Industrial IoT and Long Short-Term Memory Network-Enabled Genetic Indoor-Tracking for Factory Logistics

Abstract

Acquiring the real-time spatial–temporal information of manufacturing resources holds the promise to enable efficient operation in factory logistics. This article proposes a system architecture using industrial Internet of Things and digital twin technologies to fulfill spatial–temporal traceability and visibility with seamless cyber-physical synchronization for finished goods logistics in the workshop. A long short-term memory network-enabled genetic indoor-tracking algorithm (GITA) is developed to locate product trolleys via a bluetooth low energy technology, with ultra-wideband applied to sample labeling in the training stage. It is enlightened by genetics to achieve self-adapting online for the long-term performance. A feature selection method based on received signal strength indicator is designed to deal with signal multipath fading and streamline the learning process. In addition, the spatial–temporal information obtained is leveraged to activate location-based services that can help promote operational efficiency. Moreover, a real-life case study is carried out in a world-leading computer manufacturer’s factory to illustrate the viability and practicality of the system and methods proposed, with hardware and software developed. By comparison, the GITA shows superiority over existing approaches despite various noises under the manufacturing scenario, attaining a location precision of about 2 m with a 98.12% accuracy.