A vehicle health dynamic monitoring method and system based on acoustic fingerprint

Abstract

The application relates to a vehicle health dynamic monitoring method and system based on acoustic fingerprints, belonging to the field of vehicle safety. The method comprises capturing soundprint transmission delay difference and sensing baseline spacing, calculating sound source azimuth, and positioning abnormal sound source coordinates; based on the abnormal sound source coordinates, an active soundprint collection protocol is triggered, original abnormal sound signals are collected, and environmental noise is suppressed to obtain high signal-to-noise ratio pure signals; an acoustic fingerprint layered scanning protocol is started, the high signal-to-noise ratio pure signals are decomposed into fine sub-frequency bands, and key monitoring frequency bands are extracted, and a frequency band attention index is obtained based on the key monitoring frequency bands; when the frequency band attention index exceeds a preset threshold range, a fault troubleshooting instruction is output, and a reverse acoustic signal and a vibration hedging amplitude are generated. The application realizes high-precision acoustic space perception and adaptive noise suppression optimization, and effectively performs dynamic monitoring on vehicle health.

Description

Technical Field

[0001] This invention belongs to the field of vehicle safety technology, specifically relating to a method and system for dynamic monitoring of vehicle health based on acoustic fingerprinting. Background Technology

[0002] With the development of intelligent vehicle detection technology, acoustic diagnostic technology has become an important research direction in the field of fault detection. Current mainstream technologies suffer from the following limitations: Insufficient sound source localization accuracy: Traditional single-point microphone detection systems are limited by spatial resolution, making accurate sound source localization difficult. Existing time-difference-based localization algorithms are susceptible to multipath effects in complex vehicle structures, leading to significantly increased localization errors. Weak noise suppression capabilities: Conventional noise suppression methods (such as fixed threshold filtering and spectral subtraction) have poor adaptability to non-steady-state environmental noise, easily causing distortion of effective abnormal noise signals in dynamic driving scenarios. Limited fault feature extraction: Existing technologies mostly use fixed-band energy threshold methods for anomaly detection, lacking in-depth analysis of multi-band coupling effects and frequency-energy weighting relationships, resulting in high misjudgment rates for complex faults such as engine knocking and bearing wear. Lack of dynamic compensation mechanisms: Traditional active noise cancellation systems do not consider the Doppler frequency shift effect caused by vehicle motion and the dynamic changes in sound wave propagation paths, leading to decreased noise reduction efficiency at high vehicle speeds. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for dynamic monitoring of vehicle health based on acoustic fingerprinting.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A method for dynamic monitoring of vehicle health based on acoustic fingerprinting, the implementation of which includes the following steps:

[0006] Capture the acoustic signature transmission delay difference and sensing baseline spacing, calculate the azimuth angle of the sound source, and locate the coordinates of abnormal sound sources;

[0007] Based on the coordinates of the abnormal sound source, an active voiceprint acquisition protocol is triggered to acquire the original abnormal sound signal and perform environmental noise suppression to obtain a clean signal with a high signal-to-noise ratio.

[0008] The acoustic fingerprint layered scanning protocol is initiated to decompose the high signal-to-noise ratio pure signal into fine sub-frequency bands and extract key monitoring frequency bands. Based on the key monitoring frequency bands, the frequency band attention index is obtained.

[0009] When the frequency band attention index exceeds the preset threshold range, a fault investigation command is output and a reverse acoustic signal and vibration offset amplitude are generated.

[0010] Preferably, the mathematical description of the high signal-to-noise ratio clean signal is... , of which S clean For a high signal-to-noise ratio clean signal, N is the number of microphones in the microphone array, and M is the number of microphones in the array. i W represents the original abnormal noise signal captured by the i-th microphone. i Let α be the corresponding environmental noise, and α be the noise attenuation coefficient.

[0011] Preferably, the mathematical description of the frequency band attention index is... , where R q E represents the frequency band attention index for the q-th key monitoring frequency band. q f represents the average energy of the q-th key monitoring frequency band, with a value of [0,1]. q For the q-th key monitoring frequency band, E m f is the average energy of the m-th fine subband. m Let q be the frequency of the m-th fine sub-band, where q = 1, 2, ..., Q, Q is the number of key monitoring frequency bands, and M is the number of fine sub-bands.

[0012] Preferably, the generation of the reverse acoustic signal and the vibration offset amplitude includes:

[0013] The inverse acoustic signal is generated based on the high signal-to-noise ratio pure signal;

[0014] The phase compensation factor set is analyzed, which includes the distance between the abnormal noise source and the driver's microphone, the distance between the speaker and the driver, the real-time vehicle speed, and the angle between the sound wave and the vehicle speed. The dynamic sound wave compensation amount is calculated based on the phase compensation factor set, and the coordinates of the abnormal sound source are updated synchronously to obtain the dynamic sound source coordinates.

[0015] The precise transmission of the reverse sound wave signal is performed based on the dynamic sound source coordinates and the dynamic sound wave compensation amount.

[0016] It detects the vibration amplitude and frequency of the seat, outputs the vibration countermeasure amplitude, and performs vibration countermeasure.

[0017] Preferably, the formula for calculating the dynamic acoustic compensation amount is as follows: Where u is the dynamic sound wave compensation amount, D1 is the distance between the abnormal noise source and the driver's side microphone, D2 is the distance between the speaker and the driver's side, and v c Where β is the real-time vehicle speed, and β is the angle between the sound wave and the vehicle speed; the expression for the dynamic sound source coordinates is: , where (x',y') are the x and y coordinates of the dynamic sound source, (x,y) are the x and y coordinates of the abnormal sound source, and θ is the azimuth angle of the sound source.

[0018] Preferably, the output of the vibration counter-damping amplitude includes:

[0019] The vibration decay time constant is calibrated, and an exponential decay term is obtained based on the vibration decay time constant and the seat vibration frequency.

[0020] Calibrate the reference speed and vehicle speed coupling coefficient and obtain the vehicle speed gain term;

[0021] The vibration offset amplitude is obtained based on the seat vibration amplitude, the exponential decay term, and the vehicle speed gain term.

[0022] Preferably, the expression for the exponential decay term is: ,in, f is an exponentially decaying term. z The frequency of seat vibration. is the vibration decay time constant.

[0023] Preferably, the mathematical description of the vehicle speed gain term is... ,in, For vehicle speed gain, k is the vehicle speed coupling coefficient, and v0 is the reference speed.

[0024] Preferably, the mathematical description of the vibration counter-vibration amplitude is... Where A2 is the vibration offset amplitude and A1 is the seat vibration amplitude.

[0025] A vehicle health dynamic monitoring system based on acoustic fingerprinting, used to execute the vehicle health dynamic monitoring method described above, includes an abnormal noise location module, an abnormal noise capture module, a fault detection module, and an abnormal noise elimination module;

[0026] The abnormal noise localization module is used to capture the soundprint transmission delay difference and the sensing baseline spacing and calculate the sound source azimuth angle to locate the coordinates of the abnormal sound source.

[0027] The abnormal noise capture module is used to trigger an active voiceprint acquisition protocol based on the coordinates of the abnormal sound source, acquire the original abnormal noise signal and perform environmental noise suppression to obtain a clean signal with a high signal-to-noise ratio;

[0028] The fault detection module is used to initiate the acoustic fingerprint hierarchical scanning protocol, decompose the high signal-to-noise ratio pure signal into fine sub-frequency bands and extract key monitoring frequency bands, and obtain the frequency band attention index based on the key monitoring frequency bands;

[0029] The noise cancellation module is used to output a fault investigation command and generate a reverse acoustic wave signal and vibration offset amplitude when the frequency band attention index exceeds a preset threshold range.

[0030] The beneficial effects of this invention are as follows:

[0031] (1) High-precision acoustic spatial perception: Based on the owl bionic principle, an asymmetric microphone array is deployed to improve the positioning accuracy of the azimuth angle of the sound source;

[0032] (2) Adaptive noise suppression optimization: Improve the suppression accuracy of high-frequency mechanical noise signals by adaptively adjusting the noise attenuation coefficient;

[0033] (3) Multi-dimensional fault feature analysis: The frequency band attention index is introduced to effectively identify the hidden fault feature frequency bands with low energy proportion, and the fault response speed is shortened by using the hierarchical frequency domain scanning protocol.

[0034] (4) Improved user experience: The introduction of vibration offset amplitude effectively eliminates abnormal noise and vibration during the noise suppression process, thereby improving user comfort. Attached Figure Description

[0035] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0036] Figure 1 This is a flowchart of the steps of a vehicle health dynamic monitoring method based on acoustic fingerprinting according to the present invention. Detailed Implementation

[0037] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description of the specific implementation methods, structures, features and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0038] Working principle and usage process of this invention:

[0039] Please see Figure 1 A method for dynamic monitoring of vehicle health based on acoustic fingerprinting, comprising:

[0040] S1: Employing biomimetic principles to simulate the asymmetrical structure of an owl's ear, a multi-channel acoustic sensing matrix is ​​deployed. This matrix consists of a high-frequency sound wave capture unit (top microphone) positioned at an elevation angle and a low-frequency vibration sensing unit (bottom microphone) positioned at a depression angle. When a potential vehicle noise is detected (distinguishing between normal and abnormal acoustic events using acoustic signature spectrum comparison technology), the acoustic signature transmission delay difference and sensing baseline spacing are captured based on the multi-channel acoustic sensing matrix. The acoustic signature transmission delay difference is the difference between the time it takes for the same sound wave to travel to the high-frequency sound wave capture unit and the time it takes to travel to the low-frequency vibration sensing unit. The sensing baseline spacing is the distance between the high-frequency sound wave capture unit and the low-frequency vibration sensing unit. Based on the acoustic signature transmission delay difference and the sensing baseline spacing, the sound source azimuth angle is calculated to locate the abnormal sound source coordinates. The formula for calculating the sound source azimuth angle is as follows: Where θ is the azimuth angle of the sound source. Let v be the soundprint transmission delay difference, v be the speed of sound (taken as 343 m / s), and d be the sensing baseline spacing. Example: Establish a vehicle body coordinate system and pre-store the coordinates of key components. When an abnormal noise occurs in the vehicle, the soundprint transmission delay difference is captured at 1.19 ms, and the sensing baseline spacing is 650 mm. Therefore, the azimuth angle of the sound source is approximately 39°. By calculating the sound wave propagation time, the distance from the sound source to the high-frequency sound wave capture unit can be determined (L = 343 m / s × 0.002 s = 0.686 m, where 0.002 s is the time it takes for the sound wave to travel to the high-frequency sound wave capture unit). Based on the sound source azimuth angle and the aforementioned distance, the coordinates of the abnormal sound source can be located. Comparing this with the previously pre-stored coordinates of key components reveals which part is suspected of producing the abnormal noise.

[0041] S2: Based on the coordinates of the abnormal sound source, an active voiceprint acquisition protocol is triggered. A sensor node coordinate traversal algorithm is executed, and the microphone array closest to the coordinates of the abnormal sound source is activated. The original abnormal sound signal is acquired, and environmental noise suppression is performed to obtain a high signal-to-noise ratio clean signal. Mathematically, this is described as follows: , of which S clean For a high signal-to-noise ratio clean signal, N is the number of microphones in the microphone array, and M is the number of microphones in the array. i W represents the original abnormal noise signal from the i-th microphone. i The corresponding ambient noise (collected in advance), α is the noise attenuation coefficient (empirical value 0.2-0.5);

[0042] S3: Initiate the acoustic fingerprint layered scanning protocol to decompose the high signal-to-noise ratio clean signal into M fine sub-frequency bands and extract Q key monitoring frequency bands (such as the high-speed engine operation area, brake friction sound area, etc.). Based on the key monitoring frequency bands, obtain the frequency band attention index, mathematically described as follows: , where R q E represents the frequency band attention index for the q-th key monitoring frequency band. q f represents the average energy of the q-th key monitoring frequency band, with a value of [0,1]. q For the q-th key monitoring frequency band, E m f is the average energy of the m-th fine subband. m Let q be the frequency of the m-th fine sub-band, q = 1, 2, ..., Q, where Q is the number of key monitoring frequency bands and M is the number of fine sub-bands. Example: Assume the abnormal engine noise is in the 5th key monitoring frequency band (2000Hz band), and its average energy percentage is high (E5 = 0.8), while the average energy of other frequency bands is E = 0.1. Then W5 = (0.8 * 2000...). 1.5 )·100 / [(0.8·2000 1.5 )+(M-1)·0.1·Other frequency items)], When W5 exceeds the preset threshold, the car engine may malfunction and needs to be checked;

[0043] S4: When the frequency band attention index exceeds the preset threshold range, the frequency band is abnormal. Output a fault investigation command to investigate vehicle faults and generate reverse sound wave signals and vibration offset amplitude to eliminate the influence of abnormal frequency bands and noise elimination processes.

[0044] In this embodiment, the generation of reverse acoustic signals and the influence of vibration impulse amplitude elimination on abnormal frequency bands and noise elimination processes can be implemented through the following steps:

[0045] S401: Generate the inverse acoustic signal based on the high signal-to-noise ratio pure signal;

[0046] S402: Analyze the phase compensation factor set, which includes the distance between the abnormal noise source and the driver's microphone, the distance between the speaker and the driver's seat, the real-time vehicle speed, and the sound wave-vehicle speed angle. The sound wave-vehicle speed angle is the angle between the vehicle's driving direction and the reverse sound wave signal transmission direction. Calculate the dynamic sound wave compensation amount based on the phase compensation factor set, and synchronously update the abnormal sound source coordinates to obtain the dynamic sound source coordinates. The calculation formula for the dynamic sound wave compensation amount is as follows: Where u is the dynamic sound wave compensation amount, in seconds; D1 is the distance from the source of the noise to the driver's side microphone; D2 is the distance from the speaker to the driver's side; and v... c Where β is the real-time vehicle speed, and β is the angle between the sound wave and the vehicle speed (set to zero when the vehicle is traveling at high speed); To compensate for the dynamic changes in the sound wave propagation path caused by vehicle motion, when the vehicle travels at a speed v c When the vehicle is moving, the actual path length of the engine sound waves to the microphone will change. For example, when the vehicle is traveling at a speed of 100 km / h (27.78 m / s), and D1 is 1.5 m and D2 is 0.6 m, and β is taken as 0, then the basic delay term is (1.5-0.6) / 343 = 0.0026 s, and the dynamic change compensation term is (27.78 × 1 × 1.5) / (2 × 343) 2 =0.00019s, meaning the total dynamic sound wave compensation is 0.00279s; the expression for the dynamic sound source coordinates is... , where (x',y') are the x and y coordinates of the dynamic sound source, and (x,y) are the x and y coordinates of the abnormal sound source.

[0047] S403: Based on the dynamic sound source coordinates and the dynamic sound wave compensation amount, perform precise transmission of the reverse sound wave signal, that is, transmit the reverse sound wave signal to the position of the dynamic sound source coordinates with a delay / advance of u seconds;

[0048] S404: The seat vibration amplitude and frequency are detected by the sensor, and a vibration counter-vibration amplitude is output based on the seat vibration amplitude and frequency to perform vibration counter-vibration, so as to eliminate the discomfort caused to the user by the seat vibration when the reverse sound wave signal is emitted.

[0049] In this embodiment, the vibration offset amplitude is output based on the seat vibration amplitude and the seat vibration frequency, and vibration offset is performed. This can be implemented through the following steps:

[0050] S404-1: Calibrate the vibration decay time constant. Based on the vibration decay time constant and the seat vibration frequency, obtain an exponential decay term. The expression for the exponential decay term is: ,in, The term is an exponentially decaying term, dimensionless, f z The frequency of seat vibration. The vibration decay time constant has an empirical value of 0.07 s;

[0051] S404-2: Calibrate the reference speed and vehicle speed coupling coefficient and obtain the vehicle speed gain term, mathematically described as follows: ,in, This is the vehicle speed gain term, which is dimensionless. k is the vehicle speed coupling coefficient, which is 0.2 by default. v0 is the base speed, which is 100km / h by default.

[0052] S404-3: The vibration offset amplitude is obtained based on the seat vibration amplitude, the exponential decay term, and the vehicle speed gain term, mathematically described as follows: Where A2 is the vibration offset amplitude in millimeters, and A1 is the seat vibration amplitude in millimeters; Example: When a reverse sound wave signal is emitted, a seat vibration amplitude of 0.4 mm and a seat vibration frequency of 8 Hz are detected, and the real-time vehicle speed is 80 km / h, then the vibration offset amplitude is... This generates a vibration counterweight of 0.265 mm to counteract the seat vibration during the transmission of the reverse acoustic signal.

[0053] A vehicle health dynamic monitoring system based on acoustic fingerprinting includes an abnormal noise location module, an abnormal noise capture module, a fault detection module, and an abnormal noise elimination module.

[0054] The abnormal noise localization module is used to simulate the asymmetrical structure of an owl's ear using biomimetic principles, and deploys a multi-channel acoustic sensing matrix. The multi-channel acoustic sensing matrix consists of a high-frequency sound wave capture unit (top microphone) positioned at an elevation angle and a low-frequency vibration sensing unit (bottom microphone) positioned at a depression angle. When a potential abnormal noise from a vehicle is detected (by distinguishing between normal acoustic events and abnormal events through voiceprint feature spectrum comparison technology), the module captures the voiceprint transmission delay difference and the sensing baseline distance based on the multi-channel acoustic sensing matrix. The voiceprint transmission delay difference is the difference between the time it takes for the same sound wave to travel to the high-frequency sound wave capture unit and the time delay it takes to travel to the low-frequency vibration sensing unit. The sensing baseline distance is the distance between the high-frequency sound wave capture unit and the low-frequency vibration sensing unit. Based on the voiceprint transmission delay difference and the sensing baseline distance, the module calculates the azimuth angle of the sound source and realizes the coordinate localization of the abnormal sound source.

[0055] The abnormal noise capture module is used to trigger an active voiceprint acquisition protocol based on the coordinates of the abnormal sound source, execute a sensor node coordinate traversal algorithm and activate the microphone array closest to the coordinates of the abnormal sound source, acquire the original abnormal noise signal and perform environmental noise suppression to obtain a high signal-to-noise ratio pure signal.

[0056] The fault detection module is used to initiate the acoustic fingerprint hierarchical scanning protocol, decompose the high signal-to-noise ratio pure signal into M fine sub-frequency bands and extract Q key monitoring frequency bands (such as the high-speed engine running area, brake friction sound area, etc.), and obtain the frequency band attention index based on the key monitoring frequency bands;

[0057] The abnormal noise elimination module is used to output a fault investigation command when the frequency band attention index exceeds a preset threshold range, to investigate vehicle faults, and to generate a reverse sound wave signal and vibration offset amplitude to eliminate the abnormal frequency band and the impact of noise elimination process.

[0058] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0059] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0060] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. The computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0061] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for dynamic monitoring of vehicle health based on acoustic fingerprinting, characterized in that, The implementation of the vehicle health dynamic monitoring method includes the following steps: Capture the acoustic signature transmission delay difference and sensing baseline spacing, calculate the azimuth angle of the sound source, and locate the coordinates of abnormal sound sources; Based on the coordinates of the abnormal sound source, an active voiceprint acquisition protocol is triggered to acquire the original abnormal sound signal and perform environmental noise suppression to obtain a clean signal with a high signal-to-noise ratio. The acoustic fingerprint layered scanning protocol is initiated to decompose the high signal-to-noise ratio pure signal into fine sub-frequency bands and extract key monitoring frequency bands. Based on the key monitoring frequency bands, the frequency band attention index is obtained. When the frequency band attention index exceeds the preset threshold range, a fault troubleshooting command is output and a reverse acoustic wave signal and vibration offset amplitude are generated. The generation of the reverse acoustic signal and the vibration offset amplitude includes: The inverse acoustic signal is generated based on the high signal-to-noise ratio pure signal; The phase compensation factor set is analyzed, which includes the distance between the abnormal noise source and the driver's microphone, the distance between the speaker and the driver, the real-time vehicle speed, and the angle between the sound wave and the vehicle speed. The dynamic sound wave compensation amount is calculated based on the phase compensation factor set, and the coordinates of the abnormal sound source are updated synchronously to obtain the dynamic sound source coordinates. The precise transmission of the reverse sound wave signal is performed based on the dynamic sound source coordinates and the dynamic sound wave compensation amount. It detects the vibration amplitude and frequency of the seat, outputs the vibration countermeasure amplitude, and performs vibration countermeasure.

2. The vehicle health dynamic monitoring method according to claim 1, characterized in that, The mathematical description of the high signal-to-noise ratio pure signal is , of which S clean For a high signal-to-noise ratio clean signal, N is the number of microphones in the microphone array, and M is the number of microphones in the array. i W represents the original abnormal noise signal captured by the i-th microphone. i Let α be the corresponding environmental noise, and α be the noise attenuation coefficient.

3. The vehicle health dynamic monitoring method according to claim 1, characterized in that, The mathematical description of the frequency band attention index is: , where R q E represents the frequency band attention index for the q-th key monitoring frequency band. q f represents the average energy of the q-th key monitoring frequency band, with a value of [0,1]. q For the q-th key monitoring frequency band, E m f is the average energy of the m-th fine subband. m Let q be the frequency of the m-th fine sub-band, where q = 1, 2, ..., Q, Q is the number of key monitoring frequency bands, and M is the number of fine sub-bands.

4. The vehicle health dynamic monitoring method according to claim 1, characterized in that, The formula for calculating the dynamic acoustic compensation amount is as follows: Where u is the dynamic sound wave compensation amount, D1 is the distance between the abnormal noise source and the driver's side microphone, D2 is the distance between the speaker and the driver's side, and v c Where β is the real-time vehicle speed, and β is the angle between the sound wave and the vehicle speed; the expression for the dynamic sound source coordinates is: , where (x',y') are the x and y coordinates of the dynamic sound source, (x,y) are the x and y coordinates of the abnormal sound source, and θ is the azimuth angle of the sound source.

5. The vehicle health dynamic monitoring method according to claim 4, characterized in that, The output of the vibration counter-damping amplitude includes: The vibration decay time constant is calibrated, and an exponential decay term is obtained based on the vibration decay time constant and the seat vibration frequency. Calibrate the reference speed and vehicle speed coupling coefficient and obtain the vehicle speed gain term; The vibration offset amplitude is obtained based on the seat vibration amplitude, the exponential decay term, and the vehicle speed gain term.

6. The vehicle health dynamic monitoring method according to claim 5, characterized in that, The expression for the exponential decay term is: ,in, f is an exponentially decaying term. z The frequency of seat vibration. is the vibration decay time constant.

7. The vehicle health dynamic monitoring method according to claim 6, characterized in that, The mathematical description of the vehicle speed gain term is ,in, For vehicle speed gain, k is the vehicle speed coupling coefficient, and v0 is the reference speed.

8. The vehicle health dynamic monitoring method according to claim 7, characterized in that, The mathematical description of the vibration impulse amplitude is Where A2 is the vibration offset amplitude and A1 is the seat vibration amplitude.

9. A vehicle health dynamic monitoring system based on acoustic fingerprinting, characterized in that, The system is applied to the vehicle health dynamic monitoring method as described in any one of claims 1-8, and includes an abnormal noise location module, an abnormal noise capture module, a fault detection module, and an abnormal noise elimination module; The abnormal noise localization module is used to capture the soundprint transmission delay difference and the sensing baseline spacing and calculate the sound source azimuth angle to locate the coordinates of the abnormal sound source. The abnormal noise capture module is used to trigger an active voiceprint acquisition protocol based on the coordinates of the abnormal sound source, acquire the original abnormal noise signal and perform environmental noise suppression to obtain a clean signal with a high signal-to-noise ratio; The fault detection module is used to initiate the acoustic fingerprint hierarchical scanning protocol, decompose the high signal-to-noise ratio pure signal into fine sub-frequency bands and extract key monitoring frequency bands, and obtain the frequency band attention index based on the key monitoring frequency bands; The noise cancellation module is used to output a fault investigation command and generate a reverse acoustic wave signal and vibration offset amplitude when the frequency band attention index exceeds a preset threshold range.

Images