For effective monitoring and control of the fermentation process, an accurate real-time measurement of important variables is necessary. These variables are very hard to measure in real-time due to constraints such as the time-varying, nonlinearity, strong coupling, and complex mechanism of the fermentation process. Constructing soft sensors with outstanding performance and robustness has become a core issue in industrial procedures. In this paper, a comprehensive review of existing data pre-processing approaches, variable selection methods, data-driven (black-box) soft-sensing modeling methods and optimization techniques was carried out. The data-driven methods used for the soft-sensing modeling such as support vector machine, multiple least square support vector machine, neural network, deep learning, fuzzy logic, probabilistic latent variable models are reviewed in detail. The optimization techniques used for the estimation of model parameters such as particle swarm optimization algorithm, ant colony optimization, artificial bee colony, cuckoo search algorithm, and genetic algorithm, are also discussed. A comprehensive analysis of various soft-sensing models is presented in tabular form which highlights the important methods used in the field of fermentation. More than 70 research publications on soft-sensing modeling methods for the estimation of variables have been examined and listed for quick reference. This review paper may be regarded as a useful source as a reference point for researchers to explore the opportunities for further enhancement in the field of soft-sensing modeling.

l-Lysine is produced by a complex non-linear fermentation process. A non-linear model predictive control (NMPC) scheme is proposed to control product concentration in real time for enhancing production. However, product concentration cannot be directly measured in real time. Least-square support vector machine (LSSVM) is used to predict product concentration in real time. Grey-Wolf Optimization (GWO) algorithm is used to optimize the key model parameters (penalty factor and kernel width) of LSSVM for increasing its prediction accuracy (GWO-LSSVM). The proposed optimal prediction model is used as a process model in the non-linear model predictive control to predict product concentration. GWO is also used to solve the non-convex optimization problem in non-linear model predictive control (GWO-NMPC) for calculating optimal future inputs. The proposed GWO-based prediction model (GWO-LSSVM) and non-linear model predictive control (GWO-NMPC) are compared with the Particle Swarm Optimization (PSO)-based prediction model (PSO-LSSVM) and non-linear model predictive control (PSO-NMPC) to validate their effectiveness. The comparative results show that the prediction accuracy, adaptability, real-time tracking ability, overall error and control precision of GWO-based predictive control is better compared to PSO-based predictive control.

Due to the high degree of strong coupling and nonlinearity of marine lysozyme fermentation process, it is difficult to accurately model the mechanism. In order to achieve real‐time online measurement and effective control of bacterial concentration during fermentation, a generalized predictive control method based on least squares support vector machines is proposed. The particle swarm optimization least squares support vector machine (PSO‐LS‐SVM) model of lysozyme concentration is established by optimizing the regularization parameters and the kernel parameters of the least squares support vector machine by particle swarm optimization. To avoid the nonlinear problems in predictive control, the model is linearized at each sampling point and the generalized predictive algorithm is used to predict the bacteria concentration of lysozyme. The experimental simulation shows that the least squares support vector machine model with particle swarm optimization can achieve good prediction effect. The linearized model performs generalized predictive control, which makes the total activity of the enzyme increased from 60% to 80% and the yield improved by 30%.

The l -lysine fermentation process is a complex, nonlinear, dynamic biochemical reaction process with multiple inputs and multiple outputs. There is a complex nonlinear dynamic relationship between each state variable. Some key variables in the fermentation process that directly reflect the quality of the fermentation cannot be measured online in real-time which greatly limits the application of advanced control technology in biochemical processes. This work introduces a hybrid ICS-MLSSVM soft-sensor modeling method to realize the online detection of key biochemical variables (cell concentration, substrate concentration, product concentration) of the l -lysine fermentation process. First of all, a multi-output least squares support vector machine regressor (MLSSVM) model is constructed based on the multi-input and multi-output characteristics of l -lysine fermentation process. Then, important parameters ( , , ) of MLSSVM model are optimized by using the Improved Cuckoo Search (ICS) optimization algorithm. In the end, the hybrid ICS-MLSSVM soft-sensor model is developed by using optimized model parameter values, and the key biochemical variables of the l -lysine fermentation process are realized online. The simulation results confirm that the proposed regression model can accurately predict the key biochemical variables. Furthermore, the hybrid ICS-MLSSVM soft-sensor model is better than the MLSSVM soft-sensor model based on standard CS (CS-MLSSVM), particle swarm optimization (PSO) algorithm (PSO-MLSSVM) and genetic algorithm (GA-MLSSVM) in prediction accuracy and adaptability.

Fermentation process is a time-varying, nonlinear and multivariable dynamic coupling system. Therefore, it is difficult to directly measure the key biological variables using traditional physical sensors during the process of fermentation, which makes the monitoring and real-time control impossible. To resolve this problem, a data-driven soft sensor modeling method based on deep neural network (DNN) is proposed in this paper. This method is suitable for large amount of data and it enjoys high efficiency and robustness. At the same time, an adaptive moment estimation (Adam) algorithm is used to optimize the hyper-parameters of the DNN model, which is a technique for efficient stochastic optimization that only requires first-order gradients with little memory requirement. The consistent correlation method is used to determine the auxiliary variables of the soft sensor model. The penicillin and l-lysine fermentation processes are taken as the research object, substrate concentration, cell concentration, and product concentration are selected as a target variable. The performance of established soft sensor model is evaluated through the indexes of mean square error (MSE), root-mean-square error (RMSE), and mean absolute error (MAE). The simulation results show that the prediction performance of the soft sensor model based on DNN-Adam is good and compared with model based on stochastic gradient descent (SGD) with momentum optimization algorithm. It is verified that the proposed method can make a more accurate real-time prediction of quality variables in the fermentation process, and it has higher prediction accuracy than DNN-SGD method.