Data-driven synchronization-avoiding algorithms in the explicit distributed structural analysis of soft tissue
This work addresses computational bottlenecks in distributed structural analysis for biomedical engineering applications, representing an incremental improvement.
The authors tackled the computational inefficiency of explicit finite element methods in soft tissue analysis by developing a data-driven framework using an encoder-decoder LSTM network to predict synchronized displacements, reducing inter-processor communication and achieving improved efficiency in numerical experiments.
We propose a data-driven framework to increase the computational efficiency of the explicit finite element method in the structural analysis of soft tissue. An encoder-decoder long short-term memory deep neural network is trained based on the data produced by an explicit, distributed finite element solver. We leverage this network to predict synchronized displacements at shared nodes, minimizing the amount of communication between processors. We perform extensive numerical experiments to quantify the accuracy and stability of the proposed synchronization-avoiding algorithm.