Intelligent noise reduction method and system based on mine earphone

Abstract

The invention discloses an intelligent noise reduction method and system based on a mine earphone, and the method comprises the following steps: S1, obtaining an original noise signal in a mine operation environment, and carrying out the preprocessing of the original noise signal; s2, designing an adaptive compensation mechanism according to the reflection characteristics of the closed space of the mine, calculating a sound wave propagation attenuation coefficient and reflection delay, constructing a roadway reverberation model, and generating advanced compensation sound waves; and S3, carrying out collaborative fusion on the advanced compensation sound wave and a main noise reduction signal to generate a composite noise reduction signal. The invention relates to the technical field of intelligent noise reduction. According to the intelligent noise reduction method and system based on the mine earphone, the noise level in a mine operation environment is effectively reduced, the communication efficiency and the working comfort of operators are improved, potential damage of noise to hearing of the operators is reduced, and therefore the overall safety and the production efficiency of mine operation are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent noise reduction, more particularly, to an intelligent noise reduction method and system based on mine earphones. BACKGROUND

[0002] In the working environment of a closed space such as a mine, factors such as equipment operation, airflow flow, and roadway resonance can generate a large amount of noise, which not only affects the communication efficiency of the workers, but also can cause long-term damage to the hearing of the workers.

[0003] Traditional noise reduction methods, such as passive noise reduction earphones, mainly rely on physical soundproofing materials to block noise, but in the complex and variable environment of a mine, their noise reduction effect is limited, especially for low-frequency noise and reflected noise.

[0004] With the development of electronic technology and signal processing technology, active noise reduction technology (ANC) has gradually become a research hotspot. Active noise reduction technology generates an anti-noise signal that is opposite in phase and amplitude to the original noise to cancel out the original noise, thereby achieving the purpose of noise reduction. However, in a closed space such as a mine, due to the existence of sound wave reflection and reverberation effect, traditional active noise reduction technology is difficult to be directly applied, and needs to be optimized and improved according to the particularity of the mine environment. SUMMARY

[0005] The present application aims to provide an intelligent noise reduction method and system based on mine earphones, which solves the problem that traditional active noise reduction technology is difficult to be directly applied due to the existence of sound wave reflection and reverberation effect in a closed space such as a mine.

[0006] The present application achieves the above-mentioned purpose through the following technical solutions: an intelligent noise reduction method based on mine earphones, the method comprising the following steps: S1, obtaining an original noise signal in a mine working environment and pre-processing the original noise signal; S2, designing an adaptive compensation mechanism according to the reflection characteristics of the mine closed space, calculating the sound wave propagation attenuation coefficient and reflection delay, constructing a roadway reverberation model and generating a leading compensation sound wave; S3, synergistically fusing the leading compensation sound wave with a main noise reduction signal to generate a composite noise reduction signal; S4, real-time acquisition of residual noise signals in the ear canal, correction of reverberation compensation parameters based on the residual noise signals, dynamic optimization of the composite noise reduction signal, and realization of intelligent noise reduction in the mine environment.

[0007] Furthermore, in step S1, acquiring the raw noise signal in the mine working environment involves collecting multi-channel raw noise signals within the mine working area using a noise acquisition component installed on the mine headphones. These raw noise signals include equipment operating noise, airflow noise, and tunnel resonance noise, denoted as the signal set. ,in This represents the number of channels in the noise acquisition component. It is a time variable.

[0008] Furthermore, step S1 involves preprocessing the original noise signal, including: The original noise signal is filtered to remove ultra-low frequency interference and high frequency noise; A time-frequency conversion algorithm is used to convert the time-domain noise signal into a frequency-domain signal; The signal-to-noise ratio of the frequency domain signal is optimized to remove isolated noise spikes and retain the main noise frequency band characteristics in the mining environment.

[0009] Furthermore, the filtering process employs a bandpass filter, the frequency range of which is 20Hz-8kHz; The time-frequency conversion algorithm is a short-time Fourier transform, and its calculation formula is as follows: , in, For frequency, For frame shift parameters, For window functions; The signal-to-noise ratio optimization employs the spectral threshold method.

[0010] Furthermore, step S2 designs an adaptive compensation mechanism, including: The current ambient air pressure value and the spatial posture angle of the headset wearer are obtained by the environmental parameter acquisition component set on the mine headset. The system calls upon a pre-defined database of roadway cross-section parameters, selects the corresponding cross-section model based on the type of mine operation area, and calculates the sound wave propagation attenuation coefficient and reflection delay based on the theory of sound wave propagation.

[0011] Furthermore, the environmental parameter acquisition component includes a miniature barometric pressure sensor and a gyroscope, and the spatial attitude angle includes at least a horizontal deflection angle. With vertical pitch angle ; The tunnel cross-section model includes a circular cross-section model and a trapezoidal cross-section model. The parameters of the circular cross-section model include the radius r of the circular cross-section, and the parameters of the trapezoidal cross-section model include the upper base width a, the lower base width b, and the height h of the trapezoidal cross-section.

[0012] Furthermore, step S2, which involves constructing a tunnel reverberation model and generating a lead-compensated sound wave, includes: simulating the tunnel reverberation model using a filtering device, wherein the transfer function of the filtering device satisfies... , in The order of the filter device. For the first Filter coefficients of order, This represents the number of delay units; A time-domain lead-compensated sound wave is generated through iterative computation. Using the frequency domain characteristics of the pre-processed noise signal as input, a preliminary compensation signal is output based on a reverberation model. The signal phase is then adjusted using a phase adjustment algorithm so that the time difference between the compensation sound wave and the main noise reduction signal equals the reflection delay, resulting in a time-domain lead-compensated sound wave. .

[0013] Furthermore, step S3 generates the main noise reduction signal, including the following steps: The adaptive noise cancellation principle is adopted. The preprocessed original noise signal is used as the reference input, and the filter coefficients are updated through an adaptive filtering algorithm to make the main noise reduction signal out of phase and matched with the original noise signal. The advanced compensation sound wave is collaboratively fused with the main noise reduction signal, and the advanced compensation sound wave is processed through a collaborative fusion module. With the main noise reduction signal Time-domain weighted fusion is performed, and the fused signal is then jointly optimized in the time and frequency domains. The optimized signal is then converted back to the time domain to obtain a composite denoised signal.

[0014] Furthermore, step S4 involves real-time acquisition of residual noise signals within the ear canal, including the following steps: Residual noise signals inside the ear canal are collected at preset intervals using a feedback acquisition component installed inside the earphone. ; Based on the residual noise signal, the reverberation compensation parameters are corrected, and the energy of the residual noise signal is calculated. When the calculated average energy is greater than a preset threshold, the reverberation compensation parameter correction process is started to correct the relevant parameters of the reverberation model. The composite noise reduction signal is dynamically optimized, and the advance compensation sound wave is regenerated according to the corrected reverberation compensation parameters. The fusion weight of the collaborative fusion module is adjusted, and the optimized composite noise reduction signal is output through the headphone speaker to achieve real-time adaptive noise reduction.

[0015] A smart noise reduction system based on mine headphones, used to implement the aforementioned smart noise reduction method based on mine headphones, includes: The system includes a noise acquisition module, a preprocessing module, an adaptive compensation module, a collaborative fusion module, a residual noise acquisition module, a parameter correction and optimization module, and a signal output module. The noise acquisition module is used to acquire the raw noise signal in the mine working environment; The preprocessing module is used to preprocess the original noise signal; The adaptive compensation module is used to design an adaptive compensation mechanism for the reflection characteristics of the closed space in the mine, calculate the sound wave propagation attenuation coefficient and reflection delay, construct a roadway reverberation model and generate advanced compensation sound waves. The collaborative fusion module is used to collaboratively fuse the advanced compensation sound wave with the main noise reduction signal to generate a composite noise reduction signal. The residual noise acquisition module is used to acquire residual noise signals in the ear canal in real time. The parameter correction and optimization module is used to correct the reverberation compensation parameters based on the residual noise signal and dynamically optimize the composite noise reduction signal. The signal output module is used to output the optimized composite noise reduction signal to achieve intelligent noise reduction in the mining environment.

[0016] The beneficial effects of this invention are as follows: 1. By designing an adaptive compensation mechanism, this invention can dynamically adjust the noise reduction strategy according to the real-time changes in the mine environment, ensuring that a good noise reduction effect can be achieved under different operating conditions, making the noise reduction system more flexible and practical.

[0017] 2. In view of the reflection characteristics of the enclosed space of the mine, the present invention constructs a roadway reverberation model and generates advanced compensation sound waves to cancel reflected noise, which solves the problem that the traditional active noise reduction technology is not effective in enclosed spaces and significantly improves the noise reduction performance.

[0018] 3. Through the noise acquisition component set on the mine earpiece, the present invention can acquire multi-channel raw noise signals and perform preprocessing operations such as filtering, time-frequency conversion and signal-to-noise ratio optimization, effectively removing ultra-low frequency interference, high frequency noise and isolated noise spikes, while retaining the main noise frequency band characteristics in the mine environment, providing a high-quality data foundation for subsequent noise reduction processing.

[0019] 4. The advanced compensation sound wave is synergistically fused with the main noise reduction signal to generate a composite noise reduction signal. The reverberation compensation parameters are corrected by real-time acquisition of residual noise signals in the ear canal, and the composite noise reduction signal is dynamically optimized to ensure the continuous effectiveness and stability of the noise reduction system.

[0020] 5. Effectively reduces noise levels in the mine working environment, which not only improves the communication efficiency and work comfort of workers, but also reduces the potential damage of noise to workers' hearing, thereby improving the overall safety and production efficiency of mine operations. Attached Figure Description

[0021] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of the overall method of the present invention; Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1: Please see Figure 1 This invention provides a technical solution: an intelligent noise reduction method based on mine headphones, characterized in that the method includes the following steps: S1. Acquire the raw noise signal in the mine working environment and preprocess the raw noise signal; The raw noise signal is an unprocessed sound signal generated in the mining environment by the operation of various equipment, geological activities, and personnel activities. These signals contain sound wave components of various frequencies and intensities and are the starting point for subsequent noise reduction processing. Preprocessing is a series of pre-processing operations performed on the acquired raw noise signal, which usually includes filtering, amplification, and analog-to-digital conversion, with the aim of making the raw noise signal more suitable for subsequent analysis and processing. S2. An adaptive compensation mechanism is designed for the reflection characteristics of the closed space in the mine. The sound wave propagation attenuation coefficient and reflection delay are calculated, a roadway reverberation model is constructed, and an advance compensation sound wave is generated. Among them, the reflection characteristics of a closed space in a mine refer to the fact that the internal space of a mine is relatively closed, and sound waves will encounter obstacles such as roadway walls and be reflected when propagating within it; the adaptive compensation mechanism is a mechanism that can automatically adjust parameters according to changes in the reflection characteristics of a closed space in a mine; the sound wave propagation attenuation coefficient is a physical quantity that describes the degree to which the energy of a sound wave gradually weakens during propagation. In a mine environment, sound waves attenuate due to factors such as air absorption, scattering, and interaction with roadway walls during propagation. The sound wave propagation attenuation coefficient reflects the rate of this attenuation and is related to factors such as the frequency of the sound wave, the properties of the propagation medium, and the propagation distance; the reflection delay is the time it takes for a sound wave to travel from emission to being reflected back by an obstacle; the roadway reverberation model is a mathematical model established based on parameters such as the reflection characteristics of a closed space in a mine, the sound wave propagation attenuation coefficient, and the reflection delay, which can simulate the propagation and reflection process of sound waves in mine roadways; the advance compensation sound wave is a sound wave signal calculated based on the roadway reverberation model and used to compensate for the loss of sound wave signals caused by reflection and attenuation during propagation; S3. The advanced compensation sound wave is fused with the main noise reduction signal to generate a composite noise reduction signal; The main noise reduction signal is generated by active noise reduction technology and has the same amplitude but opposite phase as the original noise signal. It is used to directly cancel the main components of the original noise signal. The collaborative fusion is the process of combining the advance compensation sound wave with the main noise reduction signal in a certain way and proportion. Through collaborative fusion, the compensation effect of the advance compensation sound wave on the reflection and attenuation during the propagation of the sound wave and the direct cancellation effect of the main noise reduction signal on the original noise can be fully utilized to generate a more effective composite noise reduction signal. The composite noise reduction signal is the signal obtained after the collaborative fusion of the advance compensation sound wave and the main noise reduction signal. It combines the advantages of the two signals and can more effectively reduce the noise in the mine working environment. S4. Real-time acquisition of residual noise signals in the ear canal, correction of reverberation compensation parameters based on the residual noise signals, dynamic optimization of the composite noise reduction signal, and realization of intelligent noise reduction in the mining environment; Among them, residual noise signal in the ear canal refers to the noise signal that remains in the ear canal and cannot be completely eliminated after wearing noise reduction equipment; correcting reverberation compensation parameters is the process of adjusting and optimizing the parameters used to construct the roadway reverberation model in step S2 based on the residual noise signal in the ear canal collected in real time; dynamic optimization is the process of continuously correcting the reverberation compensation parameters and adjusting the composite noise reduction signal in real time based on the residual noise signal in the ear canal collected in real time during mine operations; intelligent noise reduction is an intelligent noise reduction system that can automatically adapt to changes in the mine environment and effectively reduce noise through the above series of steps, including real-time collection of residual noise signal, parameter correction, and dynamic optimization of composite noise reduction signal.

[0024] It should be noted that during operation, the original noise signal is acquired and preprocessed to lay the foundation for subsequent processing. An adaptive compensation mechanism is designed to construct a roadway reverberation model to generate advanced compensation sound waves, which accurately address the reflection characteristics of the enclosed space in the mine. The advanced compensation sound waves are then fused with the main noise reduction signal to enhance the noise reduction effect. The residual noise signal in the ear canal is collected in real time to correct parameters and optimize the composite noise reduction signal. The system dynamically adapts to changes in the mine environment, achieving intelligent noise reduction, effectively reducing mine noise, protecting personnel's hearing, and improving operational safety and comfort.

[0025] In one embodiment, acquiring the raw noise signal in the mine working environment and preprocessing the raw noise signal includes: acquiring multi-channel raw noise signals within the mine working area through an omnidirectional microphone array built into a mine headset. The raw noise signals include equipment operating noise, airflow noise, and roadway resonance noise, denoted as the signal set. ,in Number of microphone channels It is a time variable; The original noise signal is pre-filtered by using a 20Hz-8kHz bandpass filter to remove ultra-low frequency interference and high frequency noise; the time-domain noise signal is then converted to a frequency-domain signal using a short-time Fourier transform, calculated as follows: in, For frequency, For frame shift parameters, For the Hanning window function; The signal-to-noise ratio of the frequency domain signal is initially optimized, and isolated noise spikes are removed by the spectral thresholding method, while retaining the main noise frequency band characteristics in the mining environment.

[0026] This design uses an omnidirectional microphone array to collect multi-channel raw noise signals, covering equipment, airflow, and tunnel resonance noise, comprehensively reflecting the noise situation in the mine. Pre-filtering uses a 20Hz-8kHz bandpass filter to remove interference, and short-time Fourier transform converts the time domain to the frequency domain for easy analysis of noise characteristics. Initial signal-to-noise ratio optimization uses the spectral thresholding method to remove isolated spikes, retaining the main noise frequency bands, accurately acquiring and processing raw noise, removing irrelevant interference, highlighting key noise characteristics, and providing high-quality signals for subsequent adaptive compensation and noise reduction. This ensures that the noise reduction system works based on real and effective noise data, improving the overall noise reduction effect.

[0027] In one embodiment, the adaptive compensation mechanism designed for the reflection characteristics of a confined space in a mine, which calculates the sound wave propagation attenuation coefficient and reflection delay, constructs a roadway reverberation model, and generates a lead-compensated sound wave, includes: The current ambient air pressure value is collected through a miniature barometric pressure sensor built into the mine earpiece. Combined with gyroscope to obtain the spatial posture angle of the headphone wearer (Horizontal deflection angle) and (Vertical pitch angle); The system calls up a pre-defined database of roadway cross-section parameters and selects the corresponding cross-section model (circular cross-section radius) based on the type of mine operation area. Or the width of the top base of the trapezoidal cross section Bottom width and height The sound wave attenuation coefficient is calculated based on the sound wave propagation theory. With reflection delay : When the tunnel has a circular cross-section, the attenuation coefficient ,in air density (derived from air pressure) With ambient temperature It is deduced that, , (where the gas constant is...) For the speed of sound , The area of ​​the circular cross-section; When the tunnel has a trapezoidal cross-section, the attenuation coefficient ,in The area of ​​the trapezoidal cross section; Reflection Delay ,in The average distance between the headphones and the tunnel wall (estimated from cross-sectional parameters and attitude angle); A multi-order comb filter is used to simulate the reverberation model of the tunnel. The filter transfer function is: in Let this be the order of the comb filter (set to order 8). For the first Filtering coefficients (with attenuation coefficient) Dynamic adjustment , (sampling frequency) The number of delay units (based on reflection delay) calculate, , It is the reflection delay, which is the time it takes for a sound wave to reflect within the tunnel. Given the sampling frequency, the number of delay units is obtained by multiplying the reflection delay by the sampling frequency and rounding down. This value is used to determine in The delay amount of each order of filtering in the transformation, thus simulating the delay effect of sound wave reflection in digital signal processing. The advanced compensation sound wave is generated through iterative computation: taking the frequency domain characteristics of the preprocessed noise signal as input, an initial compensation signal is output based on the reverberation model, and the signal phase is adjusted through a minimum phase reconstruction algorithm so that the time difference between the compensation sound wave and the main noise reduction signal is equal to the reflection delay. Ultimately, time-domain advance-compensated sound waves are generated. .

[0028] This design utilizes miniature barometric pressure sensors and gyroscopes to obtain ambient air pressure and the wearer's posture angle. Combined with a pre-set database and acoustic wave theory, it calculates the sound wave propagation attenuation coefficient and reflection delay for different cross-section tunnels. A multi-stage comb filter simulates tunnel reverberation, and iterative calculations generate advance compensation sound waves. The phase is adjusted using a minimum phase reconstruction algorithm, and parameters are dynamically calculated based on the actual environment and posture. This accurately simulates sound wave propagation, generates realistic advance compensation sound waves, effectively compensates for noise caused by reflection and attenuation, and improves the targeting and effectiveness of noise reduction.

[0029] In one embodiment, the step of synergistically fusing the advanced compensation sound wave with the main noise reduction signal to generate a composite noise reduction signal includes: The main noise reduction signal is generated using the adaptive noise cancellation principle. Using the preprocessed original noise signal as a reference input, the filter coefficients are updated through an adaptive filter (LMS algorithm). This ensures that the main noise reduction signal is out of phase and matches the amplitude of the original noise signal. The calculation formula is as follows: in This is the step size factor (set to 0.005). For error signals, The discrete sampled values ​​are used as a reference noise signal; Construct a collaborative fusion module to provide advanced compensation for sound waves. With the main noise reduction signal Perform time-domain weighted fusion: in The fusion weights are set initially to 0.6 and dynamically adjusted based on subsequent residual noise feedback. The fused signal undergoes joint time-domain and frequency-domain optimization. The frequency-domain optimized signal is then converted back to the time domain using an overlap-addition method to obtain the final composite denoised signal. .

[0030] This design employs an adaptive noise cancellation principle to generate the main denoising signal. Using pre-processed noise as a reference, the LMS algorithm is used to update the filter coefficients, ensuring that the main denoising signal matches the original noise. The collaborative fusion module performs time-domain weighted fusion of the advance compensation sound wave and the main denoising signal, followed by joint optimization in the time and frequency domains. The main denoising signal directly cancels out the main components of the original noise, while the advance compensation sound wave compensates for propagation loss. The collaborative fusion fully leverages the advantages of both, and the joint optimization makes the signal more reasonable in the time and frequency domains. The resulting composite denoising signal can more comprehensively and effectively reduce noise, improving the denoising effect and stability.

[0031] In one embodiment, the real-time acquisition of residual noise signals within the ear canal, the correction of reverberation compensation parameters based on the residual noise signals, and the dynamic optimization of the composite noise reduction signal to achieve intelligent noise reduction in a mining environment include: The residual noise signal inside the ear canal is collected every 50ms using a miniature feedback microphone placed inside the ear canal of the mine earphone. Short-time energy calculation is performed on the residual noise signal: in The number of sampling points per frame (determined by the sampling frequency) =16kHz) and the acquisition interval of 50ms were determined. =800); when Greater than the preset residual noise threshold When the reverberation compensation parameter correction process is initiated (set to 10% of the average energy of the original noise signal), the minimum mean square error algorithm is used to adjust the residual noise signal. With advance compensation sound waves error To optimize the target, the filter coefficients of the multi-order comb filter are modified. With delay unit number : in To adjust the step size (set to 0.003); The advance compensation sound wave is regenerated based on the corrected reverberation compensation parameters. And adjust the fusion weight of the collaborative fusion module. (when When it increases, Reducing it by 0.05~0.1 enhances the effect of compensating for sound waves; when When decreasing, Maintain or increase by 0.02~0.05). The optimized composite noise reduction signal Real-time adaptive noise reduction of the dynamic sound field in the enclosed space of the mine is achieved through headphone speaker output.

[0032] This design uses a miniature feedback microphone to periodically collect residual noise signals in the ear canal, calculates short-time energy and compares it with a threshold. If the energy exceeds the threshold, the reverberation compensation parameters are corrected using a minimum mean square error algorithm, a new lead compensation sound wave is generated, the fusion weight is adjusted, and an optimized composite noise reduction signal is output. The noise reduction effect is perceived in real time. When the residual noise exceeds the standard, the parameters are automatically corrected, the fusion ratio is adjusted, and the composite noise reduction signal is dynamically optimized. This allows the noise reduction system to adapt to changes in the mine environment, maintain good noise reduction performance, and achieve intelligent and efficient real-time adaptive noise reduction.

[0033] Example 2: Please see Figure 2 A smart noise reduction system based on mine headphones, used to implement the aforementioned smart noise reduction method based on mine headphones, includes: The system includes a noise acquisition module, a preprocessing module, an adaptive compensation module, a collaborative fusion module, a residual noise acquisition module, a parameter correction and optimization module, and a signal output module. The noise acquisition module is used to acquire the raw noise signal in the mine working environment; The preprocessing module is used to preprocess the original noise signal; The adaptive compensation module is used to design an adaptive compensation mechanism for the reflection characteristics of the closed space in the mine, calculate the sound wave propagation attenuation coefficient and reflection delay, construct a roadway reverberation model and generate advanced compensation sound waves. The collaborative fusion module is used to collaboratively fuse the advanced compensation sound wave with the main noise reduction signal to generate a composite noise reduction signal. The residual noise acquisition module is used to acquire residual noise signals in the ear canal in real time. The parameter correction and optimization module is used to correct the reverberation compensation parameters based on the residual noise signal and dynamically optimize the composite noise reduction signal. The signal output module is used to output the optimized composite noise reduction signal to achieve intelligent noise reduction in the mining environment.

[0034] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0035] The above embodiments provide a detailed description of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A smart noise reduction method based on mine headphones, characterized in that, The method includes the following steps: S1. Acquire the raw noise signal in the mine working environment and preprocess the raw noise signal; S2. An adaptive compensation mechanism is designed for the reflection characteristics of the closed space in the mine. The sound wave propagation attenuation coefficient and reflection delay are calculated, a roadway reverberation model is constructed, and an advance compensation sound wave is generated. S3. The advanced compensation sound wave is fused with the main noise reduction signal to generate a composite noise reduction signal; S4. Real-time acquisition of residual noise signals in the ear canal, correction of reverberation compensation parameters based on the residual noise signals, dynamic optimization of the composite noise reduction signal, and realization of intelligent noise reduction in the mining environment.

2. The intelligent noise reduction method based on mine headphones according to claim 1, characterized in that, In step S1, the raw noise signal in the mine working environment is acquired by collecting multi-channel raw noise signals within the mine working area through a noise acquisition component installed on the mine headphones. The raw noise signal includes equipment operating noise, airflow noise, and tunnel resonance noise, denoted as the signal set. ,in This represents the number of channels in the noise acquisition component. It is a time variable.

3. The intelligent noise reduction method based on mine headphones according to claim 2, characterized in that, Step S1 involves preprocessing the original noise signal, including: The original noise signal is filtered to remove ultra-low frequency interference and high frequency noise; A time-frequency conversion algorithm is used to convert the time-domain noise signal into a frequency-domain signal; The signal-to-noise ratio of the frequency domain signal is optimized to remove isolated noise spikes and retain the main noise frequency band characteristics in the mining environment.

4. The intelligent noise reduction method based on mine headphones according to claim 3, characterized in that: The filtering process employs a bandpass filter, the frequency range of which is 20Hz-8kHz. The time-frequency conversion algorithm is a short-time Fourier transform, and its calculation formula is as follows: ， in, For frequency, For frame shift parameters, For window functions; The signal-to-noise ratio optimization employs the spectral threshold method.

5. The intelligent noise reduction method based on mine headphones according to claim 1, characterized in that, Step S2 involves designing an adaptive compensation mechanism, including: The current ambient air pressure value and the spatial posture angle of the headset wearer are obtained by the environmental parameter acquisition component set on the mine headset. The system calls upon a pre-defined database of roadway cross-section parameters, selects the corresponding cross-section model based on the type of mine operation area, and calculates the sound wave propagation attenuation coefficient and reflection delay based on the theory of sound wave propagation.

6. The intelligent noise reduction method based on mine headphones according to claim 5, characterized in that: The environmental parameter acquisition component includes a miniature barometer and a gyroscope, and the spatial attitude angle includes at least a horizontal deflection angle. With vertical pitch angle ; The tunnel cross-section model includes a circular cross-section model and a trapezoidal cross-section model. The parameters of the circular cross-section model include the radius r of the circular cross-section, and the parameters of the trapezoidal cross-section model include the upper base width a, the lower base width b, and the height h of the trapezoidal cross-section.

7. The intelligent noise reduction method based on mine headphones according to claim 6, characterized in that, Step S2 involves constructing a tunnel reverberation model and generating a lead-compensated sound wave, including: simulating the tunnel reverberation model using a filtering device, wherein the transfer function of the filtering device satisfies... ， in The order of the filter device. For the first Filter coefficients of order, This represents the number of delay units; A time-domain lead-compensated sound wave is generated through iterative computation. Using the frequency domain characteristics of the pre-processed noise signal as input, a preliminary compensation signal is output based on a reverberation model. The signal phase is then adjusted using a phase adjustment algorithm so that the time difference between the compensation sound wave and the main noise reduction signal equals the reflection delay, resulting in a time-domain lead-compensated sound wave. .

8. The intelligent noise reduction method based on mine headphones according to claim 1, characterized in that, Step S3 generates the main noise reduction signal, including the following steps: The adaptive noise cancellation principle is adopted. The preprocessed original noise signal is used as the reference input, and the filter coefficients are updated through an adaptive filtering algorithm to make the main noise reduction signal out of phase and matched with the original noise signal. The advanced compensation sound wave is collaboratively fused with the main noise reduction signal, and the advanced compensation sound wave is processed through a collaborative fusion module. With the main noise reduction signal Time-domain weighted fusion is performed, and the fused signal is then jointly optimized in the time and frequency domains. The optimized signal is then converted back to the time domain to obtain a composite denoised signal.

9. The intelligent noise reduction method based on mine headphones according to claim 1, characterized in that, Step S4 involves real-time acquisition of residual noise signals within the ear canal, including the following steps: Residual noise signals inside the ear canal are collected at preset intervals using a feedback acquisition component installed inside the earphone. ; Based on the residual noise signal, the reverberation compensation parameters are corrected, and the energy of the residual noise signal is calculated. When the calculated average energy is greater than a preset threshold, the reverberation compensation parameter correction process is started to correct the relevant parameters of the reverberation model. The composite noise reduction signal is dynamically optimized, and the advance compensation sound wave is regenerated according to the corrected reverberation compensation parameters. The fusion weight of the collaborative fusion module is adjusted, and the optimized composite noise reduction signal is output through the headphone speaker to achieve real-time adaptive noise reduction.

10. A smart noise reduction system based on mine headphones, used to implement the smart noise reduction method based on mine headphones as described in any one of claims 1-9, characterized in that, include: The system includes a noise acquisition module, a preprocessing module, an adaptive compensation module, a collaborative fusion module, a residual noise acquisition module, a parameter correction and optimization module, and a signal output module. The noise acquisition module is used to acquire the raw noise signal in the mine working environment; The preprocessing module is used to preprocess the original noise signal; The adaptive compensation module is used to design an adaptive compensation mechanism for the reflection characteristics of the closed space in the mine, calculate the sound wave propagation attenuation coefficient and reflection delay, construct a roadway reverberation model and generate advanced compensation sound waves. The collaborative fusion module is used to collaboratively fuse the advanced compensation sound wave with the main noise reduction signal to generate a composite noise reduction signal. The residual noise acquisition module is used to acquire residual noise signals in the ear canal in real time. The parameter correction and optimization module is used to correct the reverberation compensation parameters based on the residual noise signal and dynamically optimize the composite noise reduction signal. The signal output module is used to output the optimized composite noise reduction signal to achieve intelligent noise reduction in the mining environment.

Images