ACTOR- ACTIVE MONITORING
Meccanica del Sarca
Company name
Meccanica del Sarca
project title
ACTOR- ACTIVE MONITORING
size and location
Large enterprise, Trento
partner
Cefriel
Competencies used
The problem
Benefits for the company proposing the project
– Improved risk management: based on hazard identification, the most appropriate solution to mitigate the detected hazard can be identified
– Reduction of damage due to fires triggered within the plant and related downtime: it is believed that with this system the economic impact of potential fire damage can be reduced by 90%
– Implementation of an intelligent solution that goes beyond the functionality offered by market solutions: possible possibility of protecting, through industrial privatisation, the results obtained from the prototype solution, which is the subject of the innovation project.
Impacts
1. The generation of an artificial intelligence algorithm makes it possible to endow a traditional camera with additional functionality: identification and classification of hazard and risk conditions appropriately cataloged for Sarca Mechanics’ workings.
2. Integration between the connectivity features offered by the camera and those offered by the AI algorithm allow detection, identification and “detection” activities to be carried out in real time.
3. The integration and connection of the described solution with the alarm system makes it possible to create an intelligent real time monitoring system of the working conditions of the mechanical woodworking process, enabling the company to afford unmanned processing.
Technologies
1. Artificial intelligence applied to computer vision and deep learning techniques used for automatic, real-time identification of sparks that could ignite the fire.
2. Intelligent continuous monitoring system that by means of normal optical cameras placed in the machines detects automatically and under all operating conditions situations of fire danger by generating an alarm signal.
The solution subsists in the development of an algorithm that analyzes in real time the images of a normal HD camera installed inside the machine tools and is able to detect processing anomalies that can potentially create the conditions for the ignition of a fire. The effectiveness of such an algorithm ensures immediate warning of a critical issue in real time, then allowing for an intervention strategy that may differ depending on the level of risk and the specific company organization.
