A Real Time Intelligent Resource Management System for Facilitating Inbound Operations in Manufacturing

In order to satisfy customer requirements and punctually meet the delivery time, it is necessary to handle several customers' orders simultaneously and allocate the appropriate machines and resources before starting production. Production scheduling and planning is an important process for avoiding delay in production and improving manufacturing performance to fulfill customers' needs. Different constraints are considered in formulating the most satisfactory production plan. These constraints are constant and predictable. However, in the actual manufacturing environment, shop floor managers face numerous unpredictable risks in day-to-day operations, such as defects in the supplied components or raw materials, errors, failures, and wastage in various production processes. The unpredictable risks not only entail stringent requirements regarding the replenishment of materials but also increase in the difficulty in preparing material stock. Therefore, it is essential to effectively and efficiently handle such risks to achieve smooth production.;To efficiently and effectively solve stochastic production material demand problems, a real-time production operations decision support system (R-PODSS) is developed. The proposed system consists of three modules: Real-time Data Collection, Data Storage and Exchange, and Formulation Module of Optimal Pickup and Delivery Route. Real-time Data Collection Module utilizes Radio Frequency Identification (RFID) technology in capturing production operations information. Data Storage and Exchange Module systematically stores captured production and warehouse information in the centralized database and transforms them into meaningful information. The Formulation Module of Optimal Pickup and Delivery Route provides an optimal resource allocation plan for utilizing appropriate resources to pick/transfer/store production materials from the warehouse to the production lines. Artificial Intelligent techniques, such as Case-Based Reasoning (CBR) and Genetic Algorithm (GA) are adopted to select appropriate warehouse resources and formulate the shortest pickup and delivery routes, respectively.;To validate the feasibility of the proposed system, two case studies are conducted. Through the pilot run of the system in the case studies, the improved visibility of production and warehouse operations is observed. The efficiency of production and warehouse operations is also significantly enhanced. The results reveal that the proposed system effectively achieves the objectives of this research.