用机器学习提升激光光谱法，在复杂环境下无参考地检测多种气体。
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
- 结合深度去噪自编码器与光谱增强，提升弱信号检测精度。
- 在无完整参考数据时，可分离多达八种气体成分并重建其光谱。
- 适合燃烧研究、环境监测和工业安全中的实时气体检测场景。
激光吸收光谱（LAS）是燃烧与大气环境中非侵入式气体检测的成熟技术，但传统方法在动态或干扰严重的多组分混合物中表现受限。重叠光谱特征、噪声及不完整的参考数据导致未知或弱吸收物种检测不可靠。本文提出将机器学习（ML）与激光光谱融合的诊断方案：采用深度去噪自编码器（DDAE）处理高速烃类热解的激波管数据，提升信号保真度与痕量物种检测极限；设计结构化无监督框架HT-SIMNet，通过光谱增广与Noise2Noise机制，在缺乏完整校准数据时分离未知物种；针对无参考光谱情况，提出基于自编码器的无监督盲源分离方法UnblindMix，可直接从混合数据中重构多达八组分的浓度与光谱；为识别被强吸收体掩盖的弱吸收物种，引入一阶导数与卷积特征工程以突出微弱信号；最后，VOC-certifire结合随机平滑与Voigt型光谱扰动，实现挥发性有机物在不同条件下的可认证分类。所有方法均经实验验证与基准测试。该技术融合光谱硬件与机器学习，为燃烧科学、环境监测与工业安全提供实时、抗干扰、无需参考的气体检测新路径。
原文摘要 · Abstract (English)
Laser absorption spectroscopy (LAS) is a well-established technique for non-intrusive measurement of gas species in combustion and atmospheric environments, but conventional methods struggle with multi-species mixtures under dynamic or interference-laden conditions. Overlapping spectral features, noise, and incomplete reference data limit reliability when unknown or weakly absorbing species are present. This dissertation develops diagnostics combining LAS with machine learning (ML) to address these limitations. Deep denoising autoencoders (DDAEs) are applied to shock-tube measurements during high-speed hydrocarbon pyrolysis, improving signal fidelity and detection limits for trace species. A structured unsupervised framework, HT-SIMNet, then mitigates interference from unknown species without full calibration data, using spectral augmentation and a Noise2Noise-inspired scheme to isolate species in reactive systems. Where reference spectra are unavailable, UnblindMix, an autoencoder-based blind source separation method, reconstructs concentrations and spectral signatures directly from mixture data, validated on mixtures of up to eight components. To recover weakly absorbing species masked by broader absorbers, a feature-engineering method based on first derivatives and convolutions selectively highlights minor species. Finally, VOC-certifire combines randomized smoothing with Voigt-based spectral perturbation to provide certifiable classification of volatile organic compounds under varying conditions. All techniques are experimentally validated and benchmarked. The integration of spectroscopic hardware with ML offers a path toward real-time, interference-resilient, reference-free gas detection for combustion science, environmental monitoring, and industrial safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。