Kellanova花了四年和500万美元给薯片面团做了个数字孪生，结果废料少了13%，能耗降了7%，产能还涨了10%。
Kellanova与西门子合作四年，斥资约500万美元在波兰工厂为薯片生面团构建实时数字孪生。系统以每毫秒200个数据点的频率采集数据，涵盖面粉粒径、面团湿度、土豆收获时间等200多个参数。机器学习模型在问题出现前推荐配方调整，但每次更改仍需人工审批。该产线废料减少13%，能耗降低7%，产能提升10%。
Kellanova, the company that makes Pringles in Europe, spent four years and roughly $5M working with ...
Kellanova, the company that makes Pringles in Europe, spent four years and roughly $5M working with Siemens to build a real time digital twin of its potato chip dough at a factory in Poland. The problem it solves is variability. More than 200 parameters affect the final chip, from flour particle size to the humidity of the dough to where and when the potatoes were harvested, and workers previously corrected for all of it by hand and by feel. Now sensors capture 200 data points every millisecond and feed a machine learning model that recommends recipe adjustments before problems appear. A human operator still approves each change. The line has seen 13 percent less waste, 7 percent lower energy use and a 10 percent capacity gain. Digital twins have been a concept in manufacturing for years, but this is what it looks like when one finally starts paying for itself. Your browser does not support the video tag. 🔗 View on Twitter 💬 2 🔄 0 ❤️ 8 👀 2061 📊 3 ⚡