Digital twin technology offers the advantage of monitoring the status of equipment, systems, and more in a virtual environment, allowing validation through simulation. This technology has found numerous applications in the industrial robotics field, driven by recent advancements in the manufacturing industry. Consequently, predicting machining quality using digital twin technology is imperative for ensuring high-quality processed goods. In this study, we developed a digital twin program based on a cutting-force physical model and created a performance enhancement module that allows the visualization of material removal for user convenience. The predicted cutting forces from both conventional CNC and the physical model demonstrate a high accuracy of within 2%. Within the digital twin environment, the error rate for the robotic drilling process is 13.5%. Building upon this, we developed and validated a module for material removal visualization, aiming to increase convenience for on-site operators.

The key components of smart manufacturing, a central concept in the era of the 4th Industrial Revolution, consist of digital twin technology, AI, and computer vision technology. In this study, these technologies were utilized to govern the Poppy robot, a humanoid robot designed for educational and research purposes. The digital twin creates a virtual environment capable of real-time simulation, analysis, and control of the robot’s motions. The digital twin of the robot was constructed using Unity, a 3D development program. Motion data was captured while simulating the physical structure and movements of the virtual robot. This data was then fed into a Tensorflow-based deep neural network to generate a regression modelthat predicts motor rotation based on the position of the robot’s hand. By integrating this model with a Python-based robot control program, the robot’s movements could be effectively managed. Additionally, the robot was controlled using Openpose, a computer vision algorithm that predicts characteristic points on a human body. Position data for human joint points was collected from 2D images, and the motor angle was calculated based on this data. By implementing this approach on an actual robot, it became possible to enable the robot to replicate human movements.

With the advent of the 4th industrial revolution, advanced digital manufacturing technologies are actively developed to strengthen manufacturing competitiveness. Smart factories require a real-time digital twin including a Cyber-Physical System (CPS) of machines and processes and intelligent technologies based on the CPS. To predict machining quality and optimize machines and processes, it is necessary to analyze the cutting force during machining. Therefore, for real-time digital twin, a fast cutting force simulation model that receives information such as the positions of the feed axes in short time intervals from the CNC and calculates the cutting force until the next information is input is required. This paper proposes a voxel-based fast cutting force simulation in NC milling for real-time digital twin. The proposed simulation model quickly calculates the cutting force by using only information of voxel elements removed by each tool edge without complicated Cutter-Workpiece Engagement (CWE) and chip thickness calculations in previous studies. To verify the performance of the developed simulation, experimental machining was performed and the measured cutting force and simulated cutting force were compared. It was demonstrated that the proposed model can successfully predict the cutting force 3.5 times faster than the actual process.

Recently, industrial manufacturing has developed into additive manufacturing, benefiting from multi-item small-sized production and effective manufacturing. Importantly, Wire Arc Additive Manufacturing, which uses metal wires, is attracting worldwide attention for its high-quality metal product technology. Technological innovation that combines virtual physics with reality through big data communication, such as process variables along with Wire Arc Additive Manufacturing, is an essential task for implementing smart manufacturing technology. Due to the characteristic of Wire Arc Additive Manufacturing, numerous variable conditions exist, making it difficult to standardize robot"s process path data generation algorithms and data application methods, and this data generation method is being studied as a core element technology. The present study generated foundation process implementation, simulation, and generated path data for robots in virtual space using RoboDK, which provides robot libraries from multiple manufacturers, and Python, which is a universal programming language. To implement the experimental data in practice, ABB"s industrial six-axis robots IRB-6700 and Fronius TPS500i were used to control the arcing plasma heat source, and the process path worked the same as simulation. Based on the underlying experimental results, this process can be applied to generation of additive manufacturing in the Wire Arc Additive Manufacturing process for 3D models.