Intelligent Advanced Scheduling and Monitoring in Production Planning


The intelligent planning and monitoring software PSIasm/Qualicision combines
planning and real-time control with KPI based production optimization



  • Integrated basic planning of workflows in sequence
  • Key performance indicator (KPI)-oriented evaluation of planning scenarios
  • Various qualitative optimization goals such as urgency, importance, compactness, and number of alternatives
  • Optimization and decision making for the selection of planning scenarios with Qualicision
  • Fast identification of bottlenecks by multi-criteria planning
  • Increased transparency and responsiveness in production
abb1 Figure 1: PSIasm/Qualicision with planning scenario selection

PSIasm/Qualicision is a powerful tool for managing and visualizing multiple resources in chained production processes. An integrated basic scheduling feature allows planning simple workflows. For the planning of more complex work steps of multi-criteria key performance indicators (KPIs) are considered in PSIasm. The integration of Qualicision technology creates added value that combines technological software progress with optimization intelligence.

For this purpose, a Qualicision-based solver was integrated in PSIasm. In the simplest case, the Qualicision solver can initially schedule single-stage operations in sequence, considering different qualitative optimization goals such as urgency, importance, compactness and number of alternatives.

The use of PSIasm/Qualicision allows the automatic creation of planning and decision scenarios, see Figure 2, which enable an optimization history by means of logging the degrees of goal achievement. This is the basis for the use of machine learning methods paired with the Qualicision learning algorithm.

This can map the respective data situations (order data, deadlines, capacities, utilization levels, setup times, etc.) to the process plans in such a way that PSIasm/Qualicision continuously learns the required process behavior automatically from the interactions with the user and proposes preference settings that are optimally matched and parameterized to the current data situation.

abb2 Figure 2: Planning scenarios, e.g., urgency of production orders, even utilization of machines