A Physical State Prediction Method Based on Reduce Order Model and Deep Learning applied in Virtual Reality

Pengbo Yu¹Qiyu Liu^1,2,3,4*Siyun Yi⁵Ming Zhu¹Yangheng Hu¹Gexiang Zhang^1,4

• ¹Chengdu University of Information Technology, Chengdu, China
• ²Northwestern Polytechnical University, Xi'an, China
• ³Chongqing Saibao Industrial Technology Research Institute Co., Ltd., Chongqing, China
• ⁴Advanced Cryptography System Security Key Laboratory of Sichuan Province, Chengdu, China
• ⁵Civil Aviation Flight University of China, Guanghan, China

The application of virtual reality (VR) in industrial training and safety emergency needs to reflect realistic changes in physical object properties. However, existing VR systems still lack fast and accurate simulation of complex, high-fidelity dynamic display of physical object evolution. To enhance the application of VR, a real-time VR visualization method is introduced, which adopts a pre-trained deep learning model to construct high-fidelity physical dynamic changes. This method firstly integrates data dimensionality reduction and temporal convolutional network (TCN) to pre-capture time-series data from numerical simulation results, and then employs Kolmogorov–Arnold Networks (KAN) to approximate nonlinear characteristics to improved Long Short-Term Memory (LSTM) network, thereby predict time-series simulation data accurately to achieves realistic and responsive dynamic displays. The experimental results of predicting time-series numerical simulation data demonstrate that the method balances computational efficiency and achieves good prediction accuracy, with Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values increased to 0.0087 and 0.0063, respectively. These studies indicate that the proposed method significantly enhances VR’s capability for realistic physical modeling, paving the way for its broader application in high-stakes industrial training and emergency training environments.