Prediction of N-acetylglucosamine Content Based on RF-GA-BP Neural Network

doi:10.16182/j.issn1004731x.joss.20-FZ0335

Abstract

Abstract: In order to solve the problem that the content of N-acetylglucosamine (GlcNAc) in the process of preparing glucocosamine (GlcN) by microbial fermentation is difficult to measure online, an improved prediction algorithm based on stochastic forest algorithm, genetic algorithm and neural network algorithm is proposed. The algorithm utilizes the feature of decreasing average impurity in random forest algorithm to analyze the relevance of the input characteristics. The initial weights and thresholds of the neural networks are optimized by the genetic algorithm. A prediction model based on the RF-GA-BP algorithm is established based on the data from the fermentation process of an ammonia sugar production enterprise. The results show that the model has a good prediction ability for the content of GlcNAc. The prediction model has a fast convergence rate and a high accuracy. The average error is less than 7%, which is better than the GA-BP model and the traditional BP model.

Key words: n-acetylglucosamine, BP neural network, random forest, soft sensor

CLC Number:

TP398.1

Yang Wenfeng, Wang Yan, Ji Zhichen. Prediction of N-acetylglucosamine Content Based on RF-GA-BP Neural Network[J]. Journal of System Simulation, 2020, 32(10): 2034-2040.

References 16

[1]	Dostrovsky N R, Towheed T E, Hudson R W, et al.The effect of glucosamine on glucose metabolism in humans: a systematic review of the literature[J]. Osteoarthr Cartil (S1063-4584), 2011, 19(4): 375-380.
[2]	Igarashi M, Sakamoto K, Nagaoka I.Effect of glucosamine, a therapeutic agent for osteoarthritis, on osteoblastic cell differentiation[J]. Int J Mol Med (S1107-3756), 2011, 28(3): 373-379.
[3]	El Sayed H El Ashry, Mohamed R E Aly. Synthesis and biological relevance of N-acetylglucosamine-containing oligosaccharides[J]. Pure and Applied Chemistry (S0033-4545), 2007, 79(12): 2229-2242.
[4]	郑昭奕. 生物法生产N-乙酰氨基葡萄糖[D]. 北京: 北京化工大学, 2018.Zheng Shaoyi.Production of GlcNAc by biosynthesis[D]. Beijing: Beijing University of Chemical Technology, 2018.
[5]	沈丹丹, 曾杰, 王玥, 等. HPLC测定盐酸氨基葡萄糖有关物质与含量[J]. 中国药学杂志, 2017, 52(4): 314-318.Shen Dandan, Zeng Jie, Wang Yue, et al.Determination of Related Substances and Content of Glucosamine Hydrochloride by HPLC[J]. Chinese Pharmaceutical Journal, 2017, 52(4): 314-318.
[6]	刘升涛, 李师, 尹鸿萍, 等. 高效液相色谱法测定氨基葡萄糖中的乙酰氨基葡萄糖[J]. 药物分析杂志, 2015, 35(5): 900-905.Liu Shengtao, Li Shi, Yin Hongping, et al.Determination of acetylglucosamine in glucosamine by HPLC[J]. Chinese Journal of Pharmaceutical Analysis, 2015, 35(5): 900-905.
[7]	白书华, 况明星. 基于PSO-GA-BP神经网络的林火预测设计与研究[J]. 系统仿真学报, 2018, 30(5): 1739-1748.Bai Shuhua, Kuang Mingxing.Design and Study of Forest Fire Forecasting Based on PSO and GA-BP Neural Network[J]. Journal of System Simulation, 2018, 30(5): 1739-1748.
[8]	花亚梅, 赵贤林, 王效华, 等. 基于改进BP神经网络的厌氧发酵产气量预测模型[J]. 环境工程学报, 2016(10) : 5951-5956.Hua Yamei, Zhao Xianlin, Wang Xiaohua, et al.Prediction modeling for gas production of anaerobic fermentation based on improved BP neural network[J]. Chinese Journal of Environmental Engineering, 2016(10): 5951-5956.
[9]	朱湘灵, 宋彦, 王博, 等. 基于改进布谷鸟算法-BP神经网络的松茸发酵过程软测量建模[J]. 计算机测量与控制, 2019, 27(5): 39-43.Zhu Xiangling, Song Yan, Wang Bo, et al.Soft Sensor Modeling of Matsutake Fermentation Based on Improved CS-BPNN[J]. Computer Measurement & Control, 2019, 27(5): 39-43.
[10]	黄小龙. 基于改进BP神经网络的市际客运班线客流预测研究[D]. 哈尔滨: 哈尔滨工业大学, 2019.Huang Xiaolong.Study on Passenger Flow Prediction of Intercity Passenger Line Based on Improved BP Network[D]. Harbin: Harbin Institute of Technology, 2019.
[11]	刘丹. 基于神经网络的哈尔滨城市空气质量预测研究[D]. 哈尔滨: 哈尔滨工业大学, 2018.Liu Dan.Neural Network Based Prediction of Harbin Urban Air Quality[D]. Harbin: Harbin Institute of Technology, 2018.
[12]	王海峰, 李萍, 王博, 等. 灰狼算法优化BP神经网络的图像去模糊复原[J]. 液晶与显示, 2019, 34(10): 992-999.Wang Haifeng, Li Ping, Wang Bo, et al.Image deblurring restoration of BP neural network based on grey wolf algorithm[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(10): 992-999.
[13]	Zhang L, Wang F L, Xu B, et al.Prediction of stock prices based on LM-BP neural network and the estimation of over fitting point by RDCI[J]. Neural Computing and Applications (S0941-0643), 2018, 30(5): 1425-1444.
[14]	孙禹. 基于神经网络和蚁群算法的木材干燥过程含水率预测研究[D]. 哈尔滨: 东北林业大学, 2018.Sun Yu.Prediction of Moisture Content in Wood Drying based on Neural Network and Ant Colony Algorithm[D]. Harbin: Northeast Forestry University, 2018
[15]	周子程. 基于Stacking模型融合的电信客户信用度模型研究与设计[D]. 广州: 华南理工大学, 2011.Zhou Zicheng.The Research and Design of Telecom Customer Credit Model Based on Stacking Model Fusion[D]. Guangzhou: South China University of Technology, 2011.
[16]	李晨. 基于蚁群算法的改进型BP神经网络与应用[D]. 咸阳: 西北农林科技大学, 2018.Li Chen.Improved BP Neural Network Based on Ant Colony Algorithm and Its Application[D]. Xianyang: Northwest A&F University, 2018.