Abedi Elahe, Sayadi Mehran, Mousavifard Maryam, Roshanzamir Farzad
Department of Food Science and Technology, Faculty of Agriculture Fasa University Fasa Iran.
Department of Food Safety and Hygiene, School of Health Fasa University of Medical Sciences Fasa Iran.
Food Sci Nutr. 2024 Jul 9;12(9):6752-6771. doi: 10.1002/fsn3.4300. eCollection 2024 Sep.
In this study, the effect of high-power bath and horn ultrasound at different powers on specific surface area ( ), total pore volume ( ), and average pore volume ( ) of bleaching clay was examined. After subjecting the bleaching clay to ultrasonication treatment, the SBET values demonstrated an escalation from 31.4 ± 2.7 m g to 59.8 ± 3.1 m g for HU200BC, 143.8 ± 3.9 m g for HU400BC, 54.4 ± 3.6 m g for BU400BC, and 137.5 ± 2.8 m g for BU800BC. The mean pore diameter ( ) declined from 29.7 ± 0.14 nm in bleaching clay to 11.3 ± 0.13 nm in HU200BC, 8.3 ± 0.12 nm in HU400BC, 16.7 ± 0.14 nm in BU400BC, and 9.6 ± 0.12 nm in BU800BC. Therefore, horn ultrasound-treated bleaching clay significantly increased and , indicating improved adsorption capacity. Moreover, to establish the relationship between bleaching parameters, seven multi-output ML regression models of Feedforward Neural Network (FNN), Random Forest (RF), Support Vector Regression (SVR), Multi-Task Lasso, Ridge regression, Extreme Gradient Boosting (XGBoost), and Gradient Boosting are used, and compared with response surface methodology (RSM). ML has revolutionized the understanding of complex relationships between ultrasonic parameters, oil color, and pigment degradation, providing insights into how various factors such as temperature, ultrasonic power, and time can influence the bleaching process, ultimately enhancing the efficiency and precision of the treatment. The XGBoost model showed outstanding performance in predicting the target variables with a high -train up to 1, -test up to .983, and a minimum mean absolute error (MAE) of 0.498. The lower error between the predicted and experimental values implies the superiority of the XGBoost model to predict outcomes rather than RSM. It represents the suitability of bath ultrasound as a mild condition for low-pigmented oil bleaching. Finally, the Bayesian optimization method in conjunction with XGBoost was used to optimize the amount of bleaching clay and energy consumption, and its performance was compared with RSM. It was observed that the consumption of bleaching clay was reduced by approximately 60% for sunflower oil and 30%-35% for soybean oil.
在本研究中，考察了不同功率的高功率浴式超声和喇叭超声对漂白土比表面积（ ）、总孔体积（ ）和平均孔体积（ ）的影响。对漂白土进行超声处理后，HU200BC的比表面积值从31.4±2.7 m²/g增至59.8±3.1 m²/g，HU400BC为143.8±3.9 m²/g，BU400BC为54.4±3.6 m²/g，BU800BC为137.5±2.8 m²/g。平均孔径（ ）从漂白土中的29.7±0.14 nm降至HU200BC中的11.3±0.13 nm、HU400BC中的8.3±0.12 nm、BU400BC中的16.7±0.14 nm和BU800BC中的9.6±0.12 nm。因此，经喇叭超声处理的漂白土显著增加了 和 ，表明吸附能力得到改善。此外，为了建立漂白参数之间的关系，使用了前馈神经网络（FNN）、随机森林（RF）、支持向量回归（SVR）、多任务套索、岭回归、极端梯度提升（XGBoost）和梯度提升这七种多输出ML回归模型，并与响应面方法（RSM）进行比较。ML彻底改变了人们对超声参数、油颜色和色素降解之间复杂关系的理解，深入了解了温度、超声功率和时间等各种因素如何影响漂白过程，最终提高了处理的效率和精度。XGBoost模型在预测目标变量方面表现出色，训练集 高达1，测试集 高达0.983，平均绝对误差（MAE）最小为0.498。预测值与实验值之间较低的误差意味着XGBoost模型在预测结果方面优于RSM。这表明浴式超声适合作为低色素油漂白的温和条件。最后，结合XGBoost使用贝叶斯优化方法来优化漂白土用量和能耗，并将其性能与RSM进行比较。结果发现，葵花籽油的漂白土消耗量减少了约60%，大豆油减少了30%-35%。
