Abstract

ABSTRACT To increase the accuracy of clean coal ash content prediction during the dense medium separation process and address the time lag issue encountered when measuring clean coal ash content, a prediction model based on WaOA-VMD-SGMD-WaOA-LSTM was proposed. The model adopts the dual decomposition techniques of optimized Variational Mode Decomposition (VMD) and Symplectic Geometric Mode Decomposition (SGMD), which can completely decompose the original clean coal ash data, and uses the Walrus optimization algorithm (WaOA) to optimize the hyperparameters of the Long Short-Term Memory (LSTM) model. In the process of model construction, the characteristic data of ore content ( Z 2 ), raw coal ash ( Z 3 ), heavy mesoporous cyclone pressure ( Z 4 ), heavy mesoporous suspension density ( Z 5 ), and magnetic content ( Z 6 ) were combined with the decomposed cleaned coal ash grouping S-IMF0~S-IMFn, CO-IMF1, and CO-IMF2 as input variables to construct multiple LSTM prediction models. Finally, the prediction value is superimposed to realize the prediction of clean coal ash content. Based on industrial data of a coal preparation plant in Shanxi, China, the results show that the coefficient of determination ( R 2 ) of the model is 0.9974. After adding secondary decomposition technology, the average absolute error was reduced by 60.99% compared with that of the single decomposition strategy.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

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.