Recursive quality optimization of a smart forming tool under use of perception based hybrid datasets for training of a deep neural network
JSON Export
{
"updated": "2022-01-31T14:56:37.436636+00:00",
"id": "1202",
"metadata": {
"id": "1202",
"status": "published",
"_files": [
{
"description": "This archive contains the training and validation datasets, including the trained neural network of the SIMKI-Project of Hochschule-Aalen.",
"size": 17828319,
"key": "220122_SIMKI_Training_Datasets.zip",
"checksum": "md5:a5233cc5e8b5d5fb201611175f5e4b61"
}
],
"contributors": [
{
"givennames": "Sebastian",
"familyname": "Feldmann",
"affiliations": [
"University of Applied Science - Aalen, Beethovenstr. 1, 73430 Aalen, Germany"
],
"email": "Sebastian.Feldmann@HS-Aalen.de"
},
{
"givennames": "Michael",
"familyname": "Schmiedt",
"affiliations": [
"University of Applied Science - Aalen, Beethovenstr. 1, 73430 Aalen, Germany"
],
"email": "Michael.Schmiedt@HS-Aalen.de"
},
{
"givennames": "Julian",
"familyname": "Schlosser",
"affiliations": [
"University of Applied Science - Aalen, Beethovenstr. 1, 73430 Aalen, Germany"
],
"email": "Julian.Schlosser@HS-Aalen.de"
},
{
"givennames": "Wolfgang",
"familyname": "Rimkus",
"affiliations": [
"University of Applied Science - Aalen, Beethovenstr. 1, 73430 Aalen, Germany"
],
"email": "Wolfgang.Rimkus@HS-Aalen.de"
},
{
"givennames": "Tobias",
"familyname": "Stempfle",
"affiliations": [
"University of Applied Science - Aalen, Beethovenstr. 1, 73430 Aalen, Germany"
],
"email": "Tobias.Stempfle@Studimail.HS-Aalen.de"
}
],
"conceptrecid": "1201",
"doi": "10.24435/materialscloud:74-x1",
"references": [
{
"citation": "S. Feldmann, M. Schmiedt, J. M. Schlosser, W. Rimkus, T. Stempfle, Recursive Quality Optimization of a Smart Forming Tool under use of Perception Based Hybrid Datasets for Training of a Deep Neural Network (submitted).",
"type": "Journal reference"
}
],
"title": "Recursive quality optimization of a smart forming tool under use of perception based hybrid datasets for training of a deep neural network",
"publication_date": "Jan 31, 2022, 15:56:37",
"description": "In industrial metal forming processes, the generation of datasets for inline and optical quality assessment is expensive and time-consuming. Within the research project SimKI, conventional metal forming plants were digitalized under use of perception-based sensors in combination with a completely redesigned forming tool. The integration of optical quality observation methods connected with a retrofitting approach of the press tool provides the opportunity to generate an information-feedback loop that predicts part defects prior to their occurrence. The SimKI-method additionally combines conventional statistical measurement methods with AI-based defect detection algorithms that are trained by a) generic datasets of a finite-element simulation, b) real component images of a 3D imaging device, and c) a combination of both. The generated datasets are used to accelerate the training of a DNN-based algorithm in order to identify the position and deviation from the agreed quality. The high degree of innovation is based on obtaining real-time component quality information under use of AI-based optical quality assessment, which in turn provides information to the control algorithm of the smart forming tool.",
"mcid": "2022.16",
"edited_by": 576,
"version": 1,
"is_last": true,
"owner": 637,
"license_addendum": null,
"keywords": [
"Artificial Intelligence",
"Gocator",
"Defect Detection"
],
"_oai": {
"id": "oai:materialscloud.org:1202"
},
"license": "Creative Commons Attribution 4.0 International"
},
"revision": 17,
"created": "2022-01-04T17:05:57.999212+00:00"
}