基于TCN-BiGRU结合自注意力机制的储粮温度预测研究

摘要/Abstract

摘要： 粮食仓储管理对于国家具有重要意义，储粮温度是判断粮食仓储安全的重要指标之一。准确地预测储粮温度并及时做出相应的防护措施能够有效降低粮食仓储损耗。针对传统储粮温度预测模型预测准确度较低的问题，本文提出了一种融合时域卷积网络（TCN）、自注意力机制（Self-Attention）和双向门控循环单元（BiGRU）的网络模型。首先通过TCN提取储粮温度数据的局部特征，并根据储粮温度数据的时序特征将自注意力机制加入网络为不同粮情特征分配权重，突出对储粮温度预测影响更大的特征，之后利用BiGRU网络学习粮情序列的双向依赖关系来获取序列中的更多信息，实现对储粮温度的预测。实验结果显示所提出的模型RMSE为0.3895，MAE为0.3281，R²为0.9912，与其他模型相比误差小，预测精度高，能够为粮仓的温度管控提供决策依据。

关键词: 储粮温度预测, 时域卷积网络, 自注意力机制, 门控循环单元网络

Abstract: Efficient grain storage management holds significant importance for a nation, with storage temperature is one of the key indicators of storage safety. Accurately predict the temperature of stored grain and make timely and appropriate protective measures can effectively reduce grain storage losses.To address the limitations of traditional prediction models, this paper introduces a novel network model integrating a time-domain convolutional network (TCN), a self-attention mechanism, and a bi-directional gated recursive unit (BiGRU). First of all, the local features of grain storage temperature data are obtained by TCN, and the Self-Attention mechanism is incorporated into the network according to the temporal characteristics of grain storage temperature to assign weights to different grain features, highlighting the features that have a greater impact on the prediction of grain storage temperature. In addition, BiGRU network is used to learn the bi-directional dependency of grain condition sequences to obtain more information in the sequences and achieve the prediction of grain storage temperature. The experimental results show that the RMSE of the model is 0.3895, the MAE is 0.3281, and the R² is 0.9912. Compared with other models, the proposed method reduces the error and improves the prediction accuracy, thus providing a solid foundation for decision-making in grain storage temperature control.

Key words: grain storage temperature prediction, TCN, self-attention mechanism, GRU

中图分类号:

S379','1');return false;" target="_blank"> S379
TP183

祝玉华, , 张钰涵, , 李智慧, , 甄彤, . 基于TCN-BiGRU结合自注意力机制的储粮温度预测研究[J]. 中国农机化学报.

Zhu Yuhua, , Zhang Yuhan, , Li Zhihui, , Zhen Tong, . Research on temperature prediction of grain storage based on TCN-BiGRU combined with self-attention mechanism[J]. Journal of Chinese Agricultural Mechanization.

参考文献

[1] 李雯雯. 国家粮食和物资储备局：“十四五”统筹推进粮食安全治理体系和治理能力现代化[J]. 中国粮食经济, 2021, (05): 30-33.

[2] 郭利进, 王永旭. 基于XGBoost优化算法的储粮温度预测研究[J]. 粮食与油脂, 2022, 35(11): 78-82.

Guo Lijin , Wang Yongxu. Research on prediction of stored grain temperature based on XGBoost optimization algorithm[J]. Cereals & Oils, 2022, 35(11): 78-82.

[3] 黄琦兰, 王涛. 基于智能算法的储粮通风过程中温度场预测[J]. 保鲜与加工, 2022, 22 (03): 30-34.

Huang Qilan, Wang Tao. Temperature field prediction of grain storage ventilation process based on intelligent algorithm[J]. Storage and Process, 2022, 22(03): 30-34.

[4] 王赫, 曹毅, 李玉, 等. 基于改进粒子群算法的平房仓粮温BP神经网络预测模型建立[J]. 中国粮油学报, 2023, 38(06): 113-118.

Wang He, Cao Yi, Li Yu, et al. Prediction model of grain temperature in warehouse based on improved particle swarm optimization BP neural network [J]. Journal of the Chinese Cereals and Oils Association, 2023, 38(06): 113-118.

[5] 苑江浩, 郑丹, 孟祥雪, 等. 粮情监测预警技术研究进展[J]. 中国粮油学报, 2022, 37(11): 19-26.

Yuan Jianghao, Zheng Dan, Meng Xiangxue, et al. Research progress of grain monitoring and early warning technology [J]. Journal of the Chinese Cereals and Oils Association, 2022, 37(11): 19-26.

[6] 苑江浩, 常青, 李燕羽, 等. 神经网络在粮食储藏领域中的应用概述[J]. 中国粮油学报, 2021, 36(02): 155-161.

Yuan Jianghao, Chang Qing, Li Yanyu, et al. Application of neural network in the field of grain storage[J]. Journal of the Chinese Cereals and Oils Association, 2021, 36(02): 155-161.

[7] 高松, 宋辉. 基于BP神经网络方法的高大平房仓温度场预测研究[J]. 粮油食品科技, 2015, 23(01): 94-97.

Gao Song, Song Hui. Prediction of the temperature field of high & large warehouse based on BP neural network[J]. Science and Technology of Cereals,Oils and Foods, 2015, 23(01): 94-97.

[8] 冯鸿超. 基于温湿度粮情的储粮安全风险预警模型及应用[D]. 郑州：河南工业大学, 2019.

Feng Hongchao. Pre-warning model of stored grain safety risk based on temperature and humidity and its application [D]. Zhengzhou: Henan University of Technology, 2019.

[9] 蒋思玮, 孙妍, 陈静, 等. 改进粒子群优化GRU网络的储粮温度预测方法[J]. 计算机与数字工程, 2023, 51 (05): 1036-1041+1156.

Jiang Siwei, Sun Yan, Chen Jing, et al. Grain storage temperature prediction method based on GRU network optimized by improved particle swarm optimization[J]. Computer & Digital Engineering, 2023, 51 (05): 1036-1041+1156.

[10] Xie Y, Zeng P, Chen J. Hybrid attention-based improved temporal convolutional BiGRU approach for short-term load forecasting[C]//Journal of Physics: Conference Series. IOP Publishing, 2024, 2703(1): 012052.

[11] Song Y, Luktarhan N, Shi Z, et al. TGA: a novel network intrusion detection method based on TCN, BiGRU and attention mechanism[J]. Electronics, 2023, 12(13): 2849.

[12] Limouni T, Yaagoubi R, Bouziane K, et al. Accurate one step and multistep forecasting of very short-term PV power using LSTM-TCN model[J]. Renewable Energy, 2023, 205: 1010-1024.

[13] 吴晓丹, 范波, 王建祥, 等. 基于VMD-TCN-Attention的锂电池寿命预测[J]. 电源技术, 2023, 47 (10): 1319-1325.

Wu Xiaodan, Fanbo, Wang jianxiang Life prediction of lithium battery based on VMD-TCN-Attention[J]. Chinese Journal of Power Sources, 2023, 47 (10): 1319-1325.

[14] Yang L, Wang S, Chen X, et al. High-fidelity permeability and porosity prediction using deep learning with the self-attention mechanism[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 34 (7):3429 - 3443.

[15] 刘森, 刘美, 贺银超, 等. 基于DCNN网络及Self-Attention-BiGRU机制的轴承剩余寿命预测[J]. 机电工程, 2024, 41 (05): 786-796.

Liu Sen, Liu Mei, He Yinchao, et al. Residual life prediction of bearings based on DCNN network and Self-Attention-BiGRU mechanism[J]. Journal of Mechanical & Electrical Engineering, 2024, 41 (05): 786-796.

[16] Zhao Z, Yun S, Jia L, et al. Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features[J]. Engineering Applications of Artificial Intelligence, 2023, 121: 105982.

[17] Mahjoub S, Chrifi-Alaoui L, Marhic B, et al. Predicting energy consumption using LSTM, multi-layer GRU and drop-GRU neural networks[J]. Sensors, 2022, 22(11): 4062.

[18] Zhang Y, Zhang L, Sun D, et al. Short-Term Wind Power Forecasting Based on VMD and a Hybrid SSA-TCN-BiGRU Network[J]. Applied Sciences, 2023, 13(17): 9888.

[19] 邹智, 吴铁洲, 张晓星, 等. 基于贝叶斯优化CNN-BiGRU混合神经网络的短期负荷预测[J]. 高电压技术, 2022, 48 (10): 3935-3945.

Zou Zhi, Wu Tiezhou, Zhang Xiaoxing, et al. Short-term load forecast based on bayesian optimized CNN-BiGRU hybrid neural networks[J]. High Voltage Engineering, 2022, 48 (10): 3935-3945.

[20] 张明跃, 周慧玲, 钱荣荣, 等. 粮堆温度预测插值算法的研究[J]. 中国粮油学报, 2021, 36(12): 136-143.

Zhang Mengyue, Zhou Huiling, Qian Rongrong, et al. Prediction and interpolation algorithm of temperature of grain bulk[J]. Journal of the Chinese Cereals and Oils Association, 2021, 36(12): 136-143.

[21] Lin Z, Yue W, Huang J, et al. Ship trajectory prediction based on the TTCN-attention-GRU model[J]. Electronics, 2023, 12(12): 2556.

[22] 倪凌. 基于双向长短期记忆网络的医院电子病历数据挖掘[J]. 计算机应用与软件, 2023, 40(06): 70-76.

Ni Ling. Data mining for electronic medical records of hospital based on Bidirectional long short term memory network[J]. Computer Applications and Software, 2023, 40(06): 70-76.