{"id":31102,"date":"2024-04-03T09:46:50","date_gmt":"2024-04-03T07:46:50","guid":{"rendered":"https:\/\/risc.web-email.at\/referenzprojekte\/nextbase\/"},"modified":"2026-03-10T14:22:48","modified_gmt":"2026-03-10T13:22:48","slug":"nextbase","status":"publish","type":"project","link":"https:\/\/risc.web-email.at\/en\/referenceprojects\/nextbase\/","title":{"rendered":"NextBase: Intelligent adaptation of production and intralogistics systems"},"content":{"rendered":"\n
\n
\n

The implementation of data-driven methods from prescriptive analytics and machine learning is the core objective of the project at industrial solution provider ABF GmbH. Together with RISC Software GmbH, ABF is developing new approaches to enable the on-line optimization of decisions in control processes in particular. <\/p>\n\n\n\n

challengeschallenges in the integration of new production processes<\/strong><\/strong><\/h3>\n\n\n\n

ABF’s systems control complex production environments and intralogistics systems based on the OneBase<\/strong> platform. When new products, production systems or transport facilities are introduced, software and regulations have to be adapted. This places high demands on both ABF staff and customers. This is because the effects on the running overall system are difficult to predict, especially in special cases. <\/p>\n\n\n\n

OneBase <\/strong>supports these adaptations with simulation functions that can be used to record production processes and repeat them in test environments. However, this requires considerable effort. At the same time, the introduction of changes during ongoing operations causes additional stress, as most customers’ systems are in operation around the clock. <\/p>\n\n\n\n

Use of prescriptive analytics and machine learning for process optimization<\/strong><\/h3>\n\n\n\n

The project partners want to simplify the change processes using modern methods from prescriptive analytics and machine learning. This allows adjustments to be made automatically, reducing manual intervention in logics and rules. The approaches used include machine learning, simulation and optimization using current heuristic research strategies. The partners also use these methods to improve order planning and allocation. There is also potential for allocation and routing problems. This is because the quality of the solution increases when the time component is taken into account. Suitable forecasts of the future order situation therefore contribute directly to more efficient management. <\/p>\n<\/div>\n\n\n\n

\n
<\/div>\n\n\n\n
\"\"<\/figure>\n\n\n\n
<\/div>\n\n\n\n
\"\"<\/figure>\n<\/div>\n<\/div>\n
\n
\n

This project is funded by the FFG.<\/p>\n\n\n\n

\"\"<\/figure>\n<\/div>\n<\/div>\n
\n
\n

Project partners<\/h2>\n\n\n\n
\"\"<\/figure>\n<\/div>\n\n\n\n
\n

Project details<\/h2>\n\n\n\n