Digital Twin-based Prediction for CNC Machines Inspection using Blockchain for Industry 4.0

Abstract

The rapid growth and advancement of technology in industries provide a better quality of services to the end-user in the industrial Internet of Things (IIoT). The digital twin (DT) is an innovative technology recently developed in Industry 4.0 to provide a virtual representation of physical components, products, or equipment such as computer numerical control (CNC) machines. It can be used to run simulations before manufacturing. However, traditional DT platforms lack data privacy, traceability, immutability, authentication of stakeholders. Moreover, manual prediction of the wearing of the tool condition of the CNC machine is challenging. Motivated from these gaps, in this paper, we propose a six-layered architecture for DT of CNC, which predicts CNC tool wear detection using a novel ensemble technique based soft voted prediction model consisting of XGBoost, random forest, and AdaBoost models. The proposed architecture also incorporates the public Ethereum blockchain (BC) to maintain the aforementioned issues of authentication, traceability, and transparency through constraints and automation programmed into the smart contracts (SC) developed. We evaluate the proposed scheme’s performance through simulation and compare it with other traditional approaches concerning several performance parameters (accuracy, F1-score, precision, and recall). The result shows that the proposed approach outperforms the traditional approaches on these same performance parameters such as accuracy, F1-score, precision, and recall.