Predicting Multiple Numerical Solutions to the Duffing Equation Using Machine Learning

• Published in: Applied sciences Vol. 13; no. 18; p. 10359
• Main Authors: Wang, Yi-Ren, Chen, Guan-Wei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023
• Subjects: Accuracy; Algorithms; Artificial intelligence; Deep learning; Differential equations; Digital twins; Dimensional analysis; Duffing equation; Fault diagnosis; Forecasting; long short-term memory; Machine learning; Neural networks; Neurons; Optimization techniques; Oscillators; Partial differential equations; recurrent neural networks; Time series; Vibration
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app131810359

This study addresses the problem of predicting convergence outcomes in the Duffing equation, a nonlinear second-order differential equation. The Duffing equation exhibits intriguing behavior in both undamped free vibration and forced vibration with damping, making it a subject of significant interest. In undamped free vibration, the convergence result oscillates randomly between 1 and −1, contingent upon initial conditions. For forced vibration with damping, multiple variables, including initial conditions and external forces, influence the vibration patterns, leading to diverse outcomes. To tackle this complex problem, we employ the fourth-order Runge–Kutta method to gather convergence results for both scenarios. Our approach leverages machine learning techniques, specifically the Long Short-Term Memory (LSTM) model and the LSTM-Neural Network (LSTM-NN) hybrid model. The LSTM-NN model, featuring additional hidden layers of neurons, offers enhanced predictive capabilities, achieving an impressive 98% accuracy on binary datasets. However, when predicting multiple solutions, the traditional LSTM method excels. The research encompasses three critical stages: data preprocessing, model training, and verification. Our findings demonstrate that while the LSTM-NN model performs exceptionally well in predicting binary outcomes, the LSTM model surpasses it in predicting multiple solutions.