A food safety management decision support system for enhancing the quality level in a distribution centre

Abstract

With increasing concern about food management, attention is being paid to the monitoring of different potential risk factors in food handling, such as contamination, toxic ingredients, and bacterial infection. Many food companies have adopted food management systems to improve the quality of the inventory. The existing ways of determining hazards and of exercising control relied mainly on human beings. However, with the increase in the number of food items and value added activities performed in Distribution Centres (DC), the current practices can no longer support the operations in a short timeframe. In addition, potential hazards and corrective actions are unable to be identified effectively, so the quality of the inventory and food safety is below standard. Therefore, a system that helps (i) facilitate and improve the quality of decision making, (ii) reduce the level of substandard goods, and, (iii) facilitate the data capturing and manipulation, is proposed to help warehouses improve the quality assurance in the inventory- receiving process with the support of technology. In this research project, an integrative system called the Real-time Food Quality Assurance decision support System (R-FQAS) is proposed. The proposed system is designed to control the food quality assurance operations in a DC by gathering different food attributes within the receiving and storage process, and suggesting instant operations handling guidelines. The operation data is converted into knowledge in terms of case and rule sets, decisions are then made based on the knowledge stored in the knowledge domain. The aim of this procedure is to increase the visibility of the status of the inventory, identify any potential food hazards during the receiving operation and suggest corresponding corrective actions to ensure the safety of food. This system consists of three modules, which involve radio frequency identification (RFID) technology, case- based reasoning (CBR), and fuzzy reasoning (FR) techniques to help monitor the food quality assurance activities. In the first module, the data collection module, raw warehouse and work station data is collected. In the second module, the data sorting module, the collected data is stored in a database. In this module, the data is decoded, the coding stored in the RFID tags is transformed into meaningful information. The last module is the decision making module, through which the operation guidelines and optimal storage conditions are determined. To validate the feasibility of the proposed system, R-FQAS, two case studies were conducted in two local logistics companies. The pilot run of the system in the case studies revealed that the performance of the receiving operation assignment and food quality assurance activities improved significantly. In addition, the decision making time frame has been shortened. Such outcomes show that the objectives of this research were successfully achieved. In summary, the major contribution of this research is to develop an effective infrastructure for managing the food receiving process and facilitating decision making in quality assurance. Integrating CBR and FR techniques to improve the quality of decision making on food inventories is an emerging idea. The system development roadmap demonstrated the way to future research opportunities in managing the receiving operations of food inventories and implementing artificial intelligence techniques in the logistics industry.