Application of IoT and blockchain technology in the integration of innovation and industrial chains in high-tech manufacturing

Abstract

In industrial IoT (Internet of Things) environments, accurate anomaly detection and high-quality data management are crucial yet challenging due to noisy and incomplete sensor data. This study introduces BD-IoTQNet, a novel framework designed to address these challenges by integrating data fusion, anomaly detection using the Isolation Forest algorithm, and blockchain-enabled DQM (Data Quality Management). The framework leverages blockchain technology to ensure data transparency and security, while smart contracts automate exception handling to enhance efficiency. Experiments conducted on the NASA Turbofan Engine Degradation and UCI Hydraulic Systems datasets demonstrate that BD-IoTQNet outperforms existing models in accuracy, precision, and data quality improvement, with reduced latency and enhanced robustness under noisy and missing data conditions. An ablation study validates the critical role of each component, showing significant performance drops when modules like DQM or blockchain are excluded. These findings highlight BD-IoTQNet as an effective solution for improving anomaly detection, predictive maintenance, and operational efficiency in industrial IoT systems.