Hybrid intelligent control of substrate feeding for industrial fed-batch chlortetracycline fermentation process

Bringing a scalable adaptive hybrid modeling framework closer to industrial use: Application on a multiscale fungal fermentation

Digitalization has paved the way for new paradigms such as digital shadows and digital twins for fermentation processes, opening the door for real-time process monitoring, control, and optimization. With a digital shadow, real-time model adaptation to accommodate complex metabolic phenomena such as metabolic shifts of a process can be monitored. Despite the many benefits of digitalization, the potential has not been fully reached in the industry. This study investigates the development of a digital shadow for a very complex fungal fermentation process in terms of microbial physiology and fermentation operation on pilot-scale at Novonesis and the challenges thereof. The process has historically been difficult to optimize and control due to a lack of offline measurements and an absence of biomass measurements. Pilot-scale and lab-scale fermentations were conducted for model development and validation. With all available pilot-scale data, a data-driven soft sensor was developed to estimate the main substrate concentration (glucose) with a normalized root mean squared error (N-RMSE) of 2%. This robust data-driven soft sensor was able to estimate accurately in lab-scale (volume < 20× pilot) with a N-RMSE of 7.8%. A hybrid soft sensor was developed by combining the data-driven soft sensor with a mass balance to estimate the glycerol and biomass concentrations on pilot-scale data with N-RMSEs of 11% and 21%, respectively. A digital shadow modeling framework was developed by coupling a mechanistic model (MM) with the hybrid soft sensor. The digital shadow modeling framework significantly improved the predictability compared with the MM. The contribution of this study brings the application of digital shadows closer to industrial implementation. It demonstrates the high potential of using this type of modeling framework for scale-up and leads the way to a new generation of in silico-based process development.

Online prediction of total sugar content and optimal control of glucose feed rate during chlortetracycline fermentation based on soft sensor modeling

In the process of chlortetracycline (CTC) fermentation, no instrument can be used to measure the total sugar content of the fermentation broth online due to its high viscosity and large amount of impurities, so it is difficult to realize the optimal control of glucose feed rate in the fermentation process. In order to solve this intractable problem, the relationship between on-line measurable parameters and total sugar content (One of the parameters that are difficult to measure online) in fermentation tank is deeply analyzed, and a new soft sensor model of total sugar content in fermentation tank and a new optimal control method of glucose feed rate are proposed in this paper. By selecting measurable variables of fermentation tank, determining different fermentation stages, constructing recursive fuzzy neural network (RFNN) and applying network rolling training method, an online soft sensor model of total sugar content is established. Based on the field multi-batch data, the change trend of the amount of glucose feed required at each fermentation stage is divided, and the online prediction of total sugar content and the optimal control strategy of glucose feed rate are realized by using the inference algorithm of expert experience regulation rules and soft sensor model of total sugar content. The experiment results in the real field demonstrate that the proposed scheme can effectively predict the total sugar content of fermentation broth online, optimize the control of glucose feed rate during fermentation process, reduce production cost and meet the requirements of production technology.

Research on soft sensing method of photosynthetic bacteria fermentation process based on ant colony algorithm and least squares support vector machine

Photosynthetic bacteria wastewater treatment is an efficient water pollution treatment method, but photosynthetic bacteria fermentation is a multivariable, non-linear, and time-varying process. So it is difficult to establish an accurate model. Aiming at the difficulty of online measurement of key parameters, such as bacterial concentration and matrix concentration in photosynthetic bacteria fermentation process, an improved ant colony algorithm least squares support vector machine (AC-LSSVM) soft sensing model method is proposed in this paper. Firstly, the virtual sensing subsystem of the photosynthetic bacteria fermentation process is proposed, with measurable parameters as input and unmeasurable key parameters as output, and the left inverse soft sensing model of virtual sensing is constructed. Then, the ant colony algorithm can quickly find the shortest path to optimize the parameters of the traditional PI regulation, to improve the dynamic performance and accuracy of parameter measurement in the fermentation process. After that, the ant colony algorithm is used to optimize penalty parameters C and kernel parameters σ of LSSVM, which effectively avoids the local optimization and improves the computing power and global optimization ability. Finally, the soft sensing prediction model of the photosynthetic bacteria fermentation process based on AC-LSSVM is established. Compared with SVM and LSSVM prediction models, the root mean square error of bacterial concentration and matrix concentration based on the AC-LSSVM model are 0.468 and 0.126, respectively. The simulation analysis shows that this model has less error and better prediction ability, and it can meet the needs of online prediction of key parameters of photosynthetic bacteria fermentation.

State estimation and nonlinear tracking control simulation approach. Application to a bioethanol production system

Tracking control of specific variables is key to achieve a proper fermentation. This paper analyzes a fed-batch bioethanol production process. For this system, a controller design based on linear algebra is proposed. Moreover, to achieve a reliable control, on-line monitoring of certain variables is needed. In this sense, for unmeasurable variables, state estimators based on Gaussian processes are designed. Cell, ethanol and glycerol concentrations are predicted with only substrates measurement. Simulation results when the controller and estimators are coupled, are shown. Furthermore, the algorithms were tested with parametric uncertainties and disturbances in the control action, and are compared, in all cases, with neural networks estimators (previous work). Bayesian estimators show a performance improvement, which is reflected in a decrease of the total error. Proposed techniques give reliable monitoring and control tools, with a low computational and economic cost, and less mathematical complexity than neural network estimators.

Tracking control of concentration profiles in a fed-batch bioreactor using a linear algebra methodology

Based on a linear algebra approach, this paper aims at developing a novel control law able to track reference profiles that were previously-determined in the literature. A main advantage of the proposed strategy is that the control actions are obtained by solving a system of linear equations. The optimal controller parameters are selected through Monte Carlo Randomized Algorithm in order to minimize a proposed cost index. The controller performance is evaluated through several tests, and compared with other controller reported in the literature. Finally, a Monte Carlo Randomized Algorithm is conducted to assess the performance of the proposed controller.