Education, Science, Technology, Innovation and Life
Open Access
Sign In

Design of a ship fault diagnosis system based on a radial basis neural network

Download as PDF

DOI: 10.23977/jnca.2024.090104 | Downloads: 5 | Views: 136

Author(s)

Yiwen Liu 1

Affiliation(s)

1 Marine Engineering College, Jiangsu Shipping Vocational and Technical College, Nantong, 226010, China

Corresponding Author

Yiwen Liu

ABSTRACT

Marine diesel engines in the operation process often exhibit single-cylinder oil stops, uneven single-cylinder oil supplies, excessively large exhaust valve gaps, injection timing lags, and other errors. Technicians with experience often cannot accurately determine the fault type. To improve the accuracy of the fault diagnosis, a simulation experiment was carried out in MATLAB, the initial evaluation was carried out using the sensor, and the fault type was determined based on the radial basis neural network during deep diagnosis. The results showed that the radial-based neural network ship fault diagnosis system can stabilize the assessment accuracy by more than 90%, which improves the accuracy of the fault assessment of technicians, thus reducing the incidence of ship accidents.

KEYWORDS

MATLAB, RBF, Marine diesel engines, fault diagnosis, Confusion matrix (mathematical)

CITE THIS PAPER

Yiwen Liu, Design of a ship fault diagnosis system based on a radial basis neural network. Journal of Network Computing and Applications (2024) Vol. 9: 24-39. DOI: http://dx.doi.org/10.23977/jnca.2024.090104.

REFERENCES

[1] JIN Bingzhe, Chen Dongmei, Xu Zaiqiang. Development of diesel Engine Fault Diagnosis Software based on database and expert System [J]. Diesel Engine,2017,39(01):42-45.
[2] Xu Xiaojian. Research on Evidential Reasoning for Intelligent Diagnosis of Marine Diesel Engine Wear Failure [D]. Wuhan University of Technology, 2018.
[3] Ye Hongcai, Hou Tongyu, Zhang Defu. Fault diagnosis of marine diesel engine based on self-encoder[J]. Tianjin Navigation, 2023, (04):10-12.
[4] Liu XL. Research on data-based fault diagnosis of marine diesel engine[D]. Dalian Maritime University, 2022. DOI: 10.26989/d.cnki.gdlhu.2022.001694.
[5] Liu Xinlong, Zeng Hong, Dong Jianwei, et al. Fault diagnosis of marine diesel engine based on optimised stack self-encoder[J]. China Navigation, 2022, 45(04):45-51+57.
[6] Wang Yongjian, Fan Jinyu, Cai Hangxi, et al. Fault diagnosis of cylinder liner-piston ring of marine diesel engine based on improved EEMD-MB1DCNN[J]. Marine Engineering, 2024, 53(01):30-35.
[7] Lu Jiayin, Xu Feixiang, Lin Yejin. Fault diagnosis of marine diesel engine based on optimised deep limit learning machine [J]. Computer Application and Software, 2023, 40(08):50-58.

Downloads: 1371
Visits: 128833

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.