- 专利标题: COMPONENT CLASSIFICATION DEVICE, METHOD FOR CLASSIFYING COMPONENTS, AND METHOD FOR TRAINING A COMPONENT CLASSIFICATION DEVICE
-
申请号: US18559274申请日: 2022-04-21
-
公开(公告)号: US20240242490A1公开(公告)日: 2024-07-18
- 发明人: Fabian Steinhart , Rolf Burmeister , Ali-Reza Rahnama , Steffen Claus , Timo Pohl , Semih Dinc , Nico Koppold , Dominik Kugler , Sebastian Plamauer , Robin Dehde , Verena Lang , Banjamin Braun
- 申请人: MTU Aero Engines AG
- 申请人地址: DE Muenchen
- 专利权人: MTU Aero Engines AG
- 当前专利权人: MTU Aero Engines AG
- 当前专利权人地址: DE Muenchen
- 优先权: DE 2021112068.3 2021.05.10 DE 2021123761.0 2021.09.14
- 国际申请: PCT/DE2022/100303 2022.04.21
- 进入国家日期: 2023-11-06
- 主分类号: G06V10/776
- IPC分类号: G06V10/776 ; G06V10/40 ; G06V10/764 ; G06V10/77 ; G06V10/82
摘要:
A component classification device for classifying components into predefined component classes, including a camera device that is configured to generate image data of a component to be classified, and a weighing device that is configured to generate weight data of the component to be classified. The component classification device includes an evaluation device that is configured to generate predefined image features from the image data according to a predefined image feature extraction method, and to supply the image data to a pretrained first neural network, and to generate bottleneck features of the image data from a predefined bottleneck layer of the first neural network. The component classification device includes a classification unit that is configured to assign at least one of multiple predetermined component classes, which describe predetermined component groups and/or components, to the component according to a predetermined classification method, based on the weight data, the image features, and the bottleneck features.
信息查询