Machine learning prediction and optimization of bio-oil production from hydrothermal liquefaction of algae
Machine learning prediction and optimization of bio-oil production from hydrothermal liquefaction of algae
复制标题
藻类水热液化生物油生产的机器学习预测和优化
DOI：
10.1016/j.biortech.2021.126011
复制
发表时间：
2021
影响因子：
11.4
通讯作者：
Li Hailong
中科院分区：
文献类型：
--
作者：
Zhang Weijin;Li Jie;Liu Tonggui;Leng Songqi;Yang Lihong;Peng Haoyi;Jiang Shaojian;Zhou Wenguang;Leng Lijian;Li Hailong
藻类水热液化是一种很有前途的生物燃料生产技术。然而，通过常规的实验研究来确定不同藻类的最佳HTL条件往往是困难和耗时的。因此，采用机器学习（ML）算法，以藻类组成和HTL条件为输入，以生物油产量（Yield_oil）和生物油中氧（O_oil）和氮（N_oil）含量为输出，对生物油产量进行预测和优化。结果表明，梯度提升回归（GBR，平均测试R2 = 0.90）表现出更好的性能比随机森林（RF）的单目标和多目标任务的预测。此外，基于模型的解释表明，操作条件（温度和停留时间）的相对重要性高于藻类特性的三个目标。此外，基于ML的反向和正向优化进行了实验验证。验证是可以接受的，显示了ML辅助HTL用于生产理想的生物油的巨大潜力。
Hydrothermal liquefaction (HTL) of algae is a promising biofuel production technology. However, it is always difficult and time-consuming to identify the best optimal conditions of HTL for different algae by the conventional experimental study. Therefore, machine learning (ML) algorithms were applied to predict and optimize bio-oil production with algae compositions and HTL conditions as inputs, and bio-oil yield (Yield_oil), and the contents of oxygen (O_oil) and nitrogen (N_oil) in bio-oil as outputs. Results indicated that gradient boosting regression (GBR, average testR2∼ 0.90) exhibited better performance than random forest (RF) for both single and multi-target tasks prediction. Furthermore, the model-based interpretation suggested that the relative importance of operating conditions (temperature and residence time) was higher than algae characteristics for the three targets. Moreover, ML-based reverse and forward optimizations were implemented with experimental verifications. The verifications were acceptable, showing great potential of ML-aided HTL for producing desirable bio-oil.