App settings:

AI-supported production planning


So far, sequence planning in production has been carried out manually, and the complexity of taking all framework conditions into account is constantly increasing.


Research and development of an AI application for optimized sequencing using product and production data.

Added value

The useful output is optimized and thus the added value is increased through time savings in production.

Westaflex is a German family company that offers architectural building technology and air ducts. There are ventilation systems in a number of shapes and materials for every type of building and pipe, so that the systems can be flexibly combined and adapted to requirements. Accordingly, many different set-up processes are required in production, which in turn requires precise planning. In order for everything to run smoothly and as efficiently as possible, the sequence of orders must be planned precisely before production.

Sequential planning determines the production sequence of individual orders with the aim of making the production process lean, time-saving and therefore efficient. Currently, the sequencing of orders at westaflex is still done manually, for example using spreadsheets or analog planning boards, and not automatically. Factors such as processing, set-up and delivery times, product specifications, material or the reduction of expenses must be individually considered. This is very difficult to implement: Orders and machine sequences usually cannot simply be moved without having to manually adjust the rest of the planning.

Data analysis and AI ensure intelligent production planning

The aim is therefore to optimize the sequencing of production orders with the help of artificial intelligence. For this purpose, a wide variety of data, such as ERP data and real-time data from production, is to be evaluated in order to derive information for optimal machine utilization and to use these findings for sequence planning.

For this purpose, a data platform is being developed as a web-independent on-premise solution. Order data, resource data, process data, tool/maintenance data, logistical data and monetary data are brought together on the data platform and prepared for the AI ​​application. The data platform thus represents an IT infrastructure equipped with interfaces for the in-house data and the data from the AI ​​application. The solution found is implemented and tested, optimized and validated with real data.