Abstract:
The purpose of this thesis was to investigate the application of methods for
categorizing events and indicators of risks based on the Supply Chain methodology
by SCOR Model to analyze some levels of data by using hierarchical decision-making
processes in conjunction with defect and impact analysis, and artificial intelligence
forecasting methods. Fuzzy AHP and Fuzzy FMEA were used in the synthesis and the
Intelligent Agent based Discrete Event (IAB DES) system was used to find the best
point in power distribution. Manufactured for the supply chain. The experiment was
divided into 5 main criteria: 1. Plan Risk 2. Source Risk 3. Deliver Risk, 4. Make Risk, and
5. Return Risk. From experiments using Fuzzy AHP, it was found that experts put the
top three priorities on risk factors, with the Deliver Risk accounting for 28% as the first
place. The second place was the Plan Risk and the source risk, accounting for 11.79%
and the last place was the Make Risk and the Return Risk accounting for 2%. In addition,
the Fuzzy AHP results were used to determine the weight of defects and the effects
of RPN values according to FMEA, compared with the Fuzzy FMEA RPN values in the
risk and uncertainty using Fuzzy FMEA, it can be seen that the RPN values according
to FMEA were not able to select defects appropriately. In this study, an intelligent
simulation of discrete events was also applied to forecast to help distribute the
production capacity of supply chain factories by knowing the capacity and capabilities
of each plant that could produce optimized works by allocating the time and number
of machines used in production. The results of this simulation will be used to decide
on a system that can use the resources to its full potential while reducing costs for
the case study company.