Optical sensing technologies are pivotal in the manufacturing process, specifically in defect detection, tool condition estimation, and monitoring. The research aims to enhance the accuracy, efficiency, and reliability of manufacturing metrology by employing optical sensing technologies, such as laser profilometers and image processing techniques. The dissertation proposes intelligent and flexible metrology methodologies for defect detection, utilizing laser profilometers for capturing surface profiles and image processing techniques for comprehensive analysis.

The incorporation of optical sensing into manufacturing operations offers a non-contact and non-destructive solution for monitoring tool conditions, leading to increased productivity and reduced downtime in manufacturing operations. For tool condition estimation and monitoring, the research leverages image cameras. These cameras capture visual data during the machining process, enabling real-time monitoring of tool conditions. Advanced algorithms are developed to analyze the captured images and extract relevant features that indicate the tool’s condition, such as wear, degradation, or damage. By continuously monitoring these features, tool performance can be accurately estimated, facilitating timely maintenance and optimizing machining processes. Integrating image cameras for tool condition estimation provides a cost-effective and non-intrusive solution for monitoring tool health and ensuring efficient manufacturing operations. In the domain of defect detection, laser profilometers are employed to capture detailed surface profiles as point cloud data. The acquired data are then processed using image processing algorithms. These algorithms extract relevant features from the captured profiles and analyze them to identify and classify defects accurately. The proposed methodology enables robust defect detection in manufacturing processes by leveraging the power of image processing techniques, such as filtration approaches and morphological operations. The combination of laser profilometers and image processing techniques provides a comprehensive and reliable solution for surface defect detection.

The dissertation adopts a scholarly approach, encompassing theoretical analysis, algorithm development, and rigorous experimental validation. This research emphasizes the significant role of optical sensing in enhancing quality control, optimizing process efficiency, and increasing productivity within the manufacturing industry. The integration of optical sensing technologies offers valuable insights and practical solutions for addressing challenges related to defect detection, tool condition estimation, and process optimization, paving the way for improved manufacturing practices and industry competitiveness.