Digital Twin Based Fault Tolerant Manufacturing in Cyber Physical Production Systems

Fault detection is crucial for ensuring the safety, reliability, and efficiency of additive manufacturing systems. This involves detecting faults in both the physical components (e.g. sensors, actuators) and the network infrastructure that connects them. Monitoring and analyzing data from various sensors on the robotic production system can help detect anomalies using a digital twin. Irregularities in sensor readings can indicate hardware malfunctions or physical faults. An effective fault detection strategy in industrial robotic CPS requires a combination of sensor data analysis, redundancy, modeling, machine learning, network monitoring, and cyber security measures. This paper describes an integration approach to consider digital twin based monitoring system for 3D printer which can improve system reliability, and ensure the safe and efficient operation of manufacturing systems in the perspective of industry 4.0. Utilizing data analytics and machine learning algorithms within the digital twin to forecast potential failures can allow proactive maintenance schedule by avoiding downtime. Moreover, closed loop monitoring of the work piece is possible through camera and sensor feedback to modify G-code in real time to compensate manufacturing imperfections.