Machine learning optimization of micromachining parameters for improved surface characteristics

Micro machining has become increasingly prevalent due to the ongoing trend toward miniaturizing manufactured products. This study investigated the effect of a titanium nitride (TiN)- coated tungsten carbide electrode on the micro-discharge machining (micro-EDM) performance of high-speed steel (HSS). A factorial experimental design was employed to investigate the effects of current, servo feed rate, and pulse-on and pulse-off times on material removal rate (MRR), tool wear rate (TWR), and surface roughness (Ra). Analysis of variance (ANOVA) was used to evaluate the influence of the machining parameters; Taguchi-based optimization was applied to identify the optimal settings, and a feedforward artificial neural network (ANN) was developed to predict the machining responses. The optimum machining parameters suggested by Taguchi parametric design were a current of 3.5 A, a pulse-on time of 33 μs, a servofeed rate of 12 mm/min, and a pulse-off time of 9 μs, resulting in an MRR of 0.618 g/min and an Ra of 2.28 μm. Surface quality analysis showed that the treatment improved MRR by approximately 20% compared with uncoated electrodes. ANOVA showed that current had the strongest influence on TWR, accounting for 94.82% of the variation, whereas pulse-on time significantly affected surface roughness, contributing 24.35%. We established a feedforward propagation-based artificial neural network (ANN) model to forecast machining responses, showing good agreement between experimental and predicted results. Integrating experimental and ANN-based modeling provided an effective framework for optimizing the micro-EDM process and improving machining accuracy and process consistency, demonstrating its potential for advanced manufacturing applications in the aerospace and biomedical industries.

Authors

Publication Details

Journal
Surface Review and Letters
Published
2026-11-13
DOI
https://doi.org/10.1142/s0218625x26501386
Primary Topic
Advanced Machining and Optimization Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning optimization of micromachining parameters for improved surface characteristics

Amit Thakur, Kamal Hassan, Vinny John, Anita Gehlot et al.
Surface Review and Letters
Advanced Machining and Optimization Techniques
article

Machine learning optimization of micromachining parameters for improved surface characteristics

Amit Thakur, Kamal Hassan, Vinny John, Anita Gehlot, Saurabh Aggarwal, Rajesh Singh, Vivek John
article en

Abstract

Micro machining has become increasingly prevalent due to the ongoing trend toward miniaturizing manufactured products. This study investigated the effect of a titanium nitride (TiN)- coated tungsten carbide electrode on the micro-discharge machining (micro-EDM) performance of high-speed steel (HSS). A factorial experimental design was employed to investigate the effects of current, servo feed rate, and pulse-on and pulse-off times on material removal rate (MRR), tool wear rate (TWR), and surface roughness (Ra). Analysis of variance (ANOVA) was used to evaluate the influence of the machining parameters; Taguchi-based optimization was applied to identify the optimal settings, and a feedforward artificial neural network (ANN) was developed to predict the machining responses. The optimum machining parameters suggested by Taguchi parametric design were a current of 3.5 A, a pulse-on time of 33 μs, a servofeed rate of 12 mm/min, and a pulse-off time of 9 μs, resulting in an MRR of 0.618 g/min and an Ra of 2.28 μm. Surface quality analysis showed that the treatment improved MRR by approximately 20% compared with uncoated electrodes. ANOVA showed that current had the strongest influence on TWR, accounting for 94.82% of the variation, whereas pulse-on time significantly affected surface roughness, contributing 24.35%. We established a feedforward propagation-based artificial neural network (ANN) model to forecast machining responses, showing good agreement between experimental and predicted results. Integrating experimental and ANN-based modeling provided an effective framework for optimizing the micro-EDM process and improving machining accuracy and process consistency, demonstrating its potential for advanced manufacturing applications in the aerospace and biomedical industries.

Surface Review and Letters
Advanced Machining and Optimization Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon