Saved in:
Bibliographic Details
Main Authors: Shang, Suiyan, Cheung, Chi Fai, Zheng, Pai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04665
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918085206736896
author Shang, Suiyan
Cheung, Chi Fai
Zheng, Pai
author_facet Shang, Suiyan
Cheung, Chi Fai
Zheng, Pai
contents Accurate surface roughness prediction in ultra-precision machining (UPM) is critical for real-time quality control, but small datasets hinder model performance. We propose HAS-CGAN, a Hybrid Adversarial Spectral Loss CGAN, for effective UPM data augmentation. Among five CGAN variants tested, HAS-CGAN excels in 1D force signal generation, particularly for high-frequency signals, achieving >0.85 wavelet coherence through Fourier-domain optimization. By combining generated signals with machining parameters, prediction accuracy significantly improves. Experiments with traditional ML (SVR, RF, LSTM) and deep learning models (BPNN, 1DCNN, CNN-Transformer) demonstrate that augmenting training data with 520+ synthetic samples reduces prediction error from 31.4% (original 52 samples) to ~9%, effectively addressing data scarcity in UPM roughness prediction."
format Preprint
id arxiv_https___arxiv_org_abs_2507_04665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Adversarial Spectral Loss Conditional Generative Adversarial Networks for Signal Data Augmentation in Ultra-precision Machining Surface Roughness Prediction
Shang, Suiyan
Cheung, Chi Fai
Zheng, Pai
Machine Learning
Accurate surface roughness prediction in ultra-precision machining (UPM) is critical for real-time quality control, but small datasets hinder model performance. We propose HAS-CGAN, a Hybrid Adversarial Spectral Loss CGAN, for effective UPM data augmentation. Among five CGAN variants tested, HAS-CGAN excels in 1D force signal generation, particularly for high-frequency signals, achieving >0.85 wavelet coherence through Fourier-domain optimization. By combining generated signals with machining parameters, prediction accuracy significantly improves. Experiments with traditional ML (SVR, RF, LSTM) and deep learning models (BPNN, 1DCNN, CNN-Transformer) demonstrate that augmenting training data with 520+ synthetic samples reduces prediction error from 31.4% (original 52 samples) to ~9%, effectively addressing data scarcity in UPM roughness prediction."
title Hybrid Adversarial Spectral Loss Conditional Generative Adversarial Networks for Signal Data Augmentation in Ultra-precision Machining Surface Roughness Prediction
topic Machine Learning
url https://arxiv.org/abs/2507.04665