Prediktiv simulation : En undersökning om möjligheten att minskaslöseri vid ett industriföretag med hjälp av digitala simuleringar

Sammanfattning: The industrial company Scania CV AB is a world leader in the manufacturing of commercial vehicles. They offer a modular systems that include heavy trucks and buses that can be configured to a range of different needs. However, this adaptability leads to a problem where each order can have a large variance of assemblers that are re-quired during the manufacturing process. In other words, variant assemblers have a workflow that can shift from high workload to low workload and vice versa in a short period of time. To solve this problem a prototype will be developed. This prototype will be used to check if it’s possible to optimize the work schedule for variant assem-blers with the help of predictive simulations. The result of the study became an implementation in form of a prototype. This prototype is built up in two layers; a data layer and a simulation layer. The data layer provides the simulation layer with two different datasets. The first dataset is based on historical data and is derived from Scania’s production in Zwolle. The second dataset is based on synthetic data which is formed with a high utilization rate in order to mimic a better production situation with less product variants to assemble. The simulation layer consists of a DES-model that is modelled after a station in the final assembly of Zwolle. After a simulation has been executed, this layer generates a simulation result in form of a graph that presents the utilization rate for a group of variant assemblers. This will happened for each dataset in the data layer, in this case two times. The simulation result that got produced shows that it’s possible to create a simulation with predictive characteristics. A long term solution for Scania’s problem statement requires more research within the possibility of combining different technologies such as DES with predictive methods such as ML and GAs.