Method of soil-elastoplastic DEM parameter calibration based on recurrent neural network

Long, Sifang; Xu, Shaomin; Zhang, Yanjun; Li, Boliao; Sun, Lunqing; Wang, Yongwei; Wang, Jun

doi:10.1016/j.powtec.2023.118222

Cited by 16 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou and other scholars 5,59,60 utilized neural networks to train the relationships between microscopic and macroscopic parameters, achieving calibration. They contend that the non-linear processing capabilities of neural networks are highly effective, offering greater precision than the DOE method when handling data.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

A Review of Calibration Strategies for Microscopic Parameters in Discrete Element Method

Liu

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Discrete element method (DEM) offers a distinct advantage in addressing fracture problems due to its exemption from partial differential equations. However, the governing equations of DEM incorporate microscopic parameters that cannot be accessed via experimental methods. Parameter calibration represents the most prevalent technique currently utilized to obtain the required microscopic parameters for DEM. This article initially introduces the development history of DEM calibration, then elaborates on the governing equations of DEM and the microscopic parameters required for calibration. Next, the principles of classical DEM calibration methods are explicated in detail, alongside the validation and discussion of their properties. Lastly, this study investigates the model dependence of DEM and presents guidance for the calibration application of large-scale simulations.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

A Review of Calibration Strategies for Microscopic Parameters in Discrete Element Method

Liu

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to the design of experiments method, machine learning methods can more efficiently handle high-dimensional and nonlinear issues. Various machine learning methods have been utilized by researchers to address parameter calibration issues, including random forest method 44 , 56 , support vector machine method 44 , 56 , Bayesian filtering method 110 – 113 , and neural network method 30 , 42 , 61 , 95 , 114 .…”

Section: Review Of Calibration Strategiesmentioning

confidence: 99%

“…Neural networks can effectively model complicated nonlinear relationships and exhibit strong adaptive learning capabilities. Long et al employed neural networks for parameter calibration, leveraging a dataset consisting of 270 observations, and the result demonstrated a substantial improvement of approximately 50% in predictive accuracy compared to the traditional design of experiments approach 114 .…”

Section: Review Of Calibration Strategiesmentioning

confidence: 99%

Review of calibration strategies for discrete element model in quasi-static elastic deformation

Liu

Wang

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

This study first reviewed theories of the mechanical response of structures under loading, and the discrete element method provides a route for studying mechanical response including elastic deformation and structure failure. However, the direct acquisition of the microscopic parameters from the governing equations of the discrete element method via experiments encounters challenges. One possible strategy to obtain these microscopic parameters is parameter calibration that are widely used by researchers. Secondly, the governing equations and failure criterion of the discrete element method are summarized, and the microscopic parameters that would be calibrated are pinpointed. Next, the principles of classical calibration methods of discrete element method are explicated in detail, alongside the validation and discussion of their properties. Lastly, this study examined the applicability of calibrated parameters and points out that the size ratio, porosity, maximum radius, and minimum radius of particles should be identical in both the geometric calibration model and that for applications.

show abstract

“…When the same stacking angle was reached, the relative error of non-standard ball shapes was smaller than that of standard ball shapes. Long et al [13] considered the particle size distribution of soil particles when generating particles and adjusted the parameters of the soil EEPA model to keep the average accuracy at 80%. In summary, although there have been extensive studies on the calibration between soil and contact parts, there are few studies on the calibration between winderoded soil and contact parts in desert areas.…”

mentioning

confidence: 99%

Measurement of intrinsic parameters, calibration of contact parameters, and test verification of wind-eroded soil

ZHANG,

PEI,

XUE

et al. 2024

Preprint

View full text Add to dashboard Cite

In response to the problem of lacking an accurate and reliable model of the interaction between desert soil particles and the drilling device during the study. Perform parameter measurement, calibration, and experimental verification on wind-eroded soil in the northwest desert region of China as the research object. Obtain intrinsic information about soil through crushing tests, direct shear tests, etc. Using the soil stacking angle as the response value, the significant factors affecting the stacking angle were obtained through the Plackett-Burman test. The steepest slope test narrowed down the range of significant factors. The Box-Behnken test established a significant factor regression model to seek the optimal combination. Finally, the optimal combination was experimentally validated through a combination of simulation and physical experiments. The relative errors between simulation and physical experiments are 2.9% and 0.4%, respectively, using the opening diameter and effective depth of machines that inject water and drill holes in the desert as measurement standards. This indicates that the measured parameters are accurate and reliable, providing a reference for constructing the interaction mechanism between desert planting machinery and soil.

show abstract

Method of soil-elastoplastic DEM parameter calibration based on recurrent neural network

Cited by 16 publications

References 29 publications

A Review of Calibration Strategies for Microscopic Parameters in Discrete Element Method

A Review of Calibration Strategies for Microscopic Parameters in Discrete Element Method

Review of calibration strategies for discrete element model in quasi-static elastic deformation

Measurement of intrinsic parameters, calibration of contact parameters, and test verification of wind-eroded soil

Contact Info

Product

Resources

About