At home, in the car, and while shopping, voice-controlled digital assistants have become a part of daily life. In the future, they will also make lab work easier. The first such assistant to specifically help scientists in the coatings industry is named Coatino.

Bearing names such as Siri and Alexa, virtual assistants are now a part of the family in one out of five American homes. Boasting endless patience, they accept any voice command they are given and, if everything works right, will then play the desired music, provide a weather forecast or update the user’s calendar. Voice-controlled digital assistants promise to provide us help in our daily lives. They are rapidly spreading.

Whereas they were found in only one percent of US households in 2016, this figure had risen to 20 percent just two years later. They are also used in no less than 13 percent of German households.

If everything goes according to Dr Gaetano Blanda’s wishes, this will only be the beginning. Blanda wants to turn voice-controlled digital assistants from simple helpers for daily life into chemistry experts and use them in a place where a comprehensive amount of specialised knowledge is needed and a technical language is spoken: the laboratory.

Digital lab assistant: Coatino always recommends the most suitable additive

As the Head of the Coating Additives Business Line at Evonik, Dr Blanda knows about the great demands that the new lab assistants have to fulfill with regard to scientific expertise and language skills. His team specialises in formulations for the coatings industry and the associated additives. In order to exactly meet the customers’ wishes with respect to colour, gloss, and durability, the experts have to create complex mixtures in the lab which they supplement with the right additives. Thousands of combinations are possible – far more, in fact, than the human brain can handle.

The experts spend correspondingly much time searching through notes and data sheets on their desks. So a digital assistant will now help users research and adjust ingredients directly in the laboratory. The assistant’s name is Coatino. The idea for Coatino was born during a strategy meeting at Coating Additives. “We talked about new ways in which business could develop,” said Dr Oliver Kröhl, Head of the Strategic Business Area Development at Coating Additives and the project’s manager. “Innovations are no longer just limited to finished products or processes. Instead, you need to demonstrate your ability to come up with solutions in the form of new services and business models.”

The researchers focused on everyday challenges for the formulation of coatings and paints and soon decided that they could use a voice-controlled digital formulation assistant. The team was thrilled by the idea. But is this what the experts in the lab actually need?

FROM CAN TO PROTOTYPE

To find this out, the scientists decided to simply start working. They coated an empty can of paint in the company’s colours. They then put it into the laboratory, where they filmed a discussion between a colleague and the can. In the video, the user asked the can about a suitable waterborne anti-foaming agent for a wood coating. The can gave its reply, provided the lab employee with a selection of products, and ordered a sample.

“Back then, the questions were answered by a colleague who stood behind a wall,” said Kröhl. “Although this was rather ad hoc, we wanted to tangibly test our idea with customers and quickly get feedback.” The video was shared with a number of customers and the team also conducted structured interviews. The idea engendered a great amount of interest.

This approval encouraged the developers to move into uncharted territory. “We’re experts for paints and coatings, but not for voice-controlled assistants,” said Kröhl. “That’s why we knew that the project might not work. However, we and our customers thought it had such great potential that we were willing to take the risk.” Their aim was to develop a prototype assistant in time for the European Coating Show, the world’s most important trade fair for the paint and coatings industry.

This was no easy task, because conventional voice-recognition systems were unable to handle the specialist vocabulary. “The usual assistants simply can’t understand our language,” said Kröhl. They quickly reach their limits when you ask them about dispersion, rheology or silicone resins, for example, and they can, at best, only supply general information.

A TEST COURSE FOR COATINGS

The high-throughput experimentation unit for the testing of coating recipes at the Coating Additives Business Line provides an important pool of data for the coating industry’s digital assistant. This unit, which is housed at Evonik’s Goldschmidtstrasse location in Essen, doses raw materials, formulates them to create coatings, and characterises the finished coatings. All of this runs fully automatically according to a precisely defined program that can be reproduced at any time. As a result, the unit can formulate an average of 120 samples in 24 hours. The results can be called up and reproduced at any time. If this data is linked with Coatino, customers will receive daily updated data about individual coating formulations.

Digital lab assistant: Coatino always recommends the most suitable additive

“They have to be able to do a lot more in order to formulate a coating,” said Kröhl. “If they don’t know the components’ properties and how they interact, they won’t be any help in the laboratory.”

PREVENTING SCRATCHES

Paints, lacquers, and other coatings basically consist of four components: solvents, binders, pigments, and additives. A solvent keeps a wall paint in a liquid state, for example. The solvent evaporates after the paint is applied, causing it to dry. Pigments give the paint the desired color. Binders are used to ensure the paint remains attached to the wall and is effective. This component is colorless and bonds the paint with the substrate. Additives make up the smallest percentage of a formulation. Although their share is less than five percent, they nevertheless play a key role. Additives eliminate foam when paint is applied. They also prevent the paint’s pigments from agglutinating. They make coatings thixotropic, i. e. they make them easy to apply, but prevent them from forming runs when they dry on vertical surfaces.

Other additives make coatings more scratch-resistant, for example.  The various components influence each other’s effects, depending on the mixture. The number of possible combinations is immense. Even if only ten curing agents, ten binders, ten pigments, and ten additives are considered during the development of a coating recipe, these numbers translate into 10,000 possible combinations. And this doesn’t even take into account variations in the ratios of the components used. “Customers have very precise ideas about the capabilities that a product should have once it’s finished,” says Blanda. In order to develop a functional voice-controlled assistant for the coatings industry, the researchers at first began to structure all of the available information and feed it into a huge database. In the next step, they made it possible to call up this information using a voice-control function.

TRAINING FOR APPLICATION

For example, if you ask the assistant, “Which additive is suited for printing ink?,” the system obviously has to be able to understand each word. Among other things,

Coatino had to learn that “additive” designates a certain category of coating components. In the next step, the assistant has to access its data, search through it, create suitable links, and assign the data to a possibly relevant result. To do so, it first breaks down the sequence of sounds into their smallest components and conducts a data search on the basis of characteristic properties. A special challenge for the assistant is that Coatino has to be able to understand not only German nouns in the nominative case but also in other cases. The researchers also want to make sure that the speaker’s dialect or accent won’t hamper the result. The ultimate aim is to enable Coatino to understand customers’ pronunciations worldwide.

Added to these challenges are the speakers’ different talking speeds and pitches as well as the specific context of a discussion. “The training process is very nerve-wracking,” said Kröhl. “And after the trial run with our colleague in Shanghai was finally successful, it went wrong with our colleagues in Essen.” For almost two years now, Coatino has been jointly developed and trained by the business line and an external development company from Berlin. The assistant passed its first important development test when the prototype was demonstrated at the ECS.

Coatino has a lot of things it can say. When asked about suitable additives, it not only presents a list of products but also prioritizes them. “Coatino can tell me which additive would be best suited for my formulation and my requirements. It can thus give me well-founded recommendations,” said Blanda. Once a user has found the desired product, he can issue a voice command to tell Coatino to order a sample, directly call up the pertinent technical data sheet by e-mail or have a conversation with an expert arranged. “For us, customer-oriented digital solutions enable people to talk with one another more efficiently about innovative solutions,” said Kröhl.

NEW FORMULATIONS

The Coatino prototype was ready just in time for the start of the European Coating Show. “We immediately presented it to a select group of our customers,” said Blanda. Instead of a can, the users imparted their wishes to a tablet via a microphone. “The feedback was even better than we’d hoped. We were able to gain some of the customers as first users who will test the assistant.” They will pass on their experiences to Blanda and his team. “We wanted to get the customers involved at an early stage,” said Blanda. “Such a project can only work if customers also think it benefits them.”

In 2020 the researchers plan to make Coatino available for the entire coatings industry.

However, there is no end in sight for the system’s further development. “When you use digital assistants, you continually come up with ideas for new features,” said Kröhl. For example, Coatino could conceivably not only supply existing formulations but also suggest its own new mixtures. The scientists could directly test these mixtures in the lab and enhance them for their own use. “Our Coatino might one day really become an artificially intelligent entity,” said Blanda. “But we still have a long, long way to go until then.”