A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning
Accurate prediction of ship underwater radiated noise (URN) during navigation is critical for evaluating acoustic stealth performance and analyzing detection risks. However, the labeled data available for the training of URN prediction model is limited. Semi-supervised learning (SSL) can improve the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/7/1303 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839615823360032768 |
|---|---|
| author | Xin Huang Rongwu Xu Ruibiao Li |
| author_facet | Xin Huang Rongwu Xu Ruibiao Li |
| author_sort | Xin Huang |
| collection | DOAJ |
| description | Accurate prediction of ship underwater radiated noise (URN) during navigation is critical for evaluating acoustic stealth performance and analyzing detection risks. However, the labeled data available for the training of URN prediction model is limited. Semi-supervised learning (SSL) can improve the model performance by using unlabeled data in the case of a lack of labeled data. Therefore, this paper proposes an SSL method for URN prediction. First, an anti-perturbation regularization is constructed using unlabeled data to optimize the objective function of EL, which is then used in the Genetic algorithm to adaptively optimize base learner weights, to enhance pseudo-label quality. Second, a semi-supervised ensemble (ESS) framework integrating dynamic pseudo-label screening and uncertainty bias correction (UBC) is established, which can dynamically select pseudo-labels based on local prediction performance improvement and reduce the influence of pseudo-labels’ uncertainty on the model. Experimental results of the cabin model and sea trials of the ship demonstrate that the proposed method reduces prediction errors by up to 65.5% and 62.1% compared to baseline supervised and semi-supervised regression models, significantly improving prediction accuracy. |
| format | Article |
| id | doaj-art-db4c57b65e4d4083a3e47cb6490afc66 |
| institution | Matheson Library |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-db4c57b65e4d4083a3e47cb6490afc662025-07-25T13:27:02ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-07-01137130310.3390/jmse13071303A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble LearningXin Huang0Rongwu Xu1Ruibiao Li2Laboratory of Vibration and Noise, Naval University of Engineering, Wuhan 430033, ChinaLaboratory of Vibration and Noise, Naval University of Engineering, Wuhan 430033, ChinaLaboratory of Vibration and Noise, Naval University of Engineering, Wuhan 430033, ChinaAccurate prediction of ship underwater radiated noise (URN) during navigation is critical for evaluating acoustic stealth performance and analyzing detection risks. However, the labeled data available for the training of URN prediction model is limited. Semi-supervised learning (SSL) can improve the model performance by using unlabeled data in the case of a lack of labeled data. Therefore, this paper proposes an SSL method for URN prediction. First, an anti-perturbation regularization is constructed using unlabeled data to optimize the objective function of EL, which is then used in the Genetic algorithm to adaptively optimize base learner weights, to enhance pseudo-label quality. Second, a semi-supervised ensemble (ESS) framework integrating dynamic pseudo-label screening and uncertainty bias correction (UBC) is established, which can dynamically select pseudo-labels based on local prediction performance improvement and reduce the influence of pseudo-labels’ uncertainty on the model. Experimental results of the cabin model and sea trials of the ship demonstrate that the proposed method reduces prediction errors by up to 65.5% and 62.1% compared to baseline supervised and semi-supervised regression models, significantly improving prediction accuracy.https://www.mdpi.com/2077-1312/13/7/1303radiated noise predictionsemi-supervised ensemble learninganti-perturbation regularizationadaptive weightinguncertainty bias correction |
| spellingShingle | Xin Huang Rongwu Xu Ruibiao Li A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning Journal of Marine Science and Engineering radiated noise prediction semi-supervised ensemble learning anti-perturbation regularization adaptive weighting uncertainty bias correction |
| title | A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning |
| title_full | A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning |
| title_fullStr | A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning |
| title_full_unstemmed | A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning |
| title_short | A Ship Underwater Radiated Noise Prediction Method Based on Semi-Supervised Ensemble Learning |
| title_sort | ship underwater radiated noise prediction method based on semi supervised ensemble learning |
| topic | radiated noise prediction semi-supervised ensemble learning anti-perturbation regularization adaptive weighting uncertainty bias correction |
| url | https://www.mdpi.com/2077-1312/13/7/1303 |
| work_keys_str_mv | AT xinhuang ashipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning AT rongwuxu ashipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning AT ruibiaoli ashipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning AT xinhuang shipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning AT rongwuxu shipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning AT ruibiaoli shipunderwaterradiatednoisepredictionmethodbasedonsemisupervisedensemblelearning |