Abstract
In consequence of high cost pressure and the progressive globalization of markets, blanking, which represents the most economical process in the value chain of manufacturing companies, is particularly dependent on reducing machine downtimes and increasing the degree of utilization. For this purpose, it is necessary to be able to make a real-time prediction about the current and future process conditions even at high production rates. Therefore, this study investigates the influence of data acquisition, preprocessing and transformation on the performance of a multiclass support vector machine to classify abrasive wear states during blanking based on force signals. The performance of the model was quantitatively evaluated based on the model accuracy and the separability of the classes. As a result, it was shown, that the deviation of time series represents the key parameter for the resulting performance of the classification model and strongly depends on the sensor type and position, the preprocessing procedure as well as the feature extraction and selection. Furthermore, it is shown that the consideration of domain knowledge in the phases of data acquisition, preprocessing and transformation improves the performance of the classification model and is essential to successfully implement AI projects. Summarizing the findings of this study, trustworthy data sets play a crucial role for implementing an automated process monitoring as a basis for resilient manufacturing systems.
Highlights
Forming processes often represent the most economical part of the value-added chain and represent a key factor in times of energy and raw material shortages due to the optimal utilization of materials as well as the lower specific energy requirement compared to subtractive or additive manufacturing processes (Lange, 1985)
In order to quantify the resilience of the classification model, the performance of the multiclass support vector machine (mSVM) is analyzed at different stroke speeds
This reference model is obtained by training the mSVM with the force signals of the piezo electrical sensor in the upper tool at a maximum stroke speed of 500 spm
Summary
Forming processes often represent the most economical part of the value-added chain and represent a key factor in times of energy and raw material shortages due to the optimal utilization of materials as well as the lower specific energy requirement compared to subtractive or additive manufacturing processes (Lange, 1985). Industry 4.0 ( known as Smart Manufacturing or Smart Factory) provides an approach to this, combining elements of artificial intelligence (AI), new types of sensors as well as stateof-the-art information technologies (Oztemel & Gursev, 2020) Central to this approach are data which are more and more available to companies due to high-performance processors and sensors and cross-linking of processes (Moyne & Iskandar, 2017). Industry 4.0 aims to use this data available over the entire product life cycle to improve the value chain and build manufacturing intelligence (O’Donovan et al 2015) This steadily increasing amount of data offers the possibility of making predictions about process correlations that were not possible before. This leads to high demands on the quality of the acquired data even at high stroke rates in order to be able to physically differentiate effects in the process from noise even at minor variations (Groche et al 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
