A leading wood-based panels producer servicing mainly the B2B market, operating in Germany, faced significant challenges in providing competitive and reliable market offerings while maintaining adequate levels of operational efficiency. The company produces various types of panels and its production strategy was predominantly make-to-order (MTO), which resulted in difficulties meeting service level expectations due to the complexity of forecasting demand and managing lead times.
The initial diagnosis revealed several pain points:
Production strategy mix: The need to improve service levels by redefining the mix of make-to-stock (MTS), make-to-order (MTO), and finish-to-order (FTO) strategies.
Stock occupation: Constraints on warehousing space limited the ability to hold stock.
Lack of Coordination Among Decision-Makers: Stock program decisions by the Supply Chain and Marketing teams were made without alignment or a shared decision-support platform.
Solution
To address these challenges, a simulation-optimization solution was developed, built on top of a mixed-integer linear programming (MILP) model. This model provided the Marketing and Supply Chain teams with a shared data-driven tool capable of suggesting optimal production strategies for its large product portfolio. The key components included:
Optimization of production strategies: Involves deciding whether to adopt a Make-to-Stock (MTS), Make-to-Order (MTO), or Finish-to-Order (FTO) strategy for each product. Such decisions ensure that production is closely aligned with market demand and operational efficiency.
Lot sizes and stock levels: Model capable of determining optimal lot sizes and expected stock levels, while considering plant-workcenter congestion along with expected lead times. This helps in effectively balancing production flow and inventory management.
What-if analyses: Multi-scenario handling capability, along with multi-axes parameterization, allows for testing multiple portfolios, production mixes, and operational constraints. This flexibility is crucial for strategic planning and risk management.
Production Strategy Algorithm: Employed to optimize operational and commercial indicators while adhering to inherent operational constraints. Due to the non-linearity of the problem, a Mixed-Integer Linear Programming (MILP) approach was chosen. This approach separates the simulation of queue metrics from the actual optimization algorithm, providing a robust framework for optimizing production processes.A user-friendly architecture was developed, integrated with the company’s ERP system, featuring a parameterization interface allowing easy scenario adjustments and a dashboard KPI summary providing a comprehensive overview and detailed analysis at the material level. To ensure successful adoption, a combined approach was used:
Process mapping: A thorough mapping of production, supply chain, and marketing processes was conducted to understand the business context and identify improvement opportunities.
Parametrization interface: A tailor-made interface was developed to cater to the needs of a vast and diverse group of stakeholders. This interface allows direct parametrization across multiple axes, such as adjusting operational data or prearranging specific strategy mixes. It is equipped with a detailed output page that complements the KPI summary dashboard.
Web-based implementation: A user-friendly interface was provided to end-users, allowing them to interact with the model easily and efficiently.
Change management tactics: User training was implemented to promote the autonomous adoption of the tool. This was accompanied by frequent stakeholder engagement through meetings and training sessions. Iterative feedback was encouraged to foster acceptance and usage of the new model, supplemented by regular touchpoints to address any concerns and identify opportunities for improvement.
Result
The implementation of the simulation-optimization model yielded several positive outcomes:
Improved Lead Times: Enhanced stock utilization and optimized change-over times led to a decrease in proposed lead times.
Operational Cost Reduction: Increased stock levels for MTS, heightened by the proposed increase in the number of MTS SKUs, resulted in fewer change-overs and lower operational costs.
Effective Change Management: Adoption of the module was facilitated through various change management tactics, ensuring smooth integration into existing processes.
The project showcased the critical impact of integrating advanced simulation-optimization models with existing ERP systems on enhancing production planning and strategy optimization. By addressing key challenges and involving multiple stakeholders through effective change management, it was possible to achieve improved service levels, reduced operational costs, and gain greater control and foresight over production strategies.
This case study underscores the importance of tools designed for multi-departmental interaction, providing visibility across the entire value chain—from the shop floor to the commercial catalogue.
The success achieved highlights the necessity of combining analytical development, process mapping, and change management to realize substantial operational improvements.
