# Siyuan Chen > Siyuan Chen (陈思远) is a PhD student in Production Systems at Chalmers University of Technology, Gothenburg, Sweden. Research: industrial AI, digital twins, prescriptive maintenance, reinforcement learning and robot programming. The publication pages distinguish journal articles, conference papers, preprints, a licentiate thesis and an award-winning essay. Original English abstracts are reproduced where available. Overview text is explanatory, not an additional publication. Cite the original work using its DOI and publication metadata; an arXiv DOI identifies the preprint, not published conference proceedings. ## Profile - [Personal website](https://siyuanchen2020.github.io/): Biography, education, research projects, experience and contact. - [ORCID](https://orcid.org/0000-0001-9399-3790): Researcher identity. - [Chalmers profile](https://www.chalmers.se/en/persons/siyuanc/): Institutional profile. ## Research library - [Publications](https://siyuanchen2020.github.io/publications/): English research library with links to individual publication pages. - [Chinese research library](https://siyuanchen2020.github.io/publications/zh/): Chinese explanations and original English abstracts. - [Swedish research library](https://siyuanchen2020.github.io/publications/sv/): Swedish explanations and original English abstracts. - [Bibliography](https://siyuanchen2020.github.io/publications/citations.bib): BibTeX for all listed works. ## Publication notes - [AI-enhanced digital twins in maintenance: Systematic review, industrial challenges, and bridging research–practice gaps](https://siyuanchen2020.github.io/publications/ai-digital-twins-maintenance-review/index.md): This review combines published research with industry interviews to examine AI-enhanced digital twins in maintenance. It identifies gaps between research and industrial practice and proposes a five-layer implementation framework. - [Comparison of Unsupervised Image Anomaly Detection Models for Sheet Metal Glue Lines](https://siyuanchen2020.github.io/publications/unsupervised-anomaly-detection-glue-lines/index.md): False alarms in glue-line inspection lead to unnecessary interventions and downtime. We compare 17 unsupervised models and 28 backbones on industrial images, examining detection accuracy, robustness and inference time with limited training data. - [A Transformer Approach for Remaining Useful Life Prediction and Fault Diagnosis of Mechanical Equipment](https://siyuanchen2020.github.io/publications/transformer-rul-fault-diagnosis/index.md): Equipment lifetime prediction and fault diagnosis are often modeled separately. This Transformer shares a sensor-data encoder across both tasks and is evaluated on data from 100 industrial machines. - [Retrieval-grounded robot program generation and simulation-based correction via Model Context Protocol](https://siyuanchen2020.github.io/publications/robot-program-generation-mcp/index.md): This workflow connects retrieval-grounded ABB RAPID generation to RobotStudio through MCP. Simulation feedback reveals execution errors that static code checks miss and supports iterative correction of robot programs. - [Enhancing Digital Twins with Deep Reinforcement Learning: A Use Case in Maintenance Prioritization](https://siyuanchen2020.github.io/publications/digital-twins-deep-reinforcement-learning/index.md): Maintenance priorities change with the state of a production system. This study combines a digital twin with proximal policy optimization to prioritize maintenance tasks in a lab-scale drone factory. - [LLM-enhanced multi-agent reinforcement learning for human-centric prescriptive maintenance in manufacturing](https://siyuanchen2020.github.io/publications/llm-multi-agent-prescriptive-maintenance/index.md): Maintenance logs contain diagnostic knowledge that numerical-only agents cannot use directly. This preprint combines local LLMs with hierarchical multi-agent reinforcement learning and a production-cost reward in a lab-scale drone assembly study. - [Towards Prescriptive Maintenance Using Digital Twins and Artificial Intelligence](https://siyuanchen2020.github.io/publications/prescriptive-maintenance-licentiate-thesis/index.md): This licentiate thesis examines the transition from failure prediction to actionable maintenance decisions. It brings together five studies on industrial requirements, digital twins, reinforcement learning and anomaly detection. - [Understanding Stakeholder Requirements for Digital Twins In Manufacturing Maintenance](https://siyuanchen2020.github.io/publications/stakeholder-requirements-digital-twins/index.md): Interviews and a workshop identify what industrial stakeholders need from a maintenance digital twin. The study maps implementation requirements, decision-support needs and barriers to adoption. - [Developing RAGs for robot code generation](https://siyuanchen2020.github.io/publications/rag-robot-code-generation/index.md): Robot code generation needs reliable, domain-specific engineering knowledge. This paper explores RAG architectures that ground language models in controlled sources while retaining human oversight and traceability. - [Data-Driven Smart Maintenance Decision Analysis: A Drone Factory Demonstrator Combining Digital Twins and Adapted AHP](https://siyuanchen2020.github.io/publications/digital-twin-maintenance-decision-analysis/index.md): A drone-factory digital twin supports maintenance comparisons without interrupting real production. The demonstrator evaluates what-if scenarios and combines performance indicators with structured decision analysis. - [Toward Cognitive Augmentation: Personalization and Standardization of Humanoid Social Robot Instruction](https://siyuanchen2020.github.io/publications/humanoid-robot-personalized-instruction/index.md): Adaptive robot instruction can change the demands placed on industrial trainees. This study compares standard and personalized humanoid-robot instructions, examining mental workload and task performance. - [Synthetic simulated environment for discrete manufacturing systems: A demonstrator through a computational modeling approach](https://siyuanchen2020.github.io/publications/synthetic-simulation-manufacturing/index.md): This PyTorch-based simulation generates synthetic data for discrete manufacturing systems. Timed Petri nets and a directed graph represent production flow, creating an expandable environment for manufacturing AI experiments. - [Leveraging generative AI for smart maintenance: navigating technological tipping points in manufacturing](https://siyuanchen2020.github.io/publications/generative-ai-smart-maintenance-essay/index.md): This award-winning essay examines opportunities and barriers for generative AI in industrial maintenance. It discusses synthetic data, workforce learning, implementation costs, data quality and governance. ## Optional - [Structured publication records](https://siyuanchen2020.github.io/data/publications.json): Bibliography, source URLs, abstracts and localized explanations. - [Sitemap](https://siyuanchen2020.github.io/sitemap.xml): Indexable HTML pages.