Neuro-fuzzy decision support system for multicriteria materials management

Abstract

Materials Management, as a core function of supply chain, includes inventory management, sourcing, storing as well as materials distribution and waste management. Materials Management as part of the resource flow processes in business organizations is recently undergoing through severe changes in terms of strategic focus and methods used in its management. Material Planning and Inventory Control are the most important functions of Materials Management and it forms the nerve centre in any organization. The main aim of this research is to develop a new multicriteria inventory or material classification model for inventory control and an innovative demand forecasting model to prepare detailed Material Requirement Plan (MRP). A systematic approach to the inventory control and classification may have a significant influence on company competitiveness. In practice, all inventories cannot be controlled with equal attention. In order to efficiently control the inventory items and to determine the suitable ordering policies for them, multi-criteria inventory classification is used. The objective of this research is to develop a multicriteria inventory classification model through integration of Fuzzy Analytic Hierarchy Process (Fuzzy AHP) and Artificial Neural Network (ANN) approach. Fuzzy Analytic Hierarchy Process (Fuzzy AHP) is used to determine the relative weights of the attributes or criteria using Chang’s Extent Analysis, and to classify inventories into different categories. Various structures of multi layer feed-forward back-propagation neural networks have been analyzed and the optimal one with the minimum mean sum of squared error (MSE) between the measured and the predicted values have been selected. The predicted results are compared to those obtained by the multiple criteria classification using the fuzzy analytical hierarchy process. To accredit the proposed model, it is implemented for 351 raw materials of switch gear section of Energypac Engineering Limited (EEL), a large power engineering company of Bangladesh. An organization has to make the right decisions in time depending on demand information to enhance the commercial competitive advantage in a constantly fluctuating business environment. Therefore, estimating the demand quantity for the next period most likely appears to be crucial. The objective of the paper is to propose a new forecasting mechanism which is modeled by artificial intelligence approaches including the comparison of both artificial neural networks and adaptive network-based fuzzy inference system techniques to manage the fuzzy demand with incomplete information. The effectiveness of the proposed approach to the demand forecasting issue is demonstrated for a distribution transformer 20/25 MVA Transformer from Energypac Engineering Limited (EEL). Material requirements planning (MRP) has its strength in job shops that require flexibility in the production sequence, in the quantity of production, and in the timing of the production process. If there are any errors in the inventory data, the bill of materials data, or the master production schedule, then the output data will also be incorrect. The aim of this research work is to prepare a detailed Material Requirement Plan based on the forecasted demand, bill of material and inventory record with higher integrity and accuracy.