Metallurgical Machinery & Equipment
Research & Development
Semiotic Labs, a scale-up company based in Leiden, Netherlands, and SMS group have signed an agreement under which the two companies will cooperate in the field of predictive maintenance.
The innovative AI-based (Artificial Intelligence) technology developed by Semiotic Labs uses electrical signals and the data fingerprint of AC motors and other rotating equipment to monitor and analyze the condition of critical plant assets and enable reliable and early prediction of developing faults. In contrast to traditional, vibration-based solutions, SAM4 developed by Semiotic Labs operates based on sensors installed directly in the control cabinet - not on the asset itself. This solution is particularly useful for the monitoring of equipment in service under rough operating conditions as typical in the metallurgical industry.
SAM4 has already been implemented successfully on numerous hot wide strip mills and other applications in steel plants throughout Europe. The convincing results achieved by SAM4 under such highly demanding in-service conditions and tests at the SMS group workshops led to the decision to make this technology part of the SMS product portfolio.
“We continuously aim at expanding and enhancing the functionalities and capabilities of our Genius CM® condition monitoring system for the metallurgical industry,” says Christoph Häusler, Vice President Comprehensive Service Products, SMS group. “The integration of SAM4 into our portfolio is a very important step towards this end.”
"As part of the agreement with Semiotic Labs, SAM4 will be integrated as an App into the MySMS platform,” explains Dr. Eike Permin, COO, SMS digital. Further it is planned to integrate SAM4 into Genius CM®, SMS group’s condition monitoring system. Also cooperation in the field of data analyses and joint development activities between the two companies are planned.
The cooperation will become another important element of SMS group’s strategy of supplying Smart Maintenance Solutions that help their customers maximize uptime. Thus strategic predictive maintenance based on condition monitoring will become much more reliable and efficient than maintenance strategies based on operating times. And it will increase the components' lifetime and overall equipment efficiency.