Hintergrund und Motivation

In today's highly dynamic manufacturing landscape, the ongoing market trend towards extreme customer customization , which is driving production down to "batch size 1" , combined with radically shortened delivery times , has increased the complexity of shop floor control to an unprecedented level.

For small and medium-sized enterprises (SMEs), this market pressure reveals a critical operational gap. Although these companies store large amounts of valuable production data in their SAP systems , they are often unable to use it effectively. Historically, the high manual effort and highly specialized technical expertise required for implementing simulation-based digital twins have represented a virtually insurmountable barrier to entry.

Since SMEs are excluded from advanced, data-driven forecasting methods , they often have to manage volatile and highly complex production environments with rigid, simplified priority rules such as FIFO (First-In, First-Out) . This systemic mismatch inevitably leads to cascading production bottlenecks , the accumulation of costly excess inventory , and a significantly increased risk of missing delivery dates .

The TeaTwin project was launched to break down these barriers and transform unused SAP data into an accessible, automated basis for proactive production planning .