A novel machine learning framework for efficient calibration of complex DEM model: A case study of a conglomerate sample

• Published in: Engineering fracture mechanics 2023-02, Vol.279, p.109044, Article 109044
• Main Authors: Shentu, Junjie, Lin, Botao
• Format: Article
• Language: English
• Subjects: Conglomerate rock; Discrete element method; Machine learning; Microscopic parameter calibration; Sensitivity analysis
• ISSN: 0013-7944; 1873-7315
• DOI: 10.1016/j.engfracmech.2023.109044

•Proposing a machine learning framework to accelerate the calibration of the complex DEM model, which can be applied to rock samples with complex lithological phases and structures such as conglomerate, shale, and granite.•Carrying out the sensitivity analysis of the input parameters, and revealing the importance of input factors to the output values, which is helpful to the fine-tuning of input parameters.•Setting up the conglomerate DEM model for data preparation, which imports angular gravels to make the DEM model more like the natural conglomerate samples, and the simulation accuracy is improved. The conglomerate reservoirs in the Mahu Sag of the Junggar Basin, northeastern China are featured high heterogeneity and complicated lithology. The reservoirs have experienced a decent production with the application of horizontal well drilling and multistage fracturing. However, the mechanical behavior of the conglomerate formation remains poorly understood. In this respect, the discrete element method (DEM) can be used to efficiently investigate the mechanical behavior of geomaterials with complex lithologies. The implementation of DEM requires a precise set of microscopic parameters, for which the conventional trial-and-error methods are time-consuming. In this regard, an end-to-end machine learning (ML) framework was proposed to achieve an efficient calibration of the complex DEM model. The framework contains two stages, with one predicting the strength of a single phase geomaterial and the other forecasting the overall strength of a complex geomaterial sample containing multiple phases. Different ML models were attempted to evaluate their performances. The results demonstrate that the random forest (RF) model performs with high accuracy at the first stage, and the support vector machine (SVM) model outperforms other ML models in terms of accuracy and convergence at the second stage. From deploying the ML framework, a fast and accurate calibration approach of conglomerate DEM models was proposed and explored in the case study. Moreover, the sensitivity analysis examined the contribution of each parameter to the overall mechanical behavior and provides the suggested values of microscopic parameters. The validity of the application of the training models on the synthesized data was analyzed to address the data shortage issue. In summary, the ML framework not only enables users to fast and accurately calibrate the microscopic parameters of the complex DEM mod