发表机构
Pukyong National University; DRB Co., Ltd.（国立釜庆大学; DRB株式会社）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对部分逆向设计数据获取昂贵的问题，提出CoNN-AL框架，结合流式主动学习与协作神经网络，在汽车玻璃导槽数据集上以2.3%标签达到近全数据性能，显著减少标注需求。
AI 中文摘要
工程中的逆向设计常常面临一个简单的问题：每个带标签的训练样本都必须通过昂贵的仿真来生成，因此构建大规模数据集既缓慢又昂贵。本研究针对部分逆向设计中的这一问题展开，在部分逆向设计中，仅指定部分设计变量，其余变量需被推断以达到目标性能值。我们提出了CoNN-AL，一个用于数据高效部分逆向设计的框架，它将流式主动学习添加到带有去噪自编码器的协作神经网络（CoNN-DAE）中。该模型通过蒙特卡洛dropout估计预测不确定性，并利用该不确定性实时决定哪些传入的候选样本值得标注，从而将有限的标注预算花费在最具信息量的设计上。我们在一个包含超过900,000个独特仿真设计的真实世界汽车玻璃导槽数据集上验证了该框架。仅使用20,000个主动选择的标签，约占训练池的2.3%，CoNN-AL在所有缺失变量水平上达到了0.967至0.982的R平方值，接近基于更多数据训练的上限模型。在更困难的缺失变量水平上，与随机采样相比，CoNN-AL以少30%至40%的标签达到了至少0.95的R平方值，并且在最具挑战性的水平上，是本研究唯一达到0.98 R平方值的策略。连同这项工作，我们公开发布了该数据集，以支持数据驱动设计的未来研究。
英文摘要
Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large dataset is slow and costly. This study addresses that problem for partial inverse design, where only some design variables are specified and the rest must be inferred to reach a target performance value. We propose CoNN-AL, a framework for data-efficient partial inverse design that adds stream-based active learning to the Cooperative Neural Network with Denoising Autoencoder (CoNN-DAE). The model estimates predictive uncertainty through Monte Carlo dropout and uses it to decide, in real time, which incoming candidate samples are worth labeling, so the limited labeling budget is spent on the most informative designs. We validate the framework on a real-world automotive glass run channel dataset of more than 900,000 unique simulated designs. With only 20,000 actively selected labels, about 2.3% of the training pool, CoNN-AL reaches R-squared values of 0.967 to 0.982 across all missing-variable levels, approaching the upper-bound models trained on far more data. It reaches R-squared of at least 0.95 with 30 to 40% fewer labels than random sampling at the more difficult missing-variable levels and, at the most challenging level, is the only strategy in this study to reach R-squared of 0.98. Together with this work, we publicly release the dataset to support future research on data-driven design.
Comments21 pages, 12 figures, 3 tables
