Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
Add more filters










Database
Language
Publication year range
1.
Math Biosci Eng ; 19(11): 11453-11490, 2022 08 10.
Article in English | MEDLINE | ID: mdl-36124599

ABSTRACT

Preventive identification of mechanical parts failures has always played a crucial role in machine maintenance. Over time, as the processing cycles are repeated, the machinery in the production system is subject to wear with a consequent loss of technical efficiency compared to optimal conditions. These conditions can, in some cases, lead to the breakage of the elements with consequent stoppage of the production process pending the replacement of the element. This situation entails a large loss of turnover on the part of the company. For this reason, it is crucial to be able to predict failures in advance to try to replace the element before its wear can cause a reduction in machine performance. Several systems have recently been developed for the preventive faults detection that use a combination of low-cost sensors and algorithms based on machine learning. In this work the different methodologies for the identification of the most common mechanical failures are examined and the most widely applied algorithms based on machine learning are analyzed: Support Vector Machine (SVM) solutions, Artificial Neural Network (ANN) algorithms, Convolutional Neural Network (CNN) model, Recurrent Neural Network (RNN) applications, and Deep Generative Systems. These topics have been described in detail and the works most appreciated by the scientific community have been reviewed to highlight the strengths in identifying faults and to outline the directions for future challenges.


Subject(s)
Algorithms , Machine Learning , Neural Networks, Computer , Support Vector Machine
2.
Article in English | MEDLINE | ID: mdl-35162140

ABSTRACT

Environmental legislation in Ecuador is advancing with the legitimate aspiration of providing citizens with new standards of quality and environmental health. In the context of environmental noise, these legislative advances are based on the experience accumulated in other countries, which is an advantage that must be managed with caution by incorporating local factors into noise management procedures. This study advances two lines of work. The first is to survey the population about their attitude towards noise from a major road to try to detect local factors in the annoyance and sleep disturbances. The second uses this information to compare noise indicators for the detection and ranking of hot-spots from major roads. The interviewees exhibited a high level of annoyance and sleep disturbance due to noise compared with the results of other studies. Results show that there are small differences in the definition of hot-spots when using WHO's dose-response curves for Lden ≥ 68 dB for and for Lnight ≥ 58 dB, in comparison with the curves generated in this study (CS). Regarding the application of both dose-response curves (WHO vs. CS) to the estimation of the population at risk of the harmful effect of nighttime traffic noise (HSD), small oscillations are also observed even when Lnight ≥ 58 dB and Lnoche ≥ 60 dB are used.


Subject(s)
Noise, Transportation , Sleep Wake Disorders , Ecuador , Environmental Exposure , Humans , Noise, Transportation/adverse effects , Sleep Wake Disorders/epidemiology , Surveys and Questionnaires
3.
Article in English | MEDLINE | ID: mdl-36613032

ABSTRACT

The acoustic environment has been pointed out as a possible distractor during student activities in the online academic modality; however, it has not been specifically studied, nor has it been studied in relation to parameters frequently used in academic-quality evaluations. The objective of this study is to characterize the acoustic environment and relate it to students' satisfaction with the online learning modality. For that, three artificial neural networks were calculated, using as target variables the students' satisfaction and the noise interference with autonomous and synchronous activities, using acoustic variables as predictors. The data were obtained during the COVID-19 lockdown, through an online survey addressed to the students of the Universidad de Las Américas (Quito, Ecuador). Results show that the noise interference with comprehensive reading or with making exams and that the frequency of noises, which made the students lose track of the lesson, were relevant factors for students' satisfaction. The perceived loudness also had a remarkable influence on engaging in autonomous and synchronous activities. The performance of the models on students' satisfaction and on the noise interference with autonomous and synchronous activities was satisfactory given that it was built only with acoustic variables, with correlation coefficients of 0.567, 0.853, and 0.865, respectively.


Subject(s)
COVID-19 , Education, Distance , Humans , Universities , COVID-19/epidemiology , Communicable Disease Control , Students , Personal Satisfaction
4.
J Acoust Soc Am ; 150(1): 51, 2021 07.
Article in English | MEDLINE | ID: mdl-34340477

ABSTRACT

Metamaterials are designed by arranging artificial structural elements according to periodic geometries to obtain advantageous and unusual properties when they are hit by waves. Initially designed to interact with electromagnetic waves, their use naturally extended to sound waves, proving to be particularly useful for the construction of containment and soundproofing systems in buildings. In this work, a new metamaterial has been developed with the use of a polyvinyl chloride membrane on which buttons have been glued. Two types of buttons were used, with different weights, placing them on the membrane according to a radial geometry. Each sample of metamaterial was subjected to sound absorption coefficient measurements using the impedance tube. Measurements were made using the samples by setting three configurations, creating a cavity with different thicknesses. The results of the measurements were subsequently used as input for training a simulation model based on artificial neural networks. The model showed an excellent generalization capacity, returning estimates of the acoustic absorption coefficient of the metamaterial very similar to the measured value. Subsequently, the model was used to perform a sensitivity analysis to evaluate the contribution of the various input variables on the returned output.


Subject(s)
Acoustics , Sound , Computer Simulation , Neural Networks, Computer
5.
Article in English | MEDLINE | ID: mdl-27657105

ABSTRACT

High flows of road traffic noise in urban agglomerations can negatively affect the livability of squares and parks located at the neighborhood, district and city levels, therefore pushing anyone who wants to enjoy calmer, quieter areas to move to non-urban parks. Due to the distances between these areas, it is not possible to go as regularly as would be necessary to satisfy any needs. Even if cities are densely populated, the presence of a sea or riverfront offers the possibility of large restorative places, or at least with potential features for being the natural core of an urban nucleus after a renewal intervention. This study evaluates the soundscape of the Naples waterfront, presenting an overview of the most significant visual, acoustic and spatial factors related to the pedestrian areas, as well as areas open to road traffic and others where the road traffic is limited. The factors were chosen with feature selection methods and artificial neural networks. The results show how certain factors, such as the perimeter between the water and promenade, the visibility of the sea or the density of green areas, can affect the perception of the soundscape quality in the areas with road traffic. In the pedestrian areas, acoustic factors, such as loudness or the A-weighted sound level exceeded for 10% of the measurement duration (LA10), influence the perceived quality of the soundscape.

6.
J Occup Environ Hyg ; 13(6): 464-75, 2016.
Article in English | MEDLINE | ID: mdl-26853828

ABSTRACT

Dosimetric measurements carried out on basketball referees have shown that whistles not only generate very high peak sound pressure levels, but also play a relevant role in determining the overall exposure to noise of the exposed subjects. Because of the peculiar geometry determined by the mutual positions of the whistle, the microphone, and the ear, experimental data cannot be directly compared with existing occupational noise exposure and/or action limits. In this article, an original methodology, which allows experimental results to be reliably compared with the aforementioned limits, is presented. The methodology is based on the use of two correction factors to compensate the effects of the position of the dosimeter microphone (fR) and of the sound source (fS). Correction factors were calculated by means of laboratory measurements for two models of whistles (Fox 40 Classic and Fox 40 Sonik) and for two head orientations (frontal and oblique).Results sho w that for peak sound pressure levels the values of fR and fS, are in the range -8.3 to -4.6 dB and -6.0 to -1.7 dB, respectively. If one considers the Sound Exposure Levels (SEL) of whistle events, the same correction factors are in the range of -8.9 to -5.3 dB and -5.4 to -1.5 dB, respectively. The application of these correction factors shows that the corrected weekly noise exposure level for referees is 80.6 dB(A), which is slightly in excess of the lower action limit of the 2003/10/EC directive, and a few dB below the Recommended Exposure Limit (REL) proposed by the National Institute for Occupational Safety and Health (NIOSH). The corrected largest peak sound pressure level is 134.7 dB(C) which is comparable to the lower action limit of the 2003/10/EC directive, but again substantially lower than the ceiling limit of 140 dB(A) set by NIOSH.


Subject(s)
Basketball , Hearing Loss, Noise-Induced/etiology , Noise, Occupational/adverse effects , Occupational Exposure/adverse effects , Sound/adverse effects , Humans , Italy
SELECTION OF CITATIONS
SEARCH DETAIL
...