Thesis Format
Monograph
Degree
Doctor of Philosophy
Program
Mechanical and Materials Engineering
Supervisor
Tutunea-Fatan, O. Remus
2nd Supervisor
Bordatchev, Evgueni V.
Joint Supervisor
Abstract
Laser remelting (LRM) is a novel advanced multifunctional surface engineering technology with rapidity, versatility, accuracy and precision traits. LRM uses a high-powered laser to melt a superficial thin layer of material which redistributes through thermophysical phenomena within the molten pool for later resolidification. Surface polishing (SP-LRM) uses constant laser parameters to reallocate and redistribute molten micro-peak material into micro-valleys to create a flat surface. Surface structuring LRM (SS-LRM) uses variation in laser parameters affecting the process’ flow dynamics allowing for material redistribution control to create functional micro-structures. Being a novel and micro-process, there are numerous inputs that affect the process conditions of LRM that are not fully investigated resulting in optimization of LRM remains a heuristic trial-and-error process. Artificial intelligence (AI) is used for online monitoring and analysis of the process as a preliminary step toward AI-driven self optimizing LRM. The LRM process consists of two extreme regimes, shallow-LRM (S-LRM) and deep-LRM (D-LRM), and a novel transitional regime intermediate-LRM (I-LRM) that differ in process conditions and formation of the resultant surface. Statistical digital twins were developed for phenomenological regime understanding for effective AI usage. K-means clustering was deployed for near infrared LRM thermography stability classification. LRM processes with one optimal cluster based on Silhouette scoring was thermographically stable and processes with > 1 optimal clusters were unstable. Furthermore, Jaccard index is an image statistic that best represents k-means clustering criterion. Thermographic images where Jaccard index was < 0.8 were correlated to surface formation instabilities whereas images with high Jaccard index (> 0.8) correlate to surface formation stability. These results prove a strong correlation between thermography and surface topology exists and AI can be incorporated into LRM for online monitoring, regime recognition and stability formation self-optimization.
Summary for Lay Audience
In the manufacturing industry, rapidity and precision is desired to allow for a quick turn around on manufacturing while maintaining the best quality of parts. Existing polishing processes such as abrasive or chemical polishing is slow and time consuming. Existing micro-fabrication, such as single-point cutting, is relatively expensive and ecologically detrimental due to its subtractive process nature. This creates a need for a technology that can conduct both processes while being both economically and ecologically beneficial. Laser remelting (LRM) is a novel multifunctional technology that possess both these traits and has surface polishing (SP-LRM) functionality to improve surface quality and surface structuring (SS-LRM) for fabricating micro-structures for functional surfaces. LRM uses a high-powered laser to melt a superficial layer of material for redistribution and reallocation to fabricate new surfaces. However, its novelty and complexity results in a lack of full understanding and experimental analysis. This results in current optimization of LRM to be a sequential trial-and-error process where experiments are completed, surface is measured, and laser parameters are altered to identify change and find optimal parameters to achieve surface desideratum. To address and improve this process, artificial intelligence (AI) is developed around LRM to provide online monitoring and in-situ self optimization.
The research aims to improve scientific finding and surface engineering applicability of LRM with AI. The research goes through an extensive fundamental understanding of LRM and its regimes that affect the process conditions of LRM. The established fundamental understandings are complimented with statistical digital-twin modelling to bring deterministic correlation to a complex stochastic nonlinear process. Using the findings, AI algorithms (such as k-means clustering and convolutional neural network) may be strategically chosen for self optimization of LRM. Near infra-red (NIR) thermography of LRM is used to monitor the process and determine process stability. The results show a strong correlation between thermographic stability and process and surface stability. The results also provide further proof of concept and understanding of the regimes in LRM providing scientific breakthrough of a novel third regime (I-LRM) and their process traits. The study is a crucial preliminary step to developing a fully online monitoring, self-optimization and adaptive control LRM technology that will be more feasible and competitive in common manufacturing practice.
Recommended Citation
Cvijanovic, Srdjan, "Artificial Intelligence-Driven Monitoring of Surface Polishing by Laser Remelting: Process Stability and Regime Classification" (2025). Electronic Thesis and Dissertation Repository. 10834.
https://ir.lib.uwo.ca/etd/10834