基于近红外-X射线融合光谱与非线性残差校正的大粒度煤热值PLS-AE-RR预测模型

打开文本图片集

关键词：光谱分析；近红外光谱；X射线荧光光谱；热值预测；大粒度煤样；非线性校正；自编码器

中图分类号：O433.4;O657.34文献标识码：Adoi：10.37188/OPE.20263403.0365 CSTR：32169.14.OPE.20263403.0365

Abstract：To address the enhanced matrix effects and intensified nonlinear spectral responses caused by the dificulty of grinding large-particle coal in industrial settings，this study proposes a hybrid PLS-AE-RR predictive model based on the fusion of near-infrared spectroscopy （NIRS）and X-ray fluorescence（XRF） spectra，aimed at improving the accuracy of on-line calorific-value analysis. The method implements a three-stage hybrid framework --linear baseline + nonlinear feature extraction + residual correction-- where partial least squares regresion （PLS） first models the global linear relationship between the fused spectra and calorific value；an autoencoder（AE）then extracts low-dimensional nonlinear representations that PLS cannot capture;；and finally ridge regression （RR） fits and corrects the nonlinear residuals.Experimental validation using 153 blended coal samples from power plants demonstrates breakthrough performance in calorific value prediction for large-particle-size coal. On the test set，determination coefficients （ R2 ）for lignite and bituminous coal reached O.974 and O.938，respectively，with mean absolute errors of （204号 0.233MJ/kg and 0.216MJ/kg . The proposed method significantly outperforms standalone PLS and alternative nonlinear correction models，confirming the generalization advantage of ridge regression in residual fiting. Consequently，this achievement provides a grinding-free，high-precision online analysis solution for raw coal calorific value in coal-fired power plants，ofering critical technical support for refined fuel management and operational optimization.

Key Words： spectral analysis; NIRS spectra; XRF spectra;calorific value prediction； large-particle coal samples；nonlinear correction；autoencoder

1引言

现代化燃煤电厂不仅面临降低燃料成本的压力，还需满足日益严格的环保排放标准[]。（剩余15600字）