Improving cold chain logistics through RFID temperature sensing and predictive modelling

Abstract

The global Cold Chain Logistics (CCL) industry has grown in size with significant positive impact on the GDP of many economies. It however stills suffers from poorly managed service level agreements, inadequate cold chain visibility and cargo losses. Such losses are mainly caused by lack of real time information about the current status of cargo as well as lacking insight into the possible impact of supply chain incidents on cargo quality. This paper presents an improved approach to cold chain management (CCM) that is based on the real time monitoring of perishable cargo using RFID based sensing techniques, combined with the modelling of current and future in-cargo temperatures using the available sensed data. An empirical method is described for the characterization of cold chain processes and the development of predictive neural network models based on information that is collected using RFID temperature sensors. It is demonstrated that the use of advanced modelling techniques enables accurate monitoring using a small number of sensors, and that the models can estimate actual cargo temperatures more accurately compared to using temperatures measured on the periphery of the cold container