Ready to proof -- Niki 08/02/24

CB proofed 8/2 - one comment for Niki and one comment for Kristin

KJ proofed on 8/9. One comment for Niki by the figure.

Ready for author

Some paint and coatings companies, and those that sell raw materials to them, have started using AI to great effect. Others are more hesitant. Some are worried that they don’t have enough data in the right format to start thinking about using AI. Others are worried that they don’t have the right skill set in house to get started. This article outlines the value paint and coatings companies gain from AI, and gives practical tips on how to get started, and what to look for in an AI provider.

Return on Investment

Moving from Being a Supplier to a Partner

Whether you are a specialty coatings company selling to an OEM, or a raw material company selling into a coatings company, you need to deeply understand how your product impacts your customers’ performance so that you can recommend the correct product, charge based on value, and find a market niche with higher margins.

Companies are using AI to do exactly this. A recent article in Handlesblatt outlines how Dorfner, a mining company with a coatings ingredients division, had increased its revenues by 30%.

“[With Citrine] we are able to enter new business models…we are able to get customer lock in…we were before just a supplier, and now we are a development partner…this can’t be ROI’ed, it is far beyond,” said Mirko Mondan, CEO Dorfner.

Accelerated Time to Discovery

Many companies have seen a reduction in the number of experiments, and therefore time to discovery, needed to hit property targets. A company optimizing mechanical properties of a multi-layer polymer coating on automotive glass was able to hit target properties in two weeks, instead of the usual 10. An 80% reduction in time to discovery. This is not unusual, and by being able to predict the likelihood of achieving target properties, product experts can concentrate on performing experiments that will work.

Dealing with Problem Ingredients

Other companies need to swap out ingredients, such as certain biocides and PFAS chemicals, from product portfolios. This is where scalable AI comes in. Once a model is trained on the base formulation, it can be easily adapted for each product in the range, ensuring consistency, as well as speed. Some AI providers that concentrate on the chemicals and materials space have developed technology to “featurize” chemicals, essentially converting the molecular structure and chemical formulas into extra data, such as molecular weight or number of hydrogen bonds. By understanding the fingerprint of the problem ingredient, and the role it performs in the original formulation, AI can be used to suggest alternatives.

Cloning your Expert Formulators

Do you ever wish that you could clone your top formulator before they retire? While AI cannot stop them from leaving, it can be used to codify their expert knowledge in such a way that it can be reused by more junior staff, now, and in the future. Some AI platforms make extra efforts to be easy to use, and capture the knowledge of the team using them. This knowledge is used to focus the power of the AI model onto unknown areas, rather than re-inventing the wheel, speeding up development. Knowledge is captured as:

• Data uploaded into the system, rather than hanging around in a spreadsheet somewhere.
• In an AI model itself as a representation of what inputs affect what outputs.
• In a search space, a description of constraints on formulations, e.g. what ingredients can be used, what mixing parameters, etc.

Paint and coatings companies are seeing value from AI. AI will become an everyday tool for formulators, and those that are late to the party will find it difficult to compete.

But My Data is a Mess….

There is a difference between BIG data AI, like ChatGPT, and small data AI. Some companies have spent the last 10 years focusing specifically on developing AI that works for materials and chemicals. By necessity, their AI must work with small data. When it costs hundreds or thousands of dollars to create a sample and test it, you are not going to get big data sets to work on. Companies, therefore, developed other strategies such as expert knowledge integration (using the expertise of your team to focus the model), chemical featurization (automatically generating extra data), and uncertainty quantification (clever math to calculate the likelihood of hitting targets) to make best use of small data.

Some AI Projects Start with No Data

Sometimes, either by necessity or choice, projects start before any data in the relevant area has been gathered. In this case, an initial set of experiments are carried out, similar to a design of experiment (DOE) matrix, but stripped down to cover the search space in the fewest experiments possible. The aim is to prime the AI model so that it can guide future experiments. Sequential learning (the process by which groups of five or so experiments are suggested, run, results inputted, and the AI model re-trained and used to suggest the next set of experiments) is then used to get closer and closer to the objectives of the project. This methodology still requires fewer experiments than trial and error or DOE.

Some Companies Have Data in Silos

It may be that commercial information on ingredients is in an ERP system, and rheological measurements are in a LIMS. Or, perhaps your IP is stored in handwritten notebooks on a shelf. By running a short time-scale AI project first, you will see exactly which data is useful for your AI model, and therefore worth spending time digitizing. Any good AI provider will have an experienced team that can help you create a data strategy and get your historical data into their platform. Data pipelines can be set up to ensure all future data goes in automatically.

Whether an AI provider’s data model is scalable is an important consideration. Can it easily accept data in different formats? As you learn that a different property is important in your project, can you easily add it? Or does it all have to go into one big rigid spreadsheet or SQL database? A graphical database structure such as the open source GEMD data model is ideal.

In summary, learn by doing. By starting with a small, but valuable AI project, you will understand what data you need, and can put a data strategy in place that shows immediate value without boiling the ocean. Don’t get distracted by creating a ‘data lake’ before you get value from AI.

But I Don’t Have Any Data Scientists…

AI platforms have come a long way in the last five years. While they were once the domain of data scientists, the best ones can now be used by anyone. In fact, you want your formulators using them directly because they can then easily add their own knowledge into the platform to speed up development, learn what the AI model finds important, and thus deepen their own understanding.

No-Code, Graphical User Interface Is Essential

While most AI platforms will have an API (code-based interface) that data scientists can use if they want to, making the graphical user interface intuitive and enabling formulation experts to add information such as relationships and custom formulas directly to AI models is important for both adoption of the new way of working and acceleration of progress. In some platforms, AI models are generated automatically from the chosen data set using some assumptions. A formulator then just has to add their knowledge and check the model.

Make Sure Your Team Can Learn From the AI Platform

AI models work by figuring out connections between input and output properties. Your team will benefit from understanding these connections more deeply. If you can show that an ingredient has no effect on the target output properties, that is useful information. Sometimes non-intuitive connections will be made, and by reviewing the features that the AI model finds important, you will find out something new.

Change Management

Adopting AI is a change to people’s day-to-day working styles, and can present a challenge. However, it is a small part of an overall digital transformation for many companies and an excellent way to show the value of good data management. By doing high-value, small AI projects first, you can show your team the value of their data and motivate them to participate in wider data digitization programs.

Some companies decide to make an AI platform freely available to the whole team after they have validated its usefulness on a few projects. But you shouldn’t neglect the continued need for change management until using AI is the new normal for the whole team. It’s a little like a bowl of fruit in an office. Everyone knows it would be healthy to go and get a piece of fruit, but they feel too busy to go and get it. They need a little extra support and encouragement to take an action that would benefit them in the longer term.

What to Look for in an AI Provider

• Deep experience in AI, specific to the paint and coatings industry.
• An experienced change management team that can make the adoption process smooth.
• A platform that is chemically aware and provides chemical featurization.
• A graphical data model that can accept data from lots of different sources and is scalable.
• A no-code, easy-to-use platform that can capture your team’s expert knowledge.
• Easy ways to search, filter, visualize, and share data between team members so that no one re-invents the wheel.
• AI tailored to work with small data sets. Does it have great uncertainty prediction?

AI is inevitable. It is a great step forward for many disciplines. In the end, it is just math. But pick an easy-to-use platform, backed up by an expert team, to help you get started.

For more information, visit Citrine’s website here.