TOaCNN: Adaptive Convolutional Neural Network for Multidisciplinary Topology Optimization
Khaish Singh Chadha, Prabhat Kumar

TL;DR
This paper introduces TOaCNN, an adaptive CNN architecture that automates diverse topology optimization problems across different physics, achieving rapid and accurate design generation with minimal error.
Contribution
The paper presents a novel adaptive CNN architecture with an encoder-decoder structure and an adaptive layer, capable of handling various physics-based topology optimization tasks.
Findings
Successfully applied to compliance minimization with different loads
Generates designs closely matching open-source TO codes
Operates with negligible performance and volume fraction errors
Abstract
This paper presents an adaptive convolutional neural network (CNN) architecture that can automate diverse topology optimization (TO) problems having different underlying physics. The architecture uses the encoder-decoder networks with dense layers in the middle which includes an additional adaptive layer to capture complex geometrical features. The network is trained using the dataset obtained from the three open-source TO codes involving different physics. The robustness and success of the presented adaptive CNN are demonstrated on compliance minimization problems with constant and design-dependent loads and material bulk modulus optimization. The architecture takes the user's input of the volume fraction. It instantly generates optimized designs resembling their counterparts obtained via open-source TO codes with negligible performance and volume fraction error.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopology Optimization in Engineering · Advanced Numerical Analysis Techniques · Metaheuristic Optimization Algorithms Research
