Method and apparatus for determining parameters of micro-perforated panel for spectral noise reduction of intelligent electric appliances
By constructing a mapping relationship between parameters and noise reduction effect and using a Bayesian optimization algorithm, the problems of low accuracy and efficiency in the design of micro-perforated plate parameters were solved, and efficient noise reduction of smart appliances was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NINGBO FOTILE KITCHEN WARE CO LTD
- Filing Date
- 2026-01-07
- Publication Date
- 2026-06-05
AI Technical Summary
The parameter design of micro-perforated plates has low accuracy and efficiency, mainly relying on the subjective judgment of engineers and lacking a quantitative process, resulting in multiple adjustments and high costs.
By collecting the operating spectral data of smart appliances, and combining the sound absorption performance model of micro-perforated panels with spectral filtering simulation, a mapping relationship between parameters and noise reduction effect is constructed. The parameters of micro-perforated panels are iteratively optimized using a Bayesian optimization algorithm to achieve rapid prediction and targeted optimization.
It improves the accuracy and efficiency of micro-perforated plate parameter design, reduces the arbitrariness of engineers' experience-based judgment, and lowers design costs.
Smart Images
Figure CN122153831A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of sound absorption and noise reduction, and in particular to a method and apparatus for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances. Background Technology
[0002] With the improvement of people's living standards and the promotion and popularization of technologies such as the Internet, big data, artificial intelligence, and voice interaction, more and more traditional lifestyles are gradually changing, and the use of home appliances is gradually moving towards intelligence. While bringing more convenience to users, the functions of various home appliances are also becoming more diversified. In smart home appliances, micro-perforated panels are generally set up for sound absorption and noise reduction. Micro-perforated panels (MPP) are an advanced sound-absorbing structure that uses precisely machined micron-sized holes on the panel and the cavity behind the panel to achieve sound absorption.
[0003] However, because the sound absorption frequency range of micro-perforated panels is very narrow, the parameters of the micro-perforated panel corresponding to the sound absorption frequency are generally obtained by obtaining the highest frequency peak of the micro-perforated panel and adjusting it according to the engineer's subjective judgment. However, the engineer's subjective judgment is easily influenced by experience and habits, and lacks a quantitative process, requiring multiple adjustments and experiments, resulting in low accuracy and efficiency in the design of micro-perforated panel parameters.
[0004] There is currently no effective solution to the problem of low accuracy and efficiency in the design of micro-perforated plate parameters in related technologies. Summary of the Invention
[0005] This embodiment provides a method and apparatus for determining the parameters of a micro-perforated plate for spectrum noise reduction in smart appliances, in order to solve the problem of low accuracy and efficiency in the design of micro-perforated plate parameters in related technologies.
[0006] In a first aspect, this embodiment provides a method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances, wherein the micro-perforated plate is mounted on the smart appliance to be noise-reduced; the method includes:
[0007] Based on the initial parameters of the micro-perforated plate, the frequency attenuation curve of the micro-perforated plate is determined;
[0008] Obtain the original spectrum data of the smart appliance to be noise-reduced; determine the amount of filtering and noise reduction based on the original spectrum data and the frequency attenuation curve;
[0009] Based on a preset Bayesian optimization strategy, a target denoising prediction model is used to predict the target parameters corresponding to the predicted denoising amount that meets the preset denoising threshold range in the micro-perforated plate. The target denoising prediction model is trained on a preset regression model based on the filtered denoising amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered denoising amount corresponding to different micro-perforated plate parameters.
[0010] In some embodiments, acquiring the original spectrum data of the smart appliance to be noise-reduced; and determining the filtering and noise reduction amount based on the original spectrum data and the frequency attenuation curve, includes:
[0011] Based on the frequency attenuation curve, construct a filtering function;
[0012] The original spectrum data is filtered using the filtering function to obtain filtered and denoised data.
[0013] Based on the filtered noise reduction data and the original spectrum data, a filtered noise reduction model is determined;
[0014] In the filtering and noise reduction model, the filtering and noise reduction amount corresponding to the initial parameters is determined.
[0015] In some embodiments, the target parameters corresponding to the prediction of the predicted noise reduction amount in the micro-perforated plate that meets the preset noise reduction threshold range, based on a preset Bayesian optimization strategy and utilizing a target noise reduction prediction model, include:
[0016] In the filtering and noise reduction model, the initial parameters of the micro-perforated plate are adjusted to obtain the corresponding filtering and noise reduction amount;
[0017] The adjusted initial parameters of the micro-perforated plate, and the corresponding filtering and noise reduction amount, are used as the model training set.
[0018] Based on the model training set, a preset regression model is trained using a preset regression algorithm to obtain the target noise reduction prediction model;
[0019] Based on the Bayesian optimization strategy, the predicted noise reduction amount corresponding to the original spectral data and the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount are obtained iteratively according to the target noise reduction prediction model.
[0020] In some embodiments, the step of training a preset regression model using a preset regression algorithm based on the model training set to obtain a target noise reduction prediction model includes:
[0021] Based on the model training set, construct the structural effect mapping relationship between the parameters of the micro-perforated plate and the filtering noise reduction amount;
[0022] The target noise reduction prediction model is obtained by learning the structural effect mapping relationship through the preset regression model.
[0023] In some embodiments, the step of iteratively obtaining the predicted noise reduction amount corresponding to the original spectral data and the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount based on the Bayesian optimization strategy and the target noise reduction prediction model includes:
[0024] Based on the Bayesian optimization strategy, a search is performed in the preset parameter space of the micro-perforated plate to iteratively obtain the combination of target parameters corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the filtered and denoised data.
[0025] In some embodiments, determining the frequency attenuation curve of the microperforated plate based on its initial parameters includes:
[0026] The acoustic impedance of the micro-perforated plate is calculated based on its initial parameters.
[0027] The sound absorption coefficient of the micro-perforated plate is determined based on the acoustic impedance and the preset formula for the sound absorption coefficient of the micro-perforated plate.
[0028] The attenuation coefficient of the micro-perforated plate is determined based on the sound absorption coefficient and the absorption area of the micro-perforated plate.
[0029] Based on the attenuation coefficient, the frequency attenuation curve of the micro-perforated plate is determined.
[0030] In some embodiments, determining the filtering and noise reduction amount corresponding to the initial parameters in the filtering and noise reduction model includes:
[0031] In the filtering and noise reduction model, the original noise corresponding to the original spectrum data and the filtered noise corresponding to the filtered and noise reduction data are obtained at the same frequency.
[0032] The filtering noise reduction amount corresponding to the initial parameters is determined based on the difference between the original noise and the filtered noise.
[0033] Secondly, this embodiment provides a parameter determination device for a micro-perforated plate used for spectrum noise reduction in smart appliances, the device comprising: an attenuation module, a filtering module, and a parameter prediction module;
[0034] The attenuation module is used to determine the frequency attenuation curve of the micro-perforated plate based on the initial parameters of the micro-perforated plate.
[0035] The filtering module is used to acquire the original spectrum data of the smart appliance to be noise-reduced; and to determine the amount of noise reduction based on the original spectrum data and the frequency attenuation curve.
[0036] The parameter prediction module is used to predict the target parameters corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the micro-perforated plate based on a preset Bayesian optimization strategy and using a target noise reduction prediction model. The target noise reduction prediction model is obtained by training a preset regression model based on the filtered noise reduction amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered noise reduction amount corresponding to different micro-perforated plate parameters.
[0037] Thirdly, this embodiment provides a smart appliance, on which a micro-perforated plate is installed. The parameters of the micro-perforated plate are determined according to the parameter determination method for micro-perforated plates used for spectrum noise reduction in smart appliances described in the first aspect. The smart appliance includes one of a smart steam oven, a smart steamer, and a smart refrigerator.
[0038] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the parameter determination method for the micro-perforated plate for spectrum noise reduction in smart appliances as described in the first aspect.
[0039] Compared with related technologies, the method and apparatus for determining parameters of a micro-perforated plate for spectrum noise reduction in smart appliances provided in this embodiment obtains the initial parameters of the micro-perforated plate and determines its frequency attenuation curve based on the initial parameters. Then, using the frequency attenuation curve and the original noise spectrum data, the corresponding filtering and noise reduction amount is determined. Based on multiple sets of filtering and noise reduction amounts and the initial parameters, a preset regression model is trained to obtain a trained target noise reduction prediction model. Subsequently, according to a Bayesian optimization strategy, the target parameters of the micro-perforated plate with the best noise reduction effect are iteratively obtained. By constructing a mapping relationship between the micro-perforated plate parameters and the noise reduction effect, and using the Bayesian optimization algorithm, rapid prediction and targeted optimization of the micro-perforated plate parameters for a specific machine can be achieved.
[0040] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description
[0041] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0042] Figure 1This is a hardware structure block diagram of the terminal of the parameter determination method for the micro-perforated plate for spectrum noise reduction of smart appliances provided in the embodiments of this application;
[0043] Figure 2 This is a schematic diagram of the sound absorption coefficient curve of a micro-perforated plate provided in an embodiment of this application;
[0044] Figure 3 This is the noise spectrum of the air inlet of the range hood provided in the embodiments of this application;
[0045] Figure 4 This is a flowchart of a method for determining parameters of a micro-perforated plate for spectrum noise reduction in smart appliances, provided in an embodiment of this application.
[0046] Figure 5 This is a flowchart of the micro-perforated plate parameter optimization method based on measured spectrum and predictive noise reduction analysis provided in this specific embodiment;
[0047] Figure 6 This is a schematic diagram of a sound absorption coefficient curve provided in this specific embodiment;
[0048] Figure 7 This is a schematic diagram of an attenuation curve provided in this specific embodiment;
[0049] Figure 8 This is a schematic diagram of the filtering function provided in this specific embodiment;
[0050] Figure 9 This is a simulation diagram of the filtering and noise reduction model provided in this specific embodiment;
[0051] Figure 10 This is a comparison chart of the original noise and the octave band noise with the added micro-perforated plate provided in this specific embodiment;
[0052] Figure 11 This is a structural block diagram of a parameter determination device for a micro-perforated plate used for spectrum noise reduction in smart appliances, provided in an embodiment of this application. Detailed Implementation
[0053] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.
[0054] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or intelligent appliance that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to these processes, methods, products, or intelligent appliances. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.
[0055] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the parameter determination method of the micro-perforated plate for spectrum noise reduction of smart appliances provided in the embodiments of this application. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.
[0056] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the parameter determination method for the micro-perforated plate for spectrum noise reduction of smart appliances in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0057] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.
[0058] Micro-perforated panels can effectively reduce noise at specific frequencies. A common method is to set the parameters of the micro-perforated panel to correspond to the frequency with the highest peak in the noise. However, because the effective sound absorption range of micro-perforated panels is narrow, the sound absorption frequency of the micro-perforated panel is very narrow, making it difficult to determine the frequency with the highest peak. Figure 2 This is a schematic diagram of the sound absorption coefficient curve of a micro-perforated plate provided in an embodiment of this application. Figure 2 The figure shows the sound absorption coefficient curves corresponding to a set of micro-perforated plate parameters, where the perforation diameter d = 0.5 mm, plate thickness t = 0.8 mm, cavity depth D = 50 mm, and open area ratio is [not specified]. ; Figure 2 The horizontal axis represents frequency (Hz), and the vertical axis represents the sound absorption coefficient. Since the actual effective sound absorption range in engineering is the range with a sound absorption coefficient of 0.5 or higher, therefore Figure 2 The actual effective sound absorption frequency range corresponding to this is only about 300 to 700 Hz.
[0059] Taking a specific model of range hood as an example, Figure 3The figure shows the noise spectrum of the range hood's air inlet provided in this embodiment, with the horizontal axis representing the peak value (Hz) and the vertical axis representing the noise level (dB). At this time, the range hood is not equipped with a micro-perforated plate, is set to AutoPower, and the air inlet is set to S(A) 41. Figure 3 The red curve shows that the noise level is -70.09dB and the RMS is 70.81 when the peak value is 0.00Hz. This noise has multiple peaks in the low-frequency range. The conventional approach is to find the micro-perforated plate parameters corresponding to the sound absorption frequency by targeting the highest frequency peak among these multiple peaks.
[0060] However, the conventional approach has the following problems: 1. It mainly relies on the subjective judgment of engineers, influenced by experience and habits, lacking a quantitative and system modeling process, resulting in considerable arbitrariness in parameter selection. 2. It only back-calculates parameters for a single frequency point, thus ignoring the possibility of global optimization. 3. This method is a forward trial-and-error approach, involving setting parameters, experimental results, manual judgment, and parameter adjustment, leading to low efficiency and high cost in micro-perforated plate parameter design.
[0061] To address the aforementioned issues, this application's embodiments collect raw spectral data under the operating conditions of intelligent electrical appliances. Combining this with a micro-perforated panel sound absorption performance model and spectral filtering simulation, a mapping relationship is constructed between micro-perforated panel parameters, sound absorption coefficient, spectral changes, and noise reduction effect. A Bayesian optimization algorithm is then used to achieve rapid prediction and targeted optimization of the micro-perforated panel parameters for a specific machine.
[0062] Specifically, this embodiment provides a method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances. Figure 4 This is a flowchart of a parameter determination method for a micro-perforated plate used for spectrum noise reduction in smart appliances, as provided in an embodiment of this application. Figure 4 As shown, the process includes the following steps:
[0063] Step S410: Based on the initial parameters of the micro-perforated plate, determine the frequency attenuation curve of the micro-perforated plate.
[0064] The micro-perforated plate is installed on the smart appliance to be noise-reduced, in order to absorb the noise generated by the smart appliance. For example, the micro-perforated plate can also be micro-perforated cotton; the smart appliance to be noise-reduced can be a smart appliance in the kitchen, including a range hood, or any smart appliance that generates noise.
[0065] In addition, the micro-perforated plate installed on the smart appliance to be noise-reduced has an initial parameter design, which includes the perforation diameter d, plate thickness t, cavity depth D, and open area ratio. However, the initial parameters of the micro-perforated plate may not necessarily achieve the best sound absorption and noise reduction effect, so the parameters of the micro-perforated plate need to be designed. First, the frequency attenuation curve of the micro-perforated plate needs to be calculated based on the initial parameters, so that the initial parameters can be adjusted according to the frequency attenuation curve later.
[0066] Furthermore, based on the initial parameters of the micro-perforated plate, the frequency attenuation curve of the micro-perforated plate is determined, including: calculating the acoustic impedance of the micro-perforated plate according to the initial parameters of the micro-perforated plate; determining the sound absorption coefficient of the micro-perforated plate according to the acoustic impedance and the preset sound absorption coefficient formula of the micro-perforated plate; determining the attenuation coefficient of the micro-perforated plate according to the sound absorption coefficient and the absorption area of the micro-perforated plate; and determining the frequency attenuation curve of the micro-perforated plate based on the attenuation coefficient.
[0067] Among these parameters, the acoustic impedance of the microperforated plate is a key one, determining how the material interacts with sound waves and affecting its sound absorption performance. Specifically, acoustic impedance comprises two parts: acoustic resistance and acoustic reactance. Acoustic resistance corresponds to the energy loss portion, while acoustic reactance is related to the stored energy.
[0068] Since the acoustic impedance of the micro-perforated plate is determined by its initial parameters, namely the perforation diameter d, plate thickness t, cavity depth D, and porosity... Therefore, after determining the initial parameters of the micro-perforated plate, its acoustic impedance is calculated. Subsequently, based on the acoustic impedance, the sound absorption coefficient of the micro-perforated plate is calculated using a pre-defined formula for calculating the sound absorption coefficient. Different absorption coefficients are obtained at different frequencies, thus allowing the establishment of curves based on frequency and absorption coefficient. Furthermore, under fixed sound source and installation conditions, the sound energy absorption capacity of the micro-perforated plate is determined by the absorption area S and the absorption coefficient. A joint decision.
[0069] After obtaining the sound absorption at different frequencies, a frequency-dependent energy attenuation coefficient is defined. It represents the number of decibels that each frequency component of sound is reduced after passing through the micro-perforated plate structure, which is mainly based on the absorption area S and the sound absorption coefficient. and reference total radiation area S ref Determined. Ultimately, based on the attenuation coefficients at different frequencies... Determine the frequency attenuation curve corresponding to the initial parameters of the current micro-perforated plate.
[0070] Step S420: Obtain the original spectrum data of the smart appliance to be noise-reduced; determine the amount of filtering and noise reduction based on the original spectrum data and frequency attenuation curve.
[0071] This involves constructing a filtering model based on the frequency attenuation curve obtained in the above steps, and then implementing the filter to process the original spectrum data in acoustic analysis software to simulate the changes in the original noise spectrum and sound pressure level under different micro-perforated plate parameter conditions.
[0072] Therefore, the frequency attenuation curve of the micro-perforated plate needs to be input into the acoustic analysis software to construct a filtering function. Simultaneously, the original spectrum data of the smart appliance to be denoised, containing the original noise, is obtained, and the filtering function is loaded into the original spectrum data to obtain curves that produce noise reduction effects at certain frequencies. This allows determination of the corresponding filtering noise reduction amount for the denoised curves, thus obtaining the correspondence between the initial parameters of the micro-perforated plate and the filtering noise reduction amount at different frequencies.
[0073] Step S430: Based on the preset Bayesian optimization strategy, the target parameter corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the micro-perforated plate is predicted using the target noise reduction prediction model. The target noise reduction prediction model is obtained by training a preset regression model based on the filtered noise reduction amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered noise reduction amount corresponding to different micro-perforated plate parameters.
[0074] After obtaining the filtering and noise reduction amounts and the initial parameters of the micro-perforated plate at different frequencies, a dataset including the micro-perforated plate parameters and the filtering and noise reduction amounts needs to be constructed based on these initial parameters. Furthermore, the initial parameters can include multiple sets of parameters for different designs. Based on these multiple sets of parameters, their frequency attenuation curves are determined, and multiple corresponding filtering and noise reduction amounts are determined using the frequency attenuation curves and the original noise spectrum data. Therefore, the filtering and noise reduction amounts and initial parameters here do not simply refer to the initial parameters and corresponding filtering and noise reduction amounts of the current micro-perforated plate, but rather include a model training set encompassing multiple sets of parameters and their corresponding filtering and noise reduction amounts.
[0075] By training a pre-defined regression model on a dataset, a predictive model is established based on the regression model to predict the relationship between the denoising effect and the parameters of the micro-perforated plate, resulting in a trained target denoising prediction model. For example, the regression model can be a linear regression model or a random forest model; the pre-defined regression model is not limited here.
[0076] Subsequently, the mapping relationship between the structural parameters of the micro-perforated plate and the noise reduction effect was learned using the target noise reduction prediction model, and multiple sets of parameters corresponding to the predicted noise reduction amount in the micro-perforated plate that meet the preset noise reduction threshold range were predicted.
[0077] Subsequently, using a pre-defined Bayesian optimization strategy, multiple sets of parameters are searched in a pre-defined parameter space to iteratively find the target parameter combination of the micro-perforated plate that has the maximum attenuation effect based on the original spectral data, i.e., meets the pre-defined noise reduction threshold range.
[0078] Through the above steps, the frequency attenuation curve of the micro-perforated plate is determined using its initial parameters. Then, the corresponding filtering and noise reduction amount is determined using the frequency attenuation curve and the original noise spectrum data. Based on the filtering and noise reduction amount and the initial parameters, a preset regression model is trained to obtain a trained target noise reduction prediction model. Using a Bayesian optimization strategy, the target parameters of the micro-perforated plate with the best noise reduction effect are iteratively obtained. By constructing a mapping relationship between micro-perforated plate parameters, sound absorption coefficient, spectral change, and noise reduction effect, and utilizing the trained target noise reduction prediction model and Bayesian optimization algorithm, rapid prediction and targeted optimization of the parameters of the micro-perforated plate installed on the smart appliance to be noise-reduced can be achieved.
[0079] In some embodiments, step S420 involves acquiring the original spectrum data of the smart appliance to be noise-reduced; determining the filtering noise reduction amount based on the original spectrum data and frequency attenuation curve, including: constructing a filtering function based on the frequency attenuation curve; using the filtering function to filter the original spectrum data to obtain filtered noise-reduced data; determining a filtering noise reduction model based on the filtered noise-reduced data and the original spectrum data; and determining the filtering noise reduction amount corresponding to the initial parameters in the filtering noise reduction model.
[0080] Furthermore, in the filtering and noise reduction model, determining the filtering and noise reduction amount corresponding to the initial parameters includes: in the filtering and noise reduction model, obtaining the original noise corresponding to the original spectrum data and the filtered noise corresponding to the filtered and noise reduction data at the same frequency; and determining the filtering and noise reduction amount corresponding to the initial parameters based on the difference between the original noise and the filtered noise.
[0081] The process involves obtaining the frequency attenuation curve, importing it into acoustic simulation software, and constructing a filtering function. Then, the filtering function corresponding to the frequency attenuation curve is loaded into the original spectrum data to filter it, resulting in denoised data. Based on the values of the denoised data and the original spectrum data at different frequencies, corresponding denoised curves and original spectrum curves are constructed, thus forming a denoised model.
[0082] In the filtering and noise reduction model, the filtered noise corresponding to the filtered noise reduction data and the original noise corresponding to the original spectrum data are obtained at the same frequency. Then, the difference between the original noise and the filtered noise at different frequencies is calculated. If the difference meets the preset noise reduction threshold range, the difference is determined as the filtering noise reduction amount, and the target parameters of the micro-perforated plate corresponding to the filtering noise reduction amount are determined.
[0083] The filtering and noise reduction model here is used to characterize the process of calculating the noise reduction amount from the sound absorption coefficient and attenuation coefficient of the parameters. For ease of description, the concept of filtering and noise reduction model is introduced here. The filtering and noise reduction model includes multiple sets of parameters and the corresponding filtering and noise reduction amounts obtained through the above steps. That is, it includes determining the frequency attenuation curves based on multiple sets of parameters, and determining the corresponding multiple filtering and noise reduction amounts through the frequency attenuation curves and the original noise spectrum data.
[0084] In some embodiments, step S430, based on a preset Bayesian optimization strategy, uses a target denoising prediction model to predict the predicted denoising amount in the micro-perforated plate that meets a preset denoising threshold range, and the corresponding target parameters, including: adjusting the initial parameters of the micro-perforated plate in the filtering denoising model to obtain the corresponding filtering denoising amount; using the adjusted initial parameters of the micro-perforated plate and the corresponding filtering denoising amount as a model training set; training a preset regression model using a preset regression algorithm based on the model training set to obtain the target denoising prediction model; and iteratively obtaining the predicted denoising amount corresponding to the original spectral data and the target parameters of the micro-perforated plate corresponding to the predicted denoising amount based on the target denoising prediction model, according to the Bayesian optimization strategy.
[0085] In the process of training the preset regression model based on the initial parameters of the micro-perforated plate and the corresponding filtering and noise reduction amount, it is necessary to first construct a model training group based on the initial parameters and the corresponding filtering and noise reduction amount. Specifically, by adjusting the initial parameters of the micro-perforated plate, the filtering and noise reduction amount corresponding to the adjusted initial parameters is calculated according to the method of constructing the filtering function corresponding to the frequency attenuation curve mentioned above.
[0086] The initial parameters of the micro-perforated plate can be adjusted in conjunction with the actual noise optimization effect by adjusting the perforation diameter d, plate thickness t, cavity depth D, and open area ratio. At least one parameter value.
[0087] By repeatedly adjusting the initial parameters of the micro-perforated plate and using the corresponding filtered noise reduction values calculated based on the adjusted parameters as the model training group, a preset regression model is trained using a preset regression algorithm to obtain the target noise reduction prediction model.
[0088] Subsequently, based on the Bayesian optimization strategy, namely the Bayesian optimization algorithm, a search is performed in the preset micro-perforated plate parameter space. Then, in the filtered noise data, the predicted noise reduction amount with the maximum attenuation effect, that is, the predicted noise reduction amount that meets the preset noise reduction range threshold, is iteratively searched. After that, the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount are determined.
[0089] Furthermore, based on the model training group, a preset regression model is trained using a preset regression algorithm to obtain the target noise reduction prediction model, including: based on the model training group, constructing a structural effect mapping relationship between the parameters of the micro-perforated plate and the amount of filtering noise reduction; and learning the structural effect mapping relationship through the preset regression model to obtain the trained target noise reduction prediction model.
[0090] Based on the Bayesian optimization strategy, according to the target noise reduction prediction model, the predicted noise reduction amount corresponding to the original spectrum data and the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount are obtained iteratively. This includes: based on the Bayesian optimization strategy, searching in the preset parameter space of the micro-perforated plate to iteratively obtain the combination of target parameters corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the filtered noise reduction data.
[0091] The preset parameter space specifically refers to the parameter range defined for each parameter of the micro-perforated plate.
[0092] By learning the structural effect mapping relationship between the parameters of the micro-perforated plate and the filtering noise reduction amount through a regression model, the filtering noise reduction value of the smart appliance to be denoised is learned. Combined with the Bayesian optimization algorithm, the parameter space is iteratively searched to obtain the target parameters of the micro-perforated plate with the best noise reduction effect. This improves the accuracy and efficiency of the micro-perforated plate parameter design and avoids the arbitrariness and uncertainty caused by engineers designing micro-perforated plate parameters based on experience.
[0093] Furthermore, smart appliances can be any device that requires noise reduction, such as any of the following: smart steam oven, smart steamer, or smart refrigerator.
[0094] The following describes and illustrates this embodiment through specific examples.
[0095] Figure 5 This is a flowchart of the micro-perforated plate parameter optimization method based on measured spectrum and predictive noise reduction analysis provided in this specific embodiment, as follows: Figure 5 As shown, the method for optimizing micro-perforated plate parameters based on measured spectrum and predictive noise reduction analysis includes the following steps:
[0096] Step S510: Measure the spectrum of the target device.
[0097] The target device refers to the smart appliance to be noise-reduced in the aforementioned embodiments, and the spectrum of the target device refers to the original spectrum data of the smart appliance to be noise-reduced.
[0098] Step S520: Construct a spectral filter, i.e., an attenuation curve, using the sound absorption coefficient and area.
[0099] First, calculate the sound absorption coefficient curve of the micro-perforated plate.
[0100] After determining the acoustic impedance based on the initial parameters of the micro-perforated plate, the sound absorption coefficient of the micro-perforated plate is calculated using the formula proposed by Professor Ma Dayou. Sound absorption coefficient The formula is as follows:
[0101] ;
[0102] in, Z is the sound absorption coefficient. total This is the acoustic impedance.
[0103] Therefore, the sound absorption coefficient curve of the micro-perforated plate can be calculated based on its initial parameters, for reference. Figure 2 The sound absorption coefficient curve is shown.
[0104] Secondly, the attenuation curve of the microperforated plate was calculated.
[0105] Under the condition that the sound source and installation conditions of the smart electrical appliance to be noise-reduced are fixed, the sound energy absorption capacity of the micro-perforated plate is determined by the absorption area S and the sound absorption coefficient. It was jointly decided that, since the actual incident sound intensity is consistent for all schemes, there is no need to explicitly introduce it. Therefore, the formula for the sound absorption of the micro-perforated plate can be expressed as:
[0106] ;
[0107] in, This represents the frequency-based sound absorption coefficient expression, where S represents the absorption area.
[0108] Finally, the attenuation filter is calculated.
[0109] After obtaining the sound absorption at different frequencies, a frequency-dependent energy attenuation coefficient is defined. It represents the number of decibels that each frequency component of sound is reduced after passing through the micro-perforated plate structure, and is commonly expressed as follows:
[0110] ;
[0111] in, This represents the frequency-based sound absorption coefficient expression, where S represents the absorption area. ref This indicates the reference total radiation area. Figure 6 This is a schematic diagram of a sound absorption coefficient curve provided in this specific embodiment, where the horizontal axis represents frequency and the vertical axis represents sound absorption coefficient. Figure 7 This is a schematic diagram of an attenuation curve provided in this specific embodiment, where the horizontal axis represents frequency and the vertical axis represents attenuation in decibels; Figure 7 The attenuation curve in the middle, according to Figure 6 The sound absorption coefficient curve is determined by combining the above methods.
[0112] Figure 8 This is a schematic diagram of the filtering function provided in this specific embodiment. (Reference) Figure 8 After constructing the frequency-dependent attenuation curve, a filtering model is built based on the attenuation curve. For example, the attenuation curve is imported into LMS software to construct the filtering function. The horizontal axis represents frequency, and the vertical axis represents attenuation in decibels.
[0113] Step S530: Filter the spectrum to reduce noise in the entire device.
[0114] In the acoustic analysis software, the original spectral data is processed by the filtering function corresponding to the attenuation curve to simulate the changes in the original noise spectrum data and sound pressure level under different micro-perforated plate parameters, thus obtaining the above-mentioned filtering and noise reduction model. Figure 9 This is a simulation diagram of the filtering and noise reduction model provided in this specific embodiment. (Reference) Figure 9 The red line represents the original spectrum data, with the range hood set to AutoPower and the air inlet at setting S(A)41. The green line represents the filtered noise-reduced data, with the range hood set to AutoPower and the air inlet at setting S(A)(2)41, and this is the first set of filtered data. It can be seen that noise decreases at certain frequencies, resulting in a significant decibel difference between the red and green lines. Figure 9 The red curve shows that the noise level is -70.09 dB at a peak frequency of 0.00 Hz and 17.89 dB at a peak frequency of 6400.00 Hz, with an RMS of 70.81. From... Figure 9 The green curve shows that the noise level is -70.09 dB at a peak frequency of 0.00 Hz and 17.89 dB at a peak frequency of 6400.00 Hz, with an RMS of 70.02. The graph also shows that at the same frequency with the largest decibel difference, the original noise level is 70.81 dB, and the predicted noise level after absorption by the micro-perforated plate is 70.02 dB, resulting in a noise reduction of 70.81 - 70.02 = 0.79 dB.
[0115] Furthermore, in addition to constructing attenuation curves using LMS software, the Firwin2 and Lfiter libraries in Python can be used in combination to simulate sound attenuation, without making specific limitations here.
[0116] Step S540: Combine multiple sets of parameters to train the noise reduction prediction model.
[0117] Specifically, based on the micro-perforated plate parameters and filtering noise reduction amount obtained from the attenuation curve, a dataset of micro-perforated plate parameters and noise reduction amount is constructed. Through regression models such as linear regression or random forest, a target noise reduction prediction model between the noise reduction effect and the micro-perforated plate parameters is learned and established.
[0118] The noise reduction values of a set of initial parameters for the micro-perforated plate were obtained through simulation. By adjusting the initial parameters of the micro-perforated plate, several sets of corresponding parameter and noise reduction data can be obtained, forming a training dataset. Table 1 shows a partial selection of the training dataset.
[0119] Table 1 Partial Training Dataset
[0120]
[0121] Subsequently, the regression model was trained based on the training dataset to construct the mapping relationship between the structural parameters of the micro-perforated plate and the noise reduction effect, that is, the regression model was used to learn this mapping relationship.
[0122] Step S550, Bayesian backpropagation.
[0123] Specifically, after completing the regression modeling of the structure-performance relationship, a Bayesian optimization algorithm is introduced to search the parameter space. Through the surrogate model and confidence evaluation mechanism built into the Bayesian optimization algorithm, the combination of micro-perforated plate parameters with the maximum attenuation effect under the current noise spectrum of the smart appliance to be denoised is iteratively searched.
[0124] Step S560: Recommend the optimal parameters.
[0125] The combination of micro-perforated plate parameters that yields the maximum attenuation effect is taken as the optimal noise reduction parameters for the micro-perforated plate and recommended to users.
[0126] For example, the parameter combination of the micro-perforated plate that has the maximum attenuation effect under the noise spectrum of the smart electrical appliance to be noise-reduced includes: perforation diameter d=0.4mm, plate thickness t=0.524mm, cavity depth D=46.164mm; and open area ratio. The final predicted noise reduction was 1.127 dB.
[0127] In one specific embodiment, when the smart appliance to be noise-reduced is not equipped with the micro-perforated plate, the original noise level is 70.81 dB. After the micro-perforated plate is installed, the noise level is 70.13 dB, resulting in a noise reduction of 0.68 dB. Due to manufacturing tolerances such as burrs and thickness fluctuations in the sample prototyping process, and actual installation conditions such as sealing, the actual noise reduction may differ from the theoretically predicted noise reduction.
[0128] Figure 10This is a comparison chart of the original noise level and the noise level with and without the micro-perforated plate provided in this specific embodiment. The horizontal axis represents the peak value (Hz), and the vertical axis represents the noise level (dB). The green area in the chart indicates that the range hood is not equipped with the micro-perforated plate, set to Octave 1 / 3, and the air inlet is set to level 41, with an RMS of 70.81 dB(A). The blue area in the chart indicates that the range hood is equipped with 0.3% micro-perforated plates on the left, right, and front sides, set to Octave 1 / 3, and the air inlet is set to level 41, with an RMS of 70.81 dB(A).
[0129] Based on the micro-perforated plate parameter design method in the above embodiments, the target parameters of the micro-perforated plate corresponding to the maximum noise reduction value are predicted, namely, perforation diameter d=0.4mm, plate thickness t=0.524mm, cavity depth D=46.164mm; and open area ratio. The micro-perforated plate was then adjusted according to the target parameters. Subsequently, noise detection was performed using the adjusted micro-perforated plate. (Reference) Figure 10 As can be seen from the octave band diagram, the noise generated by the non-perforated plate and the perforated plate is basically the same at low and high frequencies. However, the noise reduction is most significant at the center octave band of 315Hz, with a noise reduction of 61.38-58.63=2.75dB. This is significantly better than the noise reduction effect of installing a micro-perforated plate with unadjusted parameters, verifying the accuracy and efficiency of the parameter determination method for micro-perforated plates used for spectrum noise reduction in smart appliances provided in this application embodiment.
[0130] In one specific embodiment, a smart appliance is also provided, on which a micro-perforated plate is installed. The parameters of the micro-perforated plate are determined according to the aforementioned method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances. Exemplarily, the smart appliance can be a kitchen appliance including a range hood, or other household appliances, or any other smart appliance that generates noise; the smart appliance is not limited herein.
[0131] It should be noted that the steps shown in the above process or in the flowcharts in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions.
[0132] This embodiment also provides a parameter determination device for a micro-perforated plate used for spectrum noise reduction in smart appliances. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0133] Figure 11This is a structural block diagram of the parameter determination device for micro-perforated plates used for spectrum noise reduction in smart appliances provided in the embodiments of this application, as shown below. Figure 11 As shown, the device includes an attenuation module 10, a filtering module 20, and a parameter prediction module 30.
[0134] The attenuation module 10 is used to determine the frequency attenuation curve of the micro-perforated plate based on the initial parameters of the micro-perforated plate.
[0135] The filtering module 20 is used to acquire the original spectrum data of the smart appliance to be noise-reduced; and to determine the amount of noise reduction by filtering based on the original spectrum data and frequency attenuation curve.
[0136] The parameter prediction module 30 is used to predict the target parameters corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the micro-perforated plate based on the preset Bayesian optimization strategy and the target noise reduction prediction model. The target noise reduction prediction model is obtained by training a preset regression model based on the filtered noise reduction amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered noise reduction amount corresponding to different micro-perforated plate parameters.
[0137] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.
[0138] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.
[0139] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.
[0140] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:
[0141] S1. Based on the initial parameters of the micro-perforated plate, determine the frequency attenuation curve of the micro-perforated plate.
[0142] S2, acquire the original spectrum data of the smart appliance to be noise-reduced; determine the amount of filtering and noise reduction based on the original spectrum data and frequency attenuation curve.
[0143] S3, based on a preset Bayesian optimization strategy, uses a target denoising prediction model to predict the target parameters corresponding to the predicted denoising amount that meets the preset denoising threshold range in the micro-perforated plate; the target denoising prediction model is obtained by training a preset regression model based on the filtered denoising amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered denoising amount corresponding to different micro-perforated plate parameters.
[0144] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.
[0145] Furthermore, in conjunction with the parameter determination method for micro-perforated plates for spectrum noise reduction in smart appliances provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the parameter determination methods for micro-perforated plates for spectrum noise reduction in smart appliances described in the above embodiments.
[0146] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.
[0147] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.
[0148] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.
[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.
Claims
1. A method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances, characterized in that, The micro-perforated plate is installed on the smart appliance to be noise-reduced; the method includes: Based on the initial parameters of the micro-perforated plate, the frequency attenuation curve of the micro-perforated plate is determined; Obtain the original spectrum data of the smart appliance to be noise-reduced; determine the amount of filtering and noise reduction based on the original spectrum data and the frequency attenuation curve; Based on a preset Bayesian optimization strategy, a target denoising prediction model is used to predict the target parameters corresponding to the predicted denoising amount that meets the preset denoising threshold range in the micro-perforated plate. The target denoising prediction model is trained on a preset regression model based on the filtered denoising amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered denoising amount corresponding to different micro-perforated plate parameters.
2. The method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances according to claim 1, characterized in that, The process of acquiring the original spectrum data of the smart appliance to be noise-reduced and determining the filtering and noise reduction amount based on the original spectrum data and the frequency attenuation curve includes: Based on the frequency attenuation curve, construct a filtering function; The original spectrum data is filtered using the filtering function to obtain filtered and denoised data. Based on the filtered noise reduction data and the original spectrum data, a filtered noise reduction model is determined; In the filtering and noise reduction model, the filtering and noise reduction amount corresponding to the initial parameters is determined.
3. The method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances according to claim 2, characterized in that, The preset Bayesian optimization strategy utilizes a target noise reduction prediction model to predict the target parameters corresponding to the predicted noise reduction amount within a preset noise reduction threshold range in the micro-perforated plate, including: In the filtering and noise reduction model, the initial parameters of the micro-perforated plate are adjusted to obtain the corresponding filtering and noise reduction amount; The adjusted initial parameters of the micro-perforated plate, and the corresponding filtering and noise reduction amount, are used as the model training set. Based on the model training set, a preset regression model is trained using a preset regression algorithm to obtain the target noise reduction prediction model; Based on the Bayesian optimization strategy, the predicted noise reduction amount corresponding to the original spectral data and the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount are obtained iteratively according to the target noise reduction prediction model.
4. The method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances according to claim 3, characterized in that, The step of training a preset regression model based on the model training set using a preset regression algorithm to obtain a target denoising prediction model includes: Based on the model training set, construct the structural effect mapping relationship between the parameters of the micro-perforated plate and the filtering noise reduction amount; The target noise reduction prediction model is obtained by learning the structural effect mapping relationship through the preset regression model.
5. The method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances according to claim 3, characterized in that, The step of iteratively obtaining the predicted noise reduction amount corresponding to the original spectral data and the target parameters of the micro-perforated plate corresponding to the predicted noise reduction amount based on the Bayesian optimization strategy and the target noise reduction prediction model includes: Based on the Bayesian optimization strategy, a search is performed in the preset parameter space of the micro-perforated plate to iteratively obtain the combination of target parameters corresponding to the predicted noise reduction amount that meets the preset noise reduction threshold range in the filtered and denoised data.
6. The method for determining parameters of a micro-perforated plate for spectral noise reduction in smart electrical appliances according to any one of claims 1 to 5, characterized in that, Determining the frequency attenuation curve of the micro-perforated plate based on its initial parameters includes: The acoustic impedance of the micro-perforated plate is calculated based on its initial parameters. The sound absorption coefficient of the micro-perforated plate is determined based on the acoustic impedance and the preset formula for the sound absorption coefficient of the micro-perforated plate. The attenuation coefficient of the micro-perforated plate is determined based on the sound absorption coefficient and the absorption area of the micro-perforated plate. Based on the attenuation coefficient, the frequency attenuation curve of the micro-perforated plate is determined.
7. The method for determining the parameters of a micro-perforated plate for spectral noise reduction in smart appliances according to claim 2, characterized in that, In the filtering and noise reduction model, determining the filtering and noise reduction amount corresponding to the initial parameters includes: In the filtering and noise reduction model, the original noise corresponding to the original spectrum data and the filtered noise corresponding to the filtered and noise reduction data are obtained at the same frequency. The filtering noise reduction amount corresponding to the initial parameters is determined based on the difference between the original noise and the filtered noise.
8. A parameter determination device for a micro-perforated plate used for spectrum noise reduction in smart electrical appliances, characterized in that, The device includes: an attenuation module, a filtering module, and a parameter prediction module; The attenuation module is used to determine the frequency attenuation curve of the micro-perforated plate based on the initial parameters of the micro-perforated plate. The filtering module is used to acquire the original spectrum data of the smart appliance to be noise-reduced; and to determine the amount of noise reduction based on the original spectrum data and the frequency attenuation curve. The parameter prediction module is used to predict the target parameters corresponding to the predicted noise reduction amount that meet the preset noise reduction threshold range in the micro-perforated plate based on a preset Bayesian optimization strategy and a target noise reduction prediction model. The target noise reduction prediction model is obtained by training a preset regression model based on the filtered noise reduction amount and the initial parameters of the micro-perforated plate, and is used to predict the filtered noise reduction amount corresponding to different micro-perforated plate parameters.
9. A smart appliance, characterized in that, The smart appliance is equipped with a micro-perforated plate, and the parameters of the micro-perforated plate are determined according to the parameter determination method of the micro-perforated plate for spectrum noise reduction of smart appliances according to any one of claims 1 to 7; the smart appliance includes one of a smart steam oven, a smart steam box, and a smart refrigerator.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the parameter determination method for the micro-perforated plate for spectrum noise reduction of smart electrical appliances as described in any one of claims 1 to 7.