Hasan, Mohammad Mainul and Saleh, Tanveer and Sophian, Ali (2025) ANN-based ensemble model for predicting micro-EDM responses and machining variability. Machining Science and Technology. ISSN 1091-0344 E-ISSN 1532-2483
![]() |
PDF
- Accepted Version
Restricted to Registered users only Download (3MB) | Request a copy |
Abstract
Micro-electrical discharge machining (mEDM) requires high precision, quality and efficiency, yet machinists rely heavily on expertise and heuristics due to the complexity of the process and the use of machining different materials. This article introduces the use of artificial neural networks (ANNs) and ensemble models to predict key mEDM responses, such as machining time (MT), tool wear rate (TWR), overcut (OC) and taper angle (TA). The model incorporates material properties like thermal conductivity, melting point and electrical resistivity, along with input factors, including capacitance, voltage, feed rate, tool speed, tool diameter and workpiece type. Experimental data, collected using an I-optimal design of experiments (DOE) technique, was used to train the ANN models and optimized through grid search. The model’s accuracy, evaluated across training, testing and validation sets, showed mean accuracies between 76.84% and 86.62%. Deployment results revealed strong alignment between experimental and predicted outcomes, with predictions within a four standard deviation (4r) range. A user-friendly graphical interface (GUI) facilitates the prediction process, improving precision and decision-making in mEDM for various workpieces.
Item Type: | Article (Journal) |
---|---|
Uncontrolled Keywords: | ANN; grid-searchoptimization; machining variability; micro-EDM; model averaging |
Subjects: | T Technology > T Technology (General) |
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): | Kulliyyah of Engineering > Department of Mechatronics Engineering Kulliyyah of Engineering |
Depositing User: | Dr. Tanveer Saleh CEng MIMechE |
Date Deposited: | 26 Mar 2025 14:35 |
Last Modified: | 26 Mar 2025 14:35 |
URI: | http://irep.iium.edu.my/id/eprint/120297 |
Actions (login required)
![]() |
View Item |