Answers are grounded in this paper and cite their sources.
Demonstrates improved DMS density accuracy in coal preparation, suggesting enhanced optimization capabilities.
High-precision and real-time detection of dense medium separation (DMS) density is critical for optimizing coal preparation processes and maintaining stable control of clean coal ash content and recovery rate. To overcome the inherent latency and limited measurement accuracy of traditional manual sampling and laboratory testing, this study proposes an innovative data-driven method based on a sparse regularized stochastic configuration network. The proposed approach tightly integrates fluid flow mechanism modeling with advanced machine learning techniques. Specifically, a comprehensive feature model of pipeline density is first established by incorporating both linear and non-linear dynamics. Subsequently, a hybrid modeling framework combining least squares method with a Least p-Norm Stochastic Configuration Network (LPSCN) is developed to achieve high-precision identification of the dynamic system governing DMS density. Industrial application results from a large-scale coal preparation plant demonstrate that the proposed method achieves a Mean Absolute Error (MAE) of 7.12 kg/m3, a Root Mean Square Error (RMSE) of 9.31 kg/m3, and a Coefficient of Determination (R2) of 99.49% in DMS density estimation. These results highlight its superior accuracy and robustness, fully satisfying the requirements of real-time density monitoring in industrial environments and providing effective support for closed-loop optimization and control of the entire coal preparation process.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: