Artificial Intelligence and Reinforcement Learning for Real-Time Process Control in Non-Traditional Machining

Manufacturing industries face mounting pressure to produce precision components from exotic materials while maintaining cost-effectiveness. Non-traditional machining (NTM) techniques—spanning electrical discharge, laser-based, and ultrasonic approaches—provide pathways to handle materials conventional methods cannot address. The fundamental limitation plaguing current NTM adoption lies in maintaining process stability when parameters shift during production runs. This research presents an adaptive control strategy leveraging reinforcement learning algorithms to manage machining operations in real-time by continuously monitoring sensor inputs and modifying operational settings automatically. Using deep Q-learning networks trained on industrial sensor data, the system learns to balance competing manufacturing objectives: achieving target surface finishes while limiting tool degradation and preventing thermal distortion. On EDM and LBM operations, the developed controller demonstrated a 23% consistency improvement in surface characteristics and reduced overall variability by 31% versus conventional parameter-fixed approaches. Processing decisions complete within 50-millisecond windows, enabling the system to respond to sudden process changes. This investigation validates the utility of adaptive RL-based controllers for advancing manufacturing automation capabilities.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24331063
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

Artificial Intelligence and Reinforcement Learning for Real-Time Process Control in Non-Traditional Machining

Saarthak Dubey, Riyon Ignatius, Sampreeth N. Ganganagoudar, Rishi Chaudhari
4 links
Zenodo (CERN European Organization for Nuclear Research)
Advanced Machining and Optimization Techniques
article

Artificial Intelligence and Reinforcement Learning for Real-Time Process Control in Non-Traditional Machining

Saarthak Dubey, Riyon Ignatius, Sampreeth N. Ganganagoudar, Rishi Chaudhari
article en

Abstract

Manufacturing industries face mounting pressure to produce precision components from exotic materials while maintaining cost-effectiveness. Non-traditional machining (NTM) techniques—spanning electrical discharge, laser-based, and ultrasonic approaches—provide pathways to handle materials conventional methods cannot address. The fundamental limitation plaguing current NTM adoption lies in maintaining process stability when parameters shift during production runs. This research presents an adaptive control strategy leveraging reinforcement learning algorithms to manage machining operations in real-time by continuously monitoring sensor inputs and modifying operational settings automatically. Using deep Q-learning networks trained on industrial sensor data, the system learns to balance competing manufacturing objectives: achieving target surface finishes while limiting tool degradation and preventing thermal distortion. On EDM and LBM operations, the developed controller demonstrated a 23% consistency improvement in surface characteristics and reduced overall variability by 31% versus conventional parameter-fixed approaches. Processing decisions complete within 50-millisecond windows, enabling the system to respond to sudden process changes. This investigation validates the utility of adaptive RL-based controllers for advancing manufacturing automation capabilities.

Zenodo (CERN European Organization for Nuclear Research)
Industry, innovation and infrastructure
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