Towards a digital twin: a hybrid data‐driven and mechanistic digital shadow to forecast the evolution of lignocellulosic fermentation

Abstract

The high substrate variability and complexity of fermentation media derived from lignocellulosic feedstock affects the concentration profiles and the length of the fermentation. Failing to account for such variability raises operational and scheduling issues and affects the overall performance of these processes. In this work, a hybrid soft sensor was developed to monitor and forecast the evolution of cellulose‐to‐ethanol fermentation. The soft sensor consisted of two modules (a data‐driven model and a kinetic model) connected sequentially. The data‐driven module used a partial‐least‐squares model to estimate the current state of glucose from spectroscopic data. The kinetic model was recursively fitted to known concentrations of glucose to update the long‐horizon predictions of glucose, xylose, and ethanol. This combination of real‐time data update from an actual fermentation process to a high‐fidelity kinetic model constitutes the basis of the digital twin concept and allows for a better real‐time understanding of complex inhibition phenomena caused by different inhibitors commonly found in lignocellulosic feedstocks. The soft sensor was experimentally validated with three different cellulose‐to‐ethanol fermentations and the results suggested that this method is suitable for monitoring and forecasting fermentation when the measurements provide reasonably good estimates of the real state of the system. These results would allow the flexibility of the operation of cellulosic processes to be increased, and would permit the scheduling to be adapted to the inherent variability of such substrates © 2020 Society of Chemical Industry and John Wiley & Sons, Ltd.

Towards smart biomanufacturing: a perspective on recent developments in industrial measurement and monitoring technologies for bio-based production processes

“…11e-h). Systematic approaches to plan the calibration sets based on design of experiments (DoE) can successfully be implemented in systems where the fermentation matrix can be isolated from the rest of the analytes [115]. This allows to completely decouple the concentrations of the different analytes and to distribute the samples evenly along the design space.…”

“…However, this information is very valuable to determine the end-point of the fermentation and to schedule the downstream operations. Cabaneros et al [115] used a hybrid framework to incorporate the PLS predictions of glucose into a mechanistic model of the fermentation to obtain high fidelity predictions of the progress of the fermentation.…”

Why Is Batch Processing Still Dominating the Biologics Landscape? Towards an Integrated Continuous Bioprocessing Alternative

“…This first type of digital twins deals with operational support and control. For example, the use of digital twins to forecast the evolution of a fermentation process, such as in [66]. On the other hand, a digital twin can be a digital representation of a future production process, where it acts as a validated test-bed which can be used to refine and build confidence in a process design prior to construction.…”

Digital Twin in biomanufacturing: challenges and opportunities towards its implementation

“…This represents a significant improvement over the traditional solution of scheduling maintenance at fixed intervals, without considering the actual state of the equipment. Similarly, in fermentation operations, a Digital Twin can be used to predict batch end times based on data in real-time [4], while also allowing for multiple operational strategies to be tested in silico. Both scenarios lead to increased understanding of how a batch is likely to develop hence allow for informed decision making either in real-time as the process progresses, or "off-line".…”

“…It receives information and communicates back in real-time, thus influences the physical object in real-time. In practice, however, many attempts that would fall into the category of a Digital Model or a Digital Shadow are also referred to as a "Digital Twin" [3][4][5]. Nonetheless, from a process engineering point of view, this definition of a Digital Twin is significantly skewed towards process control, where the defining feature is the ability of the Digital Twin to act as a closed-loop model-based controller.…”