Collection and noise reduction method, device and equipment for electric power working environment noise and medium

Abstract

The invention relates to an electric power working environment noise collection and noise reduction method and device, equipment and a medium. Comprising the following steps: for any iteration process, carrying out wavelet transform on an equipment sound signal in an electric power working environment based on a telescopic factor of the iteration process, and determining a wavelet transform coefficient corresponding to the equipment sound signal; according to the wavelet transform coefficient, performing noise reduction processing on the equipment sound signal to obtain a noise reduction signal; under the condition that the signal-to-noise ratio of the noise reduction signal does not reach a preset signal-to-noise ratio threshold value, updating the telescopic factor and re-determining the wavelet transform coefficient of the equipment sound signal until the signal-to-noise ratio reaches the preset signal-to-noise ratio threshold value; determining an equipment sound signal: acquiring an original sound collected by the unmanned aerial vehicle in an electric power working environment; and based on a beam forming algorithm, filtering out unmanned aerial vehicle noise in the original sound to obtain equipment noise, and determining an equipment sound signal. Noise in an electric power working environment can be collected more comprehensively, and then the noise reduction effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of sound processing, and particularly to a method, device, equipment, and medium for collecting and reducing noise in a power working environment. Background Art

[0002] In the power industry, the effective collection and processing (i.e., noise reduction) of working environment noise is crucial for ensuring the stable operation of equipment and maintaining the quality of the surrounding environment.

[0003] However, current traditional noise collection relies on sensors at fixed positions and has many limitations. Due to its limited coverage, it is difficult to comprehensively capture the noise situation in complex areas such as large substations and along transmission lines. For special noises formed by sound wave reflection such as standing waves, as well as low-frequency noises that are easily overlooked but seriously affect residents, fixed sensors are difficult to detect in a timely manner, resulting in the long-term undetected noise exceeding the standard in some areas, which affects the lives of residents and the stable operation of power facilities.

[0004] At the same time, based on incomplete noise collection data, subsequent noise reduction work faces great challenges. Conventional noise reduction methods are difficult to effectively handle complex and diverse noise characteristics and urgently need to be solved. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, equipment, and medium for collecting and reducing noise in a power working environment. On the one hand, it can collect noise in the power working environment more comprehensively, facilitating the acquisition of more accurate noise spectra and noise characteristics of power equipment (such as substations, transmission lines, etc.); on the other hand, based on more accurate noise spectra and noise characteristics, it can support the improvement of active noise reduction performance and enhance the noise reduction effect.

[0006] In a first aspect, the present application provides a method for collecting and reducing noise in a power working environment, including:

[0007] For any iteration process, based on the scaling factor corresponding to the current iteration process, perform wavelet transform processing on the equipment sound signal in the power working environment to determine the wavelet transform coefficients corresponding to the equipment sound signal;

[0008] According to the wavelet transform coefficients, perform noise reduction processing on the equipment sound signal to obtain a noise reduction signal;

[0009] In the case where the signal-to-noise ratio of the noise reduction signal does not reach the preset signal-to-noise ratio threshold, update the scaling factor, and use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the equipment sound signal until the signal-to-noise ratio of the noise reduction signal reaches the preset signal-to-noise ratio threshold;

[0010] Among them, the device sound signal is determined based on the following method:

[0011] Obtain the original sound collected by the drone in the power working environment; among them, the original sound includes drone noise and device noise in the power working environment;

[0012] Based on the beamforming algorithm, filter out the drone noise in the original sound to obtain the device noise;

[0013] Determine the device sound signal according to the device noise.

[0014] In one embodiment, noise reduction processing is performed on the device sound signal according to the wavelet transform coefficients to obtain a noise-reduced signal, including: determining the noise standard deviation corresponding to the device sound signal according to the wavelet transform coefficients; determining the noise reduction threshold corresponding to the device sound signal according to the noise standard deviation; performing wavelet decomposition on the wavelet transform coefficients according to the noise reduction threshold, and performing noise reduction processing on the device sound signal according to the decomposition result to obtain a noise-reduced signal.

[0015] In one embodiment, the scaling factor includes a scale factor; correspondingly, updating the scaling factor includes: determining an intermediate scale factor according to the scale factor and at least one random scale factor; determining the first fitness value corresponding to the scale factor and the second fitness value corresponding to the intermediate scale factor; in the case where the second fitness value exceeds the first fitness value, using the intermediate scale factor as the updated scale factor.

[0016] In one embodiment, obtaining the original sound collected by the drone in the power working environment includes: constructing a noise heat map corresponding to the power working environment; controlling the flight trajectory of the drone based on the noise distribution at different positions in the noise heat map, and controlling the drone to perform sound collection in the power working environment.

[0017] In one embodiment, obtaining the original sound collected by the drone in the power working environment includes: obtaining the current environmental factors; controlling the drone signal of the drone based on the current environmental factors, and controlling the drone to perform sound collection in the power working environment.

[0018] In one embodiment, the current environmental factors include at least one of wind speed and temperature; correspondingly, controlling the drone signal of the drone based on the current environmental factors includes: if the current environmental factors include wind speed, controlling the drone to activate the wind noise suppression algorithm when the wind speed exceeds the preset wind speed threshold; if the current environmental factors include temperature, controlling the drone to adjust the wavelet decomposition scale when the temperature exceeds the preset temperature threshold.

[0019] In one embodiment, after obtaining the original sound collected by the drone in the power working environment, it further includes: performing sound preprocessing on the original sound; wherein, the sound preprocessing includes at least one of pulse suppression, band - coordinated noise reduction, and sound feature extraction; correspondingly, based on the beamforming algorithm, filtering out the drone noise in the original sound to obtain the equipment noise, including: based on the beamforming algorithm, filtering out the drone noise in the preprocessed original sound to obtain the equipment noise.

[0020] In a second aspect, the present application further provides a noise reduction device for the sound in the power working environment, including:

[0021] A determination module, configured to perform wavelet transform processing on the equipment sound signal in the power working environment based on the scaling factor corresponding to the current iteration process for any iteration process, and determine the wavelet transform coefficients corresponding to the equipment sound signal;

[0022] A noise reduction module, configured to perform noise reduction processing on the equipment sound signal according to the wavelet transform coefficients to obtain a noise - reduced signal;

[0023] An update module, configured to update the scaling factor in the case where the signal - to - noise ratio of the noise - reduced signal does not reach the preset signal - to - noise ratio threshold, and use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re - execute the process of determining the wavelet transform coefficients corresponding to the equipment sound signal until the signal - to - noise ratio of the noise - reduced signal reaches the preset signal - to - noise ratio threshold;

[0024] Among them, the determination module is further configured to obtain the original sound collected by the drone in the power working environment; wherein, the original sound includes drone noise and equipment noise in the power working environment; based on the beamforming algorithm, filtering out the drone noise in the original sound to obtain the equipment noise; and determining the equipment sound signal according to the equipment noise.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] For any iteration process, perform wavelet transform processing on the equipment sound signal in the power working environment based on the scaling factor corresponding to the current iteration process, and determine the wavelet transform coefficients corresponding to the equipment sound signal;

[0027] Perform noise reduction processing on the equipment sound signal according to the wavelet transform coefficients to obtain a noise - reduced signal;

[0028] In the case where the signal-to-noise ratio of the noise-reduced signal does not reach the preset signal-to-noise ratio threshold, update the scaling factor, use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the device sound signal until the signal-to-noise ratio of the noise-reduced signal reaches the preset signal-to-noise ratio threshold;

[0029] Among them, the device sound signal is determined based on the following method:

[0030] Obtain the original sound collected by the drone in the power working environment; among them, the original sound includes drone noise and device noise in the power working environment;

[0031] Based on the beamforming algorithm, filter out the drone noise in the original sound to obtain the device noise;

[0032] Determine the device sound signal according to the device noise.

[0033] Fourthly, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0034] For any iteration process, based on the scaling factor corresponding to the current iteration process, perform wavelet transform processing on the device sound signal in the power working environment to determine the wavelet transform coefficients corresponding to the device sound signal;

[0035] According to the wavelet transform coefficients, perform noise reduction processing on the device sound signal to obtain a noise-reduced signal;

[0036] In the case where the signal-to-noise ratio of the noise-reduced signal does not reach the preset signal-to-noise ratio threshold, update the scaling factor, use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the device sound signal until the signal-to-noise ratio of the noise-reduced signal reaches the preset signal-to-noise ratio threshold;

[0037] Among them, the device sound signal is determined based on the following method:

[0038] Obtain the original sound collected by the drone in the power working environment; among them, the original sound includes drone noise and device noise in the power working environment;

[0039] Based on the beamforming algorithm, filter out the drone noise in the original sound to obtain the device noise;

[0040] Determine the device sound signal according to the device noise.

[0041] Fifthly, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] For any iteration process, based on the scaling factor corresponding to this iteration process, perform wavelet transform processing on the device sound signal in the power working environment to determine the wavelet transform coefficients corresponding to the device sound signal;

[0043] According to the wavelet transform coefficients, perform noise reduction processing on the device sound signal to obtain a noise-reduced signal;

[0044] In the case where the signal-to-noise ratio of the noise-reduced signal does not reach the preset signal-to-noise ratio threshold, update the scaling factor, and use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the device sound signal until the signal-to-noise ratio of the noise-reduced signal reaches the preset signal-to-noise ratio threshold;

[0045] Among them, the device sound signal is determined based on the following method:

[0046] Obtain the original sound collected by the unmanned aerial vehicle in the power working environment; among them, the original sound includes the noise of the unmanned aerial vehicle and the device noise in the power working environment;

[0047] Based on the beamforming algorithm, filter out the noise of the unmanned aerial vehicle in the original sound to obtain the device noise;

[0048] Determine the device sound signal according to the device noise.

[0049] In the above method, device and medium for collecting and reducing noise in the power working environment, during the process of obtaining the device sound signal, the original sound in the power working environment is collected by the unmanned aerial vehicle. Since the original sound includes the noise of the unmanned aerial vehicle itself and the device noise in the power working environment, based on the beamforming algorithm, the noise of the unmanned aerial vehicle in the original sound is filtered out to obtain the device noise, and the device sound signal is determined according to the device noise. In the above process, since the unmanned aerial vehicle can collect noise three-dimensionally, based on this noise acquisition method, more accurate original sound can be obtained. Correspondingly, the device noise obtained after filtering out the noise of the unmanned aerial vehicle can be more accurate, which further supports the improvement of the active noise reduction performance. Further, during the process of reducing noise for the device sound signal, the scaling factor affecting the wavelet transform coefficients is iteratively updated, so that the wavelet transform coefficients corresponding to the device sound signal are more and more conducive to the noise reduction of the device sound signal. That is to say, the iteration makes the noise reduction effect of the device sound signal better until the signal-to-noise ratio of the noise-reduced signal reaches the preset signal-to-noise ratio threshold. In summary, the above method can achieve the following effects: on the one hand, it can collect the noise in the power working environment more comprehensively, which is convenient for obtaining the noise spectrum and noise characteristics of more accurate power equipment (such as substations, transmission lines, etc.); on the other hand, based on the more accurate noise spectrum and noise characteristics, it can support the improvement of the active noise reduction performance and improve the noise reduction effect. Brief Description of the Drawings

[0050] To more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a schematic flowchart of the method for collecting and reducing noise in the power working environment in one embodiment;

[0052] Figure 2 It is a schematic flowchart of the noise reduction processing steps in one embodiment;

[0053] Figure 3 It is a schematic flowchart of the stretching factor update steps in one embodiment;

[0054] Figure 4 It is a schematic flowchart of the original sound acquisition steps in one embodiment;

[0055] Figure 5 It is a schematic flowchart of the original sound acquisition steps in another embodiment;

[0056] Figure 6 It is a schematic flowchart of the method for collecting noise in the power working environment in one embodiment;

[0057] Figure 7 It is a schematic flowchart of the method for reducing noise in the power working environment in another embodiment;

[0058] Figure 8 It is a structural block diagram of the noise reduction device for the power working environment sound in one embodiment;

[0059] Figure 9 It is a schematic structural diagram of a wearable device in one embodiment;

[0060] Figure 10 It is an internal structure diagram of a computer device in one embodiment. Detailed Description of the Embodiments

[0061] To make the objectives, technical solutions and advantages of the present application clearer and more understandable, the following further details the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] In one embodiment, as Figure 1As shown, a method for collecting and reducing noise in a power working environment is provided. In this embodiment, this method is exemplified by being applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0063] S110, for any iteration process, based on the scaling factor corresponding to this iteration process, perform wavelet transform processing on the device sound signal in the power working environment to determine the wavelet transform coefficients corresponding to the device sound signal.

[0064] Among them, the device sound signal can be the signal corresponding to the device noise collected in the power working environment.

[0065] Exemplarily, in this embodiment, the device sound signal can be processed by wavelet transform based on the following formula:

[0066] ;

[0067] In the formula, W x (a, b) is the wavelet transform coefficient of the device sound signal x(t), representing the energy distribution of the device sound signal x(t) under the scale factor a and the time shift factor b; a and b are the scaling factors corresponding to this iteration process, where a is the scale factor for controlling the frequency resolution; b is the time shift factor; is the complex conjugate of the wavelet mother function.

[0068] In order to make the device sound signal more accurate and thus improve the noise reduction effect, in an optional implementation, the device sound signal in the power working environment is determined based on the following method: Obtain the original sound collected by the drone in the power working environment; among them, the original sound includes drone noise and device noise in the power working environment; based on the beamforming algorithm, filter out the drone noise in the original sound to obtain the device noise; determine the device sound signal according to the device noise.

[0069] Among them, filtering out the drone noise in the original sound based on the beamforming algorithm may include the following content: Exemplarily, integrate a microphone array and a vibration sensor on the drone, and separate the drone's own noise (such as motor vibration, propeller airflow sound) and the target power device noise through an adaptive filtering algorithm. Specifically, the vibration sensor is used to collect the motor vibration spectrum of the drone in real time to generate a reference signal; and the least mean square (LMS) algorithm is used to dynamically cancel the audio signal to filter out the drone noise. Through the above method, the effect of reducing drone noise interference can be achieved, and the noise purity in the subsequent noise reduction process can be ensured.

[0070] Specifically, in this embodiment, the drone is controlled to collect the original sound of the power working environment at various spatial positions. Since the drone will generate noise during operation, the beamforming algorithm is used to filter out the noise of the drone itself and other non-target noises, so as to obtain the target sound in the power working environment, that is, the aforementioned equipment noise. Further, the equipment noise is signalized to obtain the equipment sound signal. On the one hand, in the above process, using the drone equipment to collect the original sound can obtain a more three-dimensional original sound, and then obtain a more accurate noise spectrum and noise characteristics of the power grid space such as substations and transmission lines, which supports the subsequent noise reduction process. On the other hand, it can avoid the influence of the sound in the non-power working environment on the determination process of the wavelet transform coefficients, making the equipment noise more accurate and providing a good basis for the subsequent noise reduction process.

[0071] S120. Perform noise reduction processing on the equipment sound signal according to the wavelet transform coefficients to obtain a noise reduction signal.

[0072] Exemplarily, in this embodiment, the wavelet transform coefficients and the equipment sound signal can be input into a noise reduction model to obtain a noise reduction signal.

[0073] S130. In the case where the signal-to-noise ratio of the noise reduction signal does not reach the preset signal-to-noise ratio threshold, update the scaling factor, and use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the equipment sound signal until the signal-to-noise ratio of the noise reduction signal reaches the preset signal-to-noise ratio threshold.

[0074] Exemplarily, in this embodiment, at least one of the scale factor a and the time shift factor b can be updated according to a preset update strategy, where the preset update strategy can be determined based on manual experience, and the present application does not make any limitation thereto. Exemplarily, the scale factor a can be increased by a preset value, and at the same time, the time shift factor b can be decreased by a preset value.

[0075] The above methods, devices, equipment, and media for collecting and reducing noise in the power working environment collect the original sound in the power working environment through a drone during the process of obtaining the sound signal of the equipment. Since the original sound includes the noise of the drone itself and the noise of the equipment in the power working environment, based on the beamforming algorithm, the drone noise in the original sound is filtered to obtain the equipment noise, and the equipment sound signal is determined according to the equipment noise. In the above process, since the drone can collect noise three-dimensionally, based on this noise acquisition method, more accurate original sound can be obtained. Correspondingly, the equipment noise obtained after filtering the drone noise can be more accurate, thereby supporting the improvement of the active noise reduction performance. Further, during the process of reducing the noise of the equipment sound signal, the scaling factor affecting the wavelet transform coefficient is iteratively updated, so that the wavelet transform coefficient corresponding to the equipment sound signal is more and more conducive to the noise reduction of the equipment sound signal. That is to say, the iteration makes the noise reduction effect of the equipment sound signal better until the signal-to-noise ratio of the noise reduction signal reaches the preset signal-to-noise ratio threshold. In summary, the above method can achieve the following effects: on the one hand, it can collect the noise in the power working environment more comprehensively, facilitating the acquisition of more accurate noise spectra and noise characteristics of power equipment (such as substations, transmission lines, etc.); on the other hand, based on the more accurate noise spectra and noise characteristics, it can support the improvement of the active noise reduction performance and improve the noise reduction effect.

[0076] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the process of performing noise reduction processing on the equipment sound signal according to the wavelet transform coefficient to obtain a noise reduction signal is refined.

[0077] See Figure 2 The noise reduction processing steps shown in

[0078] S210. Determine the noise standard deviation corresponding to the equipment sound signal according to the wavelet transform coefficient.

[0079] Exemplarily, in this embodiment, the noise standard deviation corresponding to the equipment sound signal can be determined based on the following formula:

[0080] ;

[0081] In the formula, represents the noise standard deviation corresponding to the equipment sound signal; W x (a, b) is the wavelet transform coefficient of the equipment sound signal x(t), representing the energy distribution of the equipment sound signal x(t) under the scale factor a and the time shift factor b; median represents the median operation.

[0082] S220. Determine the noise reduction threshold corresponding to the equipment sound signal according to the noise standard deviation.

[0083] Exemplarily, the noise reduction threshold corresponding to the device sound signal can be determined based on the following formula:

[0084] ;

[0085] In the formula, represents the noise reduction threshold corresponding to the device sound signal; represents the standard deviation of the noise corresponding to the device sound signal; N is the length of the discrete signal of the device sound signal.

[0086] S230. Perform noise reduction processing on the device sound signal according to the noise reduction threshold and the wavelet transform coefficient to obtain a noise-reduced signal.

[0087] In an alternative embodiment, the noise reduction threshold and the wavelet transform coefficient can be input into a pre-trained noise reduction model to obtain a noise-reduced signal after performing noise reduction processing on the device sound signal.

[0088] In another alternative embodiment, the wavelet transform coefficient can be wavelet decomposed according to the noise reduction threshold, and the device sound signal can be noise-reduced according to the decomposition result to obtain a noise-reduced signal.

[0089] Exemplarily, the wavelet transform coefficient can be decomposed based on the following formula:

[0090] ;

[0091] In the formula, represents the decomposition result; W x (a, b) is the wavelet transform coefficient of the device sound signal x(t), representing the energy distribution of the device sound signal x(t) under the scale factor a and the time shift factor b; represents the noise reduction threshold corresponding to the device sound signal.

[0092] Furthermore, according to the decomposition result, based on the following formula, the device sound signal is noise-reduced to obtain a noise-reduced signal:

[0093] ;

[0094] In the formula, represents the noise-reduced signal; represents the decomposition result; a is the scale factor, a max represents the maximum value of the scale range; a min represents the minimum value of the scale range; used to control the frequency resolution; b is the time shift factor; is the complex conjugate of the wavelet mother function.

[0095] Based on the technical solutions of the above embodiments, the present application also provides an alternative embodiment. In this alternative embodiment, the scaling factor includes a scale factor. In this case, the scale factor can be updated based on a heuristic algorithm according to a preset scale factor interval. In the following embodiments, the process of updating the scaling factor is introduced in detail. Among them, the heuristic algorithm adopted in this embodiment can be the red-billed blue magpie optimization algorithm.

[0096] See Figure 3 The scaling factor update steps shown include:

[0097] S310. Determine an intermediate scale factor according to the scale factor and at least one random scale factor.

[0098] S320. Determine the first fitness value corresponding to the scale factor and the second fitness value corresponding to the intermediate scale factor.

[0099] Among them, the intermediate scale factor can be understood as a to-be-determined scale factor. In the case where the second fitness value corresponding to the intermediate scale factor exceeds the first fitness value corresponding to the scale factor, the intermediate scale factor is used as the updated scale factor; in the case where the second fitness value corresponding to the intermediate scale factor does not exceed the first fitness value corresponding to the scale factor, the intermediate scale factor is re-determined until the second fitness value exceeds the first fitness value.

[0100] S330. In the case where the second fitness value exceeds the first fitness value, use the intermediate scale factor as the updated scale factor.

[0101] Exemplarily, in this embodiment, for the scale factor a, the red-billed blue magpie optimization algorithm can be used for optimization. For the red-billed blue magpie optimization algorithm, the Levy flight distribution function is used to initialize the population to solve the problem of uneven distribution caused by random initialization.

[0102] ;

[0103] In the formula, X represents the red-billed blue magpie population, represents the value of the i-th individual in the j-th dimension, that is, the value of the scale factor; i ∈ 1, 2... n; j ∈ 1, 2,..., d; n is the population size, d is the dimension of the problem; each individual represents a set of solutions of the scale factor a, ub and lb are the upper and lower bounds of the problem respectively, and Rand represents a random number between 0 and 1. represents the Levy flight distribution function, which is expressed as:

[0104] ;

[0105] The intermediate scale factor can be determined based on the following method:

[0106] Food-seeking behavior: Red-billed blue magpies usually act in small groups (2 to 5 individuals) or in flocks (more than 10 individuals) to improve search efficiency. When a small group explores food (i.e., the target scale factor), the formula used is as follows:

[0107] ;

[0108] In the formula, t represents the current iteration number, represents the updated position of the i-th individual, i.e., the intermediate scale factor; p represents the number of red-billed blue magpies in 2 to 5 small groups randomly selected from all search individuals, represents the position of the randomly selected m-th individual, represents the position of the i-th individual, represents the position of the individual randomly selected in the current iteration.

[0109] ;

[0110] In the formula, q represents the number of search agents when the flock explores food, which is between 10 and n. Similarly, it is also randomly selected from the entire group.

[0111] Prey-attacking behavior:

[0112] ;

[0113] In the formula, represents the position of the food, , and Randn represents a random number used to generate a standard normal distribution (mean 0, standard deviation 1).

[0114] Food-storing behavior:

[0115] ;

[0116] Among them, and represent the fitness values before and after the position update of the i-th red-billed blue magpie, i.e., the first fitness value and the second fitness value, respectively.

[0117] It should be noted that in the later stage of iteration, when the optimal value falls into a local optimal solution, a lens imaging reverse learning mechanism can be introduced on the basis of the original algorithm to perturb the population and make it jump out of the local optimal solution. The formula is:

[0118] ;

[0119] ;

[0120] In the formula, The individual position after the reverse learning of lens imaging, x is the individual position before the reverse learning of lens imaging, and are the upper and lower limits of the individual, that is, the preset scale factor interval. t is the t-th iteration, and T is the maximum number of iterations, which can be a preset value.

[0121] Furthermore, it is judged whether the current iteration reaches the maximum number of times. If not, the iteration continues; otherwise, the iteration stops and the optimal individual is output to obtain the best scale factor, thereby obtaining the best denoising effect.

[0122] In the above embodiment, optimizing the scale factor based on the red-billed blue magpie optimization algorithm can make the wavelet transform coefficients determined based on the updated scale factor more accurate, and thus achieve a better denoising effect.

[0123] Based on the technical solutions of the above embodiments, the present application also provides an alternative embodiment. In this alternative embodiment, the method for collecting and reducing noise in the power working environment provided by the present application is introduced in detail.

[0124] Based on the technical solutions of the above embodiments, the present application also provides an alternative embodiment. In this alternative embodiment, the process of obtaining the original sound collected by the drone in the power working environment is refined.

[0125] See Figure 4 The original sound acquisition steps shown include:

[0126] S410, constructing a noise heat map corresponding to the power working environment.

[0127] Among them, the noise heat map can characterize the noise intensity corresponding to each position point in the power working environment.

[0128] Exemplarily, the noise heat map corresponding to the power working environment can be constructed in the following manner: First, in the power working environment, noise data can be collected through fixed noise sensors, portable collectors, and mobile monitoring vehicles; among them, each device is equipped with a Global Positioning System (GPS) to record the collection location. Each device can accurately measure the full-frequency band noise, including low-frequency noise and standing wave frequency bands. Second, the collected noise data can be transmitted to the processing center, first filtered to remove noise, then normalized, and for missing data, it can be filled in with an interpolation algorithm to obtain the processed noise data; further, with the power working environment map as the base, using Geographic Information System (GIS) technology, the processed noise data is mapped onto the map according to the location, and different colors are used to represent different noise intensities, contour lines are drawn, and transparency is set to distinguish the intensity changes to complete the drawing of the noise heat map.

[0129] S420, based on the noise distribution at different positions in the noise heat map, control the flight trajectory of the unmanned aerial vehicle, and control the unmanned aerial vehicle to collect sounds in the power working environment.

[0130] Exemplarily, in this embodiment, the autonomous navigation of the unmanned aerial vehicle in the power working environment can be realized based on the Simultaneous Localization and Mapping (SLAM) technology, and the flight path of the unmanned aerial vehicle can be dynamically adjusted in combination with the noise heat map.

[0131] Exemplarily, a three-dimensional environment map can be constructed using a Laser Radar (LiDAR) to locate the main working equipment in the power working environment (including key noise sources such as transformers and circuit breakers); and in combination with the real-time noise intensity distribution shown in the noise heat map, control the flight trajectory of the unmanned aerial vehicle to collect sounds. For example, the unmanned aerial vehicle can be controlled to preferentially collect data in high-energy noise regions.

[0132] In the above embodiment, based on the noise distribution at different positions in the noise heat map, controlling the flight trajectory of the unmanned aerial vehicle can enable the collected original sounds to cover a large number (such as more than 90%) of key noise sources, making the original sounds more comprehensive and laying a foundation for subsequent noise reduction processing.

[0133] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the process of obtaining the original sounds collected by the unmanned aerial vehicle in the power working environment is refined.

[0134] See Figure 5The original sound acquisition steps shown include:

[0135] S510, obtain the current environmental factors.

[0136] Among them, the current environmental factors may include at least one of wind speed, temperature, and humidity. Exemplarily, the current environmental factors can be obtained based on different sensors.

[0137] S520, based on the current environmental factors, control the drone signal of the drone and control the drone to perform sound collection in the power working environment.

[0138] In an alternative embodiment, if the current environmental factors include wind speed, when the wind speed exceeds the preset wind speed threshold, control the drone to start the wind noise suppression algorithm. Among them, the wind speed threshold can be determined based on manual experience. For example, the wind speed threshold can be 5m / s.

[0139] Exemplarily, when it is detected that the current wind speed exceeds the wind speed threshold, control the drone to start the wind noise cancellation algorithm to correct the microphone directivity. This algorithm uses a pre-established wind noise model to preprocess the collected original sound to reduce wind noise interference.

[0140] In this way, according to the wind noise propagation direction and the current flight attitude, the microphone directivity can be automatically adjusted through the motor drive device to make it as close as possible to the direction of the power equipment noise source and avoid the wind direction, thereby reducing the impact of wind noise on the equipment noise collection, and thus accurately collecting sound data.

[0141] In another alternative embodiment, if the current environmental factors include temperature, when the temperature exceeds the preset temperature threshold, control the drone to adjust the wavelet decomposition scale. Among them, the temperature threshold can be determined based on manual experience. For example, the temperature threshold can be 30 degrees.

[0142] Exemplarily, the drone is also equipped with a high-precision temperature sensor to monitor the flight environment temperature in real time. When it is detected that the current temperature exceeds the pre-set temperature threshold, the signal processing module of the drone starts to work. This module calculates the sound speed offset caused by the change in air density at the current temperature based on the pre-established relationship model between temperature and air density and sound speed. According to the sound speed offset and combined with the signal processing requirements, the wavelet decomposition scale is automatically adjusted according to specific algorithm rules. For example, if the sound speed increases, appropriately reduce the wavelet decomposition scale to improve the time resolution of the wavelet function and more accurately capture the signal detail changes; if the sound speed decreases, appropriately increase the wavelet decomposition scale to better adapt to the overall characteristics of the signal.

[0143] In this way, it can be ensured that under the condition that the temperature change affects the sound speed, the original sound collected by the drone can be subjected to more suitable wavelet decomposition processing, improving the accuracy of signal analysis.

[0144] In the above embodiments, by controlling the drone signal of the drone based on environmental factors, it is possible to avoid the interference of environmental factors during the process of the drone collecting the original sound, further improving the accuracy of the original sound and laying a foundation for subsequent noise reduction processing.

[0145] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, a method for performing sound preprocessing on the original sound after obtaining the original sound collected by the drone in the power working environment is given.

[0146] Among them, the sound preprocessing includes at least one of pulse suppression, band - collaborative noise reduction, and sound feature extraction. The following is a brief introduction to each sound preprocessing method:

[0147] Pulse suppression: After obtaining the original sound, an algorithm for transient pulse detection and suppression based on the Teager energy operator can be used. Exemplarily, the original sound is detected. After detecting the pulse signal, the time - domain masking technique is started to avoid the acoustic oscillation caused by the active noise reduction feedback delay, and combined with a (Finite Impulse Response, FIR) filter to smooth the residual pulse components, which can improve the pulse noise suppression efficiency and reduce the distortion rate of the original sound.

[0148] Band - collaborative noise reduction: A three - stage processing module is designed according to the power noise spectrum characteristics (low - frequency electromagnetic sound, medium - frequency mechanical vibration, high - frequency discharge pulse). Exemplarily, for the low - frequency band (50 - 500 Hz): FxLMS (Filtered - X Least Mean Square) adaptive filtering is used to eliminate the transformer hum; for the medium - frequency band (500 Hz - 5 kHz): the vibration mode of the fan blade is identified by combining a deep neural network (DNN), and the notch filter parameters are dynamically adjusted; for the high - frequency band (> 5 kHz): improved wavelet threshold denoising is applied, and a transient noise suppression module is designed for the corona discharge pulse. It can improve the noise reduction effect of the entire frequency band and the signal - to - noise ratio of the original sound.

[0149] Sound feature extraction: By deploying a lightweight convolutional neural network (CNN), real-time analysis of noise features and dynamic optimization of parameters are achieved. Exemplarily, the TensorFlow Lite framework can be used to compress the model to less than 500 KB, supporting a response level of 10 ms; and the noise reduction mode can be dynamically switched according to the noise time-frequency diagram (Short-Time Fourier Transform, STFT). For example, it can include a "transformer mode" and a "switchyard mode", and the noise reduction logic may be different in different modes. This enables subsequent noise reduction methods to adapt to complex working conditions changes, and at the same time, reduces algorithm latency.

[0150] Taking sound preprocessing including pulse suppression, band-by-band collaborative noise reduction, and sound feature extraction as an example, in an optional embodiment, after obtaining the original sound, the original sound can be sequentially subjected to sound preprocessing to obtain the preprocessed original sound. Further, based on the beamforming algorithm, the drone noise in the preprocessed original sound is filtered to obtain the equipment noise.

[0151] In the above embodiments, various ways of preprocessing the original sound are provided. Filtering the drone noise after preprocessing the original sound can make the equipment noise more accurate, and further lay a foundation for the subsequent noise reduction process.

[0152] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the noise collection method in the above method for collecting and reducing noise in the power working environment is refined.

[0153] See Figure 6 The noise collection method for the power working environment shown in

[0154] S610, constructing a noise heat map corresponding to the power working environment;

[0155] S620, based on the noise distribution at different positions in the noise heat map, controlling the flight trajectory of the drone and controlling the drone to perform sound collection in the power working environment;

[0156] S630, obtaining the current environmental factors;

[0157] S640, if the current environmental factors include wind speed, then when the wind speed exceeds the preset wind speed threshold, controlling the drone to start the wind noise suppression algorithm;

[0158] S650, if the current environmental factors include temperature, then when the temperature exceeds the preset temperature threshold, controlling the drone to adjust the wavelet decomposition scale;

[0159] S660, obtaining the original sound collected by the drone in the power working environment;

[0160] S670, perform sound preprocessing on the original sound;

[0161] Among them, the sound preprocessing includes at least one of impulse suppression, band - collaborative noise reduction, and sound feature extraction;

[0162] S680, based on the beamforming algorithm, filter out the drone noise in the original sound to obtain the device noise;

[0163] S690, determine the device sound signal according to the device noise.

[0164] See Figure 7 The noise reduction method for the power working environment noise shown in the figure includes:

[0165] S701, obtain the original sound collected by the sound collector in the power working environment;

[0166] S702, based on the beamforming algorithm, filter out the sound of the sound collector in the original sound to obtain the target sound;

[0167] S703, determine the device sound signal according to the target sound;

[0168] S704, for any iteration process, based on the scaling factor corresponding to this iteration process, perform wavelet transform processing on the device sound signal in the power working environment to determine the wavelet transform coefficients corresponding to the device sound signal;

[0169] S705, determine the noise standard deviation corresponding to the device sound signal according to the wavelet transform coefficients;

[0170] S706, determine the noise reduction threshold corresponding to the device sound signal according to the noise standard deviation;

[0171] S707, according to the noise reduction threshold, perform wavelet decomposition on the wavelet transform coefficients, and perform noise reduction processing on the device sound signal according to the decomposition result to obtain the noise - reduced signal;

[0172] S708, determine whether the signal - to - noise ratio of the noise - reduced signal reaches the preset signal - to - noise ratio threshold. If so, execute S709; if not, execute S710;

[0173] S709, if so, output the noise - reduced signal;

[0174] S710, if not, then in the case where the signal - to - noise ratio of the noise - reduced signal does not reach the preset signal - to - noise ratio threshold, determine the intermediate scaling factor according to the scaling factor and at least one random scaling factor;

[0175] S711, determine the first fitness value corresponding to the scaling factor and the second fitness value corresponding to the intermediate scaling factor;

[0176] S712. When the second fitness value exceeds the first fitness value, use the intermediate scale factor as the updated scale factor.

[0177] S713. Use the updated scaling factor as the scaling factor corresponding to the next iteration process, and return to execute S704.

[0178] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of the steps or stages in other steps or other steps.

[0179] Based on the same inventive concept, an embodiment of the present application also provides a noise reduction device for power working environment sounds for implementing the above-mentioned method for collecting and reducing noise of power working environment sounds. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following noise reduction device for power working environment sounds can refer to the limitations on the method for collecting and reducing noise of power working environment sounds in the above text, and will not be repeated here.

[0180] In an exemplary embodiment, as Figure 8 shown, a noise reduction device for power working environment sounds is provided, including: a determination module 810, a noise reduction module 820, and an update module 830, where:

[0181] The determination module 810 is configured to perform wavelet transform processing on the device sound signal in the power working environment based on the scaling factor corresponding to the current iteration process for any iteration process, and determine the wavelet transform coefficients corresponding to the device sound signal.

[0182] The noise reduction module 820 is configured to perform noise reduction processing on the device sound signal according to the wavelet transform coefficients to obtain a noise reduction signal.

[0183] An update module 830, configured to update the scaling factor when the signal-to-noise ratio of the noise-reduced signal does not reach a preset signal-to-noise ratio threshold, use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficients corresponding to the device sound signal until the signal-to-noise ratio of the noise-reduced signal reaches the preset signal-to-noise ratio threshold.

[0184] In one embodiment, the noise reduction module 820 includes a first determination unit, configured to determine the noise standard deviation corresponding to the device sound signal according to the wavelet transform coefficients; a second determination unit, configured to determine the noise reduction threshold corresponding to the device sound signal according to the noise standard deviation; and a noise reduction unit, configured to perform noise reduction processing on the device sound signal according to the noise reduction threshold and the wavelet transform coefficients to obtain a noise-reduced signal.

[0185] In one embodiment, the noise reduction unit is specifically configured to perform wavelet decomposition on the wavelet transform coefficients according to the noise reduction threshold, and perform noise reduction processing on the device sound signal according to the decomposition result to obtain a noise-reduced signal.

[0186] In one embodiment, the scaling factor includes a scale factor; correspondingly, the noise reduction device for the power working environment sound includes an update module, configured to update the scale factor based on a heuristic algorithm according to a preset scale factor interval.

[0187] In one embodiment, the update module includes a third determination unit, configured to determine an intermediate scale factor according to the scale factor and at least one random scale factor; a fourth determination unit, configured to determine a first fitness value corresponding to the scale factor and a second fitness value corresponding to the intermediate scale factor; and an update unit, configured to use the intermediate scale factor as the updated scale factor when the second fitness value exceeds the first fitness value.

[0188] In one embodiment, the determination module 810 includes an acquisition unit, configured to acquire the original sound collected by the sound collector in the power working environment; a filtering unit, configured to filter out the sound of the sound collector in the original sound based on a beamforming algorithm to obtain a target sound; and a fifth determination unit, configured to determine the device sound signal according to the target sound.

[0189] Each module in the above-mentioned noise reduction device for the power working environment sound can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned modules.

[0190] In one embodiment, a wearable device is provided. The wearable device may be a noise-canceling Bluetooth headset, and its structural diagram may be as Figure 9As shown. The lower end of the device (on both sides of the helmet) is the left and right noise reduction Bluetooth headsets, which have Bluetooth sound playback function, active noise reduction function, passive noise reduction function, and this part is the main part of the device to achieve Bluetooth noise reduction. The left and right noise reduction Bluetooth headsets are each connected and fixed to a section of the fixing buckle above them, and the other end of the fixing buckle is a buckle, which can pass through the slot part of the helmet to achieve the fixing part with the helmet, so that the left and right Bluetooth on both sides of the helmet are fixed on the helmet.

[0191] The sides of the two fixed buckles are connected by a connecting bridge, which connects the fixed buckles on the left and right sides together. On the one hand, it greatly enhances the strength of the connection between the Bluetooth headset and the helmet. On the other hand, the connecting bridge, as an elastic structure, can achieve a certain distance of displacement elastic deformation through its own elastic deformation, thereby achieving fixed fit between the buckle and the helmet slot.

[0192] The specific implementation is to press the connecting bridge inward slightly before fixing to tighten the fixing buckles at both ends. The tightening distance is just enough to pass through the slot. The buckle part with the fixing buckle passes through the slot to loosen the connecting bridge. The connecting bridge returns to drive the fixing slot to reset outward. The connecting bridge resets and squeezes the slot. The buckle presses the lower side of the slot to achieve quick fixing and installation of the fixing buckle and the safety helmet. Because the fixing buckle is firmly connected to the noise-cancelling Bluetooth headset, quick connection and installation between the Bluetooth headset and the safety helmet are achieved.

[0193] The Bluetooth headset has soundproof fillers inside to achieve passive noise reduction. The Bluetooth headset has a communication program inside, and users can adjust the filter curve of active noise reduction through the mobile phone application (Application, APP) to achieve background noise reduction scene selection in the power industry.

[0194] The device will use an integrated helmet-specific fixing buckle and an outer ring clamp to fix the earphones to the helmet. When installing, you only need to align the buckles on both sides with the holes in the helmet and press them hard to snap them into the helmet. Unlike the traditional structure, the traditional structure has only one buckle but no clamp around the helmet, so the two earmuffs can only be fixed by the helmet. The left and right earmuffs are separate individuals and are very easy to loosen and fall off during use. The present invention will use a combination of a clamp and a buckle to achieve installation. Disassembly is similar to installation, just pull it off with force. The earphone body will be filled with special materials to increase the passive noise reduction capability and block the penetration of high-frequency sounds. Unlike traditional Bluetooth headsets, traditional headsets only have a thin plastic shell, and the inside is circuit components and speakers. There are no passive noise reduction measures except air, and it is difficult to remove high-frequency sounds even with active noise reduction.

[0195] Furthermore, the device innovatively combines a Bluetooth headset, a noise-canceling headset, and a safety helmet for wearing, enabling music listening (intercom signal listening), active noise-canceling function, and passive noise-canceling function while wearing the safety helmet. In addition, the device will also support the adjustment of the active noise-canceling curve through a mobile phone APP, providing noise-canceling presets for different power scenarios for users to choose from.

[0196] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 10 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for collecting and reducing noise in a power working environment. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0197] Those skilled in the art can understand that Figure 10 the structure shown in

[0198] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0199] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0200] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0201] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned method embodiments. Among them, any reference to a memory, a database, or other media used in the various embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0202] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0203] The above embodiments only express several implementation manners of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several deformations and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A method for collecting and reducing noise in an electric power working environment, characterized in that: The method comprises: For any iterative process, based on the scaling factor corresponding to this iterative process, the device sound signal in the electric power working environment is processed by wavelet transform to determine the wavelet transform coefficient corresponding to the device sound signal; According to the wavelet transform coefficients, the device sound signal is subjected to noise reduction processing to obtain a noise reduction signal; If the signal-to-noise ratio of the noise reduction signal does not reach a preset signal-to-noise ratio threshold, the scaling factor is updated, and the updated scaling factor is used as the scaling factor corresponding to the next iteration process, and the process of determining the wavelet transform coefficient corresponding to the device sound signal is re-executed until the signal-to-noise ratio of the noise reduction signal reaches the preset signal-to-noise ratio threshold; The device sound signal is determined based on the following method: Acquire original sound collected by the drone in the electric power working environment; wherein the original sound includes drone noise and equipment noise in the electric power working environment; Based on a beamforming algorithm, the drone noise in the original sound is filtered out to obtain the device noise; A device sound signal is determined according to the device noise.

2. The method according to claim 1, characterized in that The step of performing noise reduction processing on the device sound signal according to the wavelet transform coefficient to obtain a noise reduction signal includes: Determining a noise standard deviation corresponding to the device sound signal according to the wavelet transform coefficient; Determining a noise reduction threshold corresponding to the device sound signal according to the noise standard deviation; According to the noise reduction threshold, the wavelet transform coefficient is subjected to wavelet decomposition, and according to the decomposition result, the device sound signal is subjected to noise reduction processing to obtain a noise reduction signal.

3. The method according to claim 1, characterized in that The scaling factor includes a scale factor; accordingly, updating the scaling factor includes: determining an intermediate scale factor based on the scale factor and at least one random scale factor; Determining a first fitness value corresponding to the scale factor and a second fitness value corresponding to the intermediate scale factor; In a case where the second fitness value exceeds the first fitness value, the intermediate scale factor is used as an updated scale factor.

4. The method according to any one of claims 1 to 3, characterized in that The obtaining of the original sound collected by the drone in the power working environment includes: Construct a noise heat map corresponding to the power working environment; Based on the noise distribution at different positions in the noise thermodynamic map, the flight trajectory of the UAV is controlled, and the UAV is controlled to collect sound in the power working environment.

5. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the original sound collected by the drone in the power working environment includes: Get current environment factors; Based on the current environmental factors, the drone signal of the drone is controlled, and the drone is controlled to collect sound in the power working environment.

6. The method according to claim 5, characterized in that The current environmental factor includes at least one of wind speed and temperature; accordingly, the controlling the drone signal of the drone based on the current environmental factor includes: If the current environmental factor includes the wind speed, then when the wind speed exceeds a preset wind speed threshold, controlling the drone to start a wind noise suppression algorithm; If the current environmental factor includes temperature, then when the temperature exceeds a preset temperature threshold, the drone is controlled to adjust the wavelet decomposition scale.

7. The method according to any one of claims 1 to 3, characterized in that After obtaining the original sound collected by the drone in the power working environment, the method further includes: Performing sound preprocessing on the original sound; Wherein, the sound preprocessing includes at least one of pulse suppression, frequency band collaborative noise reduction and sound feature extraction; Accordingly, filtering out the drone noise in the original sound based on the beamforming algorithm to obtain the device noise includes: Based on the beamforming algorithm, the drone noise in the preprocessed original sound is filtered out to obtain the device noise.

8. A device for collecting and reducing noise in an electric power working environment, characterized in that: The device comprises: A determination module, for performing wavelet transform processing on the device sound signal in the electric power working environment based on the scaling factor corresponding to the current iteration process for any iteration process, and determining the wavelet transform coefficient corresponding to the device sound signal; A noise reduction module, used for performing noise reduction processing on the device sound signal according to the wavelet transform coefficient to obtain a noise reduction signal; an updating module, configured to update the scaling factor if the signal-to-noise ratio of the noise reduction signal does not reach a preset signal-to-noise ratio threshold, and use the updated scaling factor as the scaling factor corresponding to the next iteration process, and re-execute the process of determining the wavelet transform coefficient corresponding to the device sound signal until the signal-to-noise ratio of the noise reduction signal reaches the preset signal-to-noise ratio threshold; Among them, the determination module is also used to obtain the original sound collected by the drone in the power working environment; wherein the original sound includes drone noise and equipment noise in the power working environment; based on the beamforming algorithm, the drone noise in the original sound is filtered out to obtain the equipment noise; according to the equipment noise, the equipment sound signal is determined.

9. A wearable device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images