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.

翻译：本文提出了一种自适应卷积神经网络架构，可自动化处理具有不同物理本质的多样化拓扑优化问题。该架构采用编码器-解码器网络，中间包含密集层，并增设自适应层以捕捉复杂几何特征。网络利用从三套涉及不同物理机制的开放源代码拓扑优化代码获取的数据集进行训练。通过恒定载荷与设计相关载荷下的柔度最小化问题以及材料体积模量优化，验证了所提自适应CNN的鲁棒性与有效性。该架构接收用户输入的体积分数，可即时生成与开源拓扑优化代码所得结果高度相似的优化设计，且性能与体积分数误差可忽略不计。