当前位置: X-MOL 学术Talanta › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Raman spectroscopy based chemometric approach to predict the derived cetane number of hydrocarbon jet fuels and their mixtures
Talanta ( IF 5.6 ) Pub Date : 2024-01-09 , DOI: 10.1016/j.talanta.2024.125635
Dhananjay Ambre 1 , Manaf Sheyyab 1 , Patrick Lynch 1 , Eric K Mayhew 2 , Kenneth Brezinsky 1
Affiliation  

Fuel ignition quality, measured in the form of Derived Cetane Number (DCN), is an important part of integrating fuels, including sustainable aviation fuels, in compression ignition engines. DCN has been correlated with simulated and/or real spectroscopic measurements as well as other physical and chemical properties, but rarely have these correlations developed into a pathway to application. One application of the correlations is the use of miniaturized onboard fuel sensors that could assist, by using predicted DCN, in real-time feedforward engine control. To aid in the application of developing such DCN fuel sensors, Raman spectra coupled with chemometrics and a selection of influential spectral features were investigated. In this study, the Raman spectra were obtained from a database that included jet fuels, jet fuel mixtures, pure hydrocarbon components, and their weighted mixtures. The resulting Raman spectral database from the experimental measurements included spectra of components that span a wide range of DCNs and covered all the expected chemical functional groups present in a standard jet fuel. Chemometric models were developed to associate Raman spectra with DCN in subsets of the spectral range to aid in sensor miniaturization. The models were tested on jet fuels such as National Jet Fuel Combustion Program fuels designated A-1, A-2, and A-3 along with mixtures of jet fuels that spanned a wide range of DCN, simulating fuels that could represent real-world scenarios. An Artificial Neural Network (ANN) model trained on the fingerprint region (500 cm – 1800 cm) of the Raman spectra was able to capture the non-linearity of the association between the Raman spectra and DCN with a test R score of 0.926, a test MSE of 3.61, and a test MPE of 3.41. Around 97 % of the unseen test samples were predicted within 10 % of the DCN measured with an Ignition Quality Tester. One hundred features of the fingerprint region influencing DCN predictions in the optimal ANN model were extracted using a Global Surrogate (GS) model. A reduced ANN model trained on only these one hundred features performed slightly better with a test R score of 0.935, test MSE of 3.19, test MPE of 3.20 and with the entire set of unseen test samples predicted within 10 % of the measured DCN. For assessing applicability of real-time and online DCN sensing, the Raman spectrometer was integrated with a flow cell capable of allowing measurements of DCN in flowing fuel samples and included the optimal ANN model of the fingerprint region and the 100-feature GS-ANN model on a Raspberry Pi computer. A number of unseen F-24/alcohol-to-jet fuel mixtures composed of unknown volumes were tested using the flow cell for DCN, and all of these samples were predicted within 10 % of the measured DCN.

中文翻译:


基于拉曼光谱的化学计量学方法,用于预测碳氢喷气燃料及其混合物的十六烷值



燃料点火质量以衍生十六烷值 (DCN) 的形式测量,是将燃料(包括可持续航空燃料)集成到压燃式发动机中的重要组成部分。 DCN 已与模拟和/或真实光谱测量以及其他物理和化学特性相关联,但很少将这些相关性发展成应用途径。相关性的一种应用是使用小型化机载燃油传感器,通过使用预测的 DCN,可以帮助进行实时前馈发动机控制。为了帮助开发这种 DCN 燃料传感器的应用,研究了拉曼光谱与化学计量学的结合以及一系列有影响力的光谱特征。在这项研究中,拉曼光谱是从包括喷气燃料、喷气燃料混合物、纯碳氢化合物成分及其加权混合物的数据库中获得的。实验测量所得的拉曼光谱数据库包括跨越各种 DCN 的成分光谱,并涵盖标准喷气燃料中存在的所有预期化学官能团。开发了化学计量模型,将拉曼光谱与光谱范围子集中的 DCN 相关联,以帮助传感器小型化。这些模型在喷气燃料上进行了测试,例如国家喷气燃料燃烧计划指定的 A-1、A-2 和 A-3 燃料以及涵盖广泛 DCN 的喷气燃料混合物,模拟了可以代表现实世界的燃料场景。在拉曼光谱的指纹区域(500 cm – 1800 cm)上训练的人工神经网络 (ANN) 模型能够捕获拉曼光谱和 DCN 之间关联的非线性,测试 R 得分为 0.926,测试 MSE 为 3.61,测试 MPE 为 3.41。 大约 97% 的未见过的测试样本被预测在使用点火质量测试仪测量的 DCN 的 10% 范围内。使用全局代理(GS)模型提取了影响最佳 ANN 模型中 DCN 预测的指纹区域的 100 个特征。仅对这 100 个特征进行训练的简化 ANN 模型表现稍好,测试 R 得分为 0.935,测试 MSE 为 3.19,测试 MPE 为 3.20,并且预测的整个未见过的测试样本集在测量的 DCN 的 10% 以内。为了评估实时和在线 DCN 传感的适用性,拉曼光谱仪与流动池集成,能够测量流动燃料样品中的 DCN,并包括指纹区域的最佳 ANN 模型和 100 个特征的 GS-ANN 模型在 Raspberry Pi 计算机上。使用 DCN 流通池测试了许多由未知体积组成的未见过的 F-24/酒精到喷气燃料混合物,所有这些样品的预测值都在测量的 DCN 的 10% 以内。
更新日期:2024-01-09
down
wechat
bug