# Marine diesel engine reliable intelligent fault diagnosis method based on the generalized multi-source information fusion

## TL;DR

This paper introduces a reliable intelligent method for diagnosing faults in marine diesel engines using multi-source thermal data fusion.

## Contribution

A novel generalized multi-source information fusion framework with improved Bayesian optimization and Dempster-Shafer fusion for marine engine fault diagnosis.

## Key findings

- The method achieves 99.45% accuracy, outperforming existing models in F1-score and recall.
- Critical thermal parameters like intercooler velocity and combustion pressure are identified as key indicators.
- TreeSHAP enhances model interpretability and guides effective feature selection.

## Abstract

Diesel engines provide essential power and energy guarantee for vessels. Due to scarce fault samples and complex parameter-fault coupling, traditional methods struggle in marine diesel engine diagnosis, underscoring the need for reliable intelligent approaches based on multi-source thermal parameter fusion. This article develops a reliable intelligent fault diagnosis method based on generalized multi-source information fusion. Key parameters are selected using Pearson correlation and mutual information, while an improved Bayesian optimization algorithm automatically tunes random forest parameters to enhance accuracy. TreeSHAP interprets parameter influence, guiding feature selection for retraining. An improved Dempster-Shafer evidence fusion strategy with Shannon entropy and Jousselme distance strengthens model decision-making. The method achieves 99.45% accuracy, outperforming existing models in F1-score and recall, and identifies critical thermal parameters such as intercooler velocity, maximum pressure during combustion, brake power, and velocity of the exhaust manifold. This approach provides a reliable, interpretable, and robust diagnostic tool for marine diesel engines.

•Generalized multi-source fusion framework for marine engine diagnosis is developed•TreeSHAP interprets model decisions and guides feature selection•PCEI-based Bayesian optimization tunes model hyperparameters automatically•Enhanced Dempster-Shafer evidence fusion ensures robust, accurate model decisions

Generalized multi-source fusion framework for marine engine diagnosis is developed

TreeSHAP interprets model decisions and guides feature selection

PCEI-based Bayesian optimization tunes model hyperparameters automatically

Enhanced Dempster-Shafer evidence fusion ensures robust, accurate model decisions

Simulation of computer system; Engineering; Energy modelling; Systems engineering