Next-Gen Industry 4.0 Methodologies and Tools

The availability of inexpensive miniaturized wireless sensors with minimum energy consumption and installation impact has enabled the implementation of advanced monitoring infrastructures that are now ubiquitous in modern industrial applications. This is true also for large critical infrastructures, including energy, water, and communication networks. However, several challenges still need to be addressed to fully take advantage of the opportunities made possible by distributed industrial sensing. Within this framework, the activity carried out within the ELEDIA Research Center include

  • big data processing and anomaly detection in large energy, communications, and water networks, including trend analysis and performance evaluation;
  • exploitation of Artificial Intelligence (AI) for diagnostics and prognostics in industrial process analysis (including chemical processes, mechanical processes, etc.);
  • process evaluation and automated quality prediction in industrial production;
  • methodologies and algorithms for failure prediction in industrial machinery;
  • industrial digital twin development and application in Industry 4.0 scenarios.

For additional information contact us at

Read More

  • M. Salucci, N. Anselmi, G. Oliveri, P. Rocca, S. Ahmed, P. Calmon, R. Miorelli, C. Reboud, and A. Massa, "A nonlinear kernel-based adaptive learning-by-examples method for robust NDE-NDT of conductive tubes,” Journal of Electromagnetic Waves and Applications, vol. 33, no. 6, pp. 669–696, February 2019 (DOI: 10.1080/09205071.2019.1572546).," Journal of Electromagnetic Waves and Applications vol. 33, no. 6, pp. 669–696, February 2019 (DOI: 10.1080/09205071.2019.1572546)