Chemical contamination of objects and surfaces, caused by accident or on purpose, is a common security issue. Immediate countermeasures depend on the class of risk and consequently on the characteristics of the substances. Laser‐based standoff detection techniques can help to provide information about the thread without direct contact of humans to the hazardous materials. This article explains a data acquisition and classification procedure for laser‐induced fluorescence spectra of several chemical agents. The substances are excited from a distance of 3.5 m by laser pulses of two UV wavelengths (266 and 355 nm) with less than 0.1 mJ per laser pulse and a repetition rate of 100 Hz. Each pair of simultaneously emitted laser pulses is separated using an optical delay line. Every measurement consists of a dataset of 100 spectra per wavelength containing the signal intensities in the spectral range from 250 to 680 nm, recorded by a 32‐channel photo multiplying tube array. Based on this dataset, three classification algorithms are trained which can distinguish the samples by their single spectra with an accuracy of over 98%. These predictive models, generated with decision trees, support vector machines, and neural networks, can identify all agents (eg, benzaldehyde, isoproturon, and piperine) within the current set of substances.

中文翻译：

---

使用隔离激光诱导荧光信号在线识别化学物质

意外或故意造成的物体和表面的化学污染是一个常见的安全问题。立即采取的对策取决于风险类别，进而取决于物质的特性。基于激光的间距检测技术可以帮助提供有关线的信息，而无需人类直接接触危险材料。本文解释了几种化学试剂的激光诱导荧光光谱的数据采集和分类程序。这些物质被两个紫外线波长（266 和 355 nm）的激光脉冲从 3.5 m 的距离激发，每个激光脉冲小于 0.1 mJ，重复率为 100 Hz。每对同时发射的激光脉冲使用光学延迟线分开。每次测量都包含每个波长 100 个光谱的数据集，其中包含 250 至 680 nm 光谱范围内的信号强度，由 32 通道光电倍增管阵列记录。基于该数据集，训练了三种分类算法，可以通过单个光谱对样本进行区分，准确率超过98%。这些由决策树、支持向量机和神经网络生成的预测模型可以识别当前物质组中的所有药剂（例如，苯甲醛、异丙隆和胡椒碱）。