The Journal of Engineering Geology (지질공학)

The Korean Society of Engineering Geology (대한지질공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Correlations between the Physical Characteristics of Rock Types by Multiple Regression Analysis and Artificial Neural Network

다중회귀분석 및 인공신경망을 통한 암종별 물리적 특성간의 상관관계에 대한 연구

  • Received : 2018.11.15
  • Accepted : 2018.12.13
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The physical properties of rocks constituting the rock mass were analyzed by using various methods such as 7 kinds of physical properties of about 2,400 data. The correlation equation was derived from the correlation equation with the dependent variables by screening independent variables through the significance level using multiple regression analysis. In order to verify the reliability of this equation, verification was performed through comparison with actual data using artificial neural network learning. The analysis results by petrogenesis and strength confirmed that the elastic wave velocity (compressional wave) and elastic modulus as the main influence factors for the independent variables affecting the dependent variables. This proves that most of the correlation equations using the above items are found in existing studies. And through this study, it is confirmed whether the rock classification is based on the above items in various standards. In addition, the analysis results of representative rocks showed a high correlation as the equation for estimating unconfined compressive strength and elastic modulus exceeds the coefficient of determination 0.8.

암반을 구성하는 암석의 물리적 특성에 대하여 약 2,400개의 자료의 7가지 물리적 특성을 암종별, 강도별, 대표암석별로 다양한 방법을 통하여 상관관계 및 특성을 분석하였다. 상관관계는 다중회귀분석 방법으로 유의수준을 통해 유의한 독립변수를 선별하여 종속변수와의 상관관계식을 도출해내었으며 인공신경망 학습을 수행하여 실제 데이터와의 비교를 통하여 검증을 수행하여 신뢰성을 확인하였다. 암종별, 강도별 분석결과, 종속변수에 영향을 미치는 독립변수로는 탄성파속도(압축파), 탄성계수가 주요 영향인자로 작용하는 것을 확인하였다. 이는 기존연구에서 상기항목을 이용한 관계식이 대다수를 이루고 있는지를 증명할 수 있으며, 각종 기준에서 암반분류를 상기항목으로 기준으로 하는지를 본 연구를 통하여 확인할 수 있었다. 또한 대표암석 분석결과, 일축압축강도와 탄성계수를 추정할 수 있는 관계식이 결정계수 0.8을 상회하므로 상관관계가 높은 것으로 분석되었다.

Keywords

JJGHBG_2018_v28n4_673_f0001.png 이미지

Fig. 1. Various Standards According to Strength (Korea ex : Korea Expressway Corporation, 2009; SMG : Seoul Metropolitan Government, 1996; KENCA : Korea Engineering & Consulting Association, 2004).

JJGHBG_2018_v28n4_673_f0002.png 이미지

Fig. 2. Structure of neural system and artificial neural network.

JJGHBG_2018_v28n4_673_f0003.png 이미지

Fig. 3. Comparison of output and target of igneous rock.

JJGHBG_2018_v28n4_673_f0004.png 이미지

Fig. 4. Comparison of output and target of soft rock in igneous rock.

JJGHBG_2018_v28n4_673_f0005.png 이미지

Fig. 5. Comparison of output and target of granite.

JJGHBG_2018_v28n4_673_f0006.png 이미지

Fig. 6. Comparison of output and target of gneiss

JJGHBG_2018_v28n4_673_f0007.png 이미지

Fig. 7. Comparison of output and target of conglomerate etc.

Table 9. Correlation formula and determination coefficient of granite

JJGHBG_2018_v28n4_673_t0001.png 이미지

Table 1. Analysis of each significance level of igneous rock

JJGHBG_2018_v28n4_673_t0002.png 이미지

Table 2. Correlation formula and determination coefficient fo igneous rock

JJGHBG_2018_v28n4_673_t0003.png 이미지

Table 3. High level of significance per rock

JJGHBG_2018_v28n4_673_t0004.png 이미지

Table 4. Analysis of each significance level of soft rock in igneous rock

JJGHBG_2018_v28n4_673_t0005.png 이미지

Table 5. Correlation formula and determination coefficient of soft rock in igneous rock

JJGHBG_2018_v28n4_673_t0006.png 이미지

Table 6. High level of significance per soft rock

JJGHBG_2018_v28n4_673_t0007.png 이미지

Table 7. High level of significance per moderate rock

JJGHBG_2018_v28n4_673_t0008.png 이미지

Table 8. High level of significance per hard rock

JJGHBG_2018_v28n4_673_t0009.png 이미지

Table 10. Correlation formula and determination coefficient of gneiss

JJGHBG_2018_v28n4_673_t0010.png 이미지

Table 11. Correlation formula and determination coefficient of conglomerate etc.

JJGHBG_2018_v28n4_673_t0011.png 이미지

References

  1. American Society for Testing Materials(ASTM, D 2938-95), 2005, Standard Test Method for Unconfined Compressive Strength of Intact Rock Core Specimens, Annual Book of ASTM Standards 2005.
  2. American Society for Testing Materials(ASTM, D 7012-07e1), 2009, Standard Test Method for Compressive Strength and Elastic Moduli of Intact Rock Core Specimens under Varying States of Stress and Temperatures, Annual Book of ASTM Standards 2009.
  3. Barton, N. R., 1971, A relationship between joint roughness and joint shear strength, Proc. Int. Symposium on Rock Mechanics, Nancy, France, 1-8.
  4. Deere, D. U. and Miller, R. P., 1966, Engineering classification and index properties for intact rock, Air Force Weapons Laboratory Technical Report, AFWL-TR-65-116. Kirtland Base, New Mixico, 300.
  5. Goodman, R. E., 1989, Introducticin to Rock Mechanics, John Wiley and Sons, New York, 5, 19-53.
  6. Inoue, M. and Ohomi, M., 1981, Relation uniaxial compressive strength and elastic wave velocity of soft rock, Proc. Int. Symposium on Weak Rock, ISRM, Tokyo, 21-24.
  7. International Society for Rock Mechanics(ISRM), 1981, Suggested methods for determination of the uniaxial compressive strength of rock materials, Int. J. Rock Mech. Min. Sci. Geomech. Abstr., 18(1), 211-213. https://doi.org/10.1016/0148-9062(81)90975-X
  8. International Society for Rock Mechanics(ISRM), 1994, Suggested methods for determining Wather Content, Porosity, Density, Absorption and Properties and Swelling and Slake-Durability Index Properties, Int. J. Rock Mech. Min. Sci. Geomech. Abstr., 31(5), 547-550. https://doi.org/10.1016/0148-9062(94)90156-2
  9. Jun, I.S., 1994, Construction Standard, Construction Researcher, Seoul, 46.
  10. Judd, W. and Huber, C., 1961, Correlation of rock properties by statistical method, Int, Symp, Mining Res., Missouri Sch. Mines, Rolla, Mo. 621-648.
  11. Kahraman, S., 2001, Evaluation of simple methods for assessing the uniaxial compressive strength of rock, International Journal of Rock Mechanics and Mining Sciences, 38(7), 981-984. https://doi.org/10.1016/S1365-1609(01)00039-9
  12. Korea Engineering and Consulting Association, 2004, Ground Survey Construction Standard, 188.
  13. Korea Expressway Corporation, 2009, Korean Roadway Design Guidelines, 4(Tunnel), 80.
  14. Korea Society for Rock Mechanics and Rock Enginnering, 2005, Standard test method for uniaxial compressive strength of rock, Tunnel & Underground Space, 15(2), 85-86.
  15. Lee, J.I., Lee, H.G., Ryu, C.H. and Yang, H.S., 1982, Study on the epidemiological characteristics of major pomegranates distributed in Korea(Chapter1)", Journal of the Korean Mining Society, 19(4), 260-267.
  16. Lee, S.G. and Lee, S., 1995, "Estimation of Uniaxial Compressive Strength of Korean Granite Using Schmidt Hammer Figures", Journal of the Korean Society of Civil Engineers. 15(1), 199-210.
  17. Moradian, Z. A. and Behnia, M., 2009, Predicting the uniaxial compressive strength and static Young's modulus of intact sedimentary rocks using the ultrasonic test. International Journal of Geomechnanic, 9(1), 1-14. https://doi.org/10.1061/(ASCE)1532-3641(2009)9:1(1)
  18. Park, H.D., 1995, A Study on the P wave Velocity Measurement Technique for the Measurement of Engineering Anisotropy of Rock, Journal of the Geological Engineering Society, 5(3), 237-247.
  19. Press, F., 1966, Seismic velocities, Handbook of physical contants, Ceol. Sic. Am. Memoir, 976.
  20. Seoul Metropolitan Government(SMG), 1996, Geotechnical Investigation Handbook, Seoul Metropolitan Government, 14-24.
  21. Sharma, P. K. and Singh, T. N., 2008, A correlation between P-wave velocity, impact strength index, slake durability index and uniaxial compressive strength, Bulletin of Engineering Geology and the Environment, 68(1), 17-22. https://doi.org/10.1007/s10064-008-0183-9
  22. Yang, H.S., 1992, Fracture Condition Coefficient of Major Rock in Korea, Journal of the Korea Resources Engineering Society, 29(2), 91-102.

Cited by

  1. 서울·경기지역 화강암의 탄성파속도와 탄성계수에 의한 암석의 일축압축강도와의 상관성 연구 vol.15, pp.2, 2018, https://doi.org/10.15683/kosdi.2019.06.30.249