Abstract
We studied volatile determination in lignite coal samples using near-infrared (NIR) spectra. Firstly, spectra were pre-processed to eliminate useless information. Then, determination model was constructed by partial least squares regression. To study the influence of pre-processing on determination of volatile for NIR analysis of lignite coal samples, we applied four techniques to pre-process spectra, including normalization, standardization, centralization, derivative and discrete wavelet transform. Comparison of the mean absolute percentage error (MAPE) and root mean square error of prediction (RMSEP) of the models show that the models constructed with spectra pre-processed by discrete wavelet transform gave the best results. Through parameters optimization, the results show that discrete wavelet transform and partial least squares regression can obtain satisfactory performance for moisture and volatile determination in coal samples.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have