Journal of Quality Technology ( IF 2.5 ) Pub Date : 2021-04-20 , DOI: 10.1080/00224065.2021.1903821 Nurettin Dorukhan Sergin 1 , Hao Yan 1
Abstract
Variational autoencoders have been recently proposed for the problem of process monitoring. While these works show impressive results over classical methods, the proposed monitoring statistics often ignore the inconsistencies in learned lower-dimensional representations and computational limitations in high-dimensional approximations. In this work, we first manifest these issues and then overcome them with a novel statistic formulation that increases out-of-control detection accuracy without compromising computational efficiency. We demonstrate our results on a simulation study with explicit control over latent variations, and a real-life example of image profiles obtained from a hot steel rolling process.
中文翻译:
通过变分自编码器获得更好的监测统计数据以进行轮廓监测
摘要
最近有人提出了变分自编码器来解决过程监控问题。虽然这些工作比经典方法显示出令人印象深刻的结果,但所提出的监测统计数据往往忽略了学习到的低维表示的不一致和高维近似中的计算限制。在这项工作中,我们首先表现出这些问题,然后用一种新颖的统计公式来克服它们,该公式在不影响计算效率的情况下提高了失控检测的准确性。我们通过显式控制潜在变化的模拟研究展示了我们的结果,以及从热钢轧制过程中获得的图像轮廓的真实示例。