ProSweets Cologne, set for Feb. 2-5 in Cologne, Germany, will provide insight on how AI can help confectionery and snack manufacturers, particularly in the area of vision and quality control.

Machines on display will be equipped with smart cameras and AI-based tools that observe, learn and adapt. From collection and administration of operating and machine data, to the dynamic visualization and analysis, the systems enable total transparency of production processes in real-time.

"The potential of AI and machine learning is huge and will fundamentally change the processes of the companies – also in the field of quality assurance," says Guido Hentschke, director of ProSweets Cologne.

With the implementation of computer vision and algorithms of machine learning, modern solutions like the ones on display in Cologne offer precision in recognizing defects in biscuits, wafers and crackers. Whether round or square, sweet or savory, made of wheat or oats — even slight deviations are detected on the conveyor belt directly after leaving the continuous oven. This minimizes production stoppages and waste.

In addition to the established red-green-blue camera technology and the laser scan, more systems that work in the ultraviolet or infrared wavelength range have been implemented to inspect food. The hyperspectral image processing of the Austrian company Insort reaches down to molecule level. It allows the chemical composition of the products to be assessed spatially-resolved inline and in real-time. And even if test objects with a higher variance have to be inspected and sorted, like dried fruits and nuts, AI is no longer a future vision. With the aid of deep learning, modern vision systems like the Sherlock Hypernova by Insort decide themselves whether an object belongs in a snack mix or whether it is a foreign body. All foreign bodies, whether plastic, stones, metal or fragments of glass are removed in one step. It is also possible to determine the bitterness of almonds and have them discharged safely, where necessary.

Thanks to AI, food producers not only have the opportunity to solve complicated quality control tasks. Generative AI models that are trained using large data sets, can also help develop optimized recipes or suggest alternative raw materials. 

"They enable combinations of ingredients and production methods to be discovered that meet the requirements of the consumers more readily and which are at the same time more cost-efficient," says Pierre Wiese, managing director at Solvia Digital Solutions. The company specializes in the introduction of various SAP products and develops intelligent applications to solve local customer needs. A result of growing demand for AI applications is the increased interest in the SAP Business Technology Platform (BTP). "SAP BTP offers a host of options for putting generative artificial intelligence to targeted use," says Dirk Nolte, head of ERP Consulting (SAP), at Solvia Digital Solutions.

An example of such a service is Döhler’s product finder. The natural ingredient supplier will present the tool, which allows AI-supported recipe search, Feb. 4-5 at 11:30 a.m. in the lecture "Sweet AI – how AI supports the food and beverage industry" on the Sweet Week – Talks & Tasting Stage.

Julia Hildebrant from Mehr.Wert Qualitätslösungen will also present the lecture "AI in the Quality Section: Smart solutions for efficiency & safety.” Hildebrandt will convey how generative AI can make processes more efficient to achieve added value in the daily work routine – not only in the field of quality. The lecture will be held along five other lectures Feb. 3 during the Sweet Week Production Summit. The focus lies on practical examples and innovative approaches for cost-efficient and future-proof production, especially through the use of AI tools.