首页--工业技术论文--建筑科学论文--土力学、地基基础工程论文--岩石(岩体)力学及岩石测试论文

基于岩石微组构采用多元回归和人工智能技术估算岩石抗压强度

摘要第7-9页
Abstract第9-10页
Chapter 1:Introduction第17-27页
    1.1 Research Significance第17-19页
    1.2 Literature Review第19-23页
    1.3 Objectives of thesis第23-24页
    1.4 Structure of the Thesis第24-27页
Chapter 2:Field Data and Laboratory Experiments第27-35页
    2.1 Rock samples collection and preparation第27-30页
    2.2 Laboratory Experiments第30-35页
        2.2.1 Mechanical and dynamical tests第30-32页
            2.2.1.1 Uniaxial Compressive Strength (DCS)第30-31页
            2.2.1.2 Splitting tensile strength第31页
            2.2.1.3 Modulus of Elasticity第31页
            2.2.1.4 Ultrasonic pulse velocity (UPV)第31-32页
        2.2.2 Microscopic study and X-ray diffraction (XRD)第32-35页
Chapter 3:Quantitative Microfabrics Analysis第35-49页
    3.1 An overview of rock fabric第35页
    3.2 Petrographic Image Analysis (PIA)第35-36页
    3.3 Semi-automatic petrographic image analysis第36-38页
        3.3.1 Image acquisition第37页
        3.3.2 Image pre-processing第37页
        3.3.3 Image digitizing第37-38页
        3.3.4 Image measurement and the data analysis第38页
    3.4 Basic geometrical parameters measured by image processing第38-41页
        3.4.1 Grain Size (GS)第38-40页
        3.4.2 Aspect Ratio (AR)第40页
        3.4.3 Shape Factor (SF)第40-41页
        3.4.4 Shape preferred orientation第41页
    3.5 Petrographic description of rock samples第41-47页
    3.6 Importance and applicability of rock microfabrics analysis for the geomechanicalbehavior of rocks第47-49页
Chapter 4:Assessment of UCS by quantitative rock microfabrics parameters usingregression technique第49-67页
    4.1 Introduction第49页
    4.2 An overview to regression analysis第49-51页
    4.3 Statistical analysis第51-67页
        4.3.1 Descriptive statistics for all variables第52-55页
        4.3.2 Bivariate statistics (correlation analysis)第55-56页
        4.3.3 Development of predicting models using simple regression analysis第56-58页
        4.3.4 Multiple regression analyses第58-67页
Chapter 5:Computational Intelligence Techniques (CIT) for the prediction of UCSfrom petrographic characteristics of rock第67-89页
    5.1 Introduction第67-68页
    5.2 Artificial Neural Network第68-77页
        5.2.1 Overview of ANNs第68-69页
        5.2.2 Architecture and performance of Neural Network model第69-72页
        5.2.3 Optimal ANNs model selection第72-73页
        5.2.4 Conventional statistical analysis Versus ANN第73-74页
        5.2.5 Application of ANNs in current study第74-77页
    5.3 Fuzzy model第77-85页
        5.3.1 Overview of Fuzzy Logic (FL)第77-79页
        5.3.2 Structure of Fuzzy System第79-81页
        5.3.3 Mamadani fuzzy inference model第81-85页
    5.4 Results and performance assessment of varied models used in the study第85-89页
Chapter 6:Assessments of strength and modulus anisotropy of banded amphiboliterocks第89-101页
    6.1 Introduction第89-91页
    6.2 Velocity anisotropy第91-93页
    6.3 Strength anisotropy第93-95页
    6.4 Modulus anisotropy第95-96页
    6.5 Assessment of modulus anisotropy from wave velocity measurements第96-101页
Conclusion and recommendation第101-104页
    1. Conclusion第101-103页
    2. Recommendation第103-104页
Acknowledgement第104-105页
Appendixes第105-126页
References第126-142页
List of Publications第142页

论文共142页,点击 下载论文
上一篇:基于深度学习的视频分析系统
下一篇:面向群智感知的机会网络数据传输算法研究