Study on Centroid Height Prediction of Non-Rigid Vehicle Based on Deep Learning Combined Model

The height of the center of gravity (<i>Z_CG</i>) is a critical parameter for evaluating vehicle safety and performance. Systematic errors arise in <i>Z_CG</i> measurement via the tilt-table test method due to unlocked suspension systems and variable sprung mass conditions, which compromise accuracy. To address this limitation, a CNN-LSTM-Attention model integrating convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and an attention mechanism is proposed. The CNN extracts spatial correlations among vehicle load transfer, suspension stiffness, and tilt angles. The LSTM captures temporal dependencies in tilt angle sequences, while the attention mechanism amplifies critical load-transfer features near the 0° region. Simulations of vehicles with unlocked suspension and variable sprung mass were conducted in Adams using tilt-table protocols. The CNN-LSTM-Attention model was trained on simulation data and validated with real-world tilt-test data under identical suspension conditions. Results demonstrate that the CNN-LSTM-Attention model achieves at least a 6.9% improvement in computational speed and at least a 0.1% reduction in prediction error compared to CNN, CNN-LSTM, and Transformer baselines. The CNN-LSTM-Attention model demonstrates valid predictive capability for <i>Z_CG</i> at 0° tilt angle. This novel approach provides a robust solution for the tilt-table test method <i>Z_CG</i> measurement, enhancing practical accuracy in vehicle dynamics parameter quantification.