Knowledge-based decision support system for slow moving spare parts inventory control in a power plant

This paper describes a knowledge-based decision support system for slow moving spare parts inventory control in a power plant using hybrid artificial intelligence and web technology. At first, a novel slow moving spare parts criticality class evaluation model is constructed to confirm the target service level based on the artificial neural network learned by gene algorithms. At the same time, we integrate this model and the web-based inventory control decision support system (DSS) to obtain reasonable replenishment parameters that can be helpful for reducing of total inventory holding costs. The proposed DSS was successful in decreasing inventories holding costs significantly by modifying the unreasonable replenishment applications while maintaining the predefined supply service level.