Fan noise reduction method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the application discloses a fan noise reduction method and device, electronic equipment and computer readable storage medium, and belongs to the technical field of noise reduction. The method comprises the following steps: obtaining running state information and running condition information of a target fan; identifying the running state information to obtain noise source information; determining a target control parameter based on the noise source information and the running condition information; and performing noise reduction processing on the target fan based on the target control parameter. In this way, by accurately identifying the noise source information in the running state information of the target fan, the appropriate target control parameter can be determined in combination with the running condition information, the targeted noise reduction processing of the target fan is realized while ensuring the stable operation of the target fan, thereby effectively improving the noise reduction effect and improving the quiet comfort of the user.

Description

Technical Field

[0001] This application relates to the field of noise reduction technology, specifically to a method, apparatus, electronic device, and computer-readable storage medium for reducing noise in wind turbines. Background Technology

[0002] The noise generated during air conditioner operation is a key factor affecting user experience. The fan, as the core air-distribution component of an air conditioner, is the main source of its noise.

[0003] Current noise reduction technologies are generally divided into two types: hardware noise reduction and control noise reduction. Hardware noise reduction usually involves optimizing the fan structure or adding noise reduction devices. These methods have problems such as complex design, high cost, and potential impact on airflow efficiency. Control noise reduction usually involves adjusting the fan speed according to the set airflow. This method has poor noise reduction effect and can easily affect the user experience. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and computer-readable storage medium for reducing noise in wind turbines. By accurately identifying noise source information from the wind turbine's operating status information and comprehensively considering both noise source information and operating condition information, appropriate target control parameters can be determined for noise reduction processing, thereby effectively improving the noise reduction effect.

[0005] In a first aspect, embodiments of this application provide a method for reducing fan noise, including:

[0006] Obtain the operating status and operating condition information of the target wind turbine;

[0007] The noise source information is obtained by identifying the operating status information;

[0008] Based on the noise source information and the operating condition information, the target control parameters are determined;

[0009] Based on the target control parameters, noise reduction processing is performed on the target fan.

[0010] In one embodiment, the operating status information includes first noise information and noise association information of the target fan, wherein the noise association information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information; and the noise source information includes noise source type information and attribute information.

[0011] The step of identifying the operating status information to obtain noise source information includes:

[0012] The operating status information is preprocessed to obtain status feature information;

[0013] The noise source information is obtained by identifying the state feature information.

[0014] In one embodiment, identifying the state feature information to obtain the noise source information includes:

[0015] The state feature information is input into the noise recognition model to obtain the noise source information output by the noise recognition model.

[0016] In one embodiment, the operating condition information includes one or more of the following: target air volume information of the target fan, operating mode information, system operating status information, and environmental information;

[0017] The step of determining the target control parameters based on the noise source information and the operating condition information includes:

[0018] The noise source information and the operating condition information are input into the noise optimization model to obtain the target control parameters output by the noise optimization model.

[0019] In one embodiment, the target control parameters include the target fan's rotational speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters;

[0020] The noise reduction process for the target wind turbine based on the target control parameters includes:

[0021] Based on the aforementioned rotational speed parameters, the motor speed of the target fan is adjusted; and / or,

[0022] Based on the aforementioned angle parameters, the angle of the guide vanes of the target fan is adjusted; and / or,

[0023] Based on the aforementioned anti-phase acoustic wave parameters, the loudspeaker of the target fan is controlled to output an anti-phase acoustic wave signal.

[0024] In one embodiment, after performing noise reduction processing on the target wind turbine based on the target control parameters, the method further includes:

[0025] Obtain the second noise information of the target fan;

[0026] Based on the second noise information and the first noise information, noise reduction evaluation information is determined; the first noise information is the noise information before the target fan is subjected to noise reduction processing.

[0027] Based on the noise reduction evaluation information, the noise optimization model is updated.

[0028] In one embodiment, updating the noise optimization model based on the noise reduction evaluation information includes:

[0029] Determine the airflow difference between the first airflow information and the second airflow information; the first airflow information is the airflow information before noise reduction processing of the target fan, and the second airflow information is the airflow information after noise reduction processing of the target fan;

[0030] Based on the noise reduction assessment information and the air volume difference, the target reward value is determined;

[0031] The noise optimization model is updated based on the target reward value.

[0032] Secondly, embodiments of this application provide a fan noise reduction device, the device comprising:

[0033] The information acquisition module is used to acquire the operating status and operating condition information of the target wind turbine;

[0034] A noise identification module is used to identify the operating status information to obtain noise source information;

[0035] The parameter determination module is used to determine the target control parameters based on the noise source information and the operating condition information;

[0036] The noise reduction module is used to perform noise reduction processing on the target fan based on the target control parameters.

[0037] In one embodiment, the operating status information includes first noise information and noise association information of the target fan, wherein the noise association information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information; the noise source information includes noise source type information and attribute information; the noise identification module includes:

[0038] The preprocessing submodule is used to preprocess the running status information to obtain status feature information;

[0039] The noise identification submodule is used to identify the state feature information to obtain the noise source information.

[0040] In one embodiment, the noise recognition submodule is specifically used to input the state feature information into the noise recognition model to obtain the noise source information output by the noise recognition model.

[0041] In one embodiment, the operating condition information includes one or more of the target air volume information of the target fan, operating mode information, system operating status information, and environmental information; the parameter determination module is specifically used to input the noise source information and the operating condition information into the noise optimization model to obtain the target control parameters output by the noise optimization model.

[0042] In one embodiment, the target control parameters include the target fan's rotational speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters; the noise reduction processing module includes:

[0043] The first processing submodule is used to adjust the speed of the motor of the target fan based on the speed parameters;

[0044] The second processing submodule is used to adjust the angle of the guide vanes of the target fan based on the angle parameters.

[0045] The third processing submodule is used to control the speaker of the target fan to output an anti-phase acoustic signal based on the anti-phase acoustic wave parameters.

[0046] In one embodiment, the fan noise reduction device further includes:

[0047] The noise information acquisition module is used to acquire the second noise information of the target fan;

[0048] The evaluation information determination module is used to determine noise reduction evaluation information based on the second noise information and the first noise information; the first noise information is the noise information before the target fan is subjected to noise reduction processing.

[0049] The model update module is used to update the noise optimization model based on the noise reduction evaluation information.

[0050] In one embodiment, the model update module includes:

[0051] The airflow difference determination submodule is used to determine the airflow difference between the first airflow information and the second airflow information; the first airflow information is the airflow information before the target fan is subjected to noise reduction processing, and the second airflow information is the airflow information after the target fan is subjected to noise reduction processing.

[0052] The reward value determination submodule is used to determine the target reward value based on the noise reduction evaluation information and the air volume difference;

[0053] The model update submodule is used to update the noise optimization model based on the target reward value.

[0054] Thirdly, embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps in the above-described fan noise reduction method.

[0055] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the aforementioned fan noise reduction method.

[0056] Fifthly, embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in the embodiments of this application.

[0057] In summary, in this embodiment, by acquiring the operating status information and operating condition information of the target fan, the operating status information can be identified to obtain noise source information. Then, based on the noise source information and operating condition information, target control parameters are determined, and noise reduction processing is performed on the target fan based on these parameters. Thus, by accurately identifying noise source information from the target fan's operating status information, appropriate target control parameters can be determined in conjunction with the operating condition information. This ensures stable operation of the target fan while achieving targeted noise reduction, effectively improving the noise reduction effect and enhancing the user's quiet comfort. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram of the steps of a fan noise reduction method provided in an embodiment of this application;

[0060] Figure 2 This is a schematic diagram of the structure of a fan noise reduction device provided in an embodiment of this application;

[0061] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0062] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0063] It should be noted that hardware noise reduction mainly includes two methods: hardware optimization and adding noise reduction devices. Hardware optimization primarily involves optimizing the impeller blade profile (e.g., using backward-curved blades or specific airfoils), improving the volute duct design, adding sound-absorbing cotton, and optimizing dynamic balance. These methods are usually effective under specific operating conditions, but they suffer from design complexity, increased costs, potential impact on airflow efficiency, and difficulty adapting to dynamic changes in operating conditions (e.g., different speeds and airflow levels) and environmental parameters (e.g., filter clogging levels, outlet obstruction). Adding noise reduction devices mainly involves adding buffer rubber between the impeller and the fixed plate; however, this method increases the risk to the stability of the fan.

[0064] Controlled noise reduction is a technique that uses software to reduce noise. This method can effectively reduce the need for hardware modifications to the fan. However, current controlled noise reduction methods usually simply adjust the speed based on the set air volume, lacking a fine perception and targeted processing of the actual noise spectrum and source, resulting in poor noise reduction performance.

[0065] To address the current problem of poor noise reduction performance in wind turbines, this application aims to provide a wind turbine noise reduction method. This method acquires the operating status and operating conditions information of the target wind turbine, identifies the noise source information from the operating status information, and determines target control parameters based on the noise source information and operating conditions information. Then, based on these target control parameters, noise reduction processing is applied to the target wind turbine. Thus, by accurately identifying noise source information from the target wind turbine's operating status information, and combining this with the operating conditions information to determine appropriate target control parameters, targeted noise reduction processing is achieved while ensuring stable operation of the target wind turbine, thereby effectively improving the noise reduction effect and enhancing the user's quiet comfort.

[0066] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0067] Figure 1 A flowchart illustrating a wind turbine noise reduction method according to an embodiment of this application is shown. The entity executing this wind turbine noise reduction method may be a wind turbine noise reduction device, which may be integrated into an electronic device, such as a server or a terminal.

[0068] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0069] The terminal can be a control terminal or a device equipped with a fan; the control terminal includes smartphones, tablets, laptops, desktop computers, etc., and the device includes air conditioners, fresh air systems, air purifiers, dust removal fans, centrifugal fans, induced draft fans, and blowers, etc., but is not limited to these. The terminal and the server can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0070] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0071] In this embodiment, the description will be from the perspective of a fan noise reduction device, which can be integrated into a server or terminal. To facilitate the explanation of the fan noise reduction method of this application, the following will describe the fan noise reduction device integrated into an air conditioner, that is, the air conditioner will be used as the execution subject for detailed explanation.

[0072] Reference Figure 1 This application illustrates a method for reducing noise in wind turbines, which may specifically include the following steps:

[0073] S101: Obtain the operating status and operating condition information of the target wind turbine.

[0074] In this embodiment, the target fan can be a centrifugal impeller in an air conditioning unit. This centrifugal impeller generates noise during operation, and the noise typically increases with the rotational speed. To achieve comprehensive collection of operating status information, a multi-source sensor array can be deployed in the target fan. This allows for real-time and comprehensive collection of the target fan's operating status information during its operation.

[0075] In this embodiment, the operating status information is sensing data that reflects the current physical state of the target wind turbine. This operating status information includes at least the first noise information of the target wind turbine. By analyzing the operating status information, the noise characteristics of the wind turbine can be accurately identified.

[0076] In this embodiment, the operating condition information represents the operating status information of the target wind turbine, which may include the target wind turbine's set parameter information and operating environment information.

[0077] In this embodiment, by acquiring the operating status and operating condition information of the target wind turbine, comprehensive data collection of the target wind turbine can be achieved, thereby improving the accuracy of subsequent noise reduction analysis.

[0078] S102: Identify the operating status information to obtain noise source information.

[0079] In this embodiment, the noise source information represents the noise diagnosis result obtained after analyzing the operating status information. Specifically, the noise source information may include the type information and attribute information of the noise source. The attribute information is used to characterize the physical characteristic parameters of the noise source.

[0080] In this embodiment, the noise source type information may specifically include one or more of blade passage frequency noise, eddy current shedding noise, and unbalanced vibration noise. Blade passage frequency noise is caused by the periodic cutting of airflow by the wind turbine blades, and its frequency is related to the rotational speed and the number of blades. Eddy current shedding noise is broadband noise caused by eddies generated when airflow passes over the blades or volute. Unbalanced vibration noise is mechanical vibration noise caused by uneven mass distribution of the wind turbine or bearing wear.

[0081] In this embodiment, the attribute information of the noise source may specifically include one or more of the following: dominant frequency, amplitude, and phase information. The dominant frequency represents the frequency point where the noise energy is concentrated (e.g., 1260 Hz); the amplitude represents the intensity of the noise or vibration, which can be expressed by parameters such as sound pressure level (dB) or vibration acceleration; and the phase information of the noise source characterizes the specific location of the noise sound wave within the vibration cycle.

[0082] In this embodiment, by specifically identifying noise sources in the operating status information, noise source information can be accurately extracted from the operating status information, thereby improving the accuracy of subsequent noise reduction processing.

[0083] S103: Determine the target control parameters based on noise source information and operating condition information.

[0084] In this embodiment, by analyzing noise source information, precise control can be implemented for specific noise sources. At the same time, by analyzing operating condition information, it can be ensured that noise reduction control is carried out under the premise of meeting user settings and adapting to the actual environment.

[0085] In this embodiment, by comprehensively analyzing the noise source information and operating condition information, suitable target control parameters can be determined for the target wind turbine. These target control parameters can ensure the normal and stable operation of the target wind turbine while performing targeted noise reduction on the noise source.

[0086] S104: Based on the target control parameters, perform noise reduction processing on the target fan.

[0087] In this embodiment, the target control parameter is a noise reduction parameter determined based on noise source information and operating condition information. This target control parameter can be the control parameter of the target component of the target wind turbine.

[0088] In practical implementation, after determining the target control parameters, noise reduction processing can be performed on the target components of the target fan based on the target control parameters. Here, the target component refers to one or more components capable of noise reduction. The target component can be a component of the target fan, such as a motor and guide vanes; or it can be a noise reduction component specifically designed for the target fan, such as a loudspeaker.

[0089] In this embodiment, by collecting the operating status information of the target wind turbine in real time, the noise source information can be accurately identified, and the optimal target control parameters can be generated by combining the operating condition information. This significantly reduces the noise impact of the noise source while ensuring the stable operation of the target wind turbine, thereby achieving an intelligent balance between high efficiency, quiet operation and user experience.

[0090] In one feasible implementation, the operating status information may specifically include the first noise information and noise-related information of the target fan. The noise-related information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information.

[0091] In this embodiment, the first noise information represents the noise signal collected before noise reduction processing, and the first noise information may include sound pressure level and / or spectrum data. This first noise information can be collected by a high-precision microphone array, which can be set inside the fan casing, at the air outlet, or in the user's perception area.

[0092] In this embodiment, vibration information can be acquired by a vibration sensor, such as an accelerometer. This vibration sensor can be installed at key locations such as the motor bearing, main shaft, or volute of the target fan to monitor mechanical vibration (time domain / frequency domain signal) and identify problems such as imbalance and bearing wear.

[0093] In this embodiment, the rotational speed information is used to reflect the real-time rotational speed of the target wind turbine, and this rotational speed information can be expressed as rotational speed per minute (RPM). This rotational speed information can be obtained by a rotational speed sensor, such as an encoder.

[0094] In this embodiment, the first air volume information represents the actual air volume before noise reduction processing, and this first air volume information can be detected by an air volume sensor.

[0095] In this embodiment, the wind speed information represents the airflow speed at the outlet or duct of the target fan, which can be detected by a wind speed sensor.

[0096] In this embodiment, the step of identifying the operating status information to obtain noise source information may specifically include: preprocessing the operating status information to obtain status feature information; and identifying the status feature information to obtain noise source information.

[0097] In this embodiment, considering that the operating status information, as raw data collected by multiple sensors, is typically a high-dimensional, noisy, and dimensionlessly variable time-series signal, directly identifying the operating status information would reduce efficiency and accuracy. Therefore, the operating status information will first be preprocessed.

[0098] In specific implementations, preprocessing can include data cleaning, filtering, time-frequency domain transformation, normalization, and feature vector extraction. Data cleaning removes outliers or transient pulses caused by sensor interference; filtering, implemented using filters, removes frequency components unrelated to wind turbine noise, such as power grid interference; time-frequency domain transformation converts noise and vibration information from time-domain signals to frequency-domain signals, using Fast Fourier Transform (FFT); normalization standardizes operational status information of different dimensions to a uniform range, eliminating the influence of magnitude differences; and feature vector extraction extracts feature parameters from the preprocessed data.

[0099] In this embodiment, the first noise information is converted into a frequency spectrum by time-frequency domain transformation, which can effectively distinguish the noise type. For example, prominent single-frequency noise (such as motor whistling, blade passing frequency) and broadband noise (such as eddy current and turbulence noise) can be clearly identified. The vibration information is converted into a vibration spectrum by time-frequency domain transformation, which can accurately locate the vibration source by analyzing the vibration spectrum. For example, rotational imbalance will produce significant 1x rotational frequency and its harmonics, and bearing damage will produce impact signals of specific frequencies.

[0100] In this embodiment, by preprocessing the operating status information to obtain status feature information, and then identifying the status feature information to obtain noise source information, the accuracy and reliability of noise source identification can be significantly improved.

[0101] In this embodiment, the step of identifying state feature information to obtain noise source information may specifically include: inputting the state feature information into the noise identification model to obtain the noise source information output by the noise identification model.

[0102] In this embodiment, the noise recognition model can be trained based on a preset noise training set, which includes multiple sample running state information, each sample running state information including corresponding noise source label information. Specifically, the noise recognition model can be trained in the following way: inputting the sample running state information into the model to be trained to obtain the noise source recognition information output by the model to be trained; determining the loss function value based on the noise source recognition information and the noise source label information corresponding to the sample running state information; and training the model to be trained based on the loss function value to obtain the noise recognition model.

[0103] In this embodiment, the noise recognition model is trained using a noise training set, enabling the noise recognition model to learn noise patterns under different operating state information.

[0104] In this embodiment, the noise recognition model can be trained based on a convolutional neural network (CNN) or a temporal model such as a long short-term memory network (LSTM).

[0105] In this embodiment, the constructed state feature information is input into the trained noise recognition model. The noise recognition model can judge the current feature pattern based on the knowledge learned from a large amount of historical data, and finally output the type information and attribute information of the noise source, thereby achieving comprehensive and accurate identification of the noise source information.

[0106] In one feasible implementation, the operating condition information may specifically include one or more of the following: target air volume information of the target fan, operating mode information, system operating status information, and environmental information. The step of determining the target control parameters based on noise source information and operating condition information may specifically include: inputting the noise source information and operating condition information into a noise optimization model to obtain the target control parameters output by the noise optimization model.

[0107] In this embodiment, the target airflow information represents the ideal airflow of the target fan. This target airflow information can be user-defined or automatically set by the air conditioner. This target airflow information can serve as a constraint and optimization target for noise reduction control. Specifically, when generating target control parameters, the noise optimization model must prioritize ensuring that the second airflow information after noise reduction processing of the target fan is not significantly lower than the target airflow. For example, the second airflow information can be set to be greater than the product of the target airflow and a preset ratio, which can be set to 95%. Thus, the noise optimization model can find the optimal noise reduction strategy while meeting airflow requirements.

[0108] In this implementation, the operating mode information is used to reflect the user's preferences, with different modes corresponding to different user preferences. For example, when the operating mode information is "powerful mode," airflow and cooling / heating speed can be prioritized, while noise reduction is reduced; when the operating mode information is "quiet / sleep mode," noise reduction is given the highest priority, allowing optimization within a wider airflow range.

[0109] In this embodiment, system operating status information is used to reflect the system's health and actual capabilities. This information may specifically include filter clogging indication information and component aging status. For example, if the filter clogging indication information indicates filter clogging, it will increase wind resistance, leading to a decrease in airflow and increased noise at the same rotational speed. Based on the filter clogging indication information, the noise optimization model will adopt control strategies different from those under normal conditions for this abnormal state, such as a gentler rotational speed adjustment or proactively compensating for the performance loss caused by increased wind resistance.

[0110] In this embodiment, environmental information is used to provide information on external disturbances, enabling the target control parameters to adapt to changes in the external environment and improve generalization ability. This environmental information may specifically include ambient temperature and humidity. For example, ambient temperature and humidity affect air density and viscosity, thereby altering airflow dynamics and influencing noise generation. By learning these correlations, the noise optimization model can predict or explain changes in noise characteristics in advance, thus making more precise adjustments.

[0111] In this embodiment, the operating condition information can be preprocessed operating condition information. The preprocessing operation can refer to the preprocessing operation of the operating status information described above, and the specific preprocessing process will not be repeated here.

[0112] In this embodiment, the noise optimization model can be trained using various machine learning or optimization algorithms. In a preferred embodiment, the noise optimization model is a reinforcement learning-based agent, such as a deep deterministic policy gradient model, which learns by interacting with the environment and based on a reward function consisting of noise reduction effect and airflow deviation, thereby adaptively generating the optimal control strategy. In another embodiment, the noise optimization model can also be a deep neural network model trained through supervised learning, using a dataset consisting of historical optimal control strategies. Furthermore, the noise optimization model can also run optimization algorithms such as Bayesian optimization in real time to search for the optimal control parameters under the current operating conditions online.

[0113] In this embodiment, by simultaneously inputting noise source information and operating condition information into the noise optimization model, the model no longer blindly reduces noise, but instead pursues maximum noise reduction while ensuring that fan performance (e.g., airflow) is not significantly compromised. On one hand, this improves the targeting and effectiveness of the noise reduction strategy. For example, in nighttime silent mode, the noise optimization model adopts more aggressive noise reduction methods; when faced with filter clogging, it can adaptively adjust the strategy to avoid ineffective control or performance degradation. On the other hand, it enhances the system's adaptability and robustness, enabling the system to sense changes in its own state and the external environment and dynamically adjust its strategy.

[0114] In one feasible implementation, the target control parameters include the target fan's rotational speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters; the step of performing noise reduction processing on the target fan based on the target control parameters may specifically include the following sub-steps:

[0115] S104-1: Adjust the speed of the motor of the target fan based on the rotational speed parameter.

[0116] In this embodiment, the target fan can be controlled by a variable frequency drive. Specifically, after determining the speed parameters, the air conditioner can generate a first control command containing the speed parameters and send the first control command to the variable frequency drive, so that the variable frequency drive responds to the first control command and performs high-precision, micro-amplitude speed adjustment of the target fan motor based on the speed parameters.

[0117] In this embodiment, by adjusting the speed of the motor, the coherence of noise at a specific frequency can be disrupted or the resonance point can be avoided, thereby achieving a noise reduction effect.

[0118] S104-2: Adjust the angle of the guide vanes of the target fan based on the angle parameter.

[0119] In this embodiment, the target fan can be angled using an adjustable blade actuator. Specifically, after determining the angle parameters, the air conditioner can generate a second control command containing the angle parameters and send the second control command to the adjustable blade actuator, so that the adjustable blade actuator responds to the second control command and performs high-precision angle adjustment of the guide vanes of the target fan based on the angle parameters.

[0120] In this embodiment, the guide vanes can be installed at the inlet or outlet of the volute. By adjusting the angle of the guide vanes, the airflow field can be optimized and eddies and separation noise can be reduced.

[0121] S104-3: Based on the anti-phase acoustic wave parameters, control the loudspeaker output of the target fan to output an anti-phase acoustic wave signal.

[0122] In this embodiment, after determining the anti-phase acoustic wave parameters, the air conditioner can generate a third control command containing the anti-phase acoustic wave parameters and send the third control command to the speaker so that the speaker responds to the third control command and outputs an anti-phase acoustic wave signal based on the anti-phase acoustic wave parameters.

[0123] It should be noted that an antiphase sound wave is a sound wave with the same amplitude and frequency as the target noise, but with exactly opposite phase (180 degrees out of phase). According to the principle of sound wave superposition, when two sound waves that meet the above conditions meet in space, they will produce an interference effect. The crest (high-pressure area) of one sound wave will overlap with the trough (low-pressure area) of the other sound wave, thus effectively canceling out their sound wave energy and significantly reducing the noise in that area.

[0124] In this embodiment, by controlling the speaker output of the target fan to output an anti-phase sound wave signal to cancel the first noise information, effective noise reduction of the noise source can be achieved without changing the duct structure or adding sound insulation materials.

[0125] In one example, the air conditioner is in high-airflow cooling mode, and the user activates AI silent mode. Sensors detect a high sound pressure level near the target fan's outlet, with prominent peaks at 630Hz and 1260Hz (twice the blade passing frequency) in the spectrum. A vibration sensor detects increased vibration at the motor bearing corresponding to 1260Hz. Subsequently, the state characteristic information containing the above data is input into a noise recognition model, yielding noise source information output by the model. This noise source information indicates that the 1260Hz noise is primarily due to the wind turbine blade passing frequency, and a slight rotational imbalance exacerbates this noise. The 630Hz noise is related to a specific... The noise source information and operating condition information are then output to the noise optimization model to obtain the target control parameters output by the noise optimization model. These target control parameters include: slightly reducing the rotor speed from the current 1050 RPM to 1035 RPM (destroying coherence and reducing the 1260 Hz peak); adjusting the angle of the inlet guide vanes of the volute by 3 degrees (optimizing the inflow and suppressing the 630 Hz vortex noise); finally, the sensor feedback shows that the 1260 Hz noise is reduced by 8 dB, the 630 Hz noise is reduced by 5 dB, the overall A-weighted sound pressure level is reduced by 4 dB, and the measured air volume is 97% of the set value. This successful strategy is recorded.

[0126] In this embodiment, if the noise reduction processing corresponding to the target control parameters is determined to be effective, a correspondence between the operating status information and operating condition information and the target control parameters can be constructed to obtain a parameter lookup table. Then, when new operating status information and new operating condition information are subsequently detected, the new operating status information and new operating condition information can be matched with the operating status information and operating condition information in the parameter lookup table. If the match is successful, the target control parameters corresponding to the new operating status information and new operating condition information can be determined in the parameter lookup table, and noise reduction processing can be performed on the target fan based on the target control parameters, thereby improving the noise reduction processing efficiency.

[0127] In this embodiment, by implementing a series of noise reduction measures such as speed adjustment, angle adjustment, and outputting anti-phase acoustic signals, comprehensive and accurate noise reduction processing can be carried out on the noise source information, thereby improving the noise reduction effect.

[0128] In one feasible implementation, after noise reduction processing of the target wind turbine based on the target control parameters, the wind turbine noise reduction method may further include the following steps:

[0129] S105: Obtain the second noise information of the target fan.

[0130] In this embodiment, the second noise information is the noise information after noise reduction processing of the target fan.

[0131] In this embodiment, after the air conditioner has completed the noise reduction process, the current second noise information can be collected again through the acoustic sensor. By analyzing the second noise information, the noise reduction effect corresponding to the target control parameters can be effectively evaluated.

[0132] S106: Determine noise reduction evaluation information based on the second noise information and the first noise information.

[0133] In this embodiment, the first noise information is the noise information before the target fan is subjected to noise reduction processing.

[0134] In this embodiment, the difference between the first noise information and the second noise information can be determined as the noise reduction evaluation information. This noise reduction evaluation information represents the amount of noise reduction. For example, the first noise information and the second noise information can be the sound pressure level of the target noise frequency band, and the noise reduction evaluation information can represent the reduction amount of the sound pressure level of the target noise frequency band.

[0135] S107: Update the noise optimization model based on noise reduction evaluation information.

[0136] In this embodiment, the noise optimization model is updated using noise reduction evaluation information, enabling the model to continuously optimize its parameters and thus improve subsequent noise reduction performance. On one hand, this achieves a leap from static control to dynamic adaptation, giving the noise optimization model the ability to continuously optimize and self-adjust. For example, as the wind turbine bearings wear, the vibration and noise characteristics change, and the noise optimization model can adapt to these changes through continuous online learning, always maintaining the best noise reduction effect. On the other hand, it improves the accuracy and robustness of the noise reduction strategy, enabling personalized optimization for the individual differences of different wind turbines, thus exhibiting high reliability and stability in any real-world environment.

[0137] In one feasible implementation, the step of updating the noise optimization model based on noise reduction evaluation information may specifically include the following sub-steps:

[0138] S107-1: Determine the air volume difference between the first air volume information and the second air volume information.

[0139] In this embodiment, the first air volume information is the air volume information before the target fan is subjected to noise reduction processing, and the second air volume information is the air volume information after the target fan is subjected to noise reduction processing.

[0140] In this embodiment, by acquiring the first airflow information and the second airflow information, the airflow difference between the first airflow information and the second airflow information can be calculated. This airflow difference represents the reduction in airflow before and after the noise reduction process, and it can quantify the impact of this noise reduction process on the core performance of the fan, namely, its air delivery capacity.

[0141] S107-2: Determine the target reward value based on noise reduction assessment information and airflow difference.

[0142] In this embodiment, by comprehensively calculating the noise reduction assessment information and the air volume difference, the overall impact of the noise reduction treatment can be effectively assessed.

[0143] In practical implementation, noise reduction evaluation information and airflow difference can be input into a preset reward function to obtain the target reward value. The reward function is used to balance noise reduction effect and airflow performance, enabling the noise optimization model to maximize noise reduction while minimizing airflow loss.

[0144] In this embodiment, the reward function can be expressed as:

[0145] R=w1ⅹf(ΔS)-w2ⅹf(ΔQ) (1);

[0146] Where R represents the target reward value; ΔS represents the noise reduction evaluation information; f(ΔS) represents the reward item for the noise reduction effect, which is positively correlated with the noise reduction evaluation information, that is, the larger the noise reduction evaluation information, the higher the value of the reward item; ΔQ represents the airflow difference; f(ΔQ) represents the penalty item for airflow loss, which is positively correlated with the airflow difference, that is, the larger the absolute value of the airflow difference, the higher the value of the penalty item; w1 represents the first weight coefficient corresponding to the reward item, and w2 represents the second weight coefficient corresponding to the penalty item.

[0147] In this embodiment, by setting a reward function, the rationality of the noise reduction measures taken by the noise optimization model can be effectively indicated. For example, when the noise reduction effect is significant (ΔS is a large positive value) and the airflow loss is small (ΔQ is close to zero), a high reward will be obtained; conversely, if the airflow loss is too large, even if the noise reduction effect is very good, it will be penalized, resulting in a decrease in the total reward value.

[0148] S107-3: Update the noise optimization model based on the target reward value.

[0149] In this implementation, by feeding the target reward value R back to the noise optimization model, the model can evaluate the effectiveness of the noise reduction strategy just implemented based on the target reward value R. If the target reward value R is a high positive value, it indicates that the strategy has achieved a good balance between noise reduction and airflow maintenance, and the noise optimization model will reinforce its tendency to select this strategy again under similar conditions (i.e., similar noise source information and operating condition information). If the target reward value R is negative or a low positive value, it indicates that the strategy is ineffective or too costly, and the model will weaken the strategy and explore new strategies. In this way, the noise optimization model can learn from each intervention and continuously adjust its internal decision parameters (such as the weights of the neural network), thereby achieving continuous performance optimization.

[0150] In this embodiment, the aforementioned reward function unifies the two conflicting objectives of "maximizing noise reduction" and "minimizing airflow loss" into a quantifiable optimization objective. This allows the noise optimization model to continuously seek the global optimum during actual use, thereby achieving the highest possible noise reduction effect while ensuring the basic air supply performance set by the user. Simultaneously, through online learning, the noise optimization model possesses the ability to learn and evolve from actual operating data, reducing reliance on precise initial models or extensive manual debugging experience. This not only accelerates the product development cycle but also enables the system to continuously improve after deployment, providing users with a quiet experience that is constantly optimized over time.

[0151] To facilitate better implementation of the wind turbine noise reduction method of this application, this application also provides a wind turbine noise reduction device based on the above-described wind turbine noise reduction method. The meanings of the terms used are the same as in the above-described wind turbine noise reduction method, and specific implementation details can be found in the description of the method embodiments.

[0152] Based on the same inventive concept, and referring to Figure 2 This application provides a fan noise reduction device 200, which includes:

[0153] The information acquisition module 201 is used to acquire the operating status information and operating condition information of the target wind turbine;

[0154] The noise identification module 202 is used to identify the operating status information and obtain noise source information;

[0155] The parameter determination module 203 is used to determine the target control parameters based on noise source information and operating condition information;

[0156] The noise reduction processing module 204 is used to perform noise reduction processing on the target fan based on the target control parameters.

[0157] In one embodiment, the operating status information includes first noise information and noise association information of the target fan, wherein the noise association information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information; the noise source information includes noise source type information and attribute information; the noise identification module 202 includes:

[0158] The preprocessing submodule is used to preprocess the running status information to obtain status feature information;

[0159] The noise identification submodule is used to identify state feature information and obtain noise source information.

[0160] In one embodiment, the noise recognition submodule is specifically used to input state feature information into the noise recognition model to obtain noise source information output by the noise recognition model.

[0161] In one embodiment, the operating condition information includes one or more of the following: target air volume information of the target fan, operating mode information, system operating status information, and environmental information; the parameter determination module 203 is specifically used to input the noise source information and operating condition information into the noise optimization model to obtain the target control parameters output by the noise optimization model.

[0162] In one embodiment, the target control parameters include the target fan's rotational speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters; the noise reduction processing module 204 includes:

[0163] The first processing submodule is used to adjust the speed of the motor of the target fan based on the speed parameters;

[0164] The second processing submodule is used to adjust the angle of the guide vanes of the target fan based on the angle parameters.

[0165] The third processing submodule is used to control the speaker output of the target fan to output an anti-phase acoustic signal based on the anti-phase acoustic wave parameters.

[0166] In one embodiment, the fan noise reduction device 200 further includes:

[0167] The noise information acquisition module is used to acquire the second noise information of the target fan.

[0168] The evaluation information determination module is used to determine noise reduction evaluation information based on the second noise information and the first noise information; the first noise information is the noise information before the target wind turbine is subjected to noise reduction treatment.

[0169] The model update module is used to update the noise optimization model based on the noise reduction evaluation information.

[0170] In one embodiment, the model update module includes:

[0171] The air volume difference determination submodule is used to determine the air volume difference between the first air volume information and the second air volume information; the first air volume information is the air volume information before noise reduction processing of the target fan, and the second air volume information is the air volume information after noise reduction processing of the target fan.

[0172] The reward value determination submodule is used to determine the target reward value based on noise reduction assessment information and airflow difference;

[0173] The model update submodule is used to update the noisy optimization model based on the target reward value.

[0174] By employing the technical solution of this application embodiment, the operating status information and operating condition information of the target fan can be obtained. The operating status information can be identified to obtain noise source information. Based on the noise source information and operating condition information, target control parameters can be determined, and noise reduction processing can be performed on the target fan based on these parameters. Thus, by accurately identifying noise source information from the operating status information of the target fan, and combining it with the operating condition information, targeted noise reduction processing can be achieved while ensuring the stable operation of the target fan, thereby effectively improving the noise reduction effect and enhancing the user's quiet comfort.

[0175] Specific limitations regarding the wind turbine noise reduction device 200 can be found in the limitations of the wind turbine noise reduction method described above, and will not be repeated here. Each module in the aforementioned wind turbine noise reduction device 200 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0176] In addition, this application also provides an electronic device, such as Figure 3 As shown, it illustrates the structural diagram of the electronic device involved in this application, specifically:

[0177] The electronic device may include components such as a processor 301 with one or more processing cores and a memory 302 with one or more computer-readable storage media. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0178] The processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 302, and by calling data stored in the memory 302, thereby providing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 301.

[0179] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0180] In one feasible implementation, the electronic device further includes a power supply 303 that supplies power to the various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 may also include one or more DC or AC power supplies, recharging systems, power equipment debugging circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0181] In one feasible implementation, the electronic device may further include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0182] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device loads the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 runs the application programs stored in the memory 302, thereby implementing the steps in any of the fan noise reduction methods provided in the embodiments of this application.

[0183] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0184] In one feasible implementation, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the methods described in any embodiment of this application.

[0185] In one feasible implementation, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in any embodiment of this application.

[0186] In one feasible implementation, a computer program product is also proposed, comprising a computer program or instructions that, when executed by a processor, implement the methods described in any embodiment of this application.

[0187] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0188] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0189] Therefore, this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor to execute the steps in any of the wind turbine noise reduction methods provided in this application.

[0190] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0191] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0192] Since the instructions stored in the computer-readable storage medium can execute the steps in any of the fan noise reduction methods provided in this application, the beneficial effects that any of the fan noise reduction methods provided in this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0193] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0194] The above provides a detailed description of a wind turbine noise reduction method, apparatus, electronic device, and computer-readable storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is 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 method for reducing noise in a fan, characterized in that, The method includes: Obtain the operating status and operating condition information of the target wind turbine; The noise source information is obtained by identifying the operating status information; Based on the noise source information and the operating condition information, the target control parameters are determined; Based on the target control parameters, noise reduction processing is performed on the target fan; The operating status information includes the first noise information and noise association information of the target fan. The noise association information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information. The noise source information includes the type information and attribute information of the noise source. The step of identifying the operating status information to obtain noise source information includes: The operating status information is preprocessed to obtain status feature information; The noise source information is obtained by identifying the state feature information; The operating condition information includes one or more of the following: target air volume information of the target fan, operating mode information, system operating status information, and environmental information; The step of determining the target control parameters based on the noise source information and the operating condition information includes: The noise source information and the operating condition information are input into the noise optimization model to obtain the target control parameters output by the noise optimization model. The target control parameters include the target fan's speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters; The noise reduction process for the target wind turbine based on the target control parameters includes: Based on the aforementioned rotational speed parameters, the motor speed of the target fan is adjusted; and / or, Based on the aforementioned angle parameters, the angle of the guide vanes of the target fan is adjusted; and / or, Based on the aforementioned anti-phase acoustic wave parameters, the loudspeaker of the target fan is controlled to output an anti-phase acoustic wave signal.

2. The fan noise reduction method according to claim 1, characterized in that, The step of identifying the state feature information to obtain the noise source information includes: The state feature information is input into the noise recognition model to obtain the noise source information output by the noise recognition model.

3. The fan noise reduction method according to claim 1, characterized in that, After performing noise reduction processing on the target wind turbine based on the target control parameters, the method further includes: Obtain the second noise information of the target fan; Based on the second noise information and the first noise information, noise reduction evaluation information is determined; the first noise information is the noise information before the target fan is subjected to noise reduction processing. Based on the noise reduction evaluation information, the noise optimization model is updated.

4. The fan noise reduction method according to claim 3, characterized in that, The step of updating the noise optimization model based on the noise reduction evaluation information includes: Determine the airflow difference between the first airflow information and the second airflow information; the first airflow information is the airflow information before noise reduction processing of the target fan, and the second airflow information is the airflow information after noise reduction processing of the target fan; Based on the noise reduction assessment information and the air volume difference, the target reward value is determined; The noise optimization model is updated based on the target reward value.

5. A fan noise reduction device, characterized in that, The device includes: The information acquisition module is used to acquire the operating status and operating condition information of the target wind turbine; A noise identification module is used to identify the operating status information to obtain noise source information; The parameter determination module is used to determine the target control parameters based on the noise source information and the operating condition information; A noise reduction processing module is used to perform noise reduction processing on the target fan based on the target control parameters; The operating status information includes the first noise information and noise correlation information of the target fan, wherein the noise correlation information includes one or more of vibration information, rotational speed information, first air volume information, and wind speed information; the noise source information includes the type information and attribute information of the noise source; the noise identification module includes: The preprocessing submodule is used to preprocess the running status information to obtain status feature information; The noise identification submodule is used to identify the state feature information to obtain the noise source information; The operating condition information includes one or more of the following: target air volume information of the target fan, operating mode information, system operating status information, and environmental information; the parameter determination module is specifically used to input the noise source information and the operating condition information into the noise optimization model to obtain the target control parameters output by the noise optimization model. The target control parameters include the target fan's rotational speed parameters and / or angle parameters and / or anti-phase acoustic wave parameters; the noise reduction processing module includes: The first processing submodule is used to adjust the speed of the motor of the target fan based on the speed parameters; The second processing submodule is used to adjust the angle of the guide vanes of the target fan based on the angle parameters. The third processing submodule is used to control the speaker of the target fan to output an anti-phase acoustic signal based on the anti-phase acoustic wave parameters.

6. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the wind turbine noise reduction method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the wind turbine noise reduction method as described in any one of claims 1 to 4.

Images