A narrow window acoustic tuning system and method based on a composite noise reduction structure

Abstract

The application discloses a narrow-window acoustic tuning system and method based on a composite noise reduction structure, relates to the technical field of fault diagnosis, and comprises a modular shell, a thin-film metamaterial narrow-window low-frequency noise reduction module, a porous sound-absorbing material high-frequency noise reduction module and a data acquisition and processing module. The narrow-window acoustic tuning system and method based on the composite noise reduction structure adopts a hierarchical noise reduction processing method, deeply fuses the wide-frequency noise reduction characteristics of the porous sound-absorbing material and the low-frequency gating filtering characteristics of the thin-film metamaterial, firstly completes pre-filtering of wide-frequency noise through the porous material, then completes accurate suppression of low-frequency interference through the thin-film metamaterial, and finally completes secondary purification of residual noise through the porous material, thereby filtering out industrial field full-frequency environmental interference noise efficiently while retaining sound signals of a target fault frequency band to the maximum extent.

Description

Technical Field

[0001] This application belongs to the field of fault diagnosis technology, and in particular relates to a narrow-window acoustic tuning system and method based on a composite noise reduction structure. Background Technology

[0002] With the acceleration of globalization, the air transport industry has developed rapidly. High-performance aircraft engines, as the core component of aircraft power systems, are directly related to flight safety and economy in terms of reliability. However, during long-term operation, critical components such as gears in aircraft engines are prone to failure due to fatigue, wear, and other factors, leading to serious safety accidents and economic losses.

[0003] Currently, scholars both domestically and internationally have conducted extensive research on gear fault detection methods, mainly including vibration signal analysis, oil analysis, and acoustic monitoring techniques. Among these, vibration analysis can effectively identify gear fault types under laboratory conditions, but in actual industrial environments, complex operating conditions and strong noise backgrounds can lead to severe signal distortion, affecting detection accuracy. Oil analysis methods require collecting lubricating oil samples for testing, which has drawbacks such as long testing cycles and high costs. Summary of the Invention

[0004] To address some or all of the technical problems existing in the prior art, this application provides a narrow-window acoustic tuning system and method based on a composite noise reduction structure.

[0005] This application provides a narrow-window acoustic tuning system based on a composite noise reduction structure, including a modular shell, a thin-film metamaterial narrow-window low-frequency noise reduction module, a porous sound-absorbing material high-bandwidth noise reduction module, and a data acquisition and processing module. The modular housing has a movable fixed bracket inside its noise reduction cavity that can be adjusted along the axial direction. One end of the modular housing is provided with a housing opening, which serves as an acoustic signal input terminal; the other end of the modular housing is an acoustic signal output terminal. The thin-film metamaterial narrow-window low-frequency noise reduction module consists of a frame and a noise reduction film tensioned within the frame. Multiple thin-film metamaterial narrow-window low-frequency noise reduction modules are arranged axially at intervals within the noise reduction cavity via the movable fixed bracket. The two sets of porous sound-absorbing material high-bandwidth noise reduction modules are respectively arranged on the outermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules and on the innermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules, so that all the noise reduction films are sandwiched between the two sets of porous sound-absorbing material high-bandwidth noise reduction modules. The data acquisition and processing module includes a high-sensitivity triboacoustic sensor, a signal acquisition unit, and a database; the high-sensitivity triboacoustic sensor is installed inside the noise reduction cavity and is located on the side of the acoustic signal output end of the noise reduction cavity; the output end of the high-sensitivity triboacoustic sensor is electrically connected to the signal acquisition unit, and the signal acquisition unit is communicatively connected to the database; Both the highly sensitive triboacoustic sensor and the porous sound-absorbing material high-bandwidth noise reduction module are fixed on the movable fixed bracket.

[0006] Preferably, the thin-film metamaterial narrow window low-frequency noise reduction module is arranged in a group, namely a first noise reduction module, a second noise reduction module, a third noise reduction module, a fourth noise reduction module and a fifth noise reduction module.

[0007] Preferably, the two sets of porous sound-absorbing material high-bandwidth noise reduction modules are respectively a mid-to-high frequency porous sound-absorbing material noise reduction module and a high frequency porous sound-absorbing material noise reduction module. The mid-to-high frequency porous sound-absorbing material noise reduction module is located at the sound signal input end, and the high frequency porous sound-absorbing material noise reduction module is located at the sound signal output end.

[0008] Preferably, all five sets of the thin-film metamaterial narrow-window low-frequency noise reduction modules are disposed between the mid-to-high frequency porous sound-absorbing material noise reduction module and the high frequency porous sound-absorbing material noise reduction module; the high frequency porous sound-absorbing material noise reduction module is located between the innermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules and the high-sensitivity triboacoustic sensor.

[0009] Preferably, the thickness of the mid-to-high frequency porous sound-absorbing material noise reduction module is 5mm and the porosity is 70%; the thickness of the high frequency porous sound-absorbing material noise reduction module is 5mm and the porosity is 80%.

[0010] Preferably, a friction layer is provided on one side of the high-sensitivity triboacoustic sensor, and an aluminum electrode layer is provided on the other side of the high-sensitivity triboacoustic sensor.

[0011] A narrow-window acoustic optimization method based on a composite noise reduction structure includes the following steps: Step S1: The sound source signal enters the noise reduction cavity through the sound signal input terminal of the modular shell, and passes sequentially through the mid-to-high frequency porous sound-absorbing material noise reduction module, multiple sets of thin film metamaterial narrow window low frequency noise reduction modules and high frequency porous sound-absorbing material noise reduction module. The porous sound-absorbing material filters out mid-to-high frequency and high frequency broadband noise, and the noise reduction film filters out low frequency interference noise while retaining the sound signal of the target fault frequency band. Step S2: The noise-reduced target acoustic signal is transmitted to a high-sensitivity triboacoustic sensor and converted into an electrical signal; Step S3: After the electrical signal is acquired and preprocessed by the signal acquisition device, it is uploaded to the database. The fault feature extraction and fault type identification are completed by the deep learning model to realize the real-time monitoring of mechanical faults in a strong noise environment.

[0012] The narrow-window acoustic tuning system and method based on a composite noise reduction structure proposed in this application have the following advantages and positive effects: (1) A graded noise reduction method is adopted, which deeply integrates the broadband noise reduction characteristics of porous sound-absorbing materials with the low-frequency gating and filtering characteristics of thin film metamaterials. First, the broadband noise is pre-filtered through porous materials, then the low-frequency interference is accurately suppressed through thin film metamaterials, and finally the residual noise is purified through porous materials. While efficiently filtering out environmental interference noise in the industrial field, the acoustic signal of the target fault frequency band is preserved to the greatest extent. This solves the problem of synchronous attenuation of noise and useful signal and poor low-frequency noise suppression effect in traditional noise reduction technology, and greatly improves the signal-to-noise ratio of the target signal.

[0013] (2) It achieves a high degree of integration of noise reduction, sensing and signal acquisition functions, which not only greatly reduces the system size and reduces the loss of acoustic signal transmission, but also allows for flexible adjustment of filtering parameters and internal layout according to different monitoring objects and working conditions; with a high-sensitivity triboacoustic sensor, it can accurately capture weak fault characteristic signals in strong noise environment without additional power supply. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for further understanding of the embodiments of this application and constitute a part of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a schematic diagram of the overall system structure of this application; Figure 2 This is a schematic diagram of the internal structure of the modular shell of this application; Figure 3 This is a schematic diagram of the thin-film metamaterial narrow-window low-frequency noise reduction module structure of this application; Figure 4 This is a schematic diagram of the structure of the high-sensitivity triboacoustic sensor of this application.

[0015] Explanation of reference numerals in the attached figures: 1-Sound source signal, 2-Modular shell, 201-Shell housing, 202-Movable fixed bracket, 203-Shell opening, 3-Signal acquisition device, 4-Database, 5-Thin film metamaterial narrow window low frequency noise reduction module, 501-Frame, 502-Noise reduction film, 5a-First noise reduction module, 5b-Second noise reduction module, 5c-Third noise reduction module, 5d-Fourth noise reduction module, 5e-Fifth noise reduction module, 6-High-sensitivity triboacoustic sensor, 601-Friction layer, 602-Electrode layer, 7-Porous sound-absorbing material high bandwidth noise reduction module, 7a-Mid-high frequency band porous sound-absorbing material noise reduction module, 7b-High frequency band porous sound-absorbing material noise reduction module. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] like Figure 1 and Figure 2 As shown, the narrow-window acoustic tuning system based on a composite noise reduction structure of this application includes a modular shell 2, a thin-film metamaterial narrow-window low-frequency noise reduction module 5, a porous sound-absorbing material high-bandwidth noise reduction module 7, and a data acquisition and processing module. By integrating noise reduction, sensing, and signal acquisition functions into the same housing, the overall size is significantly reduced, and the sound signal transmission loss between the various functional units is reduced.

[0018] The inner cavity of the modular shell 2 is a noise reduction cavity, and multiple sets of movable fixed brackets 202 that can be adjusted in position along the axis are provided in the noise reduction cavity; the outer shell 201 of the modular shell 2 is made of polycarbonate.

[0019] The noise reduction cavity provides a closed and stable acoustic environment for sound signal propagation and processing, preventing external environmental noise from directly interfering with the internal acoustic processing. Polycarbonate is a material with high acoustic reflectivity and mechanical stability, which helps improve the accuracy of fault signal identification.

[0020] The movable fixed bracket 202 can be slidably moved by means of a slide rail installation.

[0021] One end of the modular housing 2 is provided with a housing opening 203, which is the sound signal input terminal; the other end of the modular housing 2 is the sound signal output terminal.

[0022] The opening 203 of the outer shell is arranged directly opposite the device to be monitored, which can collect the sound signal during the operation of the device in a directional manner and reduce the interference of environmental noise in non-target directions. The sound signal input end and the output end are set coaxially along the axis of the modular outer shell 2 to form a straight sound propagation path, avoiding reflection loss and distortion caused by the bending of the sound signal propagation, and ensuring the integrity and fidelity of the target fault sound signal.

[0023] like Figure 3 As shown, the thin-film metamaterial narrow window low-frequency noise reduction module 5 consists of a frame 501 and a noise reduction film 502 tensioned within the frame 501. The frame 501 provides uniform and stable circumferential tension support for the noise reduction film 502, ensuring that the noise reduction film 502 is always in a flat and taut state, thus avoiding the problems of filter characteristic shift and noise reduction effect attenuation caused by film relaxation.

[0024] To make the noise reduction film 502 easier to process and provide better noise reduction performance, it is made of PDMS material with a thickness of 50μm.

[0025] Multiple sets of thin-film metamaterial narrow-window low-frequency noise reduction modules 5 are arranged axially at intervals in the noise reduction cavity via movable fixing brackets 202.

[0026] In this embodiment, to optimize the noise reduction effect of low-frequency noise, the thin-film metamaterial narrow-window low-frequency noise reduction modules 5 are arranged by adjusting the spacing. To determine the arrangement of the thin-film metamaterial narrow-window low-frequency noise reduction modules 5 with different noise reduction performance in different frequency bands, the arrangement position and spacing are first determined by simulation, and then the position information is optimized by testing. The filtering parameters and internal layout can be flexibly adjusted according to different monitoring objects and operating conditions.

[0027] Two sets of porous sound-absorbing material high-bandwidth noise reduction modules 7 are respectively arranged on the outermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules 5 on the axial outer side and the innermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules 5 on the axial inner side, so that all the noise reduction films 502 are sandwiched between the two sets of porous sound-absorbing material high-bandwidth noise reduction modules 7.

[0028] The thin-film metamaterial narrow window low-frequency noise reduction module 5 is arranged in 5 groups, namely the first noise reduction module 5a, the second noise reduction module 5b, the third noise reduction module 5c, the fourth noise reduction module 5d and the fifth noise reduction module 5e.

[0029] Among them, the two sets of porous sound-absorbing material high-bandwidth noise reduction modules 7 are respectively the mid-to-high frequency range porous sound-absorbing material noise reduction module 7a and the high frequency range porous sound-absorbing material noise reduction module 7b. The mid-to-high frequency range porous sound-absorbing material noise reduction module 7a is located at the sound signal input end, and the high frequency range porous sound-absorbing material noise reduction module 7b is located at the sound signal output end. The five sets of thin-film metamaterial narrow-window low-frequency noise reduction modules 5 are all arranged between the mid-to-high frequency range porous sound-absorbing material noise reduction module 7a and the high frequency range porous sound-absorbing material noise reduction module 7b. The high frequency range porous sound-absorbing material noise reduction module 7b is located between the innermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules 5 and the high-sensitivity triboacoustic sensor 6.

[0030] After the sound signal enters the noise reduction cavity, it first passes through the mid-to-high frequency porous sound-absorbing material noise reduction module 7a to pre-filter out the mid-to-high frequency noise, so as to avoid strong mid-to-high frequency noise interfering with the low-frequency filtering characteristics of the thin film metamaterial. Then, it passes through 5 sets of thin film metamaterial narrow window low-frequency noise reduction modules 5 to accurately filter out the low-frequency noise. Finally, it passes through the high-frequency porous sound-absorbing material noise reduction module 7b at the back end to complete the secondary purification of the residual high-frequency noise.

[0031] The mid-to-high frequency porous sound-absorbing material noise reduction module 7a has a thickness of 5mm and a porosity of 70%; the high frequency porous sound-absorbing material noise reduction module 7b has a thickness of 5mm and a porosity of 80%.

[0032] The 70% porosity mid-to-high frequency porous material has a connected pore structure adapted to mid-to-high frequency sound waves, and can achieve efficient absorption of mid-to-high frequency noise in the 500-2000Hz range; the 80% porosity high frequency porous material has finer pores, and can achieve better absorption effect for high frequency noise above 2000Hz. The two materials achieve full-band wideband noise reduction coverage from mid-to-high frequency to high frequency through differentiated porosity design, which perfectly complements the low frequency filtering of the thin film metamaterial narrow window low frequency noise reduction module 5.

[0033] The data acquisition and processing module includes a high-sensitivity triboacoustic sensor 6, a signal acquisition unit 3, and a database 4. The high-sensitivity triboacoustic sensor 6 is installed inside the noise reduction cavity and is located on the side of the acoustic signal output end of the noise reduction cavity. The output end of the high-sensitivity triboacoustic sensor 6 is electrically connected to the signal acquisition unit 3, and the signal acquisition unit 3 is communicatively connected to the database 4.

[0034] The highly sensitive triboacoustic sensor 6 is positioned close to the sound signal output end, allowing it to directly receive the clean target sound signal after complete noise reduction processing, minimizing the transmission path of the processed signal and avoiding secondary interference. The signal acquisition unit 3 can perform real-time amplification, filtering, analog-to-digital conversion, and other preprocessing on the weak electrical signal output by the sensor, ensuring the accuracy and real-time performance of signal acquisition. The database 4 can store the acquired sound signal data long-term and stably, achieving standardized storage and management of the data, and providing sufficient training samples and validation data for the deep learning model. Through the automatic feature extraction and classification recognition of the deep learning model, it can eliminate the reliance on manual feature engineering and accurately identify various equipment fault types under complex working conditions.

[0035] The highly sensitive triboacoustic sensor 6 and the porous sound-absorbing material high-bandwidth noise reduction module 7 are both fixed on the movable fixed bracket 202.

[0036] like Figure 4 As shown, a friction layer 601 is provided on one side of the high-sensitivity triboacoustic sensor 6, and an aluminum electrode layer 602 is provided on the other side of the high-sensitivity triboacoustic sensor 6.

[0037] When the acoustic signal propagates to the friction layer 601, it causes the friction layer 601 to generate a micro-amplitude vibration that matches the acoustic signal, resulting in a contact-separation triboelectric effect between the friction layer 601 and the electrode layer 602, thereby directly converting the mechanical energy of the acoustic signal into an electrical signal. This structure requires no additional power supply and has the advantages of wide frequency response, high sensitivity, and low noise. It can accurately capture weak fault acoustic signals in strong noise environments and is more suitable for complex and harsh industrial environments compared to traditional capacitive and piezoelectric acoustic sensors.

[0038] A narrow-window acoustic optimization method based on a composite noise reduction structure is provided, including the following steps: Step S1: The sound source signal 1 enters the noise reduction cavity through the sound signal input terminal of the modular shell 2, and passes sequentially through the mid-to-high frequency porous sound-absorbing material noise reduction module 7a, the multiple sets of thin film metamaterial narrow window low frequency noise reduction modules 5, and the high frequency porous sound-absorbing material noise reduction module 7b. The porous sound-absorbing material filters out mid-to-high frequency and high frequency broadband noise, and the noise reduction film 502 filters out low frequency interference noise while retaining the sound signal of the target fault frequency band. Step S2: The noise-reduced target acoustic signal is transmitted to the high-sensitivity triboacoustic sensor 6 and converted into an electrical signal; Step S3: The electrical signal is collected and preprocessed by the signal acquisition device 3 and then uploaded to the database 4. The fault feature extraction and fault type identification are completed through the deep learning model, realizing real-time monitoring of mechanical faults in a strong noise environment.

[0039] The specific workflow is as follows: The sound source signal 1 generated by the operation of the monitored machinery is directionally acquired through the opening 203 at the front of the modular housing 2 and enters the noise reduction cavity inside the modular housing 2. First, it passes through the mid-to-high frequency porous sound-absorbing material noise reduction module 7a at the sound signal input end to pre-filter mid-to-high frequency broadband environmental noise. The pre-noise-reduced sound signal then passes axially through five sets of spaced-apart thin-film metamaterial narrow-window low-frequency noise reduction modules 5, namely the first noise reduction module 5a, the second noise reduction module 5b, the third noise reduction module 5c, the fourth noise reduction module 5d, and the fifth noise reduction module 5e. All these modules are fixed within the noise reduction cavity by movable fixing brackets 202. Through the resonant filtering characteristics of the noise reduction films 502 tensioned on the frame 501 within each module, multi-frequency low-frequency mechanical interference noise is filtered out step by step, while accurately retaining the sound signal of the target fault frequency band, achieving narrow-window gating filtering. The sound signal that has completed low-frequency filtering continues to propagate, passing through the high-frequency output end... The frequency band porous sound-absorbing material noise reduction module 7b performs secondary purification, filtering out residual high-frequency noise and sound wave scattering clutter to obtain a pure target sound signal with a high signal-to-noise ratio. The pure target sound signal is then directly transmitted to the high-sensitivity triboacoustic sensor 6 at the end of the noise reduction cavity. Through the contact-separation triboelectric effect between the sensor's friction layer 601 and the aluminum electrode layer 602, the mechanical vibration energy of the sound signal is directly converted into a corresponding electrical signal. The converted electrical signal is transmitted to the signal acquisition unit 3 in real time. After standardized preprocessing such as amplification, filtering, and analog-to-digital conversion, it is uploaded to the database 4 for standardized storage and management. Finally, the sound signal data in the database 4 is input into the pre-trained deep learning model. The model automatically completes the deep extraction of fault features and the classification and identification of equipment operating conditions, outputting the equipment's normal / fault status and specific fault type results, thus fully realizing the whole process, non-contact, real-time online monitoring of mechanical faults in a high-noise industrial environment.

[0040] This application employs a graded noise reduction method, deeply integrating the broadband noise reduction characteristics of porous sound-absorbing materials with the low-frequency gating and filtering characteristics of thin-film metamaterials. First, the porous material performs pre-filtering of broadband noise; then, the thin-film metamaterial precisely suppresses low-frequency interference; and finally, the porous material performs secondary purification of residual noise. This method efficiently filters out environmental interference noise across the entire frequency band in industrial environments while preserving the acoustic signal of the target fault frequency band to the greatest extent possible. It solves the problems of synchronous attenuation of noise and useful signals and poor low-frequency noise suppression in traditional noise reduction technologies, significantly improving the signal-to-noise ratio of the target signal. It achieves a high degree of integration of noise reduction, sensing, and signal acquisition functions, not only significantly reducing system size and acoustic signal transmission loss, but also allowing flexible adjustment of filtering parameters and internal layout according to different monitoring objects and operating conditions. Combined with a high-sensitivity triboacoustic sensor, it can accurately capture weak fault characteristic signals in high-noise environments without additional power supply.

[0041] It should be noted that, unless otherwise expressly specified and limited, the term "connection" or its synonyms should be interpreted broadly in this document. For example, "connection" can be a fixed connection or a detachable connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two elements or the interaction between two elements. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. Furthermore, expressions such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. At the same time, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In addition, the terms "front," "rear," "left," "right," "upper," and "lower" in this document refer to the placement states shown in the accompanying drawings.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A narrow-window acoustic tuning system based on a composite noise reduction structure, characterized in that, It includes a modular shell (2), a thin-film metamaterial narrow window low-frequency noise reduction module (5), a porous sound-absorbing material high-bandwidth noise reduction module (7), and a data acquisition and processing module; The inner cavity of the modular shell (2) is a noise reduction cavity, and multiple sets of movable fixed brackets (202) that can be adjusted along the axial direction are provided in the noise reduction cavity. One end of the modular shell (2) is provided with a shell opening (203), which is a sound signal input terminal; the other end of the modular shell (2) is a sound signal output terminal; The thin-film metamaterial narrow window low-frequency noise reduction module (5) consists of a frame (501) and a noise reduction film (502) tensioned within the frame (501). Multiple sets of the thin-film metamaterial narrow window low-frequency noise reduction modules (5) are arranged axially at intervals within the noise reduction cavity via the movable fixed bracket (202). The two sets of porous sound-absorbing material high-bandwidth noise reduction modules (7) are respectively arranged on the outermost set of thin film metamaterial narrow window low-frequency noise reduction modules (5) and the innermost set of thin film metamaterial narrow window low-frequency noise reduction modules (5), so that all the noise reduction films (502) are sandwiched between the two sets of porous sound-absorbing material high-bandwidth noise reduction modules (7); The data acquisition and processing module includes a high-sensitivity triboacoustic sensor (6), a signal acquisition unit (3), and a database (4); the high-sensitivity triboacoustic sensor (6) is installed inside the noise reduction cavity and is located on the side of the acoustic signal output end of the noise reduction cavity; the output end of the high-sensitivity triboacoustic sensor (6) is electrically connected to the signal acquisition unit (3), and the signal acquisition unit (3) is communicatively connected to the database (4); The high-sensitivity triboacoustic sensor (6) and the porous sound-absorbing material high-bandwidth noise reduction module (7) are both fixed on the movable fixed bracket (202).

2. The narrow-window acoustic tuning system based on a composite noise reduction structure according to claim 1, characterized in that, The thin-film metamaterial narrow window low-frequency noise reduction module (5) is provided in five groups in sequence, namely the first noise reduction module (5a), the second noise reduction module (5b), the third noise reduction module (5c), the fourth noise reduction module (5d) and the fifth noise reduction module (5e).

3. The narrow-window acoustic tuning system based on a composite noise reduction structure according to claim 1, characterized in that, The two sets of porous sound-absorbing material high-bandwidth noise reduction modules (7) are respectively a mid-to-high frequency porous sound-absorbing material noise reduction module (7a) and a high frequency porous sound-absorbing material noise reduction module (7b). The mid-to-high frequency porous sound-absorbing material noise reduction module (7a) is located at the sound signal input end, and the high frequency porous sound-absorbing material noise reduction module (7b) is located at the sound signal output end.

4. The narrow-window acoustic tuning system based on a composite noise reduction structure according to claim 3, characterized in that, The five sets of thin-film metamaterial narrow-window low-frequency noise reduction modules (5) are all arranged between the mid-to-high frequency porous sound-absorbing material noise reduction module (7a) and the high frequency porous sound-absorbing material noise reduction module (7b); the high frequency porous sound-absorbing material noise reduction module (7b) is located between the innermost set of thin-film metamaterial narrow-window low-frequency noise reduction modules (5) and the high-sensitivity triboacoustic sensor (6).

5. The narrow-window acoustic tuning system based on a composite noise reduction structure according to claim 3, characterized in that, The mid-to-high frequency porous sound-absorbing material noise reduction module (7a) has a thickness of 5mm and a porosity of 70%; the high frequency porous sound-absorbing material noise reduction module (7b) has a thickness of 5mm and a porosity of 80%.

6. The narrow-window acoustic tuning system based on a composite noise reduction structure according to claim 1, characterized in that, A friction layer (601) is provided on one side of the high-sensitivity triboacoustic sensor (6), and an aluminum electrode layer (602) is provided on the other side of the high-sensitivity triboacoustic sensor (6).

7. A narrow-window acoustic tuning method based on a composite noise reduction structure, applied to the narrow-window acoustic tuning system according to any one of claims 1-6, characterized in that, Includes the following steps: Step S1: The sound source signal (1) enters the noise reduction cavity through the sound signal input end of the modular shell (2), and passes through the mid-to-high frequency porous sound-absorbing material noise reduction module (7a), multiple sets of thin film metamaterial narrow window low frequency noise reduction modules (5) and high frequency porous sound-absorbing material noise reduction module (7b) in sequence. The porous sound-absorbing material filters out mid-to-high frequency and high frequency broadband noise, and the noise reduction film (502) filters out low frequency interference noise and retains the sound signal of the target fault frequency band. Step S2: The noise-reduced target acoustic signal is transmitted to the high-sensitivity triboacoustic sensor (6) and converted into an electrical signal; Step S3: The electrical signal is collected and preprocessed by the signal acquisition device (3) and then uploaded to the database (4). The fault feature extraction and fault type identification are completed through the deep learning model, so as to realize the real-time monitoring of mechanical faults in a strong noise environment.

Images