مدل‌سازی و تحلیل سیستم‌های درزه با رویکرد ترکیبی و چندمرحله‌ای خوشه‌بندی: مطالعه موردی توده گرانیتی لوچو زاهدان

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه مهندسی معدن، دانشکده مهندسی شهید نیکبخت، دانشگاه سیستان و بلوچستان، زاهدان، ایران

چکیده

درزه‌های ساختاری به دلیل تأثیر عمیق بر پایداری توده‌های سنگی و طراحی پروژه‌های مهندسی، نیازمند تحلیل دقیق و شناسایی صحیح دسته‌بندی‌ها هستند. این پژوهش باهدف ارائه روشی نوین برای شناسایی و تحلیل دسته‌های درزه، از رویکرد ترکیبی و چندمرحله‌ای شامل الگوریتم K-means برای خوشه‌بندی اولیه و الگوریتم خوشه‌بندی سلسله‌مراتبی تجمعی (AHC) برای تحلیل روابط پیچیده استفاده کرده است. داده‌های مطالعه شامل امتداد و شیب 172 صفحه درزه از توده گرانیتوئیدی لوچو زاهدان است که از طریق برداشت میدانی گردآوری شده‌اند. در ابتدا، الگوریتم K-means با استفاده از معیار فاصله اقلیدسی خوشه‌بندی اولیه را در پنج مرحله انجام داد. در این مراحل، ۲۱ داده نویز یا پرت به‌تدریج حذف شدند و با کاهش واریانس درون‌خوشه‌ای، داده‌های باقی‌مانده در ۱۲ خوشه اولیه قرار گرفتند. سپس با استفاده از الگوریتم AHC و معیار شباهت کسینوسی و اعمال سطح برش 866/0، ۱۲ خوشه اولیه به شش خوشه نهایی تقسیم شدند. نتایج نشان داد که واریانس درون‌خوشه‌ای معادل 36/16 درصد و واریانس بین‌خوشه‌ای معادل 64/83 درصد از واریانس کل است که بیانگر تفکیک مؤثر و انسجام بالای خوشه‌های نهایی با ویژگی‌های فضایی و هندسی بهینه است. در این مطالعه درزه‌ها در شش گروه نهایی شامل درزه‌های افقی (J1)، درزه‌های با شیب متوسط (J2) و درزه‌های با شیب تند (J3، J4، J5 و J6) دسته‌بندی شدند که هرکدام ویژگی‌ها و چالش‌های خاص خود را در فرآیند استخراج و پایداری دیواره‌های معدن دارند. این روش امکان تحلیل سه‌بعدی الگوهای فضایی درزه‌ها را فراهم کرده و به آشکارسازی روابط پیچیده در داده‌ها و ارائه نتایج قابل‌اعتماد منجر شد. رویکرد پیشنهادی علاوه بر بهبود دقت و تفکیک دسته‌های درزه‌ها، محدودیت‌های روش‌های متعارف را برطرف کرده و پارامترهای کمی برای تفسیر دقیق‌تر الگوهای زمین‌شناسی مرتبط با جهت‌گیری درزه‌ها فراهم می‌کند. نتایج آن به‌عنوان ابزاری کارآمد در برنامه‌ریزی استخراج معادن، بهبود پایداری شیب‌ها، طراحی سازه‌های زیرزمینی و مدیریت ریسک‌های مرتبط با توده‌های سنگی در پروژه‌های مهندسی قابل‌استفاده است.

کلیدواژه‌ها


عنوان مقاله [English]

Modeling and Analysis of Joint Systems Using a Combined and Multi-Stage Clustering Approach: A Case Study of the Lucho Granite Mass, Zahedan

نویسندگان [English]

  • Soheil Zaremotlagh
  • Seyed Amirasad Fatemi
  • Mohamad Javad Azinfar
Dept. of Mining Engineering, Shahid Nikbakht Faculty of Engineering, University of Sistan and Baluchestan, Zahedan, Iran
چکیده [English]

This study aims to develop a novel method for identifying and analyzing structural joint sets, crucial for rock mass stability and engineering projects like tunneling and mining. A hybrid, multi-stage approach was used, combining the K-means algorithm for initial clustering and Agglomerative Hierarchical Clustering (AHC) for analyzing complex relationships. The dataset includes orientation and dip measurements from 172 joint planes in the Lucho granite mass of Zahedan. The K-means algorithm improved initial clustering accuracy by reducing intra-cluster variance, while AHC formed six final clusters with high spatial coherence, enhancing inter-cluster variance and reducing intra-cluster dispersion. This method effectively eliminated noise and outliers, facilitating 3D spatial pattern analysis and revealing complex data relationships. The findings demonstrate the method's superiority over conventional approaches, providing valuable quantitative parameters for geological pattern interpretation, joint orientation analysis, and potential applications in geoscience and engineering fields.

کلیدواژه‌ها [English]

  • Joint modeling
  • Spatial patterns
  • Agglomerative Hierarchical Clustering (AHC)
  • K-means algorithm
  • Hybrid multi-stage clustering
[1]                 Hoek, E., & Brown, E. T. (1980). Empirical strength criterion for rock masses. Journal of the geotechnical engineering division. 106(9): 1013-1035.
[2]                 Rafiei Renani, H., & Cai, M. (2022). Forty-year review of the Hoek–Brown failure criterion for jointed rock masses. Rock mechanics and rock engineering. 55(1): 439-461.
[3]                 Wyllie, D. C., & Mah, C. (2017). Rock slope engineering. CRC Press.
[4]                 Delaney, R. K., Shakoor, A., & Watts, C. F. (2020). Evaluating the use of unmanned aerial systems (UAS) for collecting discontinuity orientation data for rock slope stability analysis. Environmental & Engineering Geoscience. 26(4): 427-447.
[5]                 Wang, Y., Zhou, J., Chen, Q., Chen, J., Zhu, C., & Li, H. (2024). Automatic interpretation of geometric information of discontinuities and its influence on the stability of highly-jointed rock slopes. Journal of Rock Mechanics and Geotechnical Engineering.
[6]                 Waldron, J., & Snyder, M. (2020). Geological Structures: A practical introduction.
[7]                 Lee, C.-Y., & Wang, I.-T. (2011). Analysis of highway slope failure by an application of the stereographic projection. International Journal of Geological and Environmental Engineering. 5(3): 122-129.
[8]                 To, P., & Sivakugan, N. (2023). Analytical solution for rock discontinuity prediction without stereonet. Geotechnical and Geological Engineering. 41(7): 4311-4320.
[9]                 Lisle, R. J., & Leyshon, P. R. (2004). Stereographic projection techniques for geologists and civil engineers. Cambridge University Press.
[10]             Qu, H., Pan, M., Ming, J., Wu, Z., & Sun, Z. (2008). An efficient method for high-precision 3D geological modeling from intersected folded cross-sections. Acta Scientiarum Naturalium Universitatis Pekinensis. 44(6): 915-920.
[11]             Abdollahipour, A., & Mansouri, H. (2013). SETDISC a Software for Joint Classification Based on Poisson Clustering. Journal of Analytical and Numerical Methods in Mining Engineering. 2(4): 11-19 (In Persian).
[12]             Jalali, Z., & Mousavi Nasab, S. M. (2015). Modification of rock mass rating classification system by k-means and fuzzy c-means clustering algorithms. Journal of Analytical and Numerical Methods in Mining Engineering. 5(9): 73-84 (In Persian).
[13]             Nikadat, N., & Yarahmadi Bafghi, A. (2014). Estimating Joint Normal and Shear Stiffness Coefficient Using Statistical Methods. Journal of Analytical and Numerical Methods in Mining Engineering. 3(6): 93-103 (In Persian).
[14]             Liu, Y., Chen, J., Tan, C., Zhan, J., Song, S., Xu, W., Yan, J., Zhang, Y., Zhao, M., & Wang, Q. (2022). Intelligent scanning for optimal rock discontinuity sets considering multiple parameters based on manifold learning combined with UAV photogrammetry. Engineering Geology. 309: 106851.
[15]             Farmakis, I., DiFrancesco, P.-M., Hutchinson, D. J., & Vlachopoulos, N. (2022). Rockfall detection using LiDAR and deep learning. Engineering Geology. 309: 106836.
[16]             Chen, Q., Ge, Y., & Tang, H. (2024). Rock discontinuities characterization from large-scale point clouds using a point-based deep learning method. Engineering Geology. 337: 107585.
[17]             Zangana, H. M., & Abdulazeez, A. M. (2023). Developed Clustering Algorithms for Engineering Applications: A Review. International Journal of Informatics, Information System and Computer Engineering (INJIISCOM). 4(2): 147-169.
[18]             Bouveyron, C., Hammer, B., & Villmann, T. (2012). Recent developments in clustering algorithms. ESANN,
[19]             Alasalı, T., & Ortakcı, Y. (2024). Clustering Techniques in Data Mining: A Survey of Methods, Challenges, and Applications. Computer Science. 9(1): 32-50.
[20]             Han, J., Pei, J., & Tong, H. (2022). Data mining: concepts and techniques. Morgan kaufmann.
[21]             Zaremotlagh, S., Hezarkhani, A., & Sadeghi, M. (2016). Detecting homogenous clusters using whole-rock chemical compositions and REE patterns: A graph-based geochemical approach. Journal of Geochemical Exploration. 170: 94-106.
[22]             Michalak, M., Turoboś, F., & Gladki, P. (2022). Explainable Clustering Models for Structural Geology Measurements. AGU Fall Meeting Abstracts,
[23]             Tokhmechi, B., Memarian, H., Moshiri, B., Rasouli, V., & Noubari, H. A. (2011). Investigating the validity of conventional joint set clustering methods. Engineering Geology. 118(3-4): 75-81.
[24]             Yang, X., Li, S., Liang, K., Nie, F., & Lin, L. (2022). Structured graph optimization for joint spectral embedding and clustering. Neurocomputing. 503: 62-72.
[25]             Shang, X., Li, X., Morales-Esteban, A., Dong, L., & Peng, K. (2017). K‐Means Cluster for Seismicity Partitioning and Geological Structure Interpretation, with Application to the Yongshaba Mine (China). Shock and Vibration. 2017(1): 5913041.
[26]             Caumon, G., Collon-Drouaillet, P., Le Carlier de Veslud, C., Viseur, S., & Sausse, J. (2009). Surface-based 3D modeling of geological structures. Mathematical geosciences. 41: 927-945.
[27]             Zhao, Y., Li, A., Du, Z., Chen, Y., Sun, H., & Zhi, Z. (2024). Joint Structure Detection and Multi-Scale Clustering Filtering for Tunnel Lining Extraction From Point Clouds. IEEE Transactions on Intelligent Transportation Systems.
[28]             Ma, Y., Lin, H., Wang, Y., Huang, H., & He, X. (2021). A multi-stage hierarchical clustering algorithm based on centroid of tree and cut edge constraint. Information Sciences. 557: 194-219.
[29]             Fazli, M., Bertram, R., & Striegel, D. A. (2024). Multi-layer Bundling as a New Approach for Determining Multi-scale Correlations Within a High-Dimensional Dataset. Bulletin of Mathematical Biology. 86(9): 105.
[30]             Chen, S., Zhang, F., Zhang, Z., Yu, S., Qiu, A., Liu, S., & Zhao, X. (2023). Multi-Scale Massive Points Fast Clustering Based on Hierarchical Density Spanning Tree. ISPRS International Journal of Geo-Information. 12(1): 24.
[31]             Wang, J., Wu, B., Ren, Z., Zhang, H., & Zhou, Y. (2023). Multi-scale deep multi-view subspace clustering with self-weighting fusion and structure preserving. Expert Systems with Applications. 213: 119031.
[32]             Murtagh, F., & Contreras, P. (2012). Algorithms for hierarchical clustering: an overview. Wiley interdisciplinary reviews: data mining and knowledge discovery. 2(1): 86-97.
[33]             Gupta, A., Sharma, H., & Akhtar, A. (2021). A comparative analysis of k-means and hierarchical clustering. EPRA International Journal of Multidisciplinary Research (IJMR). 7(8).
[34]             Abdulhafedh, A. (2021). Incorporating k-means, hierarchical clustering and pca in customer segmentation. Journal of City and Development. 3(1): 12-30.
[35]             Liu, Y., & Li, B. (2020). Bayesian hierarchical K-means clustering. Intelligent Data Analysis. 24(5): 977-992.
[36]             Karthikeyan, B., George, D. J., Manikandan, G., & Thomas, T. (2020). A comparative study on k-means clustering and agglomerative hierarchical clustering. International Journal of Emerging Trends in Engineering Research. 8(5).
[37]             Govender, P., & Sivakumar, V. (2020). Application of k-means and hierarchical clustering techniques for analysis of air pollution: A review (1980–2019). Atmospheric pollution research. 11(1): 40-56.
[38]             Dulanjalee, P., & Gunathilake, J. (2017). Rock Slope Stability Assessment Using Stereographic Projection Method and Limit Equilibrium Analysis. Advancing Culture of Living with Landslides: Volume 4 Diversity of Landslide Forms,
[39]             Kıncal, C. (2014). Application of two new stereographic projection techniques to slope stability problems. International Journal of Rock Mechanics and Mining Sciences. 66: 136-150.
[40]             Dershowitz, W., & Einstein, H. (1988). Characterizing rock joint geometry with joint system models. Rock mechanics and rock engineering. 21(1): 21-51.
[41]             Biabangard, H., Fatameian, M., Moridi Farimani, A., & Bakhshi Mohabi, M. (2017). Petrography, geochemistry and tectono-magmatic setting of the dykes of the north and the west of Zahedan (Southeast Iran). Petrology. 8(31): 147-164 (In Persian).
[42]             Ghasemi, H., Sadeghian, M., Kord, M., & Khanalizadeh, A. (2010). The evolution mechanism’s of Zahedan granitoidic batholith, southeast Iran [Research]. Iranian Journal of Crystallography and Mineralogy. 17(4): 551-578 (In Persian).
[43]             Sadeghian, M., & Valizadeh, M. V. (2008). Emplacement Mechanism of Zahedan Granitoidic Pluton with the Aid of AMS Method. Scientific Quarterly Journal of Geosciences. 17(66): 134-159 (In Persian).
[44]             Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern recognition letters. 31(8): 651-666.
[45]             Blömer, J., Lammersen, C., Schmidt, M., & Sohler, C. (2016). Theoretical analysis of the k-means algorithm–a survey. Algorithm Engineering: Selected Results and Surveys: 81-116.
[46]             Zhou, J.-w., Chen, J.-l., & Li, H.-b. (2024). An optimized fuzzy K-means clustering method for automated rock discontinuities extraction from point clouds. International Journal of Rock Mechanics and Mining Sciences. 173: 105627.
[47]             Tang, N., Wang, L., Jiang, H., Huang, X., Tan, G., & Zhou, X. (2023). A new clustering method of rock discontinuity sets based on modified K-means algorithm. Bulletin of Engineering Geology and the Environment. 82(11): 415.
[48]             Clero, K., Ed-Diny, S., Achalhi, M., Cherkaoui, M., Benzakour, I., Soror, T., Rziki, S., El Fkihi, S., Nadour, M., & Tagemouati, H. (2024). Rock mass joint set identification at Draa Sfar mine in Morocco through stereographic projection and K-means clustering. Mediterranean Geoscience Reviews. 6(1): 49-56.
[49]             Burkardt, J. (2009). K-means clustering. Virginia Tech, Advanced Research Computing, Interdisciplinary Center for Applied Mathematics.
[50]             Suhui, W., Ying, C., Yanning, Z., & Yuntao, P. (2011). Survey on K-means Algorithm. Data Analysis and Knowledge Discovery. 27(5): 28-35.
[51]             Muthén, B. O. (1989). Latent variable modeling in heterogeneous populations. Psychometrika. 54: 557-585.
[52]             Muthén, B. O. (1994). Multilevel covariance structure analysis. Sociological methods & research. 22(3): 376-398.
[53]             Hoff, P. D. (2009). A hierarchical eigenmodel for pooled covariance estimation. Journal of the Royal Statistical Society Series B: Statistical Methodology. 71(5): 971-992.
[54]             Miyamoto, S. (2022). Theory of agglomerative hierarchical clustering (Vol. 15). Springer.
[55]             Bouguettaya, A., Yu, Q., Liu, X., Zhou, X., & Song, A. (2015). Efficient agglomerative hierarchical clustering. Expert Systems with Applications. 42(5): 2785-2797.
[56]             Davidson, I., & Ravi, S. (2005). Agglomerative hierarchical clustering with constraints: Theoretical and empirical results. European Conference on Principles of Data Mining and Knowledge Discovery,
[57]             Bejari, H., Daya, A., & Roudini, A. (2017). Selection of chromite processing plant site using fuzzy analytic hierarchy process (FAHP). Journal of Mining and Environment. 8(2): 155-162.
[58]             Ahmadi Khounsaraki, V., Uromeihy, A., Amiri, M., & Nikudel, M. (2024). Angouran mine access tunnel stability assessment using the experimental classification method and fuzzy hierarchical analysis (FAHP). New Findings in Applied Geology. 18(35): 47-66 (In Persian).
[59]             Bagloo, H., & Ataee-pour, M. (2024). A Classification Model of Dimensional Stones Using AHP and Fuzzy Logic. Geotechnical and Geological Engineering. 42(2): 1173-1187.
[60]             Ghanbarpour, A., Zaremotlagh, S., & Dabaghi-Zarandi, F. (2024). Addressing Dependent Data in Constrained Optimization Problems: A WOA-based Algorithm. International Journal of Industrial Electronics Control and Optimization. 7(2): 119-127.
[61]             Yuan, Y.-l., Hu, C.-m., Li, L., Xu, J., & Hou, X.-h. (2024). Efficient slope reliability analysis using a surrogate-assisted normal search particle swarm optimization algorithm. Journal of Computational Design and Engineering. 11(1): 173-194.
[62]             Li, P., Chen, T., Liu, Y., Cai, M., Sun, L., Wang, P., Wang, Y., & Zhang, X. (2025). Automatic Identification of Rock Discontinuity Sets by a Fuzzy C-Means Clustering Method Based on Artificial Bee Colony Algorithm. Applied Sciences. 15(3): 1497.