DATA-DRIVEN MANUFACTURING


IT’S NOT WHAT YOU’VE GOT…


YOU USE IT! IT’S HOW


With so much process data being created on production lines today, Suzanne Callander reports on how confectionery manufacturers can best use this data to optimise their production processes.


C


onfectionery manufacturers are probably sitting on more process data today than at any point in the industry’s history – this


includes temperature and tempering curves, viscosity, moisture content, checkweigher and vision-inspection data, and cooling tunnel profiles. Despite the quantity of data now available on ever more digitised lines, a report from Schneider Electric – Beyond the Hype: Practical AI for Competitive Consumer Goods Manufacturing – estimates that 73% of industrial data still goes unused. This is one of the sector’s biggest untapped opportunities, according to Neil Smith, CPG President, Schneider Electric. “The instinct for many manufacturers is


to chase higher line speeds to meet rising demand, tighter margins and growing product variety. But, because confectionery products are inherently delicate and can be sensitive to mechanical stress, timing, temperature and humidity, speed on its own isn’t the answer,” says Neil. “Push a line too hard without the right visibility, and you trade throughput for breakage, deformation and waste.” The Schneider survey also found that UK food manufacturers appear to be more confident


26 • KENNEDY’S CONFECTION • JULY 2026


in their data quality than the global average – 95.2% of UK decision-makers, compared to 85.7% globally. However, the survey also found that they are seeing higher production losses. An estimated 18.9% of manufacturing revenue is lost for UK food and beverage producers versus 17.2% globally due to downtime, waste, delays, rework or sub- optimal use of assets. “These figures tell me that having confidence in your data is not the same as


acting on it,” continued Neil. He believes that the key to successfully utilising process data is to get the data foundations right in the first instance. Much of the data on a confectionery production line will sit in unstructured, siloed, or incomplete systems that do not talk to each other. Before any AI or analytics layer can add value, data needs to be clean,


contextualised and


PUSH A LINE TOO HARD WITHOUT THE RIGHT VISIBILITY, AND YOU


TRADE THROUGHPUT FOR BREAKAGE, DEFORMATION AND WASTE


accessible. “Software solutions, such as the vendor-agnostic AVEVA PI System, show what’s possible. It collects, stores, and contextualises high-frequency time-series data from sensors, PLCs, SCADA, and other OT sources into a ‘single source of truth’ for operations. “Without such solutions, you are building insight on sand,” argued Neil. The next step should be to focus on


targeted improvements around the data points that move the needle, for example tempering and cooling tunnel temperature profiles, moisture content, checkweigher accuracy at depositing and packaging, and defect data from vision inspection. Employing AI-augmented vision to catch subtle coating or shape defects at full line speed, for example, is a high value, self- contained addition to existing automation


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