航空学报 > 2026, Vol. 47 Issue (4): 232349-232349   doi: 10.7527/S1000-6893.2025.32349

固体力学与飞行器总体设计

基于WOA-BP-LSTM自编码器的CFRP薄壁C柱轴压响应预测

牟浩蕾1, 张贾2, 冯振宇1(), 白春玉3   

  1. 1.中国民航大学 科技创新研究院,天津 300300
    2.中国民航大学 安全科学与工程学院,天津 300300
    3.中国飞机强度研究所 强度与结构完整性全国重点实验室,西安 710065
  • 收稿日期:2025-05-30 修回日期:2025-07-03 接受日期:2025-07-28 出版日期:2025-07-31 发布日期:2025-07-30
  • 通讯作者: 冯振宇 E-mail:caucstructure@163.com
  • 基金资助:
    国家自然科学基金(U2433203);天津市应用基础研究多元投入基金(23JCYBJC00070);中央高校基本科研业务费专项资金(3122025084);中国民航大学研究生科研创新项目(2024YJSKC09002)

Prediction of axial crushing response for CFRP thin-walled C-columns based on WOA-BP-LSTM autoencoder

Haolei MOU1, Jia ZHANG2, Zhenyu FENG1(), Chunyu BAI3   

  1. 1.Science and Technology Innovation Research Institute,Civil Aviation University of China,Tianjin 300300,China
    2.College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China
    3.National Key Laboratory of Strength and Structural Integrity,Aircraft Strength Research Institute of China,Xi’an 710065,China
  • Received:2025-05-30 Revised:2025-07-03 Accepted:2025-07-28 Online:2025-07-31 Published:2025-07-30
  • Contact: Zhenyu FENG E-mail:caucstructure@163.com
  • Supported by:
    National Natural Science Foundation of China(U2433203);Tianjin Applied Basic Research Multi-Input Fund Project(23JCYBJC00070);Fundamental Research Funds for the Central Universities(3122025084);Graduate Scientific Research Innovation Project of Civil Aviation University of China(2024YJSKC09002)

摘要:

针对航空器货舱下部碳纤维增强复合材料(CFRP)薄壁C柱在准静态轴压下的力-位移响应预测问题,提出了一种融合鲸鱼优化算法(WOA)、反向传播(BP)神经网络和长短期记忆(LSTM)自编码器的智能预测模型(WOA-BP-LSTM自编码器模型)。通过CFRP薄壁C柱准静态轴压试验验证了有限元模型可靠性,其轴压响应评价指标误差均小于10%,基于该模型构建了包含700组变截面几何参数的力-位移响应数据集。采用LSTM自编码器实现力-位移响应特征降维与重建,随后采用BP神经网络对力-位移响应进行预测,并采用WOA进行神经网络参数优化。结果表明,LSTM自编码器实现了力-位移响应的高精度重建,测试集初始峰值压溃力和能量吸收的重建误差均小于3%,80%样本误差小于1%;优化后预测模型的力-位移响应预测精度显著提升,测试集平均绝对误差(MAE)降低17.55%,均方误差(MSE)降低31.77%,均方根误差(RMSE)降低17.47%,初始峰值压溃力和能量吸收的预测误差均小于8%,80%样本误差小于5%。该智能预测模型实现了变截面CFRP薄壁C柱轴压响应的快速精准预测并降低了计算成本,为其轴压响应研究提供了一种高效的参数-性能映射工具。

关键词: CFRP薄壁C柱, 轴压响应, LSTM自编码器, 鲸鱼优化算法, BP神经网络

Abstract:

To predict the force-displacement responses of Carbon Fiber Reinforced Plastic (CFRP) thin-walled C-columns in the aircraft sub-cargo area under quasi-static axial crushing, an intelligent prediction model (WOA-BP-LSTM autoencoder model) integrating the Whale Optimization Algorithm (WOA), Back Propagation (BP) neural network, and Long Short-Term Memory (LSTM) autoencoder was proposed. The reliability of the finite element model of CFRP thin-walled C-columns was validated through quasi-static axial crushing tests, with axial crushing response evaluation indicators showing errors within 10%. A dataset comprising 700 force-displacement response samples with variable cross-sectional geometric parameters was constructed based on the model. The LSTM autoencoder was employed for dimensionality reduction and reconstruction of the force-displacement responses. Subsequently, the BP neural network was used for force-displacement responses prediction, with WOA optimizing the neural network parameters. The results show that the LSTM autoencoder achieved high-precision reconstruction of force-displacement responses, where the errors for initial peak crushing force and energy absorption in the test set were both less than 3%, and 80% of the samples had errors within 1%. The optimized prediction model significantly improved prediction accuracy, reducing the test set’s Mean Absolute Error (MAE) by 17.55%, Mean Squared Error (MSE) by 31.77%, and Root Mean Squared Error (RMSE) by 17.47%. Prediction errors for the initial peak crushing force and energy absorption were both less than 8%, with 80% of samples showing errors within 5%. This model enables rapid and accurate prediction of axial crushing responses for variable cross-section CFRP thin-walled C-columns while reducing computational costs, providing an efficient parameter-performance mapping tool for the study of its axial crushing response.

Key words: CFRP thin-walled C-columns, axial crushing response, LSTM autoencoder, whale optimization algorithm, BP neural network

中图分类号: