食品科学 ›› 2025, Vol. 46 ›› Issue (17): 271-248.doi: 10.7506/spkx1002-6630-20250410-087

• 包装贮运 • 上一篇    

蓝莓货架期PKO-CNN-BiLSTM-AT预测模型

杨慧敏,郑兴婵,刘中深,郑兴秀,王鹤霏,孙仕源   

  1. (1.东北林业大学土木与交通学院,黑龙江?哈尔滨 150040;2.黑龙江农业工程职业学院生物制药学院,黑龙江?哈尔滨 150025;3.济南市技师学院轨道交通学院,山东?济南 250101)
  • 发布日期:2025-08-18
  • 基金资助:
    黑龙江省自然科学基金项目(LH2021C016)

Predictive Modeling for the Determination of Blueberry Shelf-life Based on Combination of Pied Kingfisher Optimizer, Convolutional Neural Network, Bidirectional Long Short-term Memory and Attention Mechanism

YANG Huimin, ZHENG Xingchan, LIU Zhongshen, ZHENG Xingxiu, WANG Hefei, SUN Shiyuan   

  1. (1. College of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China;2. School of Biopharmaceutical Sciences, Heilongjiang Agricultural Engineering Vocational College, Harbin 150025, China;3. Department of Rail Transit, Jinan Technician College, Jinan 250101, China)
  • Published:2025-08-18

摘要: 为探究贮藏于不同温度条件下蓝莓的品质变化及货架期,以‘怡颗莓’蓝莓为研究对象,测定其在5、10、15、20、25 ℃条件下的可溶性固形物、质量损失率、腐败率、质地参数等多个品质指标。通过基于二元灰狼优化算法进行特征选择,筛选出7 个影响货架期的关键特征作为模型的输入变量,构建附加斑翠鸟优化算法(pied kingfisher optimizer,PKO)的卷积神经网络(convolutional neural network,CNN)-双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)-注意力机制(attention mechanism,AT)的蓝莓货架期预测模型,利用PKO对CNN-BiLSTM-AT网络进行参数化寻优,主要用以确定最优学习率、正则化参数、Attention键值及BiLSTM神经元数量。结果表明,与CNN-LSTM相比,PKO-CNN-BiLSTM-AT模型的平均绝对误差、平均绝对百分比误差、均方误差和均方根误差分别降低了76.13%、80.96%、92.03%和71.75%,决定系数增加了5.85%。说明引入PKO后的CNN-BiLSTM-AT模型显著提高了货架期的预测性能,本研究可为蓝莓在不同贮藏温度条件下的货架期制定提供理论支持。

关键词: 蓝莓品质指标;二元灰狼优化算法;斑翠鸟优化算法;深度学习模型;货架期预测

Abstract: To investigate the quality changes and shelf-life of blueberries stored under different temperature conditions, ‘Yikemei’ blueberries were evaluated for several quality indicators including soluble solid content, mass loss rate, decay incidence, and texture parameters during storage at 5, 10, 15, 20, and 25 ℃. Feature selection was performed using a binary gray wolf optimization algorithm, identifying seven key features influencing the shelf life as input variables for modeling. A shelf-life prediction model of blueberries was developed by the combined use of the pied kingfisher optimizer (PKO), convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM) and attention mechanism (AT). In the CNN-BiLSTM-AT network, parameter optimization was conducted using the PKO to determine the optimal learning rate, regularization parameters, attention key values, and the number of BiLSTM neurons. The results indicated that compared with the CNN-LSTM model, the PKO-CNN-BiLSTM-AT model exhibited 76.13%, 80.96%, 92.03%, and 71.75% reductions in mean absolute error, mean absolute percentage error, mean squared error, and root mean squared error, respectively, while the coefficient of determination (R²) increased by 5.85%. These findings demonstrated that the introduction of PKO significantly improved the predictive performance of the CNN-BiLSTM-AT model. This study provides theoretical support for the shelf-life prediction of blueberries stored under different temperature conditions.

Key words: blueberry quality indicators; binary grey wolf optimization; pied kingfisher optimizer; deep learning model; shelf-life prediction

中图分类号: