A DT framework integrating human and artificial intelligence for power consumption prediction in CNC machining

Digital twins (DT) have increasingly garnered attention in today's manufacturing industry for their potential to enhance productivity, efficiency, and decision-making processes. This study presents a human-centric digital twin framework (HCDT) specifically designed for a three-axis vertical milling machine (VMC3), following the ISO 23247 standard. Our system seeks to offer a comprehensive virtual depiction of a tangible milling machine, facilitating immediate monitoring, analysis, and enhancement of machining operations. This study targets specifically the prediction of power consumption in three-axis vertical machining using advanced machine learning. Power consumption during modified Kakino toolpath cutting was examined through a series of trials that involved adjusting spindle speed, depth of cut, and feed rate. The analysis was conducted utilizing physical sensors, mathematical modeling, and machine learning. The utilization of machine learning methods, specifically random forest, exhibited encouraging outcomes, as evidenced by a mean absolute error (MAE) of 17.30. In addition, virtual simulations were performed to forecast power usage. The proposed applied digital twin (ADT) incorporates human intelligence and artificial intelligence to effectively integrate physical and virtual environments, offering a unique approach that adheres to the ISO 23247 framework. The cross-system entity of the digital twin showcases that the calculated power has large variations with the experimental power. However, the proposed ADT approach has resulted in higher similarity to the calculated, experimental, and predicted power consumption respectively in the proposed digital twin scenario. Also, the addition of explainability to the result has developed the trustworthiness in the digital twin environment.