Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (28): 240-243.DOI: 10.3778/j.issn.1002-8331.2009.28.072

• 工程与应用 • Previous Articles     Next Articles

Research on food flavor performance evaluation based on BP neural networks

SHENG Jia-chuan1,2   

  1. 1.College of Computer Science and Technology,Tianjin University,Tianjin 300072,China
    2.School of Sciences,Tianjin University of Finance and Economics,Tianjin 300200,China
  • Received:2007-11-13 Revised:2008-09-03 Online:2009-10-01 Published:2009-10-01
  • Contact: SHENG Jia-chuan

神经网络在食用香精性能评价中的应用研究

盛家川1,2   

  1. 1.天津大学 计算机科学与技术学院,天津 300072
    2.天津财经大学 理工学院,天津 300200
  • 通讯作者: 盛家川

Abstract: Neural network to food flavor performance evaluation is applied.Based on Back-Propagation(BP) neural networks,combining with the formula design information of component and proportion etc,this paper gets the performance evaluation model for food flavor.The model presents the valuable information of flavor prescription through automatic valuation.The experimental results are proved to be highly accurate,and the research and development period can be shortened.

Key words: Back-Propagation(BP) neural networks, flavor prescription, performance evaluation

摘要: 主要探讨人工神经网络在食用香精性能评价方面的应用。利用神经网络的误差反向传播(BP)算法,结合配方设计中的成分、比例等数据信息建立了食用香精性能评价模型,该模型可实现对新产品的自动评价并得到较准确的评价结果,有效缩短新产品的研发周期。

关键词: BP神经网络, 香精配方, 性能评价

CLC Number: