Tokuyama Kento, Shimodaira Yoshiki, Kodama Yohei, Matsui Ryuzo, Kusunose Yasuhiro, Fukushima Shunsuke, Nakai Hiroaki, Tsuji Yuichiro, Toya Yoshihiro, Matsuda Fumio, Shimizu Hiroshi
DX Promotion Department, Ajinomoto Co., Inc., 1-15-1 Kyobashi, Chuo-ku, Tokyo 104-8315, Japan.
Institute for Innovation, Ajinomoto Co., Inc., 1-1 Suzuki-cho, Kawasaki-ku, Kawasaki, Kanagawa 210-8681, Japan.
J Biosci Bioeng. 2021 Aug;132(2):183-189. doi: 10.1016/j.jbiosc.2021.04.002. Epub 2021 May 3.
Monitoring cell growth and target production in working fermentors is important for stabilizing high level production. In this study, we developed a novel soft sensor for estimating the concentration of a target product (lysine), substrate (sucrose), and bacterial cell in commercially working fermentors using machine learning combined with available on-line process data. The lysine concentration was accurately estimated in both linear and nonlinear models; however, the nonlinear models were also suitable for estimating the concentrations of sucrose and bacterial cells. Data enhancement by time interpolation improved the model prediction accuracy and eliminated unnecessary fluctuations. Furthermore, the soft sensor developed based on the dataset of the same process parameters in multiple fermentor tanks successfully estimated the fermentation behavior of each tank. Machine learning-based soft sensors may represent a novel monitoring system for digital transformation in the field of biotechnological processes.
监测工作发酵罐中的细胞生长和目标产物生成对于稳定高水平生产很重要。在本研究中，我们开发了一种新型软传感器，利用机器学习结合可用的在线过程数据来估计商业运行发酵罐中目标产物（赖氨酸）、底物（蔗糖）和细菌细胞的浓度。在线性和非线性模型中都能准确估计赖氨酸浓度；然而，非线性模型也适用于估计蔗糖和细菌细胞的浓度。通过时间插值进行数据增强提高了模型预测准确性并消除了不必要的波动。此外，基于多个发酵罐中相同过程参数的数据集开发的软传感器成功估计了每个罐的发酵行为。基于机器学习的软传感器可能代表了生物技术过程领域数字转型的一种新型监测系统。
