The first working prototype was ready after just 4 weeks of development
Intelligent material recognition in this form and currently unique in this market segment
Flexible API enables high scalability and future use cases
Since 1947, wagner one of the world's leading manufacturers of equipment and systems for surface coating with powder and wet paints, paints and other liquid materials. Wagner offers its customers reliable and user-friendly solutions that are characterized by high quality and pioneering technologies.
Source: J. Wagner GmbH
Wagner machines coat surfaces. As simple as this may sound at first glance, the subject is just as complex - especially in professional use. Paint is not the same as paint and varnish is not the same as varnish. Each coating material has its own characteristics and requires the correct adjustment of the Wagner spray systems in terms of nozzle, dilution and pressure - the so-called coating parameters.
In order to obtain these coating parameters, painters and plasterers have to painstakingly decipher the small print on buckets, click through manufacturers' websites or download tonnes of data sheets. J. Wagner GmbH wanted an automated solution that would add value to any spray system.
In addition, Alexander Strobl, project manager and director of digital transformation, faced the challenge of getting the project's budget approved. Less than four weeks into the project, he had to deliver a functional showcase and present the concept to the company.
Source: J. Wagner GmbH
The plan was to be able to uniquely identify the material - say, a bucket of paint - by scanning the EAN code. But reality is different. This is because material manufacturers work with number ranges that are not centrally available, unlike commercial goods from supermarkets. The solution: a combination of intelligent image and text recognition. The paint bucket is photographed with the app and a machine learning algorithm recognises the manufacturer and the exact type of material. From this result, the necessary parameters are read from a database and displayed.
In addition to the lack of the necessary EAN codes, there is no cross-manufacturer database that provides information on coating parameters. As the number of manufacturers, materials and products is hard to keep track of and new items are constantly being added, an automated solution had to be found: the development of a web crawler. In combination with Microsoft Azure Cognitive Services, it is also possible to determine important coating parameters from online product data sheets (PDFs) - a unique feature in this market segment.
Another challenge was to make an existing web-based backend API app-enabled. The solution was to develop a flexible API that could pass all the necessary parameters in a single call, working both from web to app and vice versa. This also laid the foundation for future use cases, such as connecting to a customer portal.
With a rudimentary database, existing code from the existing backend and a preliminary interface, we were able to set up a first prototype together after just four weeks of development. Alexander Strobl presented the interactive showcase at an internal event and was given the green light for the project.
Source: J. Wagner GmbH
Wagner began the project with a vision. The details of the journey were not yet clear - but the tight timeframe was. Flexibility was therefore one of the most important requirements for the service provider. Alexander Strobl, Director Digital Transformation: "The topics were completely new territory and it was impossible for me to answer all the questions in advance. In the beginning, there was a lot of mocking and prototyping. First of all, you have to find a service provider who will go along with you. generic.de simply has the right mindset for such challenges - the perfect hands-on mentality".
However, they were not just looking for a good software development partner, but also a full-stack provider. And Strobl defines this as follows: "For me, full stack means getting everything from one source: infrastructure, backend, frontend, Azure services, but also conceptual consulting and support. generic.de has this full stack approach. That convinced me once again.