Article: Enhancing the efficiency of 4D printing design through time-series prediction by dense-LSTM crossed network Journal: International Journal of Advanced Mechatronic Systems (IJAMECHS) 2025 Vol.12 No.4 pp.209 - 221 Abstract: This paper proposes a deep learning-based approach to predict the deformation of 4D-printed hydrogel models with varying lengths, aiming to improve the efficiency of the design process. A voxel-based modeling method is used to create hydrogel models in Abaqus, and their deformation data is obtained through finite element analysis (FEA). A mixed dataset is then constructed by mapping each model's expansion rate sequence to its corresponding deformation outcome. Based on this dataset, a novel deep learning architecture called dense-LSTM crossed network (DSCN) is introduced and trained. The trained model enables direct prediction of deformation results from the initial model parameters, reducing reliance on time-consuming simulation. Experimental results show that the proposed method shortens the model design verification process by 1.5–2%, thus enhancing the overall efficiency of 4D printing design. This study demonstrates the potential of combining intelligent modeling with deep learning to streamline additive manufacturing workflows involving shape-morphing materials. Inderscience Publishers - linking academia, business and industry through research

Title: Enhancing the efficiency of 4D printing design through time-series prediction by dense-LSTM crossed network

Authors: Yifan Xu; Mengtao Wang; Hidemitsu Furukawa; Zhongkui Wang; Qi Li; Lin Meng

Addresses: Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan ' Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan ' Yamagata University, 1-4-12 Kojirakawa-machi, Yamagata 990-8560, Japan ' Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan ' Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan ' Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan

Abstract: This paper proposes a deep learning-based approach to predict the deformation of 4D-printed hydrogel models with varying lengths, aiming to improve the efficiency of the design process. A voxel-based modeling method is used to create hydrogel models in Abaqus, and their deformation data is obtained through finite element analysis (FEA). A mixed dataset is then constructed by mapping each model's expansion rate sequence to its corresponding deformation outcome. Based on this dataset, a novel deep learning architecture called dense-LSTM crossed network (DSCN) is introduced and trained. The trained model enables direct prediction of deformation results from the initial model parameters, reducing reliance on time-consuming simulation. Experimental results show that the proposed method shortens the model design verification process by 1.5–2%, thus enhancing the overall efficiency of 4D printing design. This study demonstrates the potential of combining intelligent modeling with deep learning to streamline additive manufacturing workflows involving shape-morphing materials.

Keywords: 4D printing; deep learning; hydrogel; recurrent neural network; RNN; voxelisation design; mixed dataset.

DOI: 10.1504/IJAMECHS.2025.149353

International Journal of Advanced Mechatronic Systems, 2025 Vol.12 No.4, pp.209 - 221

Received: 11 Dec 2024
Accepted: 18 Mar 2025
Published online: 27 Oct 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Enhancing the efficiency of 4D printing design through time-series prediction by dense-LSTM crossed network

Keep up-to-date