neural networks

Forecasting the Business Crisis in the Auto Industry

Forecasting the Business Crisis in the Auto Industry

A comparative analysis of models
Joseph W. Dörmann, Shobith Ramakrishnaiah
This paper examines various forecasting models used to predict business crises in the automotive and electronic manufacturing industries, with a focus on German companies. By comparing the performance of these models, we aim to identify the best approach for each industry. We also discuss real-world business case scenarios to demonstrate the practical implications of our findings, including the role of risk management in supply chain and procurement departments. Our results show that the most effective model for forecasting crises in the automotive industry is the VAR model, while the EWS model is best suited for the electronic manufacturing industry. Furthermore, we identify key risk factors that supply chain and procurement departments must consider enhancing their resilience in the face of crises.
Industrie 4.0 Management | Volume 39 | 2023 | Edition 5 | Pages 6
Smart Adjustment of Deep Drawing Process Parameters

Smart Adjustment of Deep Drawing Process Parameters

Bildgebende Sensorik und maschinelles Lernen für robustere Blechumformprozesse im Automobilbau
Jens Heger, Thomas Voß, Michael Selent
A complex process in sheet metal processing is multi stage deep drawing. Once set up, it can be considered as a black box. Usually, after the sheet metal has been processes the quality is assessed. In the research project Smart Press a system is developed, incorporating inline pictures of the processed sheet metal. Pictures of failures are related to the actual state of the machine. Neural Networks are used to model the highly complex relations between parameters and product attributes. Based on the assessed real time data, the process gets adjusted to suit the needs of each individual sheet.
Industrie 4.0 Management | Volume 34 | 2018 | Edition 4 | Pages 53-56