一种LSTM神经网络和卡尔曼滤波相结合的复合材料承载预测方法

doi:10.7523/j.issn.2095-6134.2021.03.011

中国科学院大学学报 ›› 2021, Vol. 38 ›› Issue (3): 374-381.DOI: 10.7523/j.issn.2095-6134.2021.03.011

一种LSTM神经网络和卡尔曼滤波相结合的复合材料承载预测方法

肖亚楠^1,2, 周伟³, 崔杰¹, 刘亭亭¹, 肖灵¹

1. 中国科学院声学研究所, 北京 100190;
2. 中国科学院大学电子电气与通信工程学院, 北京 100049;
3. 河北大学质量技术监督学院, 河北保定 071002

收稿日期:2020-01-10 修回日期:2020-05-12 发布日期:2021-05-17
通讯作者: 肖亚楠
基金资助:
国家重点研发计划项目（2016YFB0201100）资助

A load forecast method of composite materials based on LSTM network and Kalman filtering

XIAO Ya^1,2, ZHOU Wei³, CUI Jie¹, LIU Tingting¹, XIAO Ling¹

1. Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, School of Electronic, Electrical and Communication Engineering, Beijing 100049, China;
3. School of Quality and Technical Supervision, Hebei University, Baoding 071002, Hebei, China

Received:2020-01-10 Revised:2020-05-12 Published:2021-05-17

摘要/Abstract

摘要： 复合材料是基于多种材料组分的不同组合方式经由相应工艺加工而成的新型材料，近年来凭借其优良的综合性能被广泛应用于交通、建筑等领域，其试验分析结果有时候与经验分析存在较大误差，从而建立可信的分析方法对复合材料承载性能进行验证具有十分重要的理论意义。基于长短期记忆（long short term memory，LSTM）深度学习网络模型的预测精度受数据序列长度影响，提出一种LSTM神经网络和Kalman滤波相结合的复合材料承载预测方法，既可以克服训练数据序列长度对传统LSTM神经网络的影响，又使得Kalman滤波可以从输入数据中学习。仿真结果表明，该方法可以获得优良的预测性能：LSTM-KF模型的承载预测误差将LSTM模型的预测误差从0.033 0 kN减小到0.016 0 kN，降幅为51.52%。

关键词: 复合材料, 承载预测, 长短期记忆神经网络, 卡尔曼滤波

Abstract: Composite material is a new type of material based on different combinations of various material components. It has been widely used in transportation, construction and other fields because of its excellent comprehensive properties during recent years. Despite of the large errors between experimental analysis and empirical analysis result sometimes,it is of great theoretical significance to establish a credible theoretical analysis to verify the bearing properties of composite materials.Considering that the forecast accuracy is affected by the length of the data sequence when using the memory characteristics of LSTM to predict the load, a load forecast method of composite materials combined with LSTM network and Kalman filtering is proposed. The model can learn from the data avoiding the dependence of traditional Kalman filtering on the dynamic model, at the same time the influence of training data sequence length on traditional LSTM can be overcome to some extent.The results show that the method proposed in this paper can obtain more excellent predictive performance:(1)The performance of LSTM-KF is better than the independent LSTM, and the prediction curve of LSTM-KF is closer to the actual load value;(2)The prediction error of LSTM-KF reduces that of LSTM from 0.033 0 kN to 0.016 0 kN, a decrease of 51.52%.

Key words: composite materials, load forecast, long-short term memory network, Kalman filter

中图分类号:

TB33

肖亚楠, 周伟, 崔杰, 刘亭亭, 肖灵. 一种LSTM神经网络和卡尔曼滤波相结合的复合材料承载预测方法[J]. 中国科学院大学学报, 2021, 38(3): 374-381.

XIAO Ya, ZHOU Wei, CUI Jie, LIU Tingting, XIAO Ling. A load forecast method of composite materials based on LSTM network and Kalman filtering[J]. Journal of University of Chinese Academy of Sciences, 2021, 38(3): 374-381.

参考文献

[1] 石文静,高峰,柴洪友. 复合材料在航天器结构中的应用与展望[J]. 宇航材料工艺, 2019, 49(4):1-6.
[2] 门永林,楚永萍,冯遵委. 纤维增强复合材料在转向架上的应用研究[J]. 铁道机车车辆, 2019, 39(3):92-94, 100.
[3] 王胜光,张永利,毕孝法,等. 碳纤维复合材料在轨道交通车辆空调机壳体上的应用[J]. 城市轨道交通研究, 2019, 22(5):188-191.
[4] 牟文珺,桂洪斌. 复合材料基座在船舶设备振动传递控制中的应用[J]. 舰船科学技术, 2019, 41(2):50-55.
[5] 孙佳伟,傅少君,叶建乔,等. UHTCC三点弯曲梁裂纹扩展的数值模拟研究[J]. 水利水电技术, 2019, 50(5):136-142.
[6] 徐世烺,陈超,李庆华,等. 超高韧性水泥基复合材料动态压缩力学性能的数值模拟研究[J]. 工程力学, 2019, 36(9):50-59.
[7] 林皋,张鹏冲. 板结构计算模型的新发展[J]. 计算力学学报, 2019, 36(4):429-440.
[8] 贾利勇,廖斌斌,于龙,等. 基于Puck理论的复合材料层合板横向剪切失效分析[J]. 复合材料学报, 2019, 36(10):2286-2293.
[9] 杨万友,王家序,黄彦彦,等. 热载荷作用下颗粒增强复合材料温升分布数值模拟[J]. 上海交通大学学报, 2019, 53(11):1342-1351.
[10] 惠新育,许英杰,张卫红,等. 平纹编织SiC/SiC复合材料多尺度建模及强度预测[J]. 复合材料学报, 2019, 36(10):2380-2388.
[11] Smagulova K, James A P. A survey on LSTM memristive neural network architectures and applications[J]. The European Physical Journal Special Topics, 2019, 228(10):2313-2324.
[12] 周永生. 基于LSTM神经网络的PM_2.5预测[D]. 长沙:湖南大学, 2018.
[13] Gers F A, Schtmidhuber E. LSTM recurrent networks learn simple context-free and context-sensitive languages[J]. IEEE Transactions on Neural Networks, 2001, 12(6):1333-1340.
[14] Greff K, Srivastava R K, Koutník J, et al. LSTM A search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10):2222-2232.
[15] Alahi A, Goel K, Ramanathan V, et al. Social LSTM:Human trajectory prediction in crowded spaces[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas:IEEE, 2016:961-971.
[16] Turkoglu M, Hanbay D, Sengur A. Multi-model LSTM-based convolutional neural networks for detection of apple diseases and pests[J]. Journal of Ambient Intelligence and Humanized Computing, 2019:1-11.
[17] Qi Y T, Zhou Z N, Yang L L, et al. A decomposition-ensemble learning model based on LSTM neural network for daily reservoir inflow forecasting[J]. Water Resource Management, 2019, 33:4123-4139.
[18] 杨甲甲,刘国龙,赵俊华,等. 采用长短期记忆深度学习模型的工业负荷短期预测方法[J]. 电力建设, 2018, 39(10):20-27.
[19] 杨国田,张涛,王英男,等. 基于长短期记忆神经网络的火电厂NOx排放预测模型[J]. 热力发电, 2018, 47(10):12-17.
[20] 许宁,徐昌荣. 改进型LSTM变形预测模型研究[J]. 江西理工大学学报, 2018, 39(5):45-51.
[21] Kalman R E. A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering,1960, 82(1):35-45.
[22] Haykin S. Adaptive Filter Theory, Fifth Edition[M]. Andhra Pradesh:Department of Electronics and Communication Engineering GMR Institute of Technology Rajam, 2014:409-435.

一种LSTM神经网络和卡尔曼滤波相结合的复合材料承载预测方法

A load forecast method of composite materials based on LSTM network and Kalman filtering

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	张杰, 李婧华, 胡超. 基于容积卡尔曼滤波的卫星导航定位解算方法[J]. 中国科学院大学学报, 2021, 38(4): 532-537.
[2]	宋旭鸣, 沈逸飞, 石远明. 基于深度学习的智能移动边缘网络缓存[J]. 中国科学院大学学报, 2020, 37(1): 128-135.
[3]	李静, 廖强. 新型纳米复合材料Cu/SiO₂的热特性及相变特性的分子动力学研究[J]. 中国科学院大学学报, 2018, 35(2): 248-253.
[4]	刘星, 吕孝雷. 基于卡尔曼滤波的PS-InSAR地表形变预测方法[J]. 中国科学院大学学报, 2017, 34(6): 743-750.
[5]	王泽人, 马荣华, 段洪涛, 张玉超, 齐琳. 基于集合卡尔曼滤波的太湖叶绿素a浓度同化试验系统设计及实现[J]. 中国科学院大学学报, 2013, 30(5): 628-636.
[6]	郑飞, 朱江. 一个新的大样本ENSO集合预报系统的发展与检验[J]. 中国科学院大学学报, 2010, 27(3): 420-431.