Graph-Structured Data Analysis of Component Failure in Autonomous Cargo Ships Based on Feature Fusion

2025-07-18

AI Summary

To address cascading failures and uncertain emergency decision-making triggered by component faults in autonomous cargo ships (ACS), this work constructs the first graph-structured dataset specifically designed for fault propagation modeling—encompassing 12 major shipboard systems, 1,262 fault modes, and 6,150 propagation paths. We propose a hybrid encoding framework that integrates multi-source semantic features (Word2Vec, BERT-KPCA, and Sentence-BERT) and introduce the HN-CSA optimization algorithm to enhance feature fusion efficiency. Furthermore, we design a GATE-GNN model to perform fault classification and propagation prediction directly on the graph structure. Experimental results demonstrate an overall classification accuracy of 0.735 and a maximum F1-score of 0.93 for critical systems, significantly improving fault discriminability and risk interpretability in ACS operational safety analysis.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Graphical Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

To address the challenges posed by cascading reactions caused by component failures in autonomous cargo ships (ACS) and the uncertainties in emergency decision-making, this paper proposes a novel hybrid feature fusion framework for constructing a graph-structured dataset of failure modes. By employing an improved cuckoo search algorithm (HN-CSA), the literature retrieval efficiency is significantly enhanced, achieving improvements of 7.1% and 3.4% compared to the NSGA-II and CSA search algorithms, respectively. A hierarchical feature fusion framework is constructed, using Word2Vec encoding to encode subsystem/component features, BERT-KPCA to process failure modes/reasons, and Sentence-BERT to quantify the semantic association between failure impact and emergency decision-making. The dataset covers 12 systems, 1,262 failure modes, and 6,150 propagation paths. Validation results show that the GATE-GNN model achieves a classification accuracy of 0.735, comparable to existing benchmarks. Additionally, a silhouette coefficient of 0.641 indicates that the features are highly distinguishable. In the label prediction results, the Shore-based Meteorological Service System achieved an F1 score of 0.93, demonstrating high prediction accuracy. This paper not only provides a solid foundation for failure analysis in autonomous cargo ships but also offers reliable support for fault diagnosis, risk assessment, and intelligent decision-making systems. The link to the dataset is https://github.com/wojiufukele/Graph-Structured-about-CSA.

Problem

• Analyze cascading failures in autonomous cargo ships using graph data
• Improve failure mode retrieval with enhanced cuckoo search algorithm
• Develop feature fusion framework for fault diagnosis and decision-making

Innovation

• Improved cuckoo search algorithm enhances retrieval efficiency
• Hierarchical feature fusion framework with Word2Vec and BERT
• GATE-GNN model achieves high classification accuracy