Work

Chaotic Vibration Prediction of a Laminated Composite Cantilever Beam

Year: 2025

Type: article

Abstract: The deep learning method of the recurrent neural network (RNN) is applied to predict the chaotic vibrations of a laminated composite cantilever beam. The RNN model converts time series data into a multi-step supervised learning format and normalizes it using MinMaxScaler. The cantilever structure is subjected to an evenly distributed load, and a series of chaotic vibrations are observed corresponding to different amplitudes and angular velocities of the load. Then, the RNN data-driven model is applied to predict chaotic vibrations, and the chaotic vibration prediction of RNN is evaluated. The prediction results are primarily evaluated using two metrics: mean absolute error (MAE) and root mean square error (RMSE). The analysis results show that the maximum MAE is 0.041 and the maximum RMSE is 0.067. Even under perturbed initial conditions, the RNN model maintained high prediction accuracy, with a maximum MAE of 0.022 and RMSE of 0.038, highlighting its robustness and reliability in predicting chaotic vibrations. The error analysis indicates that the RNN accurately predicts chaotic vibrations with a high degree of precision.

Source: Applied Sciences

DOI: 10.3390/app15126403

Authors: Xudong Li, Lin Sun, Xiaopei Liu, Yili Duo

Institution: Liaoning Shihua University

Language: English

Topic: Structural Health Monitoring Techniques

Subfield: Civil and Structural Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funder: National Natural Science Foundation of China