Antía Fernández López, Bruno Fernández Castro, Daniel García Coego
The dawn of Industry 4.0 fosters new opportunities for manufacturing companies in order to improve their operational efficiency and competitiveness through the use of Machine Learning (ML) and Artificial Intelligence (AI) applications. The automotive industry has always been a leading industry in applying new methodologies and R&D results to all the steps of its value chain. Due to the variety and typology of data available through these different steps, new data processing architectures shall be applied in order to empower novel data analytics applications. This chapter presents three use cases related to the application of ML and AI solutions in manufacturing processes from the automotive sector: (I) Real-time quality prediction, (ii) one-off raw material optimization and (iii) real-time industrial robot anomalous behaviour detection. Data analytics allow to identify in advance the generated product quality and speed up the production process and reduce waste, while ensuring the quality of all parts generated for each batch. In this case, this system is working in real-time while the plant is being producing. In other cases, the analysis is done once and there is no need to re-measure the parameters in real time. This is the case of the identification of the lower hydrogen consumption for a minimum product quality accepted by the client. Some industries include robots from different manufacturers. The management becomes complex due to the isolated reporting platforms. A system is presented for capturing data in real-time, analyzing and warning anomalies.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados