计算机应用 ›› 2021, Vol. 41 ›› Issue (7): 2113-2120.DOI: 10.11772/j.issn.1001-9081.2020061000

所属专题: 前沿与综合应用

• 前沿与综合应用 • 上一篇    下一篇

基于改进Elman神经网络的制糖企业原糖需求预测模型

李洋莹, 陈智军, 张子豪, 游兰   

  1. 湖北大学 计算机与信息工程学院, 武汉 430062
  • 收稿日期:2020-07-09 修回日期:2020-11-11 出版日期:2021-07-10 发布日期:2021-07-22
  • 通讯作者: 陈智军
  • 作者简介:李洋莹(1993-),女,湖北武汉人,硕士,主要研究方向:人工智能、数据库;陈智军(1977-),男,湖北石首人,副教授,硕士,主要研究方向:人工智能;张子豪(1998-),男,山西太原人,主要研究方向:深度学习;游兰(1978-),女,湖北武汉人,副教授,博士,主要研究方向:时空大数据、城市智能计算。
  • 基金资助:
    湖北省自然科学基金资助项目(2019CFB757);内河航运技术湖北省重点实验室基金资助项目(NHHY2017001);国家水运安全工程技术研究中心开放基金资助项目(A2019011)。

Raw sugar demand forecasting model for sugar manufacturing enterprise based on modified Elman neural network

LI Yangying, CHEN Zhijun, ZHANG Zihao, YOU Lan   

  1. School of Computer Science and Information Engineering, Hubei University, Wuhan Hubei 430062, China
  • Received:2020-07-09 Revised:2020-11-11 Online:2021-07-10 Published:2021-07-22
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Hubei Province (2019CFB757), the Hubei Provincial Key Laboratory Fund of Inland Waterway Technology (NHHY2017001), the Open Fund of the National Engineering Research Center for Water Transport Safety (A2019011).

摘要: 制糖企业采用传统算法进行原糖需求预测时忽略了时间因素,而且没有考虑行业特点,导致预测准确性有限。针对上述问题,结合制糖原材料的供需周期特点,提出一种时间特征关联的使用改进布谷鸟搜索(MCS)优化的Elman神经网络需求量预测模型TMCS-ENN。首先,通过提出自适应学习速率公式来优化Elman神经网络(ENN);其次,引入自适应寄生失败概率和自适应步长控制量公式得到MCS算法来优化ENN的权值和阈值,从而有效提高模型的局部搜索能力,避免局部最优;最后,结合制糖企业原材料购买的时间相关性和滞后性规律,基于周粒度设计数据切片,并以节假日作为重要特征训练ENN,得到预测模型TMCS-ENN。实验结果表明,以周为时间粒度的情况下,TMCS-ENN预测模型的预测精度达到93.89%。可见TMCS-ENN能够满足制糖企业原材料采购需求的预测精度,有效提高企业生产效率。

关键词: 布谷鸟搜索算法, Elman神经网络, 时间特征, 需求量预测, 时间序列预测

Abstract: The sugar manufacturing enterprises use traditional algorithm to forcast the raw sugar demand, which ignors the influence of time factors and the industry characteristics, resulting in low accuracy. To address this problem, combining with the periodic characteristics of the supply and demand of raw materials of refining sugar,a temporal feature-correlated raw sugar demand forecast model based on improved Elman Neural Network with Modified Cuckoo Search(MCS) optimization was proposed, namely TMCS-ENN. Firstly, an adaptive learning rate formula was proposed to optimize Elman Neural Network (ENN). Secondly, the adaptive parasitic failure probability and adaptive step-length control variable formula were introduced to obtain MCS algorithm to optimize the weight and threshold of ENN, which effectively improved the local search ability of the model and avoided local optimum. Finally, combining time correlation and hysteresis of raw material purchase of sugar manufacturing enterprise, the data slices were designed based on week granularity, and the ENN was trained with festivals and holidays as important features to obtain TMCS-ENN. Experimental results show that, with week as time granularity, the forecasting accuracy of the proposed TMCS-ENN forecasting model reaches 93. 89%. It can be seen that TMCS-ENN can meet the forecast accuracy demand of sugar manufacturing enterprises and effectively improve their production efficiency.

Key words: Cuckoo Search (CS) algorithm, Elman Neural Network (ENN), temporal feature, demand forecast, time series prediction

中图分类号: