Asynchronous multisource alignment-driven real-time online detection of ash content in flotation clean coal

Accurate real-time monitoring of the ash content in flotation clean coal is pivotal for intelligent optimization and closed-loop control of the flotation process, directly affecting product quality and the economic performance of coal preparation plants. To address the limitations of traditional app...

Full description

Saved in:
Bibliographic Details
Published in:International journal of coal preparation and utilization Vol. 45; no. 12; pp. 2993 - 3020
Main Authors: Wang, Lanhao, Liu, Jiahui, Dai, Wei, Gui, Xiahui, Wang, Hongyan
Format: Journal Article
Language:English
Published: Abingdon Taylor & Francis 02.12.2025
Taylor & Francis Ltd
Subjects:
Accuracy
Alignment
clean coal
Closed loops
Coal
Coal flotation
Collinearity
Data integration
Feature extraction
Feedback control
Flotation
Fly ash
interpretable constructive algorithm
Machine learning
Monitoring
multi-timescale
multisource information fusion
Optimization
Predictions
Process variables
Real time
Regression models
X-ray fluorescence
ISSN:1939-2699, 1939-2702
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate real-time monitoring of the ash content in flotation clean coal is pivotal for intelligent optimization and closed-loop control of the flotation process, directly affecting product quality and the economic performance of coal preparation plants. To address the limitations of traditional approaches-namely response lag, insufficient accuracy, and inefficient fusion of multisource information-this study proposes an intelligent online sensing method based on multisource data fusion, with the prediction pipeline decoupled into three stages: alignment - representation - prediction. First, a multiscale, differentiable dynamic time-warping (MSSoftDTW) scheme is employed to precisely align asynchronous multisource time-series data, thereby enhancing cross-modal temporal consistency. Second, an interpretable Constructive algorithm with response-weight mechanism (ICA-RW) is introduced to enable feature learning and structural adaptation, suppressing redundancy and collinearity while improving feature robustness. Third, an ensemble regression model that combines a relevance vector machine with adaptive boosting (RVM-Adaboost) is developed to better accommodate nonlinear relationships and drifts in operating conditions. By fusing X-ray fluorescence (XRF) spectra, key process variables, and features extracted from tailings images, the method achieves high-accuracy, real-time prediction of clean-coal ash content. Validation on industrial-site data demonstrates significant gains in both accuracy and stability over conventional regression baselines, meeting the real-time requirements of online monitoring and control and providing deployable support for flotation process optimization and intelligent upgrading.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-2699
1939-2702
DOI:10.1080/19392699.2025.2581178