Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion

Muhammad Rizwan Awan; Volker Pickert; Muhammad Waqar Ashraf; Saleh Ali; Farshid Mahmouditabar; Shafiq Odhano

cs.LGApr 5, 2026

Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion

Authors: Muhammad Rizwan Awan, Volker Pickert, Muhammad Waqar Ashraf, Saleh Ali, Farshid Mahmouditabar, Shafiq Odhano

Organizations: Department of Electrical and Electronic Engineering, The Newcastle University · The Sargent Centre for Process Systems Engineering, Department of Chemical Engineering, University College London, Torrington Place, London, WC1E 7JE, UK

Abstract

Laser Powder Bed Fusion (LPBF) is highly sensitive to process parameters, which influence defect formation through complex thermal and fluid mechanisms. However, defect-related knowledge is dispersed across the literature, limiting systematic understanding. This study presents a graph-assisted retrieval framework for defect reasoning in LPBF, using Ti6Al4V as a case study. Scientific publications are transformed into a structured representation, and relationships between parameters, mechanisms, and defects are encoded into an evidence-linked knowledge graph. The framework integrates semantic and graph-based retrieval, supported by a lightweight agent-based reasoning layer to construct interpretable defect pathways. Evaluation shows high retrieval accuracy (0.9667) and recall (0.9667), demonstrating effective identification of relevant defect related evidence. The framework enables transparent reasoning chains linking process parameters to defects. This work provides a scalable approach for converting unstructured literature into a query able and interpretable knowledge resource for additive manufacturing.

Figures & tables

Figure 3: Agent based graph assisted retrieval framework

Question ID	Query Type	Precision	Recall	F1-score	Accuracy
Q1	Explanation	0.60	1.00	0.75	1.00
Q2	Explanation	0.50	1.00	0.67	1.00
Q3	Lookup	0.67	1.00	0.80	1.00
Q4	Explanation	0.50	1.00	0.67	1.00
Q5	Explanation	0.50	1.00	0.67	1.00
Q6	General	0.60	1.00	0.75	1.00

Table 1: Performance Metrics by Question ID

Additive Manufacturing

Additive manufacturing builds parts layer by layer and improves their materials, process control, inspection, and design.

See all 50 papers

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion
May 1, 2026Basit Mahmud Shahriar, Md Habibor RahmanIndustrial Inspection LLM Decision-Making
Department of Mechanical Engineering, University of Massachusetts Dartmouth, Dartmouth, MA 02747, USA
Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection
Apr 27, 2026Stefano Raimondo, Matteo Bugatti, Marco GrassoGraph Neural Networks U-Net
Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy · Department of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, Italy
Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach
Jun 22, 2026Inioluwa Emmanuel, Zhuo Yang, Ho Yeung +1Industrial Anomaly Detection Transfer Learning
Industrial and Manufacturing Engineering Florida State University Tallahassee, FL · National Institute of Standards and Technology Gaithersburg, Maryland

May 1, 2026J/K move · Enter open · S save

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

Basit Mahmud Shahriar, Md Habibor Rahman

Department of Mechanical Engineering, University of Massachusetts Dartmouth, Dartmouth, MA 02747, USA

Industrial Inspection LLM Decision-Making

Open paper AskPDF arXiv

This work presents a knowledge-driven decision-support system that integrates structured defect knowledge with LLM-based reasoning to provide explainable defect diagnosis and mitigation guidance in manufacturing, using LPBF as a representative, safety-critical case study. The proposed ontology-integrated LLM-based decision support system for LPBF defect analysis and mitigation guidance is built on a knowledge base containing 27 known LPBF defect types organized into hierarchical categories and causal relationships. The developed system supports fuzzy natural language queries for systematic knowledge retrieval, literature-supported explanation of defects, and guidance on defect causes and mitigation strategies derived from encoded process knowledge. Furthermore, a multimodal image-assessment module based on foundation models enables descriptor-guided interpretation of representative microscopic defect images through semantic alignment scoring. The proposed framework was evaluated through qualitative comparisons with general-purpose vision-language models, an ablation study, and an inter-rater reliability analysis. Evaluation on the literature-derived dataset showed that the fully integrated configuration outperformed the other three evaluated system configurations, achieving a macro-average F1 score of 0.808. Additionally, inter-rater reliability analysis using Cohen's kappa indicated substantial agreement between the model outputs and the literature-derived reference labels. These findings suggest that ontology-guided knowledge representation can improve the consistency, interpretability, and practical usefulness of LLM-assisted LPBF defect analysis.

Abstract

Additive Manufacturing

Explore similar work

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection

Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach