Spatio-temporal adaptive soft sensor for nonlinear time-varying and variable drifting processes based on moving window LWPLS and time difference model

An online soft sensor method for biochemical reaction process based on JS-ISSA-XGBoost

BACKGROUND

A method combining offline techniques and the just-in-time learning strategy (JITL) is proposed, because the biochemical reaction process often encounters changing features and parameters over time.

METHODS

Firstly, multiple sub-databases in the fermentation process are constructed offline by an improved fuzzy C-means algorithm and the sample data are adaptively pruned by a similarity query threshold. Secondly, an improved eXtreme Gradient Boosting (XGBoost) method is used on the online modeling stage to build soft sensor models, and the multi-similarity-driven just-in-time learning strategy is used to increase the diversity of the model. Finally, to improve the generalization of the whole algorithm, the output of the base learner is fused by an improved Stacking integration model and then the predictive output is performed.

RESULTS

Applying the constructed soft sensor model to the problem of predicting cell concentration and product concentration in Pichia pastoris fermentation process. The experimental results show that the root mean square error of the cell concentration is 0.0260, the coefficient of determination is 0.9945, the root mean square error of the product concentration is 2.6688, and the coefficient of determination is 0.9970. It shows that the proposed method has the advantages of timely prediction and high prediction accuracy, which validates the effectiveness and practicality of the method.

CONCLUSION

The JS-ISSA-XGBoost is an extensive and excellent soft measurement model that meets the practical needs for real-time monitoring of parameters and prediction of control in biochemical reactions.

A Moving Window Double Locally Weighted Extreme Learning Machine on an Improved Sparrow Searching Algorithm and Its Case Study on a Hematite Grinding Process

In this paper, a double locally weighted extreme learning machine model based on a moving window is developed to realize process modeling. To improve model performances, an improved sparrow-searching algorithm is proposed to optimize the parameters of the proposed model. The effectiveness of the proposed model and algorithm are verified by data from a hematite grinding process. The experimental results show that the proposed algorithm can significantly improve the global search ability and convergence speed in the parameter optimization of the proposed model. The proposed model can correctly estimate the grinding particle size which is expected to be applied to other complex industries.

A dynamic soft senor modeling method based on MW-ELWPLS in marine alkaline protease fermentation process

The vital state variables in marine alkaline protease (MP) fermentation are difficult to measure in real-time online, hardly is the optimal control either. In this article, a dynamic soft sensor modeling method which combined just-in-time learning (JITL) technique and ensemble learning is proposed. First, the local weighted partial least squares algorithm (LWPLS) with JITL strategy is used as the basic modeling method. For further improving the prediction accuracy, the moving window (MW) is used to divide sub-dataset. Then the MW-LWPLS sub-model is built by selecting the diverse sub-datasets according to the cumulative similarity. Finally, stacking ensemble-learning method is utilized to fuse each MW-LWPLS sub-models. The proposed method is applied to predict the vital state variables in the MP fermentation process. The experiments and simulations results show that the prediction accuracy is better compared to other methods.