Abstract
ABSTRACT In coal preparation plant, the control strategy of the separation process is made mainly based on the timely feedback of the clean coal ash. But the results of commonly used gamma-ray coal ash monitor only could reflect the trends of coal quality and fail to satisfy the dynamic amendment of operation parameter. The actual ash remains to be obtained by a complex process, consisting of the manual sampling, sample preparation, and laboratory analysis. To solve the above problem, this paper first analyzed the working principle of ash monitor and its influence factors. Then, mass of data relevant to the obtain of online ash were collected, and the correlation analysis showed that the on-line ash deviation was highly related to the coal flux on the conveying belt. Aiming to improve the accuracy of the online measurement of coal ash, different mathematical curve models and machine learning Least Squares Support Vector Machine (LS-SVM) models are used for the on-line ash correction. The results of prediction simulation indicate that the LS-SVM algorithm (root-mean-square error [RMSE] = 0.3335) is better than the conventional regression model (RMSE = 0.1747) in predicting the ash content. Therefore, the coal flux data could be used for the correction of online ash with LS-SVM algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Coal Preparation and Utilization
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.