IRS has collaborated with theUniversity of Verona in developing a new testing methodology for testing household appliances based on new Artificial Intelligence techniques: deep learning.
The principles on which this new technique is based were presented at the IFAC International Conference held in Germany between 11/17 July 2020 and published under the title ".A deep learning unsupervised approach for fault diagnosis of household appliances".“.
Fault detection and diagnosis are crucial subsystems that must be integrated into the control architecture of modern industrial processes to ensure high quality standards.
In particular, a suitable test procedure was implemented on a real industrial production line in order to extract the most significant features that allow efficient classification of different types of faults by exploiting deep autoencoder neural network and hierarchical clustering techniques.
These methodologies have been developed within the regional project "PreMANI" - Predictive Manufacturing: design, development and implementation of Digital Manufacturing solutions for Quality Prediction and Intelligent Maintenance" and are currently being developed in the Electrolux plant in Susegana.
For more information write to email@example.com