Hearing-impaired persons often find it extremely difficult to catch and identify environmental sounds, which often include a wide variety of information types that would help them to function more effectively in their surrounding environments. Because of this, it would be very helpful if such persons could be supported by providing them with various kinds of event information in the form of visual data. The ultimate purpose of this research is to classify various types of environmental sounds that can provide important clues from the viewpoint of safe-living and then apply machine learning techniques to visually display that information in real time on smartglasses. Specifically, our method extracts the acoustic features of environmental sounds from their time-, frequency-, and time-frequency-domain characteristics and then classifies those sounds based on their extracted features. Ultimately, such information will be visually displayed on smartglasses, thus allowing hearing-impaired persons to process those environmental sounds while continuing to observe the world around them in a normal manner. In this paper, the validity of our empirical and academic research into machine learning-based environmental sound classifications is discussed.
{"title":"Case study: Empirical study on indoor environmental sound classification to support hearing-impaired persons","authors":"M. Nakaya, T. Asakura","doi":"10.3397/1/377034","DOIUrl":"https://doi.org/10.3397/1/377034","url":null,"abstract":"Hearing-impaired persons often find it extremely difficult to catch and identify environmental sounds, which often include a wide variety of information types that would help them to function more effectively in their surrounding environments. Because of this, it would be very helpful\u0000 if such persons could be supported by providing them with various kinds of event information in the form of visual data. The ultimate purpose of this research is to classify various types of environmental sounds that can provide important clues from the viewpoint of safe-living and then apply\u0000 machine learning techniques to visually display that information in real time on smartglasses. Specifically, our method extracts the acoustic features of environmental sounds from their time-, frequency-, and time-frequency-domain characteristics and then classifies those sounds based on their\u0000 extracted features. Ultimately, such information will be visually displayed on smartglasses, thus allowing hearing-impaired persons to process those environmental sounds while continuing to observe the world around them in a normal manner. In this paper, the validity of our empirical and academic\u0000 research into machine learning-based environmental sound classifications is discussed.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45763714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Active noise control technology shows good performance in those low-frequency narrowband noise control applications. Suffering from time-varying frequencies and secondary path, the performance of narrowband active noise control system may deteriorate seriously. In this work, an improved narrowband active noise control system is proposed to improve the noise reduction performance in those time-varying system. In the improved system, a frequency tracker based on the adaptive notch filter is adopted to estimate the frequencies of the noise signal. The result of frequency estimation is used to generate the reference signal and the prior information of the secondary-path modeling process. Then, the local secondary-path modeling can be conducted in the system with unknown fixed tonal noise signal or time-varying tones. Simulations and experiments are conducted to verify the performance of the proposed algorithm, and the results show that the proposed algorithm has good behavior.
{"title":"An improved parallel narrowband active noise control system with local on-line secondary-path modeling equipped with frequency estimation algorithm","authors":"Han Wang, Honglin Sun, Ming Wu, Jianfeng Guo","doi":"10.3397/1/377040","DOIUrl":"https://doi.org/10.3397/1/377040","url":null,"abstract":"Active noise control technology shows good performance in those low-frequency narrowband noise control applications. Suffering from time-varying frequencies and secondary path, the performance of narrowband active noise control system may deteriorate seriously. In this work, an improved\u0000 narrowband active noise control system is proposed to improve the noise reduction performance in those time-varying system. In the improved system, a frequency tracker based on the adaptive notch filter is adopted to estimate the frequencies of the noise signal. The result of frequency estimation\u0000 is used to generate the reference signal and the prior information of the secondary-path modeling process. Then, the local secondary-path modeling can be conducted in the system with unknown fixed tonal noise signal or time-varying tones. Simulations and experiments are conducted to verify\u0000 the performance of the proposed algorithm, and the results show that the proposed algorithm has good behavior.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41905891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Liu, Kai Shi, Jieyu Li, Hai-Zhen Sun, Qianghfu Zhao
In this paper, an in-plane Z-shaped structure with multi-span elastic supports is proposed to investigate the natural frequency and transmission response through employing in-plane governing equation and transfer matrix method. Based on the solutions of transverse vibration and torsional vibration, the total transfer matrix for the Z-shaped structure with multi-span elastic supports is derived. Furthermore, natural frequencies and mode shapes of the Z-shaped structure are calculated. Finite element simulation method (FEM) is conducted here to verify the theoretical results. In order to effectively evaluate the vibration reduction performance, transmission response of the Z-shaped structure under different boundary supports and multi-span elastic supports is analyzed. This work is significant for the vibration reduction of in-plane Z-shaped structure, especially the multi-span elastic support case in engineering applications.
{"title":"Free and forced vibration analysis of a Z-shaped structure with multi-span elastic supports","authors":"Wei Liu, Kai Shi, Jieyu Li, Hai-Zhen Sun, Qianghfu Zhao","doi":"10.3397/1/377037","DOIUrl":"https://doi.org/10.3397/1/377037","url":null,"abstract":"In this paper, an in-plane Z-shaped structure with multi-span elastic supports is proposed to investigate the natural frequency and transmission response through employing in-plane governing equation and transfer matrix method. Based on the solutions of transverse vibration and torsional\u0000 vibration, the total transfer matrix for the Z-shaped structure with multi-span elastic supports is derived. Furthermore, natural frequencies and mode shapes of the Z-shaped structure are calculated. Finite element simulation method (FEM) is conducted here to verify the theoretical results.\u0000 In order to effectively evaluate the vibration reduction performance, transmission response of the Z-shaped structure under different boundary supports and multi-span elastic supports is analyzed. This work is significant for the vibration reduction of in-plane Z-shaped structure, especially\u0000 the multi-span elastic support case in engineering applications.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42575791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ambient day and night noise levels prediction problems have traditionally been addressed using various statistical and machine learning methods. This paper presents the time-series predictions and forecasting of ambient noise levels using support vector machine (SVM) and deep learning method such as convolutional neural network (CNN) approach. This approach has been rarely reported for modeling ambient noise levels so far, although it has been widely used in air and water pollution predictions and forecasting. The study presents the applications of these techniques in time-series modeling of ambient day and night equivalent noise levels. A case study of ambient noise levels of one site each lying in commercial, residential, industrial and silence zone is presented. Ten-fold cross-validation is used in SVM model to train the model effectively and determine the optimized value of hyper-parameter (g, «, C). Also, CNN with a convolutional and pooling layer architecture framework is designed with optimum value of batch size, activation function, and filter size, among others. The validation and suitability of developed SVM and CNN models are ascertained by various statistical tests. Convolutional neural network approach is observed to outperform SVM model and thus can be a reliable approach for time-series modeling of ambient noise levels with a prediction error of 2.1 dB(A). The forecasting root mean squared error obtained for all the four zones using CNN model is observed to be less than 2.1 dB(A) for day equivalent noise levels and 1.9 dB(A) for night equivalent noise levels.
{"title":"Time-series prediction and forecasting of ambient noise levels using deep learning and machine learning techniques","authors":"Sourabh Tiwari, L. Kumaraswamidhas, Nakul Garg","doi":"10.3397/1/377039","DOIUrl":"https://doi.org/10.3397/1/377039","url":null,"abstract":"Ambient day and night noise levels prediction problems have traditionally been addressed using various statistical and machine learning methods. This paper presents the time-series predictions and forecasting of ambient noise levels using support vector machine (SVM) and deep learning\u0000 method such as convolutional neural network (CNN) approach. This approach has been rarely reported for modeling ambient noise levels so far, although it has been widely used in air and water pollution predictions and forecasting. The study presents the applications of these techniques in time-series\u0000 modeling of ambient day and night equivalent noise levels. A case study of ambient noise levels of one site each lying in commercial, residential, industrial and silence zone is presented. Ten-fold cross-validation is used in SVM model to train the model effectively and determine the optimized\u0000 value of hyper-parameter (g, «, C). Also, CNN with a convolutional and pooling layer architecture framework is designed with optimum value of batch size, activation function, and filter size, among others. The validation and suitability of developed SVM and CNN models are ascertained\u0000 by various statistical tests. Convolutional neural network approach is observed to outperform SVM model and thus can be a reliable approach for time-series modeling of ambient noise levels with a prediction error of 2.1 dB(A). The forecasting root mean squared error obtained for all the four\u0000 zones using CNN model is observed to be less than 2.1 dB(A) for day equivalent noise levels and 1.9 dB(A) for night equivalent noise levels.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45239586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Predictors of people's responses to noise inside cars are used by car companies to identify and address potential noise problems. Because significant advances have been made in the reduction of engine, powertrain, and tire/road noise, it is now important to pursue reductions in wind or aerodynamic noise. While models of loudness are commonly used to predict people's responses to stationary wind noise, some wind noises are less acceptable than is predicted by the loudness metric. Additional sound characteristics may account for this. Two listening studies were designed to examine the usefulness of including sound quality metrics in addition to loudness and sharpness in models used to predict acceptability for non-stationary wind-noise sounds, particularly noise with the kind of variations that are expected from wind gusts. Test sounds were based on recordings made in cars in a wind tunnel. A simulation method was implemented to generate sounds with controlled gusting features by modifying stationary noise recordings. A gusting metric was designed to predict subjects' acceptability responses based on the strength, modulation rate, and duration of the gusts.
{"title":"Perception of non-stationary wind noise in vehicles","authors":"Daniel Carr, P. Davies","doi":"10.3397/1/377036","DOIUrl":"https://doi.org/10.3397/1/377036","url":null,"abstract":"Predictors of people's responses to noise inside cars are used by car companies to identify and address potential noise problems. Because significant advances have been made in the reduction of engine, powertrain, and tire/road noise, it is now important to pursue reductions in wind\u0000 or aerodynamic noise. While models of loudness are commonly used to predict people's responses to stationary wind noise, some wind noises are less acceptable than is predicted by the loudness metric. Additional sound characteristics may account for this. Two listening studies were designed\u0000 to examine the usefulness of including sound quality metrics in addition to loudness and sharpness in models used to predict acceptability for non-stationary wind-noise sounds, particularly noise with the kind of variations that are expected from wind gusts. Test sounds were based on recordings\u0000 made in cars in a wind tunnel. A simulation method was implemented to generate sounds with controlled gusting features by modifying stationary noise recordings. A gusting metric was designed to predict subjects' acceptability responses based on the strength, modulation rate, and duration of\u0000 the gusts.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49661417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Xue, Esmeralda Sanchez-Torres, B. Sharma, J. Bolton
In this study, two granular aerogel materials, both consisting of particles with sizes on the scale of 1 to 50 mm, were first investigated both theoretically and experimentally to improve our understanding of their acoustical behavior. Specifically, layers of the aerogels were evaluated in terms of their sound absorption coefficients, and loss mechanisms in the frequency region below 2000 Hz were quantified for both aerogels by using a previously-developed modeling tool based on the Biot theory. Further studies were then conducted in order to optimize the acoustical performance of potential sound packages featuring these aerogel particle stacks. For example, one of the aerogel materials was placed in series with a fibrous layer to take advantage of the low and high frequency sound absorption offered by the aerogel and the fibrous layers, respectively. The two types of aerogels were also combined in parallel to show that absorption peaks of one of the materials could be used to compensate for the absorption “dips” of the other material. After experimentally validating the design concepts mentioned above, the aerogel granule stacks' properties were tuned to realize a very low frequency and wideband sound absorption treatment when combined with the fibrous layer.
{"title":"Tunable sound packages consisting of granular aerogels and fibrous media","authors":"Y. Xue, Esmeralda Sanchez-Torres, B. Sharma, J. Bolton","doi":"10.3397/1/377035","DOIUrl":"https://doi.org/10.3397/1/377035","url":null,"abstract":"In this study, two granular aerogel materials, both consisting of particles with sizes on the scale of 1 to 50 mm, were first investigated both theoretically and experimentally to improve our understanding of their acoustical behavior. Specifically, layers of the aerogels were evaluated\u0000 in terms of their sound absorption coefficients, and loss mechanisms in the frequency region below 2000 Hz were quantified for both aerogels by using a previously-developed modeling tool based on the Biot theory. Further studies were then conducted in order to optimize the acoustical performance\u0000 of potential sound packages featuring these aerogel particle stacks. For example, one of the aerogel materials was placed in series with a fibrous layer to take advantage of the low and high frequency sound absorption offered by the aerogel and the fibrous layers, respectively. The two types\u0000 of aerogels were also combined in parallel to show that absorption peaks of one of the materials could be used to compensate for the absorption “dips” of the other material. After experimentally validating the design concepts mentioned above, the aerogel granule stacks' properties\u0000 were tuned to realize a very low frequency and wideband sound absorption treatment when combined with the fibrous layer.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45803714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The negative health effects of road traffic noise in the EU are analyzed over the period 2020–2035. For a baseline scenario, with autonomous traffic growth and fleet development, we find that there will be 31 million highly annoyed persons and 15 million highly sleep-disturbed persons in the EU in 2030. The corresponding EU health burden in 2030 is equivalent to the loss of 1.7 million “healthy life years”. Various noise abatement scenarios are analyzed, with noise solutions such as quiet road surfaces, quiet tires, and electric vehicles. The health benefits of the scenarios are calculated as health-burden differences from the baseline scenario. The calculation methodology is based on the noise exposure distributions reported in 2017 by EU member states, for urban agglomerations and for major roads. Changes in noise exposure are calculated with EU model Cnossos for vehicle emission, considering different types of roads (residential streets, main roads, motorways,...), and taking into account the separate contributions of rolling noise and propulsion noise to the vehicle emission. Two different noise valuation methods are used to express the health benefits in Euros. The monetized health benefits are used as input for a cost-benefit analysis of the scenarios over the period 2020–2035. For quiet tires, for example, high health benefits and low costs are found, resulting in a high benefit-cost ratio. This work was part of a study for the European Commission, exploring different options for reducing the EU health burden caused by noise from road, rail, and air traffic.
{"title":"Health burden of road traffic noise in the EU in 2020–2035","authors":"E. Salomons, M. Dittrich","doi":"10.3397/1/377038","DOIUrl":"https://doi.org/10.3397/1/377038","url":null,"abstract":"The negative health effects of road traffic noise in the EU are analyzed over the period 2020–2035. For a baseline scenario, with autonomous traffic growth and fleet development, we find that there will be 31 million highly annoyed persons and 15 million highly sleep-disturbed\u0000 persons in the EU in 2030. The corresponding EU health burden in 2030 is equivalent to the loss of 1.7 million “healthy life years”. Various noise abatement scenarios are analyzed, with noise solutions such as quiet road surfaces, quiet tires, and electric vehicles. The health\u0000 benefits of the scenarios are calculated as health-burden differences from the baseline scenario. The calculation methodology is based on the noise exposure distributions reported in 2017 by EU member states, for urban agglomerations and for major roads. Changes in noise exposure are calculated\u0000 with EU model Cnossos for vehicle emission, considering different types of roads (residential streets, main roads, motorways,...), and taking into account the separate contributions of rolling noise and propulsion noise to the vehicle emission. Two different noise valuation methods are used\u0000 to express the health benefits in Euros. The monetized health benefits are used as input for a cost-benefit analysis of the scenarios over the period 2020–2035. For quiet tires, for example, high health benefits and low costs are found, resulting in a high benefit-cost ratio. This work\u0000 was part of a study for the European Commission, exploring different options for reducing the EU health burden caused by noise from road, rail, and air traffic.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49491271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liping Xie, Chihua Lu, Zhien Liu, Yawei Zhu, Weizhi Song
The active sound generation technique for automobiles, where car sounds can be synthesized by means of electronic sound production, is one of the effective methods to achieve the target sound. A method for active sound generation of automobile based on the granular synthesis algorithm is put forward here to avoid the broadband beating phenomena that occur due to the mismatch of parameters of sound granular signals. The comparison of the function expression of sound signal and Hilbert transformation is performed based on the principle of overlap and add; moreover, those parameters (phase, frequency and amplitude) of sound signals are interpolated by means of the Hermite interpolation algorithm which can ensure the continuity of the phase, frequency and amplitude curves. Thus, the transition audio is constructed by means of the sound signal function here to splice the adjacent sound granules. Our simulations show that our method can be applied to solve the current broadband beating issue for splicing sound granules and achieve natural continuity of synthesized car sounds. The subjective test results also indicate that our transition audio can produce high quality audio restitution.
{"title":"A method of generating car sounds based on granular synthesis algorithm","authors":"Liping Xie, Chihua Lu, Zhien Liu, Yawei Zhu, Weizhi Song","doi":"10.3397/1/377031","DOIUrl":"https://doi.org/10.3397/1/377031","url":null,"abstract":"The active sound generation technique for automobiles, where car sounds can be synthesized by means of electronic sound production, is one of the effective methods to achieve the target sound. A method for active sound generation of automobile based on the granular synthesis algorithm\u0000 is put forward here to avoid the broadband beating phenomena that occur due to the mismatch of parameters of sound granular signals. The comparison of the function expression of sound signal and Hilbert transformation is performed based on the principle of overlap and add; moreover, those\u0000 parameters (phase, frequency and amplitude) of sound signals are interpolated by means of the Hermite interpolation algorithm which can ensure the continuity of the phase, frequency and amplitude curves. Thus, the transition audio is constructed by means of the sound signal function here to\u0000 splice the adjacent sound granules. Our simulations show that our method can be applied to solve the current broadband beating issue for splicing sound granules and achieve natural continuity of synthesized car sounds. The subjective test results also indicate that our transition audio can\u0000 produce high quality audio restitution.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47317814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaobo Liu, Zhongcheng Jiang, Xianfeng Wang, Dengke Li
The passenger comforts are directly affected by the air supply uniformity and noise of air-conditioning duct inside the metro vehicle. In order to solve the integrated design problem of air supply uniformity and noise control of air-conditioning ducts, a theoretical model is established to analyze the air supply uniformity, noise attenuation, and airflow regeneration noise of the air-conditioning duct. The distribution law of the sound pressure level along the longitudinal air outlet was calculated, and the calculated results were compared with test ones. For a typical air supply duct with a constant cross section: (1) In order to ensure air supply uniformity at the outlet of the static pressure chamber, the area of the side air hole should be gradually increased in an exponential form along the direction of the main flow, and cannot be designed in the equal area form. (2) The airflow speed of each side hole decreased in sequence along the air duct length. In order to ensure the uniformity air supply of each side hole, the area of each side hole must be gradually increased. (3) The noise in the air conditioner duct was mainly concentrated at the front end of the air duct, and the noise at the subsequent air outlet can fully meet the current requirements of subway vehicles for indoor noise. Therefore, the front end of the air duct is the most important area for noise control.
{"title":"Noise distribution law of air-conditioning ducts for metro vehicles","authors":"Xiaobo Liu, Zhongcheng Jiang, Xianfeng Wang, Dengke Li","doi":"10.3397/1/377030","DOIUrl":"https://doi.org/10.3397/1/377030","url":null,"abstract":"The passenger comforts are directly affected by the air supply uniformity and noise of air-conditioning duct inside the metro vehicle. In order to solve the integrated design problem of air supply uniformity and noise control of air-conditioning ducts, a theoretical model is established\u0000 to analyze the air supply uniformity, noise attenuation, and airflow regeneration noise of the air-conditioning duct. The distribution law of the sound pressure level along the longitudinal air outlet was calculated, and the calculated results were compared with test ones. For a typical air\u0000 supply duct with a constant cross section: (1) In order to ensure air supply uniformity at the outlet of the static pressure chamber, the area of the side air hole should be gradually increased in an exponential form along the direction of the main flow, and cannot be designed in the equal\u0000 area form. (2) The airflow speed of each side hole decreased in sequence along the air duct length. In order to ensure the uniformity air supply of each side hole, the area of each side hole must be gradually increased. (3) The noise in the air conditioner duct was mainly concentrated at the\u0000 front end of the air duct, and the noise at the subsequent air outlet can fully meet the current requirements of subway vehicles for indoor noise. Therefore, the front end of the air duct is the most important area for noise control.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46412236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Sadeghian, Soroor Shekarizadeh, Milad Abbasi, S. Mousavi, Saeid Yazdanirad
The tonal noise of indoor mechanical systems causes an unpleasant sensation. The present study was conducted to predict tonal sound annoyance based on noise metrics and psychoacoustics parameters using artificial neural networks. Thirty-six signals of noise were produced by six tone levels, three tone frequencies, and two background noise levels in an enclosed space. Then, noise metrics and psychoacoustic parameters of the signals were determined. Subsequently, 60 subjects were asked to express their subjective perception of annoyance during exposure to various noises. Finally, the predictive model of annoyance was computed using the feed-forward neural networks. The initialization of weights and biases was performed using the Nguyen-Widrow method. The gradient descent with momentum and back-propagation algorithms were applied to learn the function and network weights, respectively. Based on the results, higher tone level, higher background noise level, lower frequency, and less sharp noise significantly increased the value of the perceived annoyance. The obtained Kaiser-Mayer-Olkin coefficient of the model was equal to 0.8. The values of recognition rate related to data of training and testing were computed by 0.83 and 0.91, respectively. The parameters of loudness, audible tone, and roughness compared to combined metrics were more substantial predictors of perceived annoyance.
{"title":"The use of artificial neural networks to predict tonal sound annoyance based on noise metrics and psychoacoustics parameters","authors":"M. Sadeghian, Soroor Shekarizadeh, Milad Abbasi, S. Mousavi, Saeid Yazdanirad","doi":"10.3397/1/377025","DOIUrl":"https://doi.org/10.3397/1/377025","url":null,"abstract":"The tonal noise of indoor mechanical systems causes an unpleasant sensation. The present study was conducted to predict tonal sound annoyance based on noise metrics and psychoacoustics parameters using artificial neural networks. Thirty-six signals of noise were produced by six tone\u0000 levels, three tone frequencies, and two background noise levels in an enclosed space. Then, noise metrics and psychoacoustic parameters of the signals were determined. Subsequently, 60 subjects were asked to express their subjective perception of annoyance during exposure to various noises.\u0000 Finally, the predictive model of annoyance was computed using the feed-forward neural networks. The initialization of weights and biases was performed using the Nguyen-Widrow method. The gradient descent with momentum and back-propagation algorithms were applied to learn the function and network\u0000 weights, respectively. Based on the results, higher tone level, higher background noise level, lower frequency, and less sharp noise significantly increased the value of the perceived annoyance. The obtained Kaiser-Mayer-Olkin coefficient of the model was equal to 0.8. The values of recognition\u0000 rate related to data of training and testing were computed by 0.83 and 0.91, respectively. The parameters of loudness, audible tone, and roughness compared to combined metrics were more substantial predictors of perceived annoyance.","PeriodicalId":49748,"journal":{"name":"Noise Control Engineering Journal","volume":" ","pages":""},"PeriodicalIF":0.4,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42839321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：