Enhancing supply chain efficiency through device quality traceability using scalable unified identity technologies

Abstract

In today’s supply chain (SC) management circumstances, ensuring device quality and authenticity is critical to preserving operational efficiency and consumer trust. The main objective of this study is to improve SC efficiency through the development of scalable unified identification systems that provide reliable device quality tracking. The study framework employs a combination of immutable data storage, Internet of Things (IoT) devices for continued monitoring, and machine learning (ML) algorithms for predictive analytics. The study presents a refined Random Forest (RRF) algorithm, meticulously designed to analyze data for demand forecasting based on the system’s operational state. This analysis is grounded in comprehensive IoT equipment sensor data, encompassing critical parameters such as temperature, humidity, pressure, vibration, and wear and tear of the equipment, ensuring inventory levels effectively align with anticipated requirements. Kalman filter algorithm for accurate state estimation of the device throughout the SC, enhancing traceability by providing real-time updates on device status. IoT sensors on essential components in the SC obtain continuous data on their status and performance. These sensors will keep track of key performance indicators for quality control. The results demonstrate our approach and conduct simulations in a controlled environment, demonstrating an increase in operational efficiency and a significant reduction in quality-related defects. The RRF model is 93.48% accurately identifying the IoT system’s operational state. This research addresses the importance of integrating scalable identity solutions to foster trust, transparency, and responsiveness in SC ecosystems.