Procedia CIRP最新文献_第3页

Synthetic data generation in manufacturing: a review of methods, domains, and emerging trends 制造中的合成数据生成：方法、领域和新兴趋势的回顾

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-18 DOI: 10.1016/j.procir.2025.08.199

Sara Shafiee

{"title":"Synthetic data generation in manufacturing: a review of methods, domains, and emerging trends","authors":"Sara Shafiee","doi":"10.1016/j.procir.2025.08.199","DOIUrl":"10.1016/j.procir.2025.08.199","url":null,"abstract":"<div><div>Data scarcity remains a major barrier to the effective deployment of AI in manufacturing, where labeled data is often limited, costly, or difficult to obtain. This review investigates how synthetic data generation techniques are being applied to address this challenge in manufacturing AI applications. Eighteen recent papers (Jan 2024- May 2025) were analyzed and categorized based on generation methods, application domains, and data modalities. Techniques covered include GAN (Generative Adversarial Networks), VAEs (Variational Autoencoders), diffusion models, simulation-based approaches, SMOTE (Synthetic Minority Oversampling Technique), and hybrid combinations. Their use spans tasks such as defect detection, predictive maintenance, process modeling, material design, and human–robot collaboration. The review highlights emerging trends, methodological trade-offs, and practical challenges shaping the future of synthetic data in intelligent manufacturing systems. In addition to consolidating recent work, the review identifies underexplored research gaps and methodological challenges that shape future directions in synthetic data use for manufacturing AI.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 440-445"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Explainable AI-Guided Feature Refinement Framework for Surface Roughness Prediction in Robotic Drilling 机器人钻孔表面粗糙度预测的可解释ai引导特征细化框架

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-18 DOI: 10.1016/j.procir.2025.09.041

Dongpeng Li , Fang Hao , Zheng Ma , Yugi Ji , Pai Zheng , Weihua Li , Liang Liu , Shuo Chen

{"title":"An Explainable AI-Guided Feature Refinement Framework for Surface Roughness Prediction in Robotic Drilling","authors":"Dongpeng Li , Fang Hao , Zheng Ma , Yugi Ji , Pai Zheng , Weihua Li , Liang Liu , Shuo Chen","doi":"10.1016/j.procir.2025.09.041","DOIUrl":"10.1016/j.procir.2025.09.041","url":null,"abstract":"<div><div>In aircraft assembly, the low structural stiffness of industrial robots complicates surface quality control, and the opacity of conventional machine learning models hinders their adoption for process optimization. To address this, this paper presents a systematic Explainable AI-Guided Feature Refinement Framework to develop a minimal, yet robust, and physically interpretable model for surface roughness prediction in robotic drilling. The framework utilizes SHapley Additive exPlanations (SHAP) as an active component in an iterative feature selection process to refine a Random Forest model. The experimental validation on an integrated industrial platform demonstrates that this approach successfully identifies a minimal set of critical features from a high-dimensional dataset, including process parameters and specific vibration characteristics. The resulting model achieves superior predictive performance and stability compared to conventional feature selection methods. Furthermore, the analysis uncovers key non-linear relationships and feature interactions, providing interpretable insights into how operational parameters and dynamic responses collectively influence surface quality, which facilitates process optimization in robotic aircraft assembly.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 319-324"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Redesigning supply chains – An industrial case study 重新设计供应链——一个工业案例研究

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.011

Judit Monostori

引用次数: 0

Innovative Approaches to High-Level End-to-End Supply Chain Planning: Large Bucket Lot Sizing Strategies for Multifaceted Integration and Optimization 创新方法高层次的端到端供应链规划：大桶批量战略的多方面整合和优化

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.013

Flavio Tonelli , Massimo Paolucci , Antonio Giovannetti

引用次数: 0

An integrated re-planning ILP approach on the production capacity and sequence in the automotive industry. 汽车工业产能和生产顺序的综合再规划ILP方法。

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.022

Simon Gruber , Patricia Freyler , Clemens Gutschi , Nikolaus Furian , Ziga Letonja , Siegfried Vössner

引用次数: 0

Workforce and Logistics Centered Lineside Stock Optimization: A Case Study in automotive Industry. 以劳动力和物流为中心的一线库存优化：汽车行业的案例研究。

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.020

Benedikt Honeder , Clemens Gutschi , Simon Gruber , Nikolaus Furian , Siegfried Vössner

引用次数: 0

Towards a conceptual guideline for an economical assessment of manufacturing process data 为制造过程数据的经济评估提供一个概念性的指导方针

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.052

Johannes Mayer , Tobias Kaufmann , Philipp Niemietz , Thomas Bergs

引用次数: 0

A data-driven approach to determine tangential cutting force in turning operations using CNC control data 利用数控控制数据确定车削操作中切向切削力的数据驱动方法

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.074

Michal Demko , Jozef Brindza , István Sztankovics , Marek Vrabeľ , Ján Kušnír

引用次数: 0

Analysis of the deflection characteristics of straight-fluted milling tools with direction-dependent compliance behavior. 具有方向相关柔度行为的直槽铣刀的偏转特性分析。

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1016/j.procir.2026.01.085

Rafael Garcia Carballo , Melina Wenzel , Jonas Baumann , Dirk Biermann , Petra Wiederkehr

引用次数: 0

A Collaborative Bayesian Optimization Dashboard for Manufacturing Process Optimization 面向制造过程优化的协同贝叶斯优化仪表板

Procedia CIRP Pub Date : 2026-01-01 Epub Date: 2026-02-18 DOI: 10.1016/j.procir.2025.09.003

Lars Leyendecker , Mohamed Amine Kooli , Christian Wergers , Dennis Grunert , Robert H. Schmitt

{"title":"A Collaborative Bayesian Optimization Dashboard for Manufacturing Process Optimization","authors":"Lars Leyendecker , Mohamed Amine Kooli , Christian Wergers , Dennis Grunert , Robert H. Schmitt","doi":"10.1016/j.procir.2025.09.003","DOIUrl":"10.1016/j.procir.2025.09.003","url":null,"abstract":"<div><div>A central task in production engineering is the parameterization of manufacturing processes and machinery. The parameterization has a significant impact on product quality, process efficiency, and profitability of the production. Bayesian optimization (BO) - an adaptive black-box optimization algorithm for efficient and performance-optimal parameterization - has emerged in recent years as a promising alternative to conventional experimental design methods such as design of experiments, one factor at a time, or trial and error. Because optimization of manufacturing processes falls under the responsibility of human process experts, close collaboration between BO and human experts is key to successful optimization. Although first approaches to collaborative BO exist, intuitive dashboards that communicate and explain parameter suggestions and optimization progress to process experts are missing. In this paper, we propose a three-phase pipeline for collaborative BO, motivate the need for a collaborative Bayesian process optimization dashboard and define a total of 15 requirements for the dashboard design. Based on this, we propose a design concept for the BO-dashboard comprising multiple metrics and visualizations to explain parameter suggestions, create transparency in the optimization process, and promote the accumulation of process knowledge. We showcase the implementation of the dashboard at the example of optimizing an ultra-short pulsed laser ablation process. By enhancing human-BO collaboration, we aim to promote the adoption of BO within the conservative industry of production engineering.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 106-113"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0