一种煤炭近红外光谱数据预处理方法研究  

Research of a data preprocessing method for near infrared spectrum of coal

作　　者：李明[1] 李翠[1] 雷萌[1] 

机构地区：[1]中国矿业大学信息与电气工程学院,江苏徐州221008

出　　处：《工矿自动化》2015年第1期62-66,共5页Journal Of Mine Automation

基　　金：高等学校博士学科点专项科研基金资助项目(20110095110011);江苏省自然科学基金资助项目(BK20130207)

摘　　要：针对煤炭原始近红外光谱数据中存在噪声的问题,提出了基于De-SNV与小波阈值去噪组合的煤炭近红外光谱数据预处理方法。采用缺省软阈值法进一步对经过Savitzky-Golay平滑和De-SNV处理的光谱数据去噪,并分别建立了水分、灰分和挥发分的PLS校正模型,通过分析模型的预测性能对该方法的有效性进行评估。实验结果表明,经过该方法预处理的光谱数据所对应的PLS校正模型性能明显优于使用原始光谱数据所建立的PLS校正模型,水分、灰分和挥发分的PLS校正模型的预测均方根误差分别降低至0.007 07,0.040 8,0.008 66,决定系数分别提高至0.858 7,0.743 8,0.778 5。For noise existed in original near infrared spectral data of coal, a data preprocessing method for near infrared spectrum of coal was proposed based on De-SNV and wavelet threshold denoising. Spectrum data processed by Savitzky-Golay smoothing and De-SNV was further processed by default soft threshold denoising method. Then PLS calibration models of moisture, ash and volatile were established. Effect of the method was evaluated by analyzing predicting performance of the models. The experiments show that performance of PLS model based on spectrum data processed by the method is much better than the one based on original spectrum data. The root-mean-square errors of prediction of the three PLS ealibration models are decreased to 0. 007 07, O. 040 8, 0. 008 66 respectively, and the determination coe{{icients are increased to 0.858 7, 0.743 8, 0.778 5.

关 键 词：煤炭光谱 近红外光谱 小波阈值去噪 Savitzky-Golay平滑 去势-标准正态变换 PLS校正模型 

分 类 号：TD67[矿业工程—矿山机电]