Wear is one of the decisive factors for the economic efficiency of sheet metal forming processes. Thereby, progressive wear phenome lead on the one hand to a poor workpiece quality and on the other hand to tool failure resulting in high machine downtimes. This trend is intensified by processing high-strength materials and the reduction of lubricant up to dry forming. In this context, data-driven monitoring methods such as machine learning (ML) provide the potential of detecting wear at an early stage to overcome manual and cost-intensive process inspections. The presented study aims to provide a ML based inline quantification of wear states within sheet metal forming processes. The development of this monitoring approach is based on a procedure model the Knowledge Discovery in Time series and image data in Engineering Epplications (KDT-EA) which is validated on two forming processes, blanking and roll forming, that strongly differ in their physical process behavior and their acquired process data. The presented inline quantification allows an estimation of wear states with a deviation of less than 0.83% for the blanking process and 2.21% for the roll forming process from the actual wear state. Furthermore, it is shown that combining different feature extraction methods as well as a compensation of unbalanced data using data augmentation techniques are able to improve the performance of the investigated ML models.
The potential of data for inline detection of changes in the physical state of sheet metal forming processes has been proven over the last decade. However, with production rates exceeding 300 parts per minute the time available for a workpiece-related processing of sensor data is reduced. Therefore, the analysis of large data sets is outsourced to the cloud taking advantage of the high computing power provided there. But within this cloud-based computing paradigm, the speed of data transmission hinders real-time analysis of data and causes latency between fault detection and its occurrence. To overcome this bottleneck, this study aims to evaluate a data-based monitoring (DBM) approach for estimating process states in high speed sheet metal forming in terms of their suitability for a decentralized analysis at the edge. Thereby, the DBM is evaluated according to the model accuracy and the absolute computing time. In order to quantify these key performance parameters and the applicability of the DBM on edge devices, a classification of 16 wear states during blanking is considered. Based on the key performance parameters, an optimal DBM approach for decentralized analysis is proposed and an empirical formulation is provided to estimate the absolute computing time depending on the computational resources used for data processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.