中文核心期刊
CSCD来源期刊
中国科技核心期刊
RCCSE中国核心学术期刊
重庆交通大学学报（自然科学版）

重庆交通大学学报（自然科学版） ›› 2026, Vol. 45 ›› Issue (6): 97-106.DOI: 10.3969/j.issn.1674-0696.2026.06.12

• 交通运输+人工智能 • 上一篇    

基于SSA-CNN-Attention-LSTM模型的龙头山船闸农产品货运量预测

彭军1,2,3,4，胡乐林2,3,4，周强强3,5，邹慧仪1   

  1. (1. 江西农业大学 计算机与信息工程学院，江西 南昌 330045；2. 江西农业大学 软件学院，江西 南昌 330045； 3. 江西省高等学校农业信息技术重点实验室，江西 南昌 330045； 4. 南昌市数字农业与智能感知协同创新重点实验室， 江西 南昌 330045； 5. 江西师范大学 人工智能学院，江西 南昌 330045)
  • 收稿日期:2026-01-05 修回日期:2026-03-05 发布日期:2026-07-10
  • 作者简介:彭军（1981—），男，江西永新人，副教授，主要从事农业信息化、交通运输方面的研究。E-mail：totato@126.com 通信作者：胡乐林（1997—），男，江西临川人，硕士研究生，主要从事农业信息化、交通运输方面的研究。E-mail：15079420053@163.com
  • 基金资助:
    江西省自然科学基金项目(20232BAB202021)

Agricultural Product Freight Volume Prediction of Longtoushan Ship Lock Based on SSA-CNN-Attention-LSTM Model

PENG Jun1,2,3,4, HU Lelin2,3,4, ZHOU Qiangqiang3,5, ZOU Huiyi1   

  1. (1. Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, China; 2. Xinjiang Key Laboratory of Green Construction and Smart Traffic Control of Transportation Infrastructure, Xinjiang University, Urumqi 830017, Xinjiang, China)
  • Received:2026-01-05 Revised:2026-03-05 Published:2026-07-10

PDF

摘要： 农产品运输具有显著的时效性特征，船闸调度部门需提前掌握未来农产品货运规模，以制定合理的过闸调度计划，因此农产品货运量的精准预测对于提升过闸效率具有重要意义。赣江农产品货运量具有波动剧烈、模式复杂的特点，当前预测方法难以捕捉其深层的非线性与复杂时序规律。因此，提出了一种融合注意力机制、麻雀搜索算法（SSA）、卷积神经网络（CNN）和长短期记忆网络（LSTM）的混合模型——SSA-CNN-Attention-LSTM。首先，利用CNN捕捉数据中的局部空间特征，并结合LSTM提取时序依赖关系，并引入了注意力机制对LSTM隐藏状态进行加权处理，进而提升模型在复杂波动情境下的关键信息捕捉能力。此外，采用了SSA对模型中的超参数进行自适应优化，以提高算法在复杂预测场景中的适应性与收敛效率。在性能评估中，对比了CNN、RNN、MLP及Transformer为架构的多种代表性方法。结果表明：提出的模型在EMA、EMAP、ERMS三项指标分别为471.26 t、0.114 30、628.81 t，均优于其他模型。预测结果显示，该组合模型能有效提高水路农产品货运量预测的准确性，有利于船闸提前做好调度计划，为赣江流域港航管理和发展决策提供可靠数据支持。

关键词: 交通运输工程;农产品货运量；SSA-CNN-Attention-LSTM；混合模型；时序预测；注意力机制；麻雀搜索算法

Abstract: Agricultural product transportation has significant timeliness characteristics. The ship lock scheduling department needs to grasp the future scale of agricultural product freight in advance in order to formulate a reasonable gate clearance dispatch plan. Therefore, accurate prediction of agricultural product freight volume is of great significance for improving gate clearance efficiency. The agricultural freight volume in the Ganjiang River exhibits characteristics such as intense fluctuations and complex patterns, and current prediction methods are difficult to capture its deep nonlinearity and complex temporal patterns. To address this issue, a hybrid model integrating attention mechanism, sparrow search algorithm (SSA), convolutional neural network (CNN), and long short-term memory network (LSTM), namely SSA-CNN-Attention-LSTM, was proposed. First, CNN was employed to capture local spatial features from the data, while LSTM was combined to extract temporal dependency relationships. An attention mechanism was further introduced to assign weights to the hidden states of LSTM, thereby enhancing the proposed model’s ability to capture key information in complex fluctuation scenarios. In addition, SSA was adopted to adaptively optimize the hyperparameters of the proposed model, improving its adaptability and convergence efficiency in complex forecasting scenarios. In the performance evaluation, multiple representative methods based on CNN, RNN, MLP, and Transformer architectures were compared. The results show that the proposed model outperforms other models in three indicators, that is EMA, EMAP and ERMS, which are 471.26, 0.114, 30, and 628.81, respectively. The prediction results indicate that the proposed hybrid model can effectively improve the prediction accuracy of waterway agricultural product freight volume, which is beneficial for the ship lock to make advance scheduling plans and provide reliable data support for port and navigation management and development decisions in the Ganjiang River Basin.

Key words: traffic and transportation engineering; agricultural product freight volume; SSA-CNN-attention-LSTM; hybrid model; time series prediction; attention mechanism; sparrow search algorithm

中图分类号: