تخمین خصوصیات مکانیکی به روش آنالیز آماری، شبکه عصبی مصنوعی و رگرسیون بردار پشتیبان (مطالعه موردی: نمونه های مرتبط به ساختگاه سد مخزنی گدار- خوش)

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشکده مهندسی معدن، دانشگاه صنعتی بیرجند

2 گروه مهندسی عمران، دانشکده فنی و مهندسی، دانشگاه اراک

3 گروه مهندسی عمران، واحد فنی و مهندسی، دانشگاه علم و صنعت ایران

4 گروه مهندسی صنایع، دانشکده مهندسی کامپیوتر و صنایع، دانشگاه صنعتی بیرجند

چکیده

با توجه به مشکلات اجرای آزمایش‌ها بخصوص در سنگ‌های ضعیف و هزینه بر بودن این آزمایش‌ها، می‌توان با بررسی روابط بین ویژگی‌های مکانیکی و فیزیکی، هزینه آزمایشات تعیین خصوصیات مکانیکی را کاهش داد. در این پژوهش آزمایش‌های پتروگرافی، فیزیکی و مکانیکی بر روی 62 مغزه از سنگ‌های شیل و مارن در ساختگاه سد گدار-خوش انجام شد. در نهایت عملکرد روش‌های شبکه عصبی مصنوعی (ANN) رگرسیون چند متغیره (MVRA) و رگرسیون بردار پشتیبان (SVR) با تابع کرنل پایه شعاعی (RBF) جهت تخمین UCS، Es بر اساس سرعت موج تراکمی و خصوصیات فیزیکی مقایسه شد. نتایج پتروگرافی نشان داد که کانی ایلیت، فراوانترین نوع کانی رسی می-باشد. نسبت مدول الاستیسیته دینامیکی به استاتیکی نمونه ها برابر با 8.51 می‌باشد. همچنین نسبت پواسون دینامیکی به استاتیکی برابر با 1.41 می‌باشد. نتایج آنالیز آماری نشان داد که مدول الاستیسیته استاتیکی همبستگی بالایی با مدول الاستیسیته دینامیکی (R=0.91, RMSE=0.22, MAPE=0.14) و سرعت موج برشی همبستگی بالایی با سرعت موج تراکمی (R=0.98, RMSE=0.08, MAPE=0.03) دارند. نتایج رگرسیون چند متغیره نشان داد که هر دو پارامتر UCS و Es دارای همبستگی معنی داری با پارامترهای فیزیکی و سرعت موج تراکمی دارند. بطوریکه ارتباط UCS با این پارامترها بیشتر از ارتباط Es با این پارامتر ها می‌باشد. مقایسه عملکرد روش‌ها در تخمین خصوصیات استاتیک نشان داد که SVR دارای دقت بالاتری نسبت به رگرسیون چند متغیره و ANN می‌باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Estimation of Mechanical Properties by Statistical Analysis, Artificial Neural Network and Support Vector Regression "Case Study: Samples Related To Godar-Khosh Reservoir Dam Site"

نویسندگان [English]

  • Amir Azadmehr 1
  • Mohammadrea Motahari 2
  • Hoorman Gharavi 3
  • Mohsen Saffarian 4
1 Department of Mining Engineering, Birjand University of Technology, Birjand, Iran
2 Department of Civil Engineering, Faculty of Engineering, Arak University, Arak, Iran
3 School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran
4 Department of Industrial Engineering, Birjand University of Technology, Birjand, Iran
چکیده [English]

Due to the difficulties of conducting tests, especially in weak rocks and the cost of these experiments, by examining the relationships between their mechanical and physical properties can be provided and reduce the cost of tests to identify mechanical properties (Minaeian and Ahangari, 2013; Azadan and Ahangari, 2014).
     In this study, petrographic, physical and mechanical experiments on 62 cores of shale and marl of Gurpi Formation were conducted in Godar-Khosh dam site, west of Iran. Non-destructive tests were performed on cores according to the ISRM standard. Physical properties such as water absorption, density and porosity of the samples were determined according to the ISRM standard. Also, uniaxial compressive strength (UCS) test according to the ASTM standard D2938 (ASTM, 1986) was performed. For each sample, the modulus of dynamic elasticity (Ed) and the dynamic Poisson ratio were calculated (Goodman, 1989). Using statistical analysis, artificial neural network (ANN( and  support vector regression (SVR) with radial base kernel function, several relationships for estimating UCS, Es and shear wave velocity were presented. The root mean square error (RMSE), the mean absolute percentage error (MAPE) and the variance account for (VAF) were also used to evaluate the results.

کلیدواژه‌ها [English]

  • Static and dynamic properties
  • Clay rocks
  • Support vector regression
  • Artificial neural network
  • Statistical analysis
افشین ح، چوپانی ن ع، فتحی ­پورآذره، "تخمین انرژی شکست بتن با استفاده از شبکه عصبی مصنوعی"، نشریه مهندسی عمران و محیط زیست دانشگاه تبریز، ‎1391، 42 (1)، 1-9.
دارای آ، زارع ش، "ارائه مدلی بین مدول دینامیکی و استاتیکی سنگ آهک در سازند آسماری براساس آزمون ­های آزمایشگاهی و برجا"، نشریه زمین ­شناسی مهندسی، 1397، 12 (4)، 25-34.
سمائی م، رنجبرنیا م، زارع ­نقده م، "پیش­ بینی شاخص تردی سنگ با استفاده از رگرسیون چند متغیره غیرخطی و درخت رگرسیون CART"،‎ نشریه مهندسی عمران و محیط زیست دانشگاه تبریز، ‎1395، 48 (3)، 33-84.
شرکت سهامی آب منطقه ­ای ایلام، گزارش زمین­ شناسی مهندسی، مرحله اول طرح سد مخزنی گدار- خوش، 1386، 157صفحه.
نجیبی ع، آصف م، اجل لوییان ر، صفیان غ ع، "تخمین ویژگی­ های مکانیکی سنگ آهک با استفاده از داده­ های پتروفیزیکی"،‎ نشریه زمین شناسی مهندسی، 1390، 5 (1). 63-78.
صالحی م، اجل ­لوئیان ر، هاشمی م، "مقایسه مدول الاستیسیته دینامیکی و استاتیکی سنگ­ های ساختگاه سد بازفت"، چهارمین همایش ملّی زمین­ شناسی، دانشگاه پیام نور مشهد، 1389.
Abbasi Dezfouli A, “Effect of eggshell powder application on the early and hardened properties of concrete”, Journal of Civil Engineering and Materials Application, 2020, 4 (4), 209-221.
Aboutaleb S, Behnia M, Bagherpour R, Bluekian B, “Using non-destructive tests for estimating uniaxial compressive strength and static Young’s modulus of carbonate rocks via some modeling techniques”, Bulletin of Engineering Geology and the Environment, 2018, 77 (4), 1717-1728.
Aladejare AE, “Evaluation of empirical estimation of uniaxial compressive strength of rock using measurements from index and physical tests”, Journal of Rock Mechanics and Geotechnical Engineering, 2020, 12 (2), 256-268.
Al-Jassar SH, Hawkins AB, “Geotechnical properties of the carboniferous limestone of the bristol area”, Proceeding 4th International Congress International Society Rock Mechanics, Montreux, A. A. Balkema, Rotterdam, 1979, 1, 3-14.
Ansari Y, Hashemi A, “Neural network approach in assessment of fiber concrete impact strength”, Journal of Civil Engineering and Materials Application, 2017, 1 (3), 88-97.
Asghari-Kaljahi E, Barzegari G, Jalali-Milani G, “Assessment of the swelling potential of Baghmisheh marls in Tabriz, Iran”, Geomechnics and Enginering, 2019, 18 (3), 267-275.
ASTM Standard test method of unconfined compressive strength of intact rock core specimens. D2938, 1986.
Azarafza M, Ghazifard A, Akgun H, Asghari-Kaljahi E, “Geotechnical characteristics and empirical geoengineering relations of the south pars zone marls”, Iran, Geomechanics and Engineering, 2019, 19 (5), 393-405.
Bagheripour P, Gholami A, Asoodeh M, Vaezzadeh-Asadi M, “Support vector regression based determination of shear wave velocity”, Journal of Petroleum Science and Engineering, 2015, 125, 95-99.
Bagherzadeh Khalkhali, A, Safarzadeh I, Rahimi Manbar H, “Investigating the Effect of Nanoclay Additives on the Geotechnical Properties of Clay and Silt Soil”, Journal of Civil Engineering and Materials Application, 2019, 3 (2), 63-74.
Baziar S, Gafoori MM, Mohaimenian Pour SM, Bidhendi MN, Hajiani R, “Toward a thorough approach to predicting klinkenberg permeability in a tight gas reservoir: a comparative study”, Iranian Journal of Oil and Gas Science and Technology, 2015, 4 (3), 18-36.
Brotons V, Toma´s R, Ivorra S, Grediage A, Martinez-Martinez J, Benavente D, Gomez-Heras M, “Improved correlation between the static and dynamic elastic modulus of different types of rocks”, Material and Structures, 2016, 49 (8), 3021-3037.
Castagna J, Backus MM, “Offset dependent reflectivity: theory and practice of AVO analysis”, SEG Investigations Geophys, Ser, 1993, 8, 345.
Chang C, Zoback MD, Khaksar A, “Empirical relations between rock strength and physical properties in sedimentary rocks”, Journal of Petroleum Science and Engineering, 2006, 51(3-4), 223-237.
Davarpanah SM, Ván P, Vásárhelyi B, “Investigation of the relationship between dynamic and static deformation moduli of rocks”, Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 2020, 6 (1), 1-14.
Ebdali M, Khorasani E, Salehin S, “A comparative study of various hybrid neural networks and regression analysis to predict unconfined compressive strength of travertine”, Innovative Infrastructure Solutions, 2020, 5 (3), 1-14.
Ebrahimi Fard H, Jabbari MM, “The effect of magnesium oxide nano particles on the mechanical and practical properties of self-compacting concrete”, Journal of Civil Engineering and Materials Application, 2017, 1 (2), 77-87.
Erasto P, “Support vector machines-backgrounds and practice”, BSc Thesis, University of Helsinki, Faculty of Science, Rolf Nevanlinna Institute, Helsinki, Finland, 2001, 78.
Erguler ZA, Ulusay R, “Water-induced variations in mechanical properties of clay-bearing rocks”, ‎Intternational Journal of Rock Mechanics and Mining Sciences, 2009, 46 (2), 355-370.
Esparham A, Moradikhou AB, Avanaki MJ, “Effect of Various Alkaline Activator Solutions on Compressive Strength of Fly Ash-Based Geopolymer Concrete”, Journal of Civil Engineering and Materials Application, 2020, 4 (2), 115-123.
Fei W, Huiyuan B, Jun Y, Yonghao Z, “Correlation of Dynamic andStatic Elastic Parameters of Rock”, Electronic Journal of Geotechnical Engineering, 2016, 21 (4), 1551-1560.
Flood I, Kartam N, “Neural networks in civil engineering. I: Principles and understanding”, Journal of Computing in Civil Engineering, ASCE, 1994, 8 (2), 131-148.
Ghafoori M, Rastegarnia A, Lashkaripour GR, “Estimation of static parameters based on dynamical and physical properties in limestone rocks”, Journal of African Earth Sciences, 2018, 137, 22-31.
Ghavami S, Rajabi M, “Investigating the Influence of the Combination of Cement Kiln Dust and Fly Ash on Compaction and Strength Characteristics of High-Plasticity Clays”, Journal of Civil Engineering and Materials Application, 2021, 5 (1), 09-16.
Goodman RE, “Introduction to rock mechanics”, 1989, Wiley New York.
Han DH, Nur AD, “Morgan, Effects of porosity and clay content on wave velocities in sandstones, Geophysics”, 1986, 51, 2093-2107.
Haykin S, “Neural networks: a comprehensive foundation”, New York, MacMillan Publishing Company, 1994, 696.
Jamshidi A, Zamanian H, Sahamieh RZ, “The effect of density and porosity on the correlation between uniaxial compressive strength and P-wave velocity”, Rock Mechanics and Rock Engineering, 2018, 51 (4), 1279-1286.
Karakul H, Ulusay R, “Empirical correlations for predicting strength properties of rocks from P-wave velocity under different degrees of saturation”, Rock Mechanics and Rock Engineering, 2013, 46 (5), 981-999.
Karaman K, Kesimal A, “Correlation of schmidt rebound hardness with uniaxial compressive strength and p-wave velocity of rock materials”, Arabian Journal of Sciences for Engineering, 2015, 40 (7), 1897-1906.
Khajevand R, “Evaluating the influence of petrographic and textural characteristics on geotechnical properties of some carbonate rock samples by empirical equations”, Innovative Infrastructure Solutions, 2021, 6 (2), 1-17.
Khandelwal M, “Correlating P-wave velocity with the physicomechanical properties of different rocks’’, Pure and Applied Geophysics, 2013, 170, 507-514.
Lashkaripour GR, “Predicting mechanical properties of mudrock from index parameters”, Bulletin of Engineering Geology and the Environment, 2002, 61 (1), 73-77.
Lotfollahi S, Ghorji M, Hoseini Toodashki V, “An investigation into the effect of foliation orientation on displacement of tunnels excavated in metamorphic rocks”, Journal of Civil Engineering and Materials Application, 2018, 2 (3), 138-145.
Madhubabu N, Singh PK, Kainthola A, Mahanta B, Tripathy A, Singh TN, “Prediction of compressive strength and elastic modulus of carbonate rocks”, Measurement, 2016, 88, 202-213.
Mahmoodzadeh A, “Mohammadi M, Ibrahim HH, Abdulhamid SN, Salim SG, Ali HFH, Majeed MK,. “Artificial intelligence forecasting models of uniaxial compressive strength”, Transportation Geotechnics, 2021, 27, 100499.
Martınez-Martınez J, Benavente D, Garcıa-del-Cura MA, “Comparison of the static and dynamic elastic modulus in carbonate rocks”, Bulletin of Engineering Geology and the Environment, 71, 2012, 263-268.
Mebarki M, Kareche T, Derfouf FEM, Taibi S, Aboubekr N, “Hydromechanical behavior of a natural swelling soil of boumagueur region (east of Algeria)”, Geomechnics and Enginering, 2019, 17 (1), 69-79.
Minaeian B, Ahangari K, “Estimation of uniaxial compressive strength based on P-wave and Schmidt hammer rebound using statistical method”, Arabian Journal Geoscience, 2013, 6, 1925-1931.
Mokhberi M, Khademi H, “The use of stone columns to reduce the settlement of swelling soil using numerical modeling”, Journal of Civil Engineering and Materials Application, 2017, 1 (2), 45-60.
Naseri F, Lotfollahi S, Bagherzadeh Khalkhali A, “dynamic mechanical behavior of rock materials”, Journal of Civil Engineering and Materials Application, 2017, 1 (2), 39-44.
Nia AR, Lashkaripour GR, Ghafoori M, “Prediction of grout take using rock mass properties”, Bulletin of Engineering Geology and the Environment, 2017, 76 (4), 1643-1654.
Onalo D, Oloruntobi O, Adedigba S, Khan F, James L, Butt S, “Static young's modulus model prediction for formation evaluation”, Journal of Petroleum Science and Engineering, 2018, 171, 394-402.
Oshnavieh D, Bagherzadeh Khalkhali A, “Use of shear wave velocity in evaluation of soil layer’s condition after liquefaction”, Journal of Civil Engineering and Materials Application, 2019, 3 (3), 119-135.
Pereira ML, da Silva PF, Fernandes I, Chastre C, “Characterization and correlation of engineering properties of basalts”, Bulletin of Engineering Geology and the Environment, 2021, 1-22.
Saghi H, Behdani M, Saghi R, Ghaffari AR, Hirdaris S, “Application of gene expression programming model to present a new model for bond strength of fiber reinforced polymer and concrete”, Journal of Civil Engineering and Materials Application, 2019, 3 (1), 15-29.
Salehin S, “Investigation into engineering parameters of marls from seydoon dam in Iran”, Journal of Rock Mechanics and Geotechnical Engineering”, 2017, 9 (5), 912-923.
Sekhavati P, Jafarkazemi M, “Investigating durability behavior and compressive strength of lightweight concrete containing the nano silica and nano lime additives in the acid environment”, Journal of Civil Engineering and Materials Application, 2019, 3 (2), 103-117.
Selcuk L, Nar A, “Prediction of uniaxial compressive strength of intact rocks using ultrasonic pulse velocity and rebound-hammer number”, Quarterly Journal of Engineering Geology and Hydrogeology, 2016, 49 (1), 67-75.
Shahri AA, Moud FM, Lialestani SPM, “A hybrid computing model to predict rock strength index properties using support vector regression”, Engineering with Computers, 2020, 1-16.
Shamsashtiany R, Ameri M, “Road accidents prediction with multilayer perceptron mlp modelling case study: roads of qazvin, zanjan and hamadan”, Journal of Civil Engineering and Materials Application, 2018, 2 (4), 181-192.
Sharma LK, Vishal V, Singh TN, “Developing novel models using neural networks and fuzzy systems for the prediction of strength of rocks from key geomechanical properties”, Measurement, 2017, 102, 158-169.
Shirmohammadi H, Hoseiny Khanshan H, “Effect of mineral pitch and zycosil nano-material on mechanical properties and moisture susceptibility of asphalt mixtures”, Journal of Civil Engineering and Materials Application, 2018, 2 (2), 97-102.
Smola AJ, Scholkopf B, “A tutorial on support vector regression”, Statistics and Computing, 2004, 14, 199-222.
Sobhani J, Pourkhorshidi AR, Masoudi F, “Iranian eocene green tuffs as natural pozzolan for use in cement industries”, Journal of Civil Engineering and Materials Application, 2020, 4 (3), 133-140.
Stan-Kłeczek I, “The study of the elastic properties of carbonate rocks on a base of laboratory and field measurement”, Acta Montan Slovaca, 2016, 21 (1), 76-83.
Taheri S, Ziad H, “Analysis and comparison of moisture sensitivity and mechanical strength of asphalt mixtures containing additives and carbon reinforcement”, Journal of Civil Engineering and Materials Application, 2021, 5 (1), 1-8.
Taylor R, “Interpretation of the correlation coefficient: a basic review”, Journal of Diagnostic Medical Sonography, 1990, 6 (1), 35-39.
Trippi RR, Turban E, “Neural networks in finance and investing”, Irwin Professional Publishing, 1996.
Vapnik VN, “Statistical learning theory”, Wiley, New York, 1998, 736.
Wen L, Luo Z quan, Yang S Jiao, “Correlation of geo-mechanics parameters with uniaxial compressive strength and p-wave velocity on dolomitic limestone using a statistical method”, Geotechnical and Geological Engineering, 2018, 37 (2), 1079-1074.
Xu C, Amar MN, Ghriga MA, Ouaer H, Zhang X, Hasanipanah M, “Evolving support vector regression using grey wolf optimization; forecasting the geomechanical properties of rock”, Engineering with Computers, 2020, 1-15.
Yale DP, Swami V, “August. Conversion of dynamic mechanical property calculations to static values for geomechanical modeling”, In 51st US Rock Mechanics/Geomechanics Symposium, American Rock Mechanics Association, 2017.
Yousefvand M, Sharifi Y, Yousefvand S, “An analysis of the shear strength and rupture modulus of polyolefin-fiber reinforced concrete at different temperatures”, Journal of Civil Engineering and Materials Application, 2019, 3 (4), 238-254.