Optimizing Cutting Parameters for Achieving Net-Zero Emissions in Dry Machining of Special-Grade Steels

2026-01-01

Flashback limit analysis of premixed hydrogen-air flames with porous media integration for enhanced combustion stability

Fuel · 2026-05-20

Surrogate model-assisted machine learning optimization of aerospace coating deposition processes for enhanced performance and uniformity

Aircraft Engineering and Aerospace Technology · 2026-01-12

Purpose Optimizing coating deposition processes is essential for aerospace applications, particularly for thermal barrier coatings, environmental barrier coatings and protective films on turbine engine components. This study aims to develop a machine learning based framework to optimize two key chemical vapor deposition performance metrics: film deposition rate and thickness uniformity. Design/methodology/approach Building on previous work that benchmarked several machine learning models against computational fluid dynamics (CFD)–generated data, the XGBoost algorithm was identified as the most accurate predictor of deposition characteristics. In this study, XGBoost outputs were used to construct polynomial surrogate models for deposition rate and uniformity. These models enabled rapid optimization using the sequential least squares programming (SLSQP) algorithm under realistic process constraints. Three optimization cases were examined: (i) maximizing deposition rate subject to a uniformity requirement, (ii) minimizing nonuniformity with a minimum deposition constraint and (iii) maximizing the deposition-to-uniformity ratio. Optimal values of susceptor temperature and inlet gas velocity were obtained for each case. Findings The machine learning–guided optimization framework produced solutions that were both more accurate and computationally efficient than conventional optimization methods. Across all cases, the ML-based surrogate models achieved less than 5% deviation from CFD reference values, confirming their fidelity. Compared with traditional response surface–based optimization, the proposed framework reduced prediction errors by up to 40% and computational cost by approximately 60%. Originality/value This study introduces a novel hybrid methodology that integrates high-fidelity CFD simulation, advanced machine learning and constrained optimization. The approach reduces computational effort while retaining predictive fidelity, making it applicable for real-time control, digital twins and smart manufacturing of aerospace coatings. Furthermore, the methodology is extendable to other thin-film deposition technologies and multiphysics manufacturing processes.

Coupled effects of mixture stratification and momentum flux on flashback and blowoff limits in partially premixed hydrogen-air flames

International Journal of Hydrogen Energy · 2026-04-28

Effect of Porous Medium and Process Parameters on Silicon Deposition in a Cold-Wall CVD Reactor: A Numerical and Taguchi Approach

Special Topics & Reviews in Porous Media An International Journal · 2026-01-01

Porous Media Augmentation for CVD: A Hybrid CFD–Surrogate–GRA Framework for Transport Optimization

Transport in Porous Media · 2026-01-07

Flow Stabilization and Uniform Thin-Film Growth in Vertical CVD Reactors Using Porous Inserts: A Coupled Transport Analysis

SSRN Electronic Journal · 2025-01-01

Flashback Limit Analysis of Premixed Hydrogen-Air Flames with Porous Media Integration for Enhanced Combustion Stability

SSRN Electronic Journal · 2025-01-01

Effect of machining parameters on the machinability of 15‐5 precipitation hardened stainless steel during dry turning

Materialwissenschaft und Werkstofftechnik · 2025-01-28

Abstract This research presents the studies on the effect of machining variables and the empirical modeling of machinability output responses during dry turning of 15–5 precipitation‐hardened stainless steel (PHSS) using the taguchi meta‐heuristic algorithm. L 9 orthogonal array (OA) robust experimental design was selected for conducting the dry turning operations. The input variables included cutting velocity, depth of cut, and feed rate, while the output responses measured were surface roughness (R a ) and cutting force (F c ). The influence of these process variables was determined through analysis of variance (ANOVA). ANOVA results revealed that cutting speed, feed rate and depth of cut were impacting the average surface roughness by 36 %, 29 %, and 31 %, respectively and influencing the cutting force by 2 %, 16 %, and 72 %, respectively, during turning operation. Empirical models for predicting cutting force and surface roughness were developed using the Taguchi meta‐heuristic algorithm. The optimization process resulted in a significant reduction in surface roughness, with R a decreasing by 17 % and a notable decrease in cutting force, F c , by 8 %. These numerical improvements indicate that the proposed optimization approach substantially enhances machining performance, validating its effectiveness.

Enhancing Response Surface Models Using Machine Learning: A Case Study on Chemical Vapor Deposition

2025-08-17 · 1 citations

Abstract This paper focuses on using machine learning to improve response surface models that approximate the deposition rate and film uniformity of silicon deposition by chemical Vapor deposition process. Traditionally, Design of Experiment (DOE) strategies were employed to run computationally expensive models as a large number of runs could not be performed. Machine learning generally requires more runs than a traditional DOE strategy. However, over a period of time, some of these computationally expensive models became less computationally expensive due to the significant improvement in hardware capabilities which drastically reduces the time required to simulate the processes and could be subject to machine learning. The simulation, response surface modeling, and optimization of silicon deposition were documented by one of the authors earlier. This paper explores the possibility of improving the earlier generated response surface models using machine learning techniques - ANN and XGBoost. The results support that machine learning techniques better predict than the starting response surface model obtained by DOE strategy. It was found that XGBoost gives a better OPE and a lower maximum error when compared to the starting Response surface model. The percentage reduction in OPE was 44.06% for deposition rate and 42.52% for film uniformity compared to the response surface model.