| 362 | 0 | 244 |
| 下载次数 | 被引频次 | 阅读次数 |
为了精准预测温室蓝莓基质的温湿度变化趋势，提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象，使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合，使模型在聚焦自注意力特征的同时兼顾LSTM特征，以增强其长期记忆力。在生成初步预测序列后，再应用LSTM算法修正模型的短期注意力，提高模型的反应速度。实验结果显示，Informer-LSTM预测模型在预测准确率、鲁棒性和响应速度等方面都有显著的优势。当温度湿度等时序输入数据发生明显变化时，模型能快速捕获短期内输入数据的动态模式变化。该模型在智慧温室管理中，对辅助人工决策及实现智能化控制具有较高实际价值。
Abstract：To predict the temperature and humidity changes of blueberry substrate in greenhouses accurately, a prediction method combined Informer-LSTM algorithms was proposed for blueberry substrate temperature and humidity. Taking on-site environmental data from blueberry greenhouses as the research object, the LSTM algorithm captured the dependent relationships of time series data. It was combined with self-attention mechanisms to dynamically adjust attention weights. It enabled the model to focus on both its own attention features and LSTM features simultaneously, and the model′s memory capacity was enhanced. After initial sequence generation, the LSTM algorithm was again applied to correct the short-term attention of the model, improving its reaction speed. Experimental results demonstrated that the Informer-LSTM prediction model showed significant advantages in terms of prediction accuracy, robustness, and response speed. When sequential input data such as temperature and humidity changes significantly, the dynamic pattern changes within short-term input data were captured quickly. This model had strong practical value for assisting human decision-making and achieving intelligent control in smart greenhouse management.
[1] SYAMALADEVI R M,ANDREWS P K,DAVIES N M,et al.Storage effects on anthocyanins,phenolics and antioxidant activity of thermally processed conventional and organic blueberries[J].Journal of the science of food and agriculture,2012,92(4):916-924.
[2] 卞东超，杨发展，赵国栋，等.蓝莓温室智能水肥一体化系统构建[J].中国农机化学报，2022,43(8):55-61.BIAN D C,YANG F Z,ZHAO G D,et al.Construction of intelligent water and fertilizer integration system for blueberry greenhouse[J].Journal of Chinese agricultural mechanization,2022,43(8):55-61.
[3] 徐艺格，王兴东，刘有春，等.蓝莓产业现状及技术发展趋势分析与展望[J/OL].北方园艺，2024(8):130-136.XU Y G,WANG X D,LIU Y C,et al.Analysis and prospects on the current situation and technological development trends of blueberry industry [J].Northern horticulture,2024(8):130-136.
[4] 张真真，贺位忠.干旱胁迫下不同栽培基质蓝莓的生理响应及其抗旱性综合评价[J].浙江海洋大学学报(自然科学版),2021,40(2):181-188.ZHANG Z Z,HE W Z.The physiological responds of different culture substrates of blueberries to drought stress and the comprehensive evaluation on their drought resistance capacity[J].Journal of Zhejiang ocean university (natural science),2021,40(2):181-188.
[5] 邓捷，潘朝斌.蓝莓产业新模式：设施基质蓝莓系统[J].现代园艺，2024,47(1):81-85.DENG J,PAN C B.A new model for the blueberry industry:facility-based soilless blueberry system [J].Modern horticulture,2024,47(1):81-85.
[6] 郑昊南.平菇温室温湿度物联网智能测控系统的设计与实现[D].泰安：山东农业大学，2022.ZHENG H N.Design and implementation of an IoT-based intelligent monitoring and control system for temperature and humidity in oyster mushroom greenhouses [D].Tai′an:Shandong agricultural university,2022.
[7] 刘传龙.设施番茄温室温湿度智能调控系统研究[D].泰安：山东农业大学，2022.LIU C L.Research on an intelligent control system for temperature and humidity in facility tomato greenhouses[D].Tai′an:Shandong agricultural university,2022.
[8] GUO H,LIN X,ZHU K P.Pyramid LSTM network for tool condition monitoring[J].IEEE transactions on instrumentation and measurement,2022,71:2509511.
[9] YANG G L,TANG H,DING M L,et al.Transformer-based attention networks for continuous pixel-wise prediction[C]//2021 IEEE/CVF International Conference on Computer Vision.Piscataway:IEEE Press,2021:16249-16259.
[10] SUN Z Q,CAO S C,YANG Y M,et al.Rethinking transformer-based set prediction for object detection[C]// IEEE/CVF International Conference on Computer Vision.Piscataway:IEEE Press,2021:3591-3600.
[11] SHUAI H,WU L L,LIU Q S.Adaptive multi-view and temporal fusing transformer for 3D human pose estimation[J].IEEE transactions on pattern analysis and machine intelligence,2023,45(4):4122-4135.
[12] WU Y X,LIAO K L,CHEN J T,et al.D-former:a U-shaped Dilated Transformer for 3D medical image segmentation[J].Neural computing and applications,2023,35(2):1931-1944.
[13] ZHOU H,ZHANG S,PENG J,et al.Informer:beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2021:11106-11115.
[14] 缪月森，夏红军，黄宁洁，等.基于Informer的负荷及光伏出力系数预测[J].综合智慧能源，2024,46(4):60-67.MIU Y S,XIA H J,HUANG N J,et al.Prediction of load and photovoltaic output coefficient based on informer [J].Integrated intelligent energy,2024,46(4):60-67.
[15] 许越，李强，崔晖.基于MIC-EEMD-改进Informer的含高比例清洁能源与储能的电力市场短期电价多步预测[J].电网技术，2024,48(3):949-958.XU Y,LI Q,CUI H.Multi-step short-term electricity price forecasting in power markets with high penetration of renewable energy and energy storage based on MIC-EEMD-improved informer [J].Power system technology,2024,48(3):949-958.
[16] 许小勇，钟太勇.三次样条插值函数的构造与Matlab实现[J].兵工自动化，2006,25(11):76-78.XU X Y,ZHONG T Y.Construction and realization of cubic spline interpolation function[J].Ordnance industry automation,2006,25(11):76-78.
[17] 柳小桐.BP神经网络输入层数据归一化研究[J].机械工程与自动化，2010(3):122-123,126.LIU X T.Study on data normalization in BP neural network[J].Mechanical engineering & automation,2010(3):122-123,126.
[18] DEVLIN J,CHANG M W,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding[EB/OL].(2018-10-11)[2024-03-12].https://arxiv.org/abs/1810.04805v2.
[19] WU H,XU J,WANG J,et al.Autoformer:Decomposition transformers with auto-correlation for long-term series forecasting[C]//Proceedings of the 35th International Conference on Neural Information Processing System.New York:ACM Press,2021:22419-22430.
[20] CHEN P,ZHANG Y,CHENG Y,et al.Pathformer:multi-scale transformers with adaptive pathways for time series forecasting[EB/OL].(2024-01-16)[2024-04-20].https://arxiv.org/pdf/2402.05956.
[21] SHABANI A,ABDI A,MENG L,et al.Scaleformer:iterative multi-scale refining transformers for time series forecasting[EB/OL].(2023-02-01)[2024-04-20].https://arxiv.org/pdf/2206.04038.
[22] ZHANG Y H,YAN J C.Crossformer:transformer utilizing cross-dimension dependency for multivariate time series forecasting[C]//The Eleventh International Conference on Learning Representations.Washington:ICLR,2023:1-21.
基本信息:
DOI：10.13705/j.issn.1671-6841.2024109
中图分类号:TP183;S663.9;S628
引用信息:
[1]胡玲艳,陈鹏宇,郭占俊,等.Informer-LSTM融合算法在蓝莓基质温湿度预测中的研究与应用[J].郑州大学学报(理学版),2026,58(01):78-86.DOI:10.13705/j.issn.1671-6841.2024109.
基金信息:
辽宁省科技计划重点项目(2022020655-JH1/109); 大连市科技创新基金项目(2022JJ12SN052)
2024-06-08
2024
2025-03-20
2025
2
2025-07-04
2025-07-04
2025-07-04