Machine learning and domain adaptation to monitor yoghurt fermentation using ultrasonic measurements
Machine learning and domain adaptation to monitor yoghurt fermentation using ultrasonic measurements
复制标题
DOI：
10.1016/j.foodcont.2023.109622
复制
发表时间：
2023-01-12
期刊：
影响因子：
6
通讯作者：
Watson, Nicholas J.
中科院分区：
文献类型：
--
作者：
Bowler, Alexander;Ozturk, Samet;Watson, Nicholas J.
在生产环境中，需要实时监控酸奶发酵，以保持最佳生产计划，确保产品质量，并防止致病菌的生长。超声波传感器与机器学习模型相结合，为非侵入式过程监控提供了可能。然而，需要方法来确保模型对于由于改变工艺条件而改变的超声测量分布是鲁棒的。由于不知道这些分布变化何时发生，因此需要可以实时应用于新采集数据的域自适应方法。在这项工作中，酸奶发酵过程中使用非侵入式超声波传感器进行监测。此外，将基于透射的方法与不需要声波穿过发酵酸奶的工业相关的非透射方法进行比较。研究了三种机器学习算法，包括全连接神经网络、具有长短期记忆层的全连接神经网络和具有长短期记忆层的卷积神经网络。三个实时域自适应策略也进行了评估，即：功能对齐，预测对齐，和功能删除。最准确的方法（均方误差为0.008，用于预测发酵过程中的pH值）是基于非传输的，并使用具有长短期记忆层的卷积神经网络，以及所有三种域自适应方法的组合。
In manufacturing environments, real-time monitoring of yoghurt fermentation is required to maintain an optimal production schedule, ensure product quality, and prevent the growth of pathogenic bacteria. Ultrasonic sensors combined with machine learning models offer the potential for non-invasive process monitoring. However, methods are required to ensure the models are robust to changing ultrasonic measurement distributions as a result of changing process conditions. As it is unknown when these changes in distribution will occur, domain adaptation methods are needed that can be applied to newly acquired data in real-time. In this work, yoghurt fermentation processes are monitored using non-invasive ultrasonic sensors. Furthermore, a transmission based method is compared to an industrially-relevant non-transmission method which does not require the sound wave to travel through the fermenting yoghurt. Three machine learning algorithms were investigated including fullyconnected neural networks, fully-connected neural networks with long short-term memory layers, and convolutional neural networks with long short-term memory layers. Three real-time domain adaptation strategies were also evaluated, namely; feature alignment, prediction alignment, and feature removal. The most accurate method (mean squared error of 0.008 to predict pH during fermentation) was non-transmission based and used convolutional neural networks with long short-term memory layers, and a combination of all three domain adaption methods.