Quantum Computing Aided Quality Control and Defect Detection in Laser Melting Deposition Manufacturing

An innovative additive manufacturing process called laser melting deposition (LMD) has many benefits for precisely generating complex structures. However, process optimization, defect detection and quality control are difficulties that LMD faces despite its potential. The manual inspection and traditional algorithms used in traditional defect identification and quality control procedures are time-consuming, computationally costly and prone to errors in high-dimensional datasets. This research examines the integration of defect detection and quality control methods in LMD production. Information from various sensors, including optical, laser, pressure and temperature sensors, are used to track the LMD process. To guarantee consistency and correctness in the dataset, the initial stage entails pre-processing the gathered data using cleaning and min-max normalization techniques. Feature extraction is performed using Principal Component Analysis (PCA), which lowers the data's dimensionality while keeping the crucial details required for a successful analysis. An approach called Dynamic Artificial Rabbits optimized quantum support vector machine (DARO-QSVM) is used to identify quality control parameters and identify flaws in the LMD process; the suggested methodology seeks to increase the accuracy (95.36%) of defect detection, and optimize process parameters in real-time. This study demonstrates how high-dimensional data problems and the dynamic, nonlinear character of LMD could be resolved with quantum-based technologies, providing a viable way forward for improvements in manufacturing quality control in the future.