Saved in:
Bibliographic Details
Main Authors: Song, Xiaoyang, Sun, Wenbo, Kayitmazbatir, Metin, Jionghua, Jin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.19652
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909803900567552
author Song, Xiaoyang
Sun, Wenbo
Kayitmazbatir, Metin
Jionghua
Jin
author_facet Song, Xiaoyang
Sun, Wenbo
Kayitmazbatir, Metin
Jionghua
Jin
contents This paper proposes a deep learning-based approach for in-situ process monitoring that captures nonlinear relationships between in-control high-dimensional process signature signals and offline product quality data. Specifically, we introduce a Deep Canonical Correlation Analysis (DCCA)-based framework that enables the joint feature extraction and correlation analysis of multi-modal data sources, such as optical emission spectra and CT scan images, which are collected in advanced manufacturing processes. This unified framework facilitates online quality monitoring by learning quality-oriented representations without requiring labeled defective samples and avoids the non-normality issues that often degrade traditional control chart-based monitoring techniques. We provide theoretical guarantees for the method's stability and convergence and validate its effectiveness and practical applicability through simulation experiments and a real-world case study on Direct Metal Deposition (DMD) additive manufacturing.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19652
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quality-Ensured In-Situ Process Monitoring with Deep Canonical Correlation Analysis
Song, Xiaoyang
Sun, Wenbo
Kayitmazbatir, Metin
Jionghua
Jin
Applications
This paper proposes a deep learning-based approach for in-situ process monitoring that captures nonlinear relationships between in-control high-dimensional process signature signals and offline product quality data. Specifically, we introduce a Deep Canonical Correlation Analysis (DCCA)-based framework that enables the joint feature extraction and correlation analysis of multi-modal data sources, such as optical emission spectra and CT scan images, which are collected in advanced manufacturing processes. This unified framework facilitates online quality monitoring by learning quality-oriented representations without requiring labeled defective samples and avoids the non-normality issues that often degrade traditional control chart-based monitoring techniques. We provide theoretical guarantees for the method's stability and convergence and validate its effectiveness and practical applicability through simulation experiments and a real-world case study on Direct Metal Deposition (DMD) additive manufacturing.
title Quality-Ensured In-Situ Process Monitoring with Deep Canonical Correlation Analysis
topic Applications
url https://arxiv.org/abs/2509.19652