Real-time intelligent monitoring system for carbonization control in sustainable laser cutting of leather

The proposed research introduces an intelligent manufacturing system that uses real-time monitoring and optimization techniques to control carbonization during sustainable leather cutting operations. The Node-RED used in this study enables real-time process monitoring through its dynamic system which allows instant adjustments to machining parameters. A blue laser diode with 5.5-W optical output power was used to study machining performance on samples of chrome vegetable-tanned leather during experiments. The intelligent optimization strategy leads to minimized carbonization effects which leads to better product quality and lower environmental impact and higher material removal rate (MRR). An artificial neural network (ANN) successfully predicted essential machining parameters through training with data from an L₂₇ orthogonal array to maintain process efficiency achieving excellent predictive performance with coefficients of determination ranging from 0.95785 to 0.99483 for carbonization and from 0.93515 to 0.97419 for MRR. The multi-objective grey wolf optimizer (MOGWO) algorithm was used to determine the optimal machining parameters determining an ideal balance at approximately 62–65% carbonization and an MRR of 0.026–0.028 g/s for sustainable leather machining. The virtual simulations allowed operators to predict machining results and make dynamic parameter adjustments which leads to better cutting efficiency. The smart manufacturing solution uses intelligent proactive carbonization control to support sustainable practices while minimizing waste in laser diode leather cutting operations.