-destructive approach to identify the real concentration of CPB after curing for certain days using hyperspectral imaging (HSI) technology. Initially, the spectral variation patterns under different concentration conditions were investigated through hyperspectral scanning experiments on CPB samples. The results demonstrate that as the CPB concentration increases from 61wt% to 73wt%, the overall spectral reflectance gradually increases, with two distinct absorption peaks observed at 1407 and 1917 nm. Notably, the reflectance at 1407 nm exhibited a strong linear relationship with the concentration. Subsequently, the K-nearest neighbors (KNN) and support vector machine (SVM) algorithms were employed to classify and identify different concentrations. The study revealed that, with the KNN algorithm, the highest accuracy was achieved when K (number of nearest neighbors) was 1, although this resulted in overfitting. When K = 3, the model displayed the optimal balance between accuracy and stability, with an accuracy of 95.03%. In the SVM algorithm, the highest accuracy of 98.24% was attained with parameters C (regularization parameter) = 200 and Gamma (kernel coefficient) = 10. A comparative analysis of precision, accuracy, and recall further highlighted that the SVM provided superior stability and precision for identifying CPB concentration. Thus, HSI technology offers an effective solution for the in-situ, non-destructive monitoring of CPB concentration, presenting a promising approach for optimizing and controlling CPB characteristic parameters.

Keywords

cemented paste backfill / concentration / hyperspectral imaging / non-destructive testing

References

[1] Wang YM, Chen QS, Dai BB, Wang DL. Guidance and review: Advancing mining technology for enhanced production and supply of strategic minerals in China. Green Smart Min. Eng., 2024, 1(1): 2-11.

[2] Li BY, Zhang JX, Yan H, Zhou N, Li M. Experimental investigation into the thermal conductivity of gangue-cemented paste backfill in mine application. J. Mater. Res. Technol., 2022, 16: 1792.

[3] Huang MQ, Zheng QW, Liu QL, Gao Z. Improvement of fluidity and long-term strength of cemented paste backfill with low calcium fly-ash. J. Geol. Soc. India, 2024, 100(9): 1338.

[4] Chen QS, Yuan XY, Wu AX, Liu YK. Enhancing CO₂ mitigation potential and mechanical properties of shotcrete in underground mining utilizing microbially induced calcium carbonate precipitation. Int. J. Min. Sci. Technol., 2024, 34(12): 1643.

[5] Li MY, Guo LJ, Zhao Y, et al. . A state-of-the-art review on delayed expansion of cemented paste backfill materials. Rare Met., 2024, 43(8): 3475.

[6] Panchal S, Deb D, Sreenivas T. Mill tailings based composites as paste backfill in mines of U-bearing dolomitic limestone ore. J. Rock Mech. Geotech. Eng., 2018, 10(2): 310.

[7] Y.P. Kou, G.B. Li, Z.P. Song, and P.T. Wang, Experimental study on the evolutive shear fracture behaviour and properties of cemented paste backfill, Constr. Build. Mater., 423(2024), art. No. 135780.

[8] X.Z. Shi, Z.K. Zhao, X. Chen, K. Kong, and J.J. Yuan, Investigation of fluidity and strength of enhanced foam-cemented paste backfill, Materials, 15(2022), No. 20, art. No. 7101.

[9] Chen QS, Wu AX. Research progress of phosphogypsum-based backfill technology. Chin. J. Eng., 2025, 47(2): 195

[10] Tuylu S. Effect of different particle size distribution of zeolite on the strength of cemented paste backfill. Int. J.Enviro. Sci. Technol., 2022, 19(1): 131.

[11] Fall M, Belem T, Samb S, Benzaazoua M. Experimental characterization of the stress-strain behaviour of cemented paste backfill in compression. J. Mater. Sci., 2007, 42(11): 3914.

[12] H. Li, X.M. Wan, Z.Q. Jin, Y.Z. Cui, and Y. Chen, A study on the mechanical properties and hydration process of slag cemented ultrafine tailings paste backfill, Sustainability, 16(2024), No. 8, art. No. 3143.

[13] Liu YK, Wang YM, Chen QS. Using cemented paste backfill to tackle the phosphogypsum stockpile in China: A down-to-earth technology with new vitalities in pollutant retention and CO₂ abatement. Int. J. Miner. Metall. Mater., 2024, 31(7): 1480.

[14] L.W. Chen, X.C. Xu, J. Wu, L. Gao, Z.Z. Zhang, and S. Jin, Characteristics variation of tailings using cemented paste backfill technique, Water Air Soil Pollut., 225(2014), No. 5, art. No. 1974.

[15] Liu H, Deng XJ, Shi XM, et al. . A new index and control method of filling effect for cemented paste backfill in coal mines. Int. J. Min. Reclam. Environ., 2023, 37(10): 805.

[16] Yilmaz E, Belem T, Benzaazoua M. Specimen size effect on strength behavior of cemented paste backfills subjected to different placement conditions. Eng. Geol., 2015, 185: 52.

[17] Z.K. Wang, Y.M. Wang, L.B. Wu, et al, Effective reuse of red mud as supplementary material in cemented paste backfill: Durability and environmental impact, Constr. Build. Mater., 328(2022), art. No. 127002.

[18] A.E. Belibi Tana, S.H. Yin, and L. Wang, Investigation on mechanical characteristics and microstructure of cemented whole tailings backfill, Minerals, 11(2021), No. 6, art. No. 592.

[19] P. Thanayamwatte, N. Sivakugan, and P. To, Hydraulic backfill consolidation in underground mine stopes, Int. J. Geosynth. Ground Eng., 10(2024), No. 3, art. No. 50.

[20] X.P. Peng, L.J. Guo, G.S. Liu, X.C. Yang, and X.Z. Chen, Experimental study on factors influencing the strength distribution of in situ cemented tailings backfill, Metals, 11(2021), No. 12, art. No. 2059.

[21] Zhou XL, Hu SH, Zhang G, Li JZ, Xuan DQ, Gao W. Experimental investigation and mathematical strength model study on the mechanical properties of cemented paste backfill. Constr. Build. Mater., 2019, 226: 524.

[22] Zhang BH, Li JB, Fan SX, et al. . Principles and applications of hyperspectral imaging technique in quality and safety inspection of fruits and vegetables. Spectrosc. Spectral Anal., 2014, 34(10): 2743

[23] Ranjan P, Gupta G. A cross-domain semi-supervised zero-shot learning model for the classification of hyperspectral images. J. Indian Soc. Remote Sens., 2023, 51(10): 1991.

[24] G.Y. Wu, M.A.A. Al-qaness, D. Al-Alimi, A. Dahou, M. Abd Elaziz, and A.A. Ewees, Hyperspectral image classification using graph convolutional network: A comprehensive review, Expert Syst. Appl., 257(2024), art. No. 125106.

[25] Wang J. A novel collaborative representation algorithm for spectral unmixing of hyperspectral remotely sensed imagery. IEEE Access, 2021, 9: 89243.

[26] Y.F. Gu, T.Z. Liu, G.M. Gao, et al., Multimodal hyperspectral remote sensing: An overview and perspective, Sci. China Inf. Sci., 64(2021), No. 2, art. No. 121301.

[27] Fabelo H, Ortega S, Szolna A, et al. . In-vivo. IEEE Access, 2019, 7: 39098.

[28] F. Guo, Z. Xu, H.H. Ma, et al., Estimating chromium concentration in arable soil based on the optimal principal components by hyperspectral data, Ecol. Indic., 133(2021), art. No. 108400.

[29] Achata EM, Inguglia ES, Esquerre CA, Tiwari BK, O’Donnell CP. Evaluation of Vis-NIR hyperspectral imaging as a process analytical tool to classify brined pork samples and predict brining salt concentration. J. Food Eng., 2019, 246: 134.

[30] Gastaldi D, Canonico F, Boccaleri E. Ettringite and calcium sulfoaluminate cement: Investigation of water content by near-infrared spectroscopy. J. Mater. Sci., 2009, 44(21): 5788.

[31] Gastaldi D, Canonico F, Irico S, Pellerej D, Paganini MC. Near-infrared spectroscopy investigation on the hydration degree of a cement paste. J. Mater. Sci., 2010, 45(12): 3169.

[32] Chen QS, Chao Z, Wang DL, Liu YK, Qi CC. Carbon sequestration potential and mechanisms of shotcrete for tunnel support in underground metal mine under cement hydration. Int. J. Miner. Metall. Mater., 2024, 32(7): 1496.

[33] F. Radica, G. Iezzi, O. Trotta, G. Bonifazi, S. Serranti, and J. de Brito, Characterization of CDW types by NIR spectroscopy: Towards an automatic selection of recycled aggregates, J. Build. Eng., 88(2024), art. No. 109005.

[34] N. Blake, R. Gaifulina, L.D. Griffin, I.M. Bell, and G.M.H. Thomas, Machine learning of raman spectroscopy data for classifying cancers: A review of the recent literature, Diagnostics, 12(2022), No. 6, art. No. 1491.

[35] Tripathy A, Agrawal A, Rath S K. Classification of sentiment reviews using n-gram machine learning approach. Expert Syst. Appl., 2016, 57: 117.

[36] L. Fan, M. Fan, A. Alhaj, G.D. Chen, and H.Y. Ma, Hyperspectral imaging features for mortar classification and compressive strength assessment, Constr. Build. Mater., 251(2020), art. No. 118935.

[37] Zhang C, Guo CT, Liu F, Kong WW, He Y, Lou BG. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine. J. Food Eng., 2016, 179: 11.

[38] J. Sun, F.Y. Yang, J.H. Cheng, S.M. Wang, and L.H. Fu, Nondestructive identification of soybean protein in minced chicken meat based on hyperspectral imaging and VGG16-SVM, J. Food Compos. Anal., 125(2024), art. No. 105713.

[39] A. Nirere, J. Sun, V. A. Atindana, A. Hussain, X. Zhou, and K.S. Yao, A comparative analysis of hybrid SVM and LS-SVM classification algorithms to identify dried wolfberry fruits quality based on hyperspectral imaging technology, J. Food Process. Preserv., 46(2022), No. 3, art. No. e16320.

[40] Liu L, Li Y, Cao YJ, et al. . Transient rotor angle stability prediction method based on SVM and LSTM network. Electr. Power Autom. Equip., 2020, 40(2): 129

[41] R.Y. Li and S.L. Li, Multimedia image data analysis based on KNN algorithm, Comput. Intell. Neurosci., 2022(2022), No. 1, art. No. 7963603.

[42] Kong WW, Zhang C, Liu F, Nie PC, He Y. Rice seed cultivar identification using near-infrared hyperspectral imaging and multivariate data analysis. Sensors, 2013, 13(7): 8916.

[43] X.T. Hu, P.P. Ma, Y.Z. He, et al., Nondestructive and rapid detection of foreign materials in wolfberry by hyperspectral imaging combing with chemometrics, Vib. Spectrosc., 128(2023), art. No. 103578.

[44] X.H. Zhu, R. Wang, L. Wang, M.M. Liu, and S.M. Li, Machine learning classification applied to the effect of AFSD process parameters on tensile properties, Mater. Lett., 377(2024), art. No. 137356.

[45] H. J. Kang, C. Kim, S. Chae, et al., Analysis of dryness in cement-based mixture via spectral imaging and dimensionality reduction, Sci. Rep., 14(2024), No. 1, art. No. 27489.

[46] Z.F. Yang, Q.M. Sui, and L. Jia, Rapid analysis of raw meal composition content based on nir spectroscopy for cement raw material proportioning control process, Processes, 10(2022), No. 12, art. No. 2494.

[47] Ahmed I, Sharma UK, Garg PK, Thakur AK. Analysis of cement properties using hyperspectral remote sensing methods. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci, 2024, X-4-2024: 15.

[48] Shi CQ, Zeng HL, Guo YJ, Liu K, Zhang XQ, Wu GN. Surface roughness detection of roof insulator based on hyperspectral technology. IEEE Access, 2020, 8: 81651.

[49] Fan L, Alhaj A, Ma HY, Chen G. Assessing moisture content on the surface of mortar samples from hyperspectral imaging. Proceedings of the 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure, 2019

[50] Chang J, Li JY, Han JN, Zhang TT. Traces of CH in a C4A3$-C2S hydration system. Constr. Build. Mater., 2019, 197: 641.

[51] D.L. Wang, Q. Na, Y.K. Liu, Y. Feng, Q.L. Zhang, and Q.S. Chen, Hydration process and fluoride solidification mechanism of multi-source solid waste-based phosphogypsum cemented paste backfill under CaO modification, Cem. Concr. Compos., 154(2024), art. No. 105804.

[52] D.L. Wang, Q.L. Zhang, B. Liu, D.B. Zhu, and Q.S. Chen, Enhanced immobilization of fluoride in phosphogypsum-based cement-free paste backfill modified by polyaluminum chloride and its mechanism, Constr. Build. Mater., 458(2025), art. No. 139622.

[53] J. Yang, W. Zhang, D.S. Hou, G.Z. Zhang, and Q.J. Ding, Structure, dynamics and mechanical properties evolution of calcium silicate hydrate induced by dehydration and dehydroxylation, Constr. Build. Mater., 291(2021), art. No. 123327.

[54] Ghosh A, Guha T, Bhar RB, Das S. Pattern classification of fabric defects using support vector machines. Int. J. Clothing Sci. Technol., 2011, 23(2–3): 142.

[55] H. Benarafa, M. Benkhalifa, and M. Akhloufi, WordNet semantic relations based enhancement of KNN model for implicit aspect identification in sentiment analysis, Int. J. Comput. Intell. Syst., 16(2023), No. 1, art. No. 3.

[56] M.W. Wang, C. Wang, J.H. Ruan, et al., Pollution level mapping of heavy metal in soil for ground-airborne hyperspectral data with support vector machine and deep neural network: A case study of southwestern Xiong’an, China, Environ. Pollut., 321(2023), art. No. 121132.

[57] K. Jo, S. Lee, S.K.C. Jeong, D.H. Lee, H. Jeon, and S. Jung, Hyperspectral imaging-based assessment of fresh meat quality: Progress and applications, Microchem. J., 197(2024), art. No. 109785.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing