ARTIFICIAL INTELLIGENCE | DIGITAL INNOVATION
Lanxess takes AI to heart
Lanxess sees Artificial Intelligence (AI) as the enabler to exploit its material data and speed product development. Chris Smith learns about the company’s first experiences and its plans for compound development
Developing polymers and compounds is no simple task, with multi-component formulations and complex interactions introducing an element of art alongside basic chemical understanding. Since 2017, Lanxess has been looking to the use of digital tools – and most specifically Artificial Intelligence (AI) technology – to allow it to make better use of its accumulat ed knowledge to speed up new material developments. The company has been working with Citrine
Informatics, a US-based leader in application of data-driven development methods for the chemi- cals industry. Co-founder and CEO Greg Mulholland explained to Compounding World at K2019 that the company’s aim is to use AI and data tools to exploit the client’s learned experience to bring product to market faster. “Innovation is becoming more and more
important in the chemical industry. You are defined by how fast you can move,” he said. “It used to be 20 years or 15 years. Now every auto maker or product maker wants a material by next quarter or next year. If you can respond in two or four or six months, your customer will buy from you and not your competitor.”
www.compoundingworld.com
Mulholland says the reason that major chemical companies such as Lanxess have reached the position they have in the market is the store of data they have built up. The challenge is that, while digital technologies make that accumulated data more available, it is difficult to manage; consistency can be variable and the volume is too great to be manually managed yet too small to apply conventional AI techniques to. “The volumes of data you need to form a machine learning system are not generally available in the chemicals industry. But you can use machine learning in chemistry even with limited data points because rules exist – this is domain knowledge. This can be integrated into an AI platform,” he says. “What does that mean? Well, an adhesive is just a really bad lubricant. So it’s about taking lessons learned in one area and applying it in another.”
Applying AI Lanxess has been working with Citrine in several areas and detailed two of them at K2019 — one project aimed at expanding its range of prepolymers for custom polyurethane systems and another to optimise the formulation of reinforcing fibre sizings.
Main image: Fibre sizing is one of the first application areas for AI at Lanxess. It is the starting point for its use in other areas, including compound development
� March 2020 | COMPOUNDING WORLD 45
IMAGE: LANXESS
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
