PhysiNet: A Combination of Physics-based Model and Neural Network Model for Digital Twins
This work addresses the challenge of improving prediction accuracy for digital twins in engineering and simulation domains, though it appears incremental as it builds on existing hybrid modeling approaches.
The paper tackled the problem of building accurate digital twins for newly designed systems where data is scarce and physics-based models are approximate, by proposing a hybrid model (PhysiNet) that combines physics-based and neural network models, which outperformed both individual models in experiments.
As the real-time digital counterpart of a physical system or process, digital twins are utilized for system simulation and optimization. Neural networks are one way to build a digital twins model by using data especially when a physics-based model is not accurate or even not available. However, for a newly designed system, it takes time to accumulate enough data for neural network model and only an approximate physics-based model is available. To take advantage of both models, this paper proposed a model that combines the physics-based model and the neural network model to improve the prediction accuracy for the whole life cycle of a system. The proposed hybrid model (PhysiNet) was able to automatically combine the models and boost their prediction performance. Experiments showed that the PhysiNet outperformed both the physics-based model and the neural network model.