Oxidation Stability of Hydrocarbons: A Machine-Learning-Based Study

Having fluids that are stable over time is important for many applications, particularly sustainable aviation fuels (SAFs) derived from various renewable sources. Being able to understand this characteristic as early as possible during the development of SAFs would facilitate the blending of renewable sources with or without fossil fuels. Oxidation stability, defined as a hydrocarbon’s resistance to reacting with oxygen at near-ambient temperatures, is one of the most important hydrocarbon-stability-related properties. Indeed, the accumulation of byproducts of oxidation reactions may result in system failures. Assessing this property experimentally remains time-consuming; thus developing fast and accurate predictive models becomes relevant and approaches based on machine learning appear as valuable alternatives. The development of quantitative structure–property relationships (QSPRs) is subject to the availability of reference data, and unfortunately, these are currently lacking in the literature. In this study, we built a database containing consistent experimental results from accelerated oxidation tests conducted on diverse pure hydrocarbonswithin the carbon atom number range of SAFsusing the PetroOxy/RapidOxy test method, and second, we applied two machine-learning-based techniques (SVM and XGBoost) on the generated data set to derive QSPR-based models. The contribution of techniques such as data augmentation applied to our data set was also investigated and compared to more classical approaches. The best model (RMSEP = 2.7 h) was obtained after log-transforming the reference Induction Period, performing Smart Data Augmentation to enrich the database content, and using XGBoost with linear learners. While the model’s accuracy is not adequate for quantitative predictions, it allows fast and semiquantitative predictions.

流体的长期稳定性对诸多应用场景至关重要，对于由多种可再生资源制备的可持续航空燃料（Sustainable Aviation Fuels, SAFs）而言尤为如此。在可持续航空燃料的研发早期阶段掌握其稳定性特性，将有助于可再生原料与含或不含化石燃料的组分进行调合。
氧化稳定性（Oxidation Stability）被定义为烃类物质在接近室温条件下抵抗氧气反应的能力，是与烃类稳定性相关的最重要性质之一。事实上，氧化反应副产物的积累可能引发系统故障。通过实验手段评估该性质仍较为耗时，因此开发快速且精准的预测模型具有重要意义，而基于机器学习的方法则成为极具价值的替代方案。
定量构效关系（Quantitative Structure-Property Relationships, QSPRs）的开发依赖于参考数据集的可用性，但遗憾的是当前文献中此类数据较为匮乏。本研究首先构建了一套数据库，其中收录了采用PetroOxy/RapidOxy测试方法，针对符合可持续航空燃料碳数范围的多种纯烃类物质开展加速氧化试验所得到的一致性实验结果；其次，基于生成的数据集，我们运用两种机器学习技术——支持向量机（Support Vector Machine, SVM）与极端梯度提升（Extreme Gradient Boosting, XGBoost）——构建了基于定量构效关系的预测模型。本研究还探究了数据增强等技术在本数据集上的应用效果，并将其与更为经典的方法进行了对比。
最优模型的均方根预测误差（Root Mean Square Error of Prediction, RMSEP）为2.7小时，其构建过程为：对参考诱导期（Induction Period）进行对数变换、采用智能数据增强（Smart Data Augmentation）丰富数据库内容，并使用搭载线性学习器的极端梯度提升模型。尽管该模型的精度尚不足以满足定量预测需求，但仍可实现快速的半定量预测。