Prediction and Analysis of Ship Engine Vibration Signals Based on Prompted Language Models
The stable operation of ship engines is vital for ensuring the safe navigation of autonomous ships. Vibration signal detection is a widely adopted method for monitoring engine conditions. With the rapid advancements in large language models (LLMs), exploring their applications in autonomous ship sys...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tamkang University Press
2025-06-01
|
| Series: | Journal of Applied Science and Engineering |
| Subjects: | |
| Online Access: | http://jase.tku.edu.tw/articles/jase-202603-29-03-0008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The stable operation of ship engines is vital for ensuring the safe navigation of autonomous ships. Vibration signal detection is a widely adopted method for monitoring engine conditions. With the rapid advancements in large language models (LLMs), exploring their applications in autonomous ship systems has become a key research focus. This study investigates the use of LLMs for analyzing continuous time-series signals in the maritime domain and proposes a novel approach to predicting marine diesel engine vibration signals. A method utilizing prompt templates was designed to transform numerical signals into textual representations, enabling LLMs to process them effectively. The proposed approach was compared with traditional models, including LSTM, RNN, and SVR, in vibration signal prediction tasks. Experimental results demonstrate that the LLM-based method not only outperforms these baselines under certain conditions but also exhibits enhanced robustness in handling missing data. This research offers new insights into integrating LLMs into intelligent monitoring systems for autonomous ships. |
|---|---|
| ISSN: | 2708-9967 2708-9975 |