Applied AcousticsPub Date : 2025-03-03DOI: 10.1016/j.apacoust.2025.110633
Jiahan Huang , Jianquan Chen , Hanlan Mai , Hengyang Wan , Rong Chen , Tingqiang He
{"title":"Performance prediction and inverse design of cylindrical plate-type acoustic metamaterials based on deep learning","authors":"Jiahan Huang , Jianquan Chen , Hanlan Mai , Hengyang Wan , Rong Chen , Tingqiang He","doi":"10.1016/j.apacoust.2025.110633","DOIUrl":"10.1016/j.apacoust.2025.110633","url":null,"abstract":"<div><div>Acoustic metamaterials are artificial structures that possess distinctive acoustic characteristics, allowing for modulation effects that are challenging to achieve in the natural world. Nevertheless, the design of acoustic metamaterials is a challenging process due to the intricate relationship between their structural parameters and nonlinear performance. In view of the limitations of conventional design methodologies, which rely on the a priori knowledge of experts and are often hindered by prolonged computation times and the necessity for iterative trials to achieve design objectives, this paper introduces a deep learning-based method for performance prediction and inverse design of Cylindrical Plate-type Acoustic Metamaterials (CPAMs). The creation of a dataset is initiated by generating a large number of samples using a parametric model, with bandgap characteristics calculated through the finite element method. A forward-design deep learning model is then developed, predicting the upper and lower bandgap limits based on input structural parameters. Additionally, an inverse design model is constructed, enabling rapid generation of structural parameters based on desired acoustic performance. The results of the inverse design are validated through simulation and experimentation, confirming the accuracy and reliability of the model. This study demonstrates the potential of deep learning in efficiently designing complex acoustic metamaterials, offering a promising solution for CPAMs development.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110633"},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-03DOI: 10.1016/j.apacoust.2025.110643
Yujie Qian , Bingxu Li , Jie Zhang
{"title":"Study of ultra-wideband acoustic metamaterial based on multi-order broadband resonance band coupling of ultra-micro perforated panel","authors":"Yujie Qian , Bingxu Li , Jie Zhang","doi":"10.1016/j.apacoust.2025.110643","DOIUrl":"10.1016/j.apacoust.2025.110643","url":null,"abstract":"<div><div>Ultra-micro perforated panels (UMPPs) have demonstrated exceptional potential for suppressing attenuation in higher-order resonance bands, enabling the design of structurally simple yet highly efficient acoustic absorbers. This study advances the field by introducing series- and parallel-coupled UMPP systems to achieve ultra-wideband sound absorption through the coupling of multi-order resonance bands. The acoustic impedance models for these configurations are developed, along with a detailed framework for calculating sound absorption coefficients. Theoretical investigations explore double- and triple-layer series UMPP structures as well as two- and three-unit parallel UMPP systems, each engineered to broaden the absorption bandwidth through resonance band integration. The influence of key structural parameters, such as cavity depth and perforation dimensions, on absorption performance is systematically analyzed. Experimental validation, conducted using impedance tube measurements for UMPPs with sub-0.1 mm perforations, confirms the accuracy of the theoretical predictions. Results reveal that multi-order wideband resonance coupling in UMPPs with minimal attenuation effects significantly enhances sound absorption bandwidth, offering a robust pathway for practical applications of ultra-wideband acoustic metamaterials in noise control. This study highlights the versatility of UMPP systems in achieving both low-frequency and broadband sound absorption, providing remarkable design flexibility while maintaining structural simplicity.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"235 ","pages":"Article 110643"},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-03DOI: 10.1016/j.apacoust.2025.110645
Yushuai Wang , Feng Liu , Kongcheng Zuo , Zhaoyong Sun
{"title":"Adaptive Vold-Kalman filter FXLMS scheme for harmonic sound quality control","authors":"Yushuai Wang , Feng Liu , Kongcheng Zuo , Zhaoyong Sun","doi":"10.1016/j.apacoust.2025.110645","DOIUrl":"10.1016/j.apacoust.2025.110645","url":null,"abstract":"<div><div>Active sound quality control (ASQC) systems for engine noise in an automobile always involve the task of improving the order sound linearity with revolving speed and balancing the proportion of each order’s contribution to the total noise. However, most current ASQC algorithms can not control the sound from the perspective of the order quantitative target. Therefore, a new algorithm, in this paper, is proposed to control the harmonic sound in terms of its order profiles. The algorithm uses the adaptive Vold-Kalman filter (VKF) to track the concerned order of disturbance and schedules the gain factors by calculating the ratio of predefined target amplitudes to the tracked disturbance amplitudes. The gain factors are used to tune the controller output of corresponding orders, which enables the algorithm to equalize single or multiple orders independently. Furthermore, simulated sounds and real engine noises are used to demonstrate the effectiveness. The proposed algorithm can equalize the order(s) sound amplitude to a much narrower range. The results reveal that it is capable of improving the linearity and balancing the proportion of orders and can be further implemented to control the harmonic sound quality.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110645"},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143534660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-03DOI: 10.1016/j.apacoust.2025.110627
Yuri P. Bórnea , Avyner L.O. Vitor , Alessandro Goedtel , Marcelo F. Castoldi , Wesley A. Souza , Gustavo V. Barbara
{"title":"A novel method for detecting bearing faults in induction motors using acoustic sensors and feature engineering","authors":"Yuri P. Bórnea , Avyner L.O. Vitor , Alessandro Goedtel , Marcelo F. Castoldi , Wesley A. Souza , Gustavo V. Barbara","doi":"10.1016/j.apacoust.2025.110627","DOIUrl":"10.1016/j.apacoust.2025.110627","url":null,"abstract":"<div><div>The study and development of fault diagnosis techniques for induction motors (IMs) have received significant attention, particularly regarding bearing failures. Although acoustic signals have been explored in the recent literature, advances in research about the quantity and model of sensors are still needed, as well as to develop approaches for extracting and selecting information that facilitates fault identification. In this context, this paper presents a new methodology to extract specific acoustic features from IMs and identify early-stage bearing distributed faults, which is unexplored in electric machine faults studies. It involves acoustic signals collected from multiple sensors, which are selected through similarity tests, and identifies the most crucial features to diagnose fault conditions using Recursive Feature Extraction and Random Forest as selectors. These selection methods highlight relevant features for the diagnostic process, improve fault identification, and reduce computational effort, resulting in a final accuracy rate of 98.86%. Identification of distributed and incipient bearing failures is achieved by using the selected features and comparing different classifiers and results in the literature. For this purpose, five sensors were used at a distance of 30 centimeters from the IM housing, and their signals were conditioned using electronic gain with operational amplifiers. The results demonstrate the system's applicability in low-noise environments such as test and inspection laboratories and IM out-of-operation testers. The methodology can be suitable for embedded systems, due to the reduction of attribute sets for fault identification.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110627"},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143534659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-01DOI: 10.1016/j.apacoust.2025.110638
Golakoti Pavan, Sneha Singh
{"title":"A coplanar metamaterial with variable channels for ventilated noise control","authors":"Golakoti Pavan, Sneha Singh","doi":"10.1016/j.apacoust.2025.110638","DOIUrl":"10.1016/j.apacoust.2025.110638","url":null,"abstract":"<div><div>Traditional noise barriers often face limitations in balancing acoustical performance and ventilation efficiency, restricting their usage in various applications. To address this, we have proposed a novel coplanar labyrinthine acoustic metamaterial with continuously varying channel widths with a micro-hole perforated cover plate for wave entry. Using an iterative backward acoustic impedance calculation by impedance translation theorem, a theoretical model for the sound absorption by the metamaterial has been developed, and validated numerically and experimentally. The sound absorption mechanism is analyzed using acoustic particle velocity fields. The key geometrical parameters (number of channels, metamaterial diameter, cover plate thickness, and micro-hole diameter) that significantly impact the sound absorption response and the method of tuning them to attain low-frequency sound attenuation below 500 Hz while maintaining a high absorption magnitude and broader bandwidth have been determined. The material is demonstrated to be a better sound absorber than Helmholtz resonator and existing coplanar metamaterials. Additionally, the impact of the metamaterial unit cell lattice on sound transmission loss, pressure drop, and ventilation efficiency is examined. The hexagonal lattice with 9.31 % ventilation provides better noise reduction than the square lattice with 21.46 % ventilation. A 17 dB difference in sound transmission loss at 510 Hz and peak sound transmission loss of 39 dB and 35 dB respectively, for hexagonal and square lattice configurations, have been experimentally verified. The proposed metamaterial has practical applications where ventilated low-frequency noise control is desired in compact spaces.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110638"},"PeriodicalIF":3.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-01DOI: 10.1016/j.apacoust.2025.110636
Manjiri Bhat , R.B. Keskar
{"title":"Self-supervised random forests for robust voice activity detection with limited labeled data","authors":"Manjiri Bhat , R.B. Keskar","doi":"10.1016/j.apacoust.2025.110636","DOIUrl":"10.1016/j.apacoust.2025.110636","url":null,"abstract":"<div><div>Voice activity detection is essential for various downstream speech-related applications. Existing deep learning models for voice activity detection and speech recognition are available, but they often require substantial annotated data and assume noise-free environments. This limitation hinders their application to the vast but sparsely labeled audio datasets available. To address this gap, we propose a novel approach: self-supervised random forest voice activity detection (SSRF-VAD), designed for noisy environments and limited labeled data. We integrate a set of five handcrafted features to optimize performance under mixed signal-to-noise ratios (SNRs). The study incorporates various noise classes covering diverse environmental sounds such as urban sounds, water sounds, indoor appliances, and animals. Our SSRF-VAD approach achieves an improvement of 3 % in F1-score using only 20 % of the labeled training data compared to state-of-the-art MarbleNet model trained on the complete training dataset. Feature selection, implemented using two distinct feature importance techniques, SHAP and GINI, reduces the feature vector dimensionality by 75 % while preserving accuracy. Further, a novel three-class classification for separating clean speech, noisy speech, and non-speech audio segments with the proposed technique achieves 98.74 % accuracy with 0.982 F1-score. This framework enhances speech analysis and noise characterization, contributing to efficient speech enhancement. Thus, the proposed SSRF-VAD method reduces the requirement for labeled data and can be implemented on resource-constrained devices such as smart hearing aids and smart home assistants.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110636"},"PeriodicalIF":3.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143526561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-03-01DOI: 10.1016/j.apacoust.2025.110619
Zhihui Hu , Shengtian Wen , Lei Xiang , Gongxian Wang
{"title":"Topology-optimized design of a solid cover layer on porous materials for low-frequency broadband sound absorption","authors":"Zhihui Hu , Shengtian Wen , Lei Xiang , Gongxian Wang","doi":"10.1016/j.apacoust.2025.110619","DOIUrl":"10.1016/j.apacoust.2025.110619","url":null,"abstract":"<div><div>To improve the low-frequency sound absorption performance of porous materials, a solid cover layer is placed over the porous material. The solid structure is designed by means of a density-based topology optimization method and in combination with polyurethane foam (PUF) to form a resonant composite structure. The performance of this PUF is modeled using the Johnson-Champoux-Allard (JCA) model. With the same dimensions, such an optimized design can significantly shift the peak sound absorption to lower frequencies compared to that of the PUF. Our sound absorption peaks up to 0.85 at 764 Hz, and the bandwidth <span><math><mrow><mo>(</mo><mi>α</mi><mo>></mo><mn>0.5</mn><mo>)</mo></mrow></math></span> is 394 Hz. The thickness of the composite structure is less than 11.1 % of the operating wavelength. Our topology optimized solid cover layer is simplified effectively. The results of our simulations and experiments corroborate the soundness of our design. Such hybrid acoustic materials and its design approach can provide more design ideas for future acoustic materials.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110619"},"PeriodicalIF":3.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143526562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Continuous frugal wavelet transform for damage detection in frame structures","authors":"Morteza Saadatmorad , Ramazan-Ali Jafari-Talookolaei , Samir Khatir , Amine Ammar , Hamidreza Ghandvar , Thanh Cuong-Le","doi":"10.1016/j.apacoust.2025.110621","DOIUrl":"10.1016/j.apacoust.2025.110621","url":null,"abstract":"<div><div>Wavelet transform is widely used for analyzing signals in the time–frequency domain. However, its effectiveness in damage detection can be limited by the selection of wavelet function and its vanishing moments. To address this, we introduce the Frugal Wavelet Transform (FWT) and its continuous version, the Continuous Frugal Wavelet Transform (CFWT). We then apply the CFWT to detect damage in frame structures, showcasing a novel approach to this problem. The results demonstrate that both the discrete and continuous frugal wavelet transforms provide highly accurate damage detection, as confirmed through numerical simulations and experimental tests. Furthermore, the results show that the Continuous Frugal Wavelet Transform consistently outperforms the traditional Continuous Wavelet Transform across all scenarios.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110621"},"PeriodicalIF":3.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-02-28DOI: 10.1016/j.apacoust.2025.110591
Emmanuel Attal , Nicolas Dauchez
{"title":"Acoustic performance of foliage based on green systems at normal incidence","authors":"Emmanuel Attal , Nicolas Dauchez","doi":"10.1016/j.apacoust.2025.110591","DOIUrl":"10.1016/j.apacoust.2025.110591","url":null,"abstract":"<div><div>The aim of this paper is to compare the acoustic parameters (absorption, reflection and transmission) of vegetation in reducing noise pollution according to types of applications: vegetation in building facades and in hedge configuration away from obstacles. The two configurations are investigated with vegetation thickness increase and leaf density in normal incidence condition. The effective and acoustic parameters of foliage were studied in the 100 Hz to 1000 Hz frequency range. Secondly, the experimental transfer matrices were compared with those derived from simulations using the Horoshenkov-Miki model, which uses the primary parameters (porosity, tortuosity and air flow resistivity) to discuss the evolution of their physical properties as a function of leaf density. The various simulations carried out using these models show that increasing foliage thickness and leaf density increasingly reduces transmission but favours acoustic reflection in the case of a foliage hedge, whereas acoustic reflection is considerably reduced in the case of a green facade.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110591"},"PeriodicalIF":3.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied AcousticsPub Date : 2025-02-28DOI: 10.1016/j.apacoust.2025.110634
Yuxing Li , Yilan Lou , Yan Yan
{"title":"Snake optimization improved multivariate multiscale slope entropy and its application to multivariate signal feature extraction","authors":"Yuxing Li , Yilan Lou , Yan Yan","doi":"10.1016/j.apacoust.2025.110634","DOIUrl":"10.1016/j.apacoust.2025.110634","url":null,"abstract":"<div><div>The multivariate slope entropy (mvSloEn) is an effective metric for characterizing the complexity of multi-channel time series. However, mvSloEn ignores the correlation between symbol patterns from different channels, making it difficult to comprehensively characterize the complexity of multi-channel signals. To address this issue, this paper proposes the improved mvSloEn (ImvSloEn), which fuses the information of symbol patterns from different channels and extends the symbol pattern types by constructing multiple pattern components, thus comprehensively characterizing the multi-channel signal complexity. To reflect the complexity of different time scales, improved multivariate multiscale slope entropy (ImvMSloEn) is introduced as a multi-scale version of ImvSloEn. Furthermore, snake optimization ImvMSloEn (SO-ImvMSloEn) is presented, which solves the threshold selection for ImvMSloEn. To the end, a multivariate signal feature extraction method is proposed in combination with multivariate variational mode decomposition (MVMD) and SO-ImvMSloEn. Simulation experiments demonstrate that SO-ImvMSloEn can accurately characterize the complexity of multivariate signals and the proposed multivariate feature extraction method can distinguish chaotic signals more accurately. Real-world experiments proved that the proposed multivariate feature extraction method has higher classification accuracy for rolling bearing signals and ship radiated noises compared to other feature extraction method.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":"234 ","pages":"Article 110634"},"PeriodicalIF":3.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}