Hybrid Adversarial Spectral Loss Conditional Generative Adversarial Networks for Signal Data Augmentation in Ultra-precision Machining Surface Roughness Prediction

2025/07/07 by Shang, Suiyan, Cheung, Chi Fai, Zheng, Pai
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2507.04665

Abstract

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."

Citations

• NASPrecision: Neural Architecture Search-Driven Multi-Stage Learning for Surface Roughness Prediction in Ultra-Precision Machining
• Data augmentation approaches for improving animal audio classification
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Conditional Generative Adversarial Networks for Emoji Synthesis with\n Word Embedding Manipulation
• Are GANs Created Equal? A Large-Scale Study
• Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation
• InfoVAE: Information Maximizing Variational Autoencoders
• Improved Training of Wasserstein GANs
• Wasserstein GAN
• Conditional Image Synthesis With Auxiliary Classifier GANs
• On-machine and in-process surface metrology for precision manufacturing

Related

• NASPrecision: Neural Architecture Search-Driven Multi-Stage Learning for Surface Roughness Prediction in Ultra-Precision Machining
• Efficient Milling Quality Prediction with Explainable Machine Learning
• Sharing Information Between Machine Tools to Improve Surface Finish Forecasting
• Data-driven prediction of tool wear using Bayesian-regularized artificial neural networks
• Development of hybrid intelligent models for prediction machining performance measure in end milling of Ti6Al4V alloy with PVD coated tool under dry cutting conditions