This paper presents the development and evaluation of a digital method for multi-criteria optimized production planning and control of production equipment in a case-study of an Austrian metal casting manufacturer. Increased energy efficiency is a major requirement for production enterprises, especially for energy intensive production sectors such as casting. Despite the significant energy-efficiency potential through optimized planning and the acknowledged application potential for sophisticated simulation-based methods, digital tools for practical planning applications are still lacking. The authors develop a planning method featuring a hybrid (discrete-continuous) simulation-based multi-criteria optimization (a multi-stage hybrid heuristic and metaheuristic method) for a metal casting manufacturer and apply it to a heat treatment process, that requires order batching and sequencing/scheduling on parallel machines, considering complex restrictions. The results show a ~10% global goal optimization potential, including traditional business goals and energy efficiency, with a ~6% energy optimization. A basic feasibility demonstration of applying the method to synchronize energy demand with fluctuating supply by considering flexible energy prices is conducted. The method is designed to be included in the planning loop of metal casting companies: receiving orders, machine availability, temperature data and (optional) current energy market price-data as input and returning an optimized plan to the production-IT systems for implementation.

This paper presents the development of an optimized planning and control method for flexible manufacturing and assembly systems. While the significant potential of flexible manufacturing concepts to help producers adapt to market developments is recognized, the complexity of the flexible systems and the need to optimally plan and control them is a major obstacle in their practical implementation. Thus, this paper aims to develop a comprehensive digital planning method, based on a digital twin and to demonstrate the feasibility of the approach for practical application scenarios. The approach consists of four modules: (1) a simulation-based optimization module that applies reinforcement learning and genetic algorithms to optimize the module configuration and job routing in cellular reconfigurable manufacturing systems; (2) a synchronization module that links the physical and virtual systems via sensors and event handling; (3) a sensor module that enables a continuous status update for the digital twin; and (4) a visualization module that communicates the optimized plans and control measures to the shop floor staff. The demonstrator implementation and evaluation are implemented in a learning factory. The results include solutions for the method components and demonstrate their successful interaction in a digital twin, while also pointing towards the current technology readiness and future work required to transfer this demonstrator implementation to a full-scale industrial implementation.

This paper presents a digital material planning approach, utilizing simulation-based optimization to select and parametrize article specific demand forecasting methods. Demand forecasts are the basis of material requirements planning in consumption-based material planning, and are an essential lever for efficient inventory and order calculation. Despite their acknowledged potential, digital tools for optimized demand calculation are still lacking in practice. Thus, the goal of the presented approach to provide an application-oriented method to optimally select and parametrize state-of-the-art forecasting methods, based on product-specific demand data. In this approach, a rule-based selection heuristic is combined with static simulation of demand time-series and a metaheuristics-based optimization of forecasting parameters, to provide automatically optimized article-specific demand forecasts. Case studies for two companies in the capital goods industry evaluate and quantify the application potential. The results point to significantly improved, item-specific demand planning.