Digital Talk | Quality Anomaly Detection: fabricating zero-defect quality

Under the auspices of

Quality is a process that must be planned so as not to generate defects during the production stages.

Managing anomalies and correctly identifying the source of defects to attack it and prevent it from recurring is a Key Success Factor for enterprises. It is estimated that on average, Cost Of Poor Quality amounts to about 15% - 20% of sales. Source ASQ (American Society for Quality)

Machine Learning applications in industry allow real-time data to be collected and processed to create systems that learn and improve performance. In quality, these applications have become particularly effective.

Through a new paradigm, Machine Learning algorithms applied for Quality Anomaly Detection solutions allow real-time production data and historical data from plants, ERPs, MESs, and quality systems to be collected, processed, and analyzed to recognize possible malfunctions and support the operator to intercept, during the production process, which defects are generated, in order to proactively solve problems.

Goal: zero defects and "digitization" of business know-how.

During the live streaming, use cases implemented in national and international realities will be presented by:

• Luca Bedogni | Assistant Professor, Artificial Intelligence Research and Innovation Center (AIRI), University of Modena and Reggio Emilia
• Michele Fantoni | Chief Technology Officer, Digibelt
• George Thrones | Client & Project Leader, Bonfiglioli Consulting

FOCUS ON.

Read HERE “Anomaly Detection and Classification in Predictive Maintenance Tasks with Zero Initial Training" the article published in the scientific journal MDPI to officially present the Machine Learning algorithm developed in collaboration with the University of Modena and Reggio Emilia.