Abstract Determination of toxic metal elements in oily sludge is meaningful to treatment, migration, improvement, monitoring, and repair of oily sludge, and an accurate and rapid analytical technology is urgent necessary to quantitative detect the toxic metal elements in oily sludge. In this study, a novel method based on laser-induced breakdown spectroscopy (LIBS) technique coupled with wavelet transform-random forest (WT-RF) was proposed to perform quantitative analysis of four toxic metal elements (Cu, Zn, Cr and Ni) in 16 oily sludge samples. In order to facilitate LIBS measurement, the 16 initial oily sludge samples with a water-oil mixed state were subjected to a drying treatment at 150 °C for 5 h, and then ground and passed through a 100 mesh to sift. The 16 oily sludge samples were sliced and collected LIBS spectra, and 11 samples were selected as calibration sets, and rest samples were set as test sets. The raw spectra were first preprocessed by wavelet transform (WT) method, and then the input variables for RF calibration model were selected and optimized based on variable importance. Finally, the WT-RF model with the optimal input variables was constructed to quantitative analysis four toxic metal elements concentration in the oily sludge. The predictive performance of WT-RF model was compared with the RF, partial least squares (PLS) and WT-PLS models. The results indicates that WT-RF model shows a better predictive ability than the other three models for prediction of potential toxic metal concentration in oily sludge, and the best determination coefficient (R2) value of four elements (Cu, Zn, Cr and Ni) were 0.9756, 0.9758, 0.9772, 0.9768, the root mean square error (RMSE) were 0.0358%, 0.0365%, 0.0446% and 0.0344%, and the relative standard deviation (RSD) were 0.0908, 0.0929, 0.0797 and 0.0628. Therefore, LIBS technique combined with WT-RF method is a promising method for the rapid prediction of the toxic metal elements in oily sludge.

中文翻译：

---

激光诱导击穿光谱结合小波变换-随机森林（WT-RF）同时定量分析含油污泥中的四种金属元素

摘要 含油污泥中有毒金属元素的测定对含油污泥的处理、迁移、改良、监测和修复具有重要意义，迫切需要一种准确、快速的分析技术来定量检测含油污泥中的有毒金属元素。在本研究中，提出了一种基于激光诱导击穿光谱 (LIBS) 技术结合小波变换-随机森林 (WT-RF) 的新方法对四种有毒金属元素（Cu、Zn、Cr ​​和 Ni）进行定量分析。在 16 个含油污泥样品中。为便于LIBS测量，将16份水油混合状态的初始含油污泥样品在150℃下干燥5h，然后研磨过100目筛分。将 16 个含油污泥样品切片并采集 LIBS 光谱，选取11个样本作为校准集，其余样本作为测试集。首先通过小波变换（WT）方法对原始光谱进行预处理，然后根据变量重要性选择和优化射频校准模型的输入变量。最后，构建具有最优输入变量的WT-RF模型，对含油污泥中四种有毒金属元素的浓度进行定量分析。WT-RF 模型的预测性能与 RF、偏最小二乘法 (PLS) 和 WT-PLS 模型进行了比较。结果表明，WT-RF模型对含油污泥中潜在有毒金属浓度的预测比其他三种模型具有更好的预测能力，四种元素（Cu、Zn、Cr和Ni）的最佳决定系数（R2）值分别为 0.9756、0.9758、0.9772、0.9768、均方根误差 (RMSE) 为 0.0358%、0.0365%、0.0446% 和 0.0344%，相对标准偏差 (RSD) 为 0.0908、0.0929、0.0797 和 0.0628。因此，LIBS技术结合WT-RF方法是一种快速预测含油污泥有毒金属元素的有效方法。