More news
- Nigeria’s paint industry navigates regulatory changes and economic challenges amid p...
- Focus on the global coatings market: Global coatings market outlook
- Ask Joe Powder – October 2024
- Chinese paint majors look to domestic consumer sales as commercial real estate slumps
- Architectural coatings in Nepal and Bhutan
Nouryon has signed a framework agreement to implement self-learning technology developed by Semiotic Labs that helps predict when to maintain and replace pumps and other rotating equipment.
Semiotic Labs was one of the winners of Nouryon’s 2018 Imagine Chemistry open innovation challenge.
The technology uses electrical waveforms that can accurately predict 90% of upcoming maintenance needs in rotating equipment, such as pumps, compressors, and conveyors, up to five months in advance.
This gives time to repair or replace critical equipment during planned stops, preventing unexpected interruptions to production and improving reliability of supply and process safety.
The technology has been successfully implemented at Nouryon’s chlorine plant at Ibbenbüren, Germany, and will now be rolled out to seven other sites in Europe.
Marco Waas, Director R&D and Technology Industrial Chemicals at Nouryon said: "Working with start-ups like Semiotic Labs allows us to tap into novel technologies that can provide significant benefits.
"Our customers rely on us for a reliable supply of essential raw materials and this predictive maintenance solution can greatly help improve the performance of our plants, while decreasing cost.”
Simon Jagers, Founder at Semiotic Labs added: "Since the Imagine Chemistry challenge in 2018, we have been working together on a pilot programme to test and improve our technology.
"I am very pleased to see it making a difference in real-life production settings and look forward to the further rollout in partnership with Nouryon.”
Nouryon and Semiotic Labs will also look at ways to generate more value from waveform analysis by developing features that will enable significant reductions in CO2 emissions.
The first large-scale implementations are planned for early 2020.