正态曲线剔除法提高LIBS快速测量煤炭灰分精确度

Research on Improving the Accuracy of LIBS Ash Measurement By Normal Curve Elimination Method

测定煤的灰分对于煤的质量评价和加工利用等都有重要意义。将激光诱导击穿光谱技术(laser induced breakdownspectroscopy,LIBS)直接应用于颗粒流检测能省去复杂的压片制样过程,有望满足在线测量的实时要求,然而由于煤粉颗粒流的波动性较大,所以有必要对异常的光谱数据进行筛选和剔除。提出正态曲线剔除异常数据的方法,并评估了该方法提高LIBS测量煤炭灰分精确度的作用。研究结果表明:采用正态曲线剔除法能有效减少光谱强度的波动,提高光谱信号的稳定性和测量的可重复性;经过正态曲线剔除法处理后,灰分预测集的平均相对误差(averagedrelativeerrorofprediction,REP)从6.35%降至6.25%,平均相对标准偏差(relative standard deviation,RSD)从3.91%降至2.80%,从而使灰分的预测精确度得到提高。

The determination of ash in coal is of great significance to the quality evaluation, processing and utilization of coal. The laser induced breakdown spectroscopy(LIBS) applied to particles flow testing can simplify the tablet sample preparation process, which is expected to meet the requirements of real-time online measurement. However, due to the flow of pulverized coal volatile, it is necessary to carry out abnormal spectral data filtering and elimination. This paper presented a method to eliminate abnormal data of normal curve,and evaluated the effect of this method to improve the accuracy of LIBS measurement of coal ash. The results show that the method can effectively reduce the fluctuation of spectral intensity and improve the stability and repeatability of spectral signals. After dealing with the normal curve excluding method,the ash content average relative error of prediction(REP) set was reduced from 6.35% to 6.25%, the average relative standard deviation(RSD) was reduced from 3.91% to 2.80%,so that the ash content of forecasting accuracy was improved.