基于SARIMA-改进RS-多步LSTM的农机装备需求组合预测模型

doi:10.13733/j.jcam.issn.20955553.2024.12.044

摘要/Abstract

摘要：

针对农机装备需求受实际农业生产和其他多种因素影响，需求数据呈现周期性、非线性等特点，难以准确预测农机需求的问题，提出一种集成SARIMA-改进RS-多步LSTM的农机装备需求预测方法。通过确定参数组合，构建季节性差分自回归滑动平均(SARIMA)模型。引入完全集合经验模态分解(CEEMDAN)、改进随机搜索(RS)算法和多步长短期记忆网络(LSTM)，构建改进RS-多步LSTM模型。将SARIMA模型和改进RS-多步LSTM模型进行最优加权组合，得到组合预测模型。以某型号农机装备进行实例验证，结果表明，所提方法能够有效预测农机装备需求的时间序列，评价指标MSE、MAE、R²分别为225.45、13.22和0.920 9。

关键词: 农机装备, 需求预测, 季节性, 多步LSTM, 模态分解

Abstract:

In view of the fact that the demand for agricultural machinery equipment is affected by actual agricultural production and many other factors, and the demand data is cyclical and non-linear, making it difficult to accurately forecast the demand for agricultural machinery, a material demand forecasting method integrating SARIMA-improved RS-multistep LSTM was proposed. The seasonal differential autoregressive moving average (SARIMA) model was constructed by determining the parameter combination. The complete set Empirical Mode decomposition (CEEMDAN), improved random search (RS) algorithm and multistep short term memory network (LSTM) were introduced to construct an improved RS-Multistep LSTM model. The optimal weighted combination of SARIMA model and improved RS multistep LSTM model was used to obtain a combined prediction model. Using a certain model of agricultural machinery equipment as an example for verification. The results have showed that the proposed method can effectively predict the time series of the demand for agricultural machinery equipment, the evaluation indicators MSE, MAE and R² are 225.45, 13.22 and 0.920 9 respectively.

Key words: agricultural machinery equipment, demand prediction, seasonal, multistep LSTM, mode decomposition

中图分类号:

F323

吕锋, 王保森, 褚慧利, 杨城, 吕玲. 基于SARIMA-改进RS-多步LSTM的农机装备需求组合预测模型[J]. 中国农机化学报, 2024, 45(12): 305-311.

Lü Feng, Wang Baosen, Chu Huili, Yang Cheng, Lü Ling. Combination prediction model of agricultural machinery equipment demand based on SARIMA-improved RS-multistep LSTM[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(12): 305-311.

参考文献

［1］　何登旭, 李艳芳, 刘向虎, 等. 基于泛函网络的非线性回归预测模型及学习算法［J］. 计算机工程与应用, 2008, 44(24): 74-77.
He Dengxu, Li Yanfang, Liu Xianghu, et al. Nonlinear regression forecast model based on functional networks and learning algorithm ［J］. Computer Engineering and Applications, 2008, 44(24): 74-77.
［2］　李之红, 申天宇, 文琰杰, 等. 基于混合机器学习框架的网约车订单需求预测与异常点识别［J］. 交通信息与安全, 2023, 41(3): 157-165, 174.
Li Zhihong, Shen Tianyu, Wen Yanjie, et al. Order demand prediction and anomalypoint identification for online carhailing orders based on hybrid machine learning framework ［J］. Journal of Transport Information and Safety, 2023, 41(3): 157-165, 174.
［3］　Maulud D, Abdulazeez A M. A review on linear regression comprehensive in machine learning ［J］. Journal of Applied Science and Technology Trends, 2020, 1(4): 140-147.
［4］　吴庚奇, 牛东晓, 耿世平, 等. 多价值链视角下基于深度学习算法的制造企业产品需求预测［J］. 科学技术与工程, 2021, 21(31): 13413-13420.
Wu Gengqi, Niu Dongxiao, Geng Shiping, et al. Product demand forecasting of manufacturing enterprises based on deep learning algorithm from the perspective of multivalue chains ［J］. Science Technology and Engineering, 2021, 21(31): 13413-13420.
［5］　武慧荣, 陈少阳, 崔淑华. 基于GM(1,1)-MLP神经网络模型的大宗货物运输需求预测［J］. 公路交通科技, 2023, 40(10): 233-240.
Wu Huirong, Chen Shaoyang, Cui Shuhua. Transportation demand forecast of bulk cargo based on GM(1,1)-MLP neural network model ［J］. Journal of Highway and Transportation Research and Development, 2023, 40(10): 233-240.
［6］　崔凯, 郭宇, 钱伟伟, 等. 基于Group-BiLSTM-LightGBM的物料配送需求量预测［J］. 组合机床与自动化加工术, 2022(8): 164-168.
Cui Kai, Guo Yu, Qian Weiwei, et al. Material distribution demand forecasting method based on Group-BiLSTM-LightGBM ［J］. Modular Machine Tool & Automatic Manufacturing Technique, 2022(8): 164-168.
［7］　王海程, 马纪颖, 张苑媛, 等. 融合时序关联动态图与常微分方程的区域间出租车需求预测［J］. 计算机应用研究, 2024, 41(3): 794-798, 860.
Wang Haicheng, Ma Jiying, Zhang Yuanyuan, et al. Interregional taxi demand forecasting based on time series correlation dynamic graph and ordinary differential equation ［J］. Application Research of Computers, 2024, 41(3): 794-798, 860.
［8］　黄国兴, 曹先怀, 钱晓飞. 一种基于随机森林的备件预测模型研究［J］. 运筹与管理, 2021, 30(10): 165-168.
Huang Guoxing, Cao Xianhuai, Qian Xiaofei. Research on spare parts prediction model based on random forest ［J］. Operations Research and Management Science, 2021, 30(10): 165-168.
［9］　付维方, 穆彩虹, 刘英杰. 基于机器学习方法的航空消耗件需求自适应预测［J］. 科学技术与工程, 2022, 22(11): 4609-4617.
Fu Weifang, Mu Caihong, Liu Yingjie. Adaptive demand prediction of aviation consumable spare parts based on machine learning method ［J］. Science Technology and Engineering, 2022, 22(11): 4609-4617.
［10］　张舜, 杨欣, 魏津瑜. 基于预防性维修的农机备件需求预测问题研究［J］. 中国农机化学报, 2020, 41(6): 225-230.
Zhang Shun, Yang Xin, Wei Jinyu. Research on forecasting of agricultural machinery spare parts demand based on preventive maintenance ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(6): 225-230.
［11］　李琼, 陈佳, 徐斌. 多产品相互制约条件下的制造业产品需求预测研究［J］. 计算机应用与软件, 2021, 38(3): 59-69.
Li Qiong, Chen Jia, Xu Bin. Demand forecasting of manufacturing products under the condition of multi product mutual restriction ［J］. Computer Applications and Software, 2021, 38(3): 59-69.
［12］　Chen X, Wang T, Liang W. General aircraft material demand forecast based on PSO-BP neural network ［J］. International Journal of Control and Automation, 2016, 9(5): 407-418.
［13］　李洁, 彭其渊, 杨宇翔. 基于SARIMA模型的广珠城际铁路客流量预测［J］. 西南交通大学学报, 2020, 55(1): 41-51.
LiJie, Peng Qiyuan, Yang Yuxiang. Passenger flow prediction for GuangzhouZhuhai intercity railway based on SARIMA model ［J］. Journal of Southwest Jiaotong University, 2020, 55(1): 41-51.
［14］　Hochreiter S, Schmidhuber J. Long shortterm memory ［J］.Neural Computation, 1997, 9(8): 1735-1780.
［15］　Yu Y, Si X, Hu C, et al. A review of recurrent neural networks: LSTM cells and network architectures ［J］. Neural Computation, 2019, 31(7): 1235-1270.
［16］　冯建英, 穆维松, 张领先, 等. 基于消费者购买意愿的农机市场需求分析［J］. 商业研究, 2008(2): 191-194.
Feng Jianying, Mu Weisong, Zhang Lingxian, et al. An empirical study on consumers purchase intention in agricultural machinery Market ［J］. Commercial Research, 2008(2): 191-194.
［17］　陈旭, 杨印生, 魏思琳. 基于向后逐步回归模型的我国农机需求特征及影响因素研究［J］. 数理统计与管理, 2017, 36(5): 774-782.
Chen Xu, Yang Yinsheng, Wei Silin. A study on characteristics and influencing factors of agricultural machinery demand in China based on backward stepwise regression model ［J］. Journal of Applied Statistics and Management, 2017, 36(5): 774-782.
［18］　张标, 张领先, 傅泽田, 等. 农户农机需求及购买行为分析——基于18省的微观调查数据实证［J］. 中国农业大学学报, 2017, 22(11): 208-223.
Zhang Biao, Zhang Lingxian, Fu Zetian, et al. Analysis on farmers requirements for agricultural machinery and purchasing behavior: Based on the survey data of 18 provinces ［J］. Journal of China Agricultural University, 2017, 22(11): 208-223.
［19］　Kuiper R. AICtype theorybased model selection for structural equation models ［J］. Structural Equation Modeling, 2022, 29(1): 151-158.
［20］　Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise ［C］. Proceedings of 2011 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2011: 4144-4147.
［21］　韩惠, 于巧, 祝义. 超参数优化对跨版本缺陷预测影响的实证研究［J］. 计算机科学与探索, 2023, 17(12):3052-3064.
Han Hui, Yu Qiao, Zhu Yi. Impact of hyperparameter optimization on crossversion defect prediction: An empirical study ［J］. Journal of Frontiers of Computer Science and Technology, 2023, 17(12): 3052-3064.

[1]	田富强, 熊友, 胡红, 王莲冀, 庄其涛, 袁瑞豪. 四川省农业机械化发展现状及建议[J]. 中国农机化学报, 2024, 45(4): 321-327.
[2]	董兆森, 张佳喜, 蒋永新, 张丽, 罗文杰, 高泽斌. 基于算数优化算法的VMD-BiLSTM模型的松土装置工况识别[J]. 中国农机化学报, 2024, 45(11): 21-27.
[3]	费焱, 王涛, 崔志超, 李怡鹏, 楼婷婷, 杨梦飞. 茭白生产机械化发展现状与对策[J]. 中国农机化学报, 2024, 45(11): 278-282.
[4]	何清燕, 应婧, 郭鹏, 王春霞, 吝祥根, 蒋昭琼. 四川省农机装备发展需求与对策[J]. 中国农机化学报, 2024, 45(10): 338-343.
[5]	轩梦辉, 赵思夏, 徐立友, 陈小亮, 李团飞. 改进VMD和LSTM的联合收割机装配质量检测方法[J]. 中国农机化学报, 2023, 44(3): 132-140.
[6]	杨小杰, 文媚, 赵茁会, 王霜. 丘陵地区农业机械化率影响因素研究——基于四川省10个典型县(市、区)的质性研究[J]. 中国农机化学报, 2023, 44(11): 224-230.
[7]	欧阳安, 樊晨龙, 赵慧慧, 董佳琪, 焦雨轩. 玉米全程机械化现状与装备研究进展[J]. 中国农机化学报, 2022, 43(6): 207-214.
[8]	刘涛;崔永正;霍静娟;. 高质量发展背景下农机装备配置效率测度及空间集聚效应研究[J]. 中国农机化学报, 2021, 42(5): 123-128.
[9]	冯雪娇;李诚诚;王俊姝;. 江西农机装备产业发展问题与对策[J]. 中国农机化学报, 2021, 42(4): 230-236.
[10]	李平;伍海君;王维薇;. 农机装备业发展研究热点动态演进规律与趋势分析[J]. 中国农机化学报, 2021, 42(3): 113-121.
[11]	姚晓娟;. 江苏农机从业人员人力资本提升对策研究[J]. 中国农机化学报, 2020, 41(9): 230-236.
[12]	周丕东;刘春波;张佩;. 贵州山地农业机械化发展现状及对策建议[J]. 中国农机化学报, 2020, 41(7): 231-236.
[13]	张舜;杨欣;魏津瑜;. 基于预防性维修的农机备件需求预测问题研究[J]. 中国农机化学报, 2020, 41(6): 225-230.
[14]	李兴远;李颖;. 基于样本熵和MFO-SVM的禽蛋蛋壳品质识别研究[J]. 中国农机化学报, 2019, 40(5): 133-139.
[15]	张桃林;. 在2019年全国农业机械化工作会议上的讲话(摘要)[J]. 中国农机化学报, 2019, 40(3): 1-6.