Developing the logic for evaluating the indoor noise of a naval vessel using a back-propagation neural network

Hong, Hyun-Soo; Shim, Sang-Ryul; Han, Hyung-Suk

doi:10.1007/s12206-011-0804-2

Cited by 3 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is simple and direct, so it's easy to accomplish; however, it has a low prediction accuracy because it neglects the strong randomness and non-linearity of subjective evaluation. However, BPNN has the ability of self-learning and is self-adaptive, so it can realize complex non-linear mapping to better solve the nonlinear problem which can be difficult through mathematical formulas [10][11][12]. Therefore, it can be widely used in the vehicle industry.…”

Section: Sound Quality Prediction Of Vehicle Interior Noise and Mathe...mentioning

confidence: 99%

Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO)

Zhang

Hou

Shen

et al. 2015

Meas. Sci. Technol.

View full text Add to dashboard Cite

To better solve the complex non-linear problem between the subjective sound quality evaluation results and objective psychoacoustics parameters, a method for the prediction of the sound quality is put forward by using a back propagation neural network (BPNN) based on particle swarm optimization (PSO), which is optimizing the initial weights and thresholds of BP network neurons through the PSO. In order to verify the effectiveness and accuracy of this approach, the noise signals of the B-Class vehicles from the idle speed to 120 km h−1 measured by the artificial head, are taken as a target. In addition, this paper describes a subjective evaluation experiment on the sound quality annoyance inside the vehicles through a grade evaluation method, by which the annoyance of each sample is obtained. With the use of Artemis software, the main objective psychoacoustic parameters of each noise sample are calculated. These parameters include loudness, sharpness, roughness, fluctuation, tonality, articulation index (AI) and A-weighted sound pressure level. Furthermore, three evaluation models with the same artificial neural network (ANN) structure are built: the standard BPNN model, the genetic algorithm-back-propagation neural network (GA-BPNN) model and the PSO-back-propagation neural network (PSO-BPNN) model. After the network training and the evaluation prediction on the three models’ network based on experimental data, it proves that the PSO-BPNN method can achieve convergence more quickly and improve the prediction accuracy of sound quality, which can further lay a foundation for the control of the sound quality inside vehicles.

show abstract

Section: Sound Quality Prediction Of Vehicle Interior Noise and Mathe...mentioning

confidence: 99%

Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO)

Zhang

Hou

Shen

et al. 2015

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Noise and Exposure of Personnel Aboard Vessels in the Royal Norwegian Navy

Sunde

Irgens-Hansen

Moen

et al. 2014

The Annals of Occupational Hygiene

View full text Add to dashboard Cite

Despite awareness of noise aboard vessels at sea, few studies have reported measured noise levels aboard ships. This study aimed to describe the noise levels aboard vessels in the Royal Norwegian Navy (RNoN), and to assess the noise exposure of personnel aboard RNoN vessels. In 2012/2013 noise measurements were conducted aboard 14 RNoN vessels from four different vessel classes (frigates, coastal corvettes, mine vessels, and coast guard vessels) which were included in this study. Mean and median A-weighted noise levels (L p,A) in decibel (dB(A)) were calculated for different locations in each vessel class. The noise exposure of RNoN personnel was assessed by dosimeter measurements, and with a task-based (TB) strategy. The TB strategy used means of area measured noise levels in locations and the personnel's mean reported time spent in the respective locations to estimate the exposure. Area measurements of noise during sailing with typical operating modes, showed that for all vessel classes the noise levels were high in engine rooms with median L p,A ranging from 86.4 to 105.3 dB(A). In all the other locations the vessel class with the highest noise levels (coastal corvettes) had a median L p,A ranging from 71.7 to 95.0 dB(A), while the vessel class with the lowest noise levels (coast guard vessels) had a median L p,A ranging from 41.5 to 57.8 dB(A). For all vessel classes the engineers and electricians had amongst the highest 24-hour noise exposure (L p,A,24h), both before and after adjusting for estimated use of hearing protective devices (L p,A,24h > 67.3 dB(A)). The vessel class with the highest personnel exposure levels (coastal corvettes) had L p,A,24h ranging from 76.6 to 79.3 dB(A). The vessel class with the lowest personnel exposure levels (coast guard vessels) had an L p,A,24h ranging from 47.4 to 67.3 dB(A). In general, the dosimeter measurements gave higher exposure levels than those estimated with the TB strategy. All vessel classes, except the coast guard vessels, had noise levels exceeding the RNoN standard's recommended maximum noise levels. The area measured noise levels and the personnel's exposure estimates indicate that navy personnel aboard RNoN vessels are at risk of acquiring adverse health effects from exposure to noise, and that a program to reduce the noise levels should be implemented.

show abstract

Acoustic Comfort Evaluation of High-Speed Trains in Tunnels Based on Eeg Signals

Liu,

Han,

et al. 2024

Preprint

View full text Add to dashboard Cite

Developing the logic for evaluating the indoor noise of a naval vessel using a back-propagation neural network

Cited by 3 publications

References 5 publications

Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO)

Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO)

Noise and Exposure of Personnel Aboard Vessels in the Royal Norwegian Navy

Acoustic Comfort Evaluation of High-Speed Trains in Tunnels Based on Eeg Signals

Contact Info

Product

Resources

About