Multi-model predictive control method for pichia pastoris fermentation process

Abstract

The invention discloses a multi-model predictive control method for a pichia pastoris fermentation process. The multi-model predictive control method comprises the following steps: dividing prior data into m training sample sets (sample clusters) by utilizing a fuzzy C-means clustering algorithm (FCM); for each sample cluster, a corresponding prediction model is obtained by adopting a least square support vector machine (LSSVM) and an improved particle swarm optimization (IPSO) method, then corresponding prediction controllers are respectively designed for m local prediction models, and finally, the deviation between the output of an object and the output of each sub-prediction model is calculated at each sampling moment, so that a prediction result is obtained. A multi-model fusion predictive controller is constructed based on a multi-model relative error weighting algorithm, and the pichia pastoris fermentation process is controlled by using the control method. According to the method, the adaptive capacity of the model is improved, so that the actual state of the nonlinear system is described more accurately.

Description

technical field [0001] The invention relates to the technical field of biological fermentation, in particular to a multi-model predictive control method for the fermentation process of Pichia pastoris. Background technique [0002] Proteinase K is a serine protease with high enzymatic activity and broad substrate specificity. It can be preferentially classified into hydrophobic amino acids, sulfur-containing amino acids, aromatic amino acids, C-terminally adjacent ester bonds, and peptide bonds, and is commonly used to degrade proteins to produce short peptides. Taking advantage of this characteristic, proteinase K has important applications in nucleic acid purification, silk, medicine, food, brewing and other fields. Pichia pastoris is a methanolotrophic yeast that uses methanol as the sole carbon source and energy source. It is currently the most widely used exogenous protein expression system. Compared with other existing expression systems, Pichia pastoris has obvious ...

AI Technical Summary

Problems solved by technology

Although MPC has strong robustness and is suitable for large time-delay systems, the control effect is not ideal when it is applied to the fermentation process of Pichia pastoris with strong nonlinearity and parameters changing with the change of working conditions.

Even with a feedback correction strategy, the effect of model mismatch cannot be weakened, thereby affecting the steady-state and dynamic performance of the fermentation process

Images