WCSE

GA-BP-based Microalgae Growth Prediction Model

Abstract— The microalgae growth model is difficult to construct. In order to predict the growth status of microalgae, the temperature and light intensity data of the microalgae growth are used as input signals, and the density and average radius of algae cells are used as pre measurement to build BP neural network prediction model. At the same time, to solve the problem that the BP weights and thresholds cannot be accurately obtained, resulting in unsatisfactory prediction accuracy, genetic algorithms (GA) were used to optimize the weights and thresholds of the BP neural network to improve the prediction ability of the BP. Prediction of the average radius of algal cells, GA-BP neural network has 13% and 10% higher decision coefficients R2than BP neural network, respectively. The BP neural network optimized by genetic algorithm has higher prediction accuracy. The research methods in this paper also provide new ideas for the study of microalgae growth models.

Index Terms— Microallgae growth model , BP neural networks, Genetic algorithm, GA-BP

Liu Jiaxing, Cui Shigang, Chen miao, Duan Huabiao, Liu Yu
School of Automation and Electrical Engineering, Tianjin University of Technology and Education, CHINA

[Download]

Cite: Liu Jiaxing, Cui Shigang, Chen miao, Duan Huabiao, Liu Yu "GA-BP-based Microalgae Growth Prediction Model " Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 323-329 , Shanghai, China, 19-21 June, 2020.