A HIERARCHICAL MACHINE LEARNING WORKFLOW FOR OBJECT DETECTION OF ENGINEERING COMPONENTS
A HIERARCHICAL MACHINE LEARNING WORKFLOW FOR OBJECT DETECTION OF ENGINEERING COMPONENTS
复制标题
用于工程组件目标检测的分层机器学习工作流程
DOI：
10.1017/pds.2023.21
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Kent L
中科院分区：
文献类型：
--
作者：
Kent L
机器学习（ML）技术在工程领域的应用和价值越来越大。对象检测方法，通过机器学习系统从呈现给它的图像中识别对象，已经证明了在许多应用中搜索和检索以及同步物理/数字版本控制的前景。然而，随着系统考虑的对象数量的增加，检测的准确性往往会下降，再加上非常高的训练时间和计算开销，使得广泛使用变得不可行。这项工作提出了一个分层的机器学习工作流程，该工作流程利用工程组件的预先存在的分类结构和丰富的数字模型（CAD）来简化训练并提高准确性。通过两层结构，该方法可以将精度提高到90%，节省75%的时间，并大大提高了灵活性和可扩展性。虽然需要进一步改进以提高检测的鲁棒性和研究可扩展性，但该方法显示出在工程中提高目标检测技术可行性的重大承诺。
Machine Learning (ML) techniques are showing increasing use and value in the engineering sector. Object Detection methods, by which an ML system identifies objects from an image presented to it, have demonstrated promise for search and retrieval and synchronised physical/digital version control, amongst many applications.However, accuracy of detection often decreases as the number of objects considered by the system increases which, combined with very high training times and computational overhead, makes widespread use infeasible.This work presents a hierarchical ML workflow that leverages the pre-existing taxonometric structures of engineering components and abundant digital models (CAD) to streamline training and increase accuracy. With a two-layer structure, the approach demonstrates potential to increase accuracy to >90%, with potential time savings of 75% and greatly increased flexibility and expandability.While further refinement is required to increase robustness of detection and investigate scalability, the approach shows significant promise to increase feasibility of Object Detection techniques in engineering.
影响因子：
2.4
作者：
Alex Burnap;J. Hartley;Yanxin Pan;Rich Gonzalez;P. Papalambros
通讯作者：
Alex Burnap;J. Hartley;Yanxin Pan;Rich Gonzalez;P. Papalambros
区分伪影：评估卷积神经网络的饱和点
DOI：
10.1016/j.procir.2021.05.089
发表时间：
2021
期刊：
ArXiv
影响因子：
--
作者：
Ric Real;J. Gopsill;D. Jones;C. Snider;B. Hicks
通讯作者：
B. Hicks
通过计算机辅助设计存储库的代理模型卷积神经网络实现设计民主化
DOI：
10.1017/dsd.2020.93
发表时间：
2020
期刊：
Proceedings of the Design Society: DESIGN Conference
影响因子：
--
作者：
J. Gopsill;S. Jennings
通讯作者：
S. Jennings