Abnormal sound detection method and device of range hood and electronic equipment

Abstract

The application provides an abnormal sound detection method and device for a range hood and electronic equipment, comprising: obtaining a noise signal when a range hood to be detected is running; extracting time-frequency domain features and frequency superposition characteristics of the noise signal; determining the size of the time-frequency domain features and a preset time-frequency domain feature threshold to obtain a first determination result; and determining whether the frequency superposition characteristics have frequency superposition to obtain a second determination result; and determining whether the range hood to be detected has objective abnormal sound according to the first determination result and the second determination result. The method extracts time-frequency domain features and frequency superposition characteristics of a noise signal and analyzes the features, thereby solving the problem of abnormal sound detection of a range hood before leaving the factory.

Description

Technical Field

[0001] This invention relates to the field of abnormal noise detection technology, and in particular to a method, device and electronic equipment for detecting abnormal noise in a range hood. Background Technology

[0002] Range hoods generate significant noise during operation, making it a major noise source in homes and impacting user experience. This noise has become a crucial factor for consumers when purchasing the product. Range hoods use either DC or AC motors. AC motors vibrate more during operation, easily exciting vibrations in structures such as the air duct, resulting in noticeable peak noise. This noise significantly reduces the user experience, leading to complaints and even returns. In some markets, the problem of abnormal noise from AC motors is frequently observed, becoming a critical noise issue that urgently needs to be addressed.

[0003] To suppress range hood noise, the industry has conducted relevant research on motor installation and vibration reduction, achieving significant results. Currently, range hood noise testing follows the new national standard, conducting semi-anechoic chamber testing and operating noise testing. However, there is a lack of methods for detecting abnormal noise before range hoods leave the factory, posing a risk of abnormal noise for range hoods using AC motors once they enter the market.

[0004] Overall, the issue of how to conduct abnormal noise testing on range hoods before they leave the factory urgently needs to be addressed. Summary of the Invention

[0005] The purpose of this invention is to provide a method, device, and electronic equipment for detecting abnormal noises in range hoods, so as to solve the technical problem of detecting abnormal noises in range hoods before they leave the factory.

[0006] In a first aspect, the present invention provides a method for detecting abnormal noise in a range hood, comprising: acquiring a noise signal during the operation of the range hood to be tested; extracting the time-frequency domain features and frequency superposition characteristics of the noise signal; determining the magnitude of the time-frequency domain features and a preset time-frequency domain feature threshold to obtain a first determination result; and determining whether the frequency superposition characteristics exist to obtain a second determination result; and determining whether the range hood to be tested has objective abnormal noise based on the first determination result and the second determination result.

[0007] In a preferred embodiment of the present invention, the step of extracting the time-frequency domain features and frequency superposition characteristics of the noise signal includes: extracting the sound pressure time-domain mean, sound pressure time-domain peak, sound pressure frequency-domain mean, sound pressure frequency-domain peak, and frequency superposition characteristics of the noise signal; and the step of determining the magnitude of the time-frequency domain features and a preset time-frequency domain feature threshold to obtain a first determination result includes: determining the magnitude of the sound pressure time-domain mean, the sound pressure time-domain peak, and a preset sound pressure envelope time-domain line, and determining and comparing the magnitude of the sound pressure frequency-domain mean, the sound pressure frequency-domain peak, and the preset sound pressure frequency-domain envelope line to obtain a first determination result.

[0008] In a preferred embodiment of the present invention, the step of extracting the frequency superposition characteristics of the noise signal includes: analyzing the frequency superposition characteristics of the noise signal using a preset wavelet analysis algorithm.

[0009] In a preferred embodiment of the present invention, before determining the magnitudes of the sound pressure time-domain mean and the sound pressure time-domain peak values ​​relative to a preset sound pressure envelope time-domain line, and comparing the magnitudes of the sound pressure frequency-domain mean and the sound pressure frequency-domain peak values ​​relative to a preset sound pressure frequency-domain envelope line to obtain a first determination result, the method includes: acquiring first experimental noise from multiple experimental tobacco machines under different operating states; preprocessing the first experimental noise to obtain first preprocessed noise; filtering the first preprocessed noise into experimental time-domain noise and experimental frequency-domain noise; performing convolution calculations on the experimental time-domain noise and experimental frequency-domain noise respectively to obtain the sound pressure mean and peak time-domain envelope line and the sound pressure mean and peak frequency-domain envelope line; determining the sound pressure envelope time-domain line based on the sound pressure mean and peak time-domain envelope line, and determining the sound pressure frequency-domain envelope line based on the sound pressure mean and peak frequency-domain envelope line.

[0010] In a preferred embodiment of the present invention, after determining whether the range hood to be tested has objective abnormal noise based on the first judgment result and the second judgment result, the method includes: if it is determined that the range hood to be tested does not have objective abnormal noise, inputting the noise signal into a preset subjective sound evaluation model and outputting a subjective score of the noise signal; the subjective sound evaluation model is constructed based on experimental noise and the subjective score corresponding to the experimental noise; and determining whether the range hood to be tested has subjective noise based on the relationship between the subjective score and a preset subjective score threshold.

[0011] In a preferred embodiment of the present invention, the steps of constructing the above-mentioned subjective sound evaluation model include: acquiring second experimental noise from multiple experimental tobacco machines under different operating states; preprocessing the second experimental noise to obtain second preprocessed noise; extracting objective parameter values ​​from the second preprocessed noise and scoring the second preprocessed noise using preset noise analysis software to obtain a scoring result; the objective parameter values ​​are used to indicate the noise characteristic values ​​of the second preprocessed noise; performing correlation analysis between the objective parameter values ​​and the scoring result to obtain a correlation degree; selecting target objective parameter values ​​from the objective parameter values ​​whose correlation degree is greater than a preset threshold; and determining the above-mentioned subjective sound evaluation model based on the target objective parameter values.

[0012] In a preferred embodiment of the present invention, the step of determining the above-mentioned subjective sound evaluation model based on the above-mentioned objective parameter values ​​includes: performing multivariate nonlinear fitting on the above-mentioned objective parameter values ​​to obtain a preliminary prediction model; performing correlation verification on the above-mentioned preliminary prediction model based on a preset verification noise to obtain a verification error; determining whether the above-mentioned verification error is less than or equal to a preset error threshold; if so, determining the above-mentioned preliminary prediction model as the above-mentioned subjective sound evaluation model.

[0013] In a preferred embodiment of the present invention, the above-mentioned objective parameter values ​​include: the loudness value, roughness value, sharpness value, jitter value, and noise mean value of the second experimental noise.

[0014] Secondly, embodiments of the present invention provide a noise detection device for a range hood, comprising: a noise acquisition module for acquiring noise signals during the operation of the range hood to be tested; a feature extraction module for extracting time-frequency domain features and frequency superposition characteristics of the noise signals; a judgment module for judging the magnitude of the time-frequency domain features and a preset time-frequency domain feature threshold to obtain a first judgment result; and judging whether the frequency superposition characteristics exist to obtain a second judgment result; and a noise result output module for determining whether the range hood to be tested has objective noise based on the first judgment result and the second judgment result.

[0015] Thirdly, the present invention provides an electronic device, which includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to realize the abnormal noise detection of the range hood.

[0016] The embodiments of the present invention have the following beneficial technical effects:

[0017] This invention provides a method, apparatus, and electronic device for detecting abnormal noise in a range hood, comprising: acquiring a noise signal during the operation of the range hood under test; extracting the time-frequency domain features and frequency superposition characteristics of the noise signal; determining the magnitude of the time-frequency domain features compared to a preset time-frequency domain feature threshold to obtain a first determination result; further determining whether frequency superposition exists in the frequency superposition characteristics to obtain a second determination result; and determining whether the range hood under test has objective abnormal noise based on the first determination result and the second determination result. This method solves the problem of detecting abnormal noise in range hoods before they leave the factory by extracting and analyzing the time-frequency domain features and frequency superposition characteristics of the noise signal.

[0018] Other features and advantages disclosed in this embodiment will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0019] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for detecting abnormal noises in a range hood, provided in an embodiment of the present invention;

[0022] Figure 2 A flowchart illustrating another method for detecting abnormal noises in a range hood provided in an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of experimental results for a sound pressure time-domain characteristic provided in an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of experimental results for a sound pressure frequency domain characteristic provided in an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of an abnormal noise detection device for a range hood provided in an embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0027] Icons: 51-Noise acquisition module; 52-Feature extraction module; 53-Judgment module; 54-Abnormal noise result output module; 61-Memory; 62-Processor; 63-Bus; 64-Communication interface. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0029] Currently, noise testing for range hoods follows the new national standard, involving both semi-anechoic chamber testing and operating noise testing. However, there is a lack of methods for detecting abnormal noise before range hoods leave the factory, posing a risk of abnormal noise for range hoods using AC motors once they enter the market.

[0030] Based on this, embodiments of the present invention provide a method, apparatus, and electronic device for detecting abnormal noise in range hoods. This method solves the problem of detecting abnormal noise in range hoods before they leave the factory by extracting and analyzing the time-frequency domain features and frequency superposition features of the noise signal. To facilitate understanding of this embodiment, a detailed description of the method for detecting abnormal noise in range hoods disclosed in this invention will be provided first.

[0031] Example 1

[0032] Figure 1 This is a flowchart illustrating a method for detecting abnormal noises in a range hood, as provided in an embodiment of the present invention.

[0033] Depend on Figure 1 As seen, the method includes:

[0034] Step S101: Obtain the noise signal of the range hood under test during operation.

[0035] In this embodiment, noise signals of the range hood under test are acquired when it is operating at multiple preset speeds. These preset speeds include: low speed, high speed, and stir-fry speed.

[0036] Step S102: Extract the time-frequency domain features and frequency superposition characteristics of the above noise signal.

[0037] In this embodiment, the aforementioned time-frequency domain features include time-domain features and frequency-domain features. Here, the time domain is the analysis of the noise signal with the time axis as the coordinate axis; the frequency domain is the analysis of the noise signal with the frequency as the coordinate axis.

[0038] Furthermore, the step of extracting the frequency superposition characteristics of the noise signal includes: analyzing the frequency superposition characteristics of the noise signal using a preset wavelet analysis algorithm.

[0039] Step S103: Determine the magnitude of the above time-frequency domain features and the preset time-frequency domain feature threshold to obtain a first determination result; and determine whether the above frequency superposition characteristics have frequency superposition to obtain a second determination result.

[0040] Here, if the time-frequency domain feature is greater than the preset time-frequency domain feature threshold, it can be determined that there is a sudden change in sound in the noise signal, thereby determining that the range hood under test has an objective abnormal noise.

[0041] The aforementioned objective abnormal noises are used to indicate objectively existing abnormal sounds.

[0042] Furthermore, if it is determined that the above frequency superposition characteristics exist, multiple noise sources can be identified. For example, the vibration of the excitation duct caused by the operation of the AC motor can cause noise superposition, thereby confirming that the range hood under test has objective abnormal noise.

[0043] Step S104: Based on the first judgment result and the second judgment result, determine whether the range hood to be tested has any objective abnormal noise.

[0044] This invention provides a method for detecting abnormal noise in a range hood, comprising: acquiring a noise signal during the operation of the range hood under test; extracting the time-frequency domain features and frequency superposition characteristics of the noise signal; determining the magnitude of the time-frequency domain features compared to a preset time-frequency domain feature threshold to obtain a first determination result; further determining whether frequency superposition exists in the frequency superposition characteristics to obtain a second determination result; and determining whether the range hood under test has objective abnormal noise based on the first determination result and the second determination result. This method solves the problem of abnormal noise detection for range hoods before they leave the factory by extracting and analyzing the time-frequency domain features and frequency superposition characteristics of the noise signal.

[0045] Example 2

[0046] Based on Example 1, Figure 2 This is a flowchart illustrating another method for detecting abnormal noises in a range hood, provided in an embodiment of the present invention.

[0047] Depend on Figure 2 As seen, the method includes:

[0048] Step S201: Obtain the noise signal of the range hood under test during operation.

[0049] In this embodiment, before step S201, a noise signal acquisition time range is set, so that only noise signals within the specified time range are acquired in step S201. Here, the specified time range can be 10 seconds.

[0050] Step S202: Extract the sound pressure time-domain mean, sound pressure time-domain peak, sound pressure frequency-domain mean, sound pressure frequency-domain peak, and frequency superposition characteristics of the above noise signal.

[0051] Step S203: Determine the magnitudes of the sound pressure time-domain mean, the sound pressure time-domain peak value, and the preset sound pressure envelope time-domain line, respectively; and determine and compare the magnitudes of the sound pressure frequency-domain mean, the sound pressure frequency-domain peak value, and the preset sound pressure frequency-domain envelope line, respectively, to obtain a first determination result; and determine whether the frequency superposition characteristic exists, to obtain a second determination result.

[0052] In actual operation, the method includes the following steps A1-A4 before step S203:

[0053] Step A1: Obtain the first experimental noise of multiple experimental tobacco machines under different operating conditions.

[0054] Step A2: Preprocess the first experimental noise to obtain the first preprocessed noise.

[0055] In this embodiment, step A2 includes: screening the first experimental noise and removing abnormal noise from the first experimental noise.

[0056] Step A3: Filter the above-mentioned first preprocessed noise into experimental time-domain noise and experimental frequency-domain noise.

[0057] Step A4: Perform convolution calculations on the time-domain noise and frequency-domain noise of the above experiments to obtain the time-domain envelope of the mean and peak sound pressure levels and the frequency-domain envelope of the mean and peak sound pressure levels.

[0058] In practice, the convolution process takes the log-Mel spectrum after time-frequency masking as input, scans the convolution kernel on the spectrum, and multiplies the corresponding terms to obtain the output.

[0059] Furthermore, using the log-Mel spectrum after time-frequency masking as input, the convolution kernel is scanned across the spectrum using the following formula, and the corresponding terms are multiplied together to obtain the output:

[0060]

[0061] Where x(t) is the first preprocessing noise mentioned above, h(t) is the convolution kernel, y(t) is the output, and p is the time step.

[0062] Step S204: Based on the first judgment result and the second judgment result, determine whether the range hood to be tested has any objective abnormal noise.

[0063] For ease of understanding, Figure 3 A schematic diagram of experimental results for a sound pressure time-domain characteristic provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of experimental results for a sound pressure frequency domain characteristic provided in an embodiment of the present invention.

[0064] In this embodiment, after step S204, the method further includes the following steps B1-B2:

[0065] Step B1: If it is determined that there is no objective abnormal noise from the range hood to be tested, the noise signal is input into the preset subjective sound evaluation model, and the subjective score of the noise signal is output; the subjective sound evaluation model is constructed based on the experimental noise and the subjective score corresponding to the experimental noise.

[0066] In this embodiment, constructing the above-mentioned subjective sound evaluation model includes the following steps C1-C6:

[0067] Step C1: Obtain the second experimental noise from multiple experimental tobacco machines under different operating conditions.

[0068] Step C2: Preprocess the above-mentioned second experimental noise to obtain the second preprocessed noise.

[0069] In actual operation, the operating principle of step C2 above can be found in step A2 above, and will not be repeated here.

[0070] Step C3: Extract the objective parameter values ​​of the second preprocessed noise and score the second preprocessed noise using preset noise analysis software to obtain the scoring results; the objective parameter values ​​are used to indicate the noise characteristic values ​​of the second preprocessed noise.

[0071] Here, the aforementioned objective parameter values ​​include: the loudness value, roughness value, sharpness value, jitter value, and noise mean of the second experimental noise; the step of the noise analysis software scoring the second pre-processed noise can also be manually scored by multiple operators.

[0072] Furthermore, since multiple operators perform manual scoring, there are multiple scoring results. After obtaining the scoring results, the total variance is calculated using the sum of squared deviations to calculate the variance of the above scoring results, and the scoring results with variances less than a preset value are selected as the final scoring results.

[0073] Step C4: Perform a correlation analysis between the above objective parameter values ​​and the above scoring results to obtain the correlation degree.

[0074] Step C5: From the above objective parameter values, filter the target objective parameter values ​​whose relevance is greater than the preset threshold.

[0075] Step C6: Determine the above-mentioned subjective sound evaluation model based on the objective parameter values ​​of the above targets.

[0076] In this embodiment, step C6 includes: First, performing multivariate nonlinear fitting on the target objective parameter values ​​to obtain a preliminary prediction model. Then, performing correlation verification on the preliminary prediction model based on preset verification noise to obtain a verification error. Finally, determining whether the verification error is less than or equal to a preset error threshold; if so, determining the preliminary prediction model as the subjective sound evaluation model.

[0077] Step B2: Based on the relationship between the above subjective score and the preset subjective score threshold, determine whether the range hood to be tested has subjective noise.

[0078] This invention provides a method for detecting abnormal noise in a range hood, comprising: acquiring a noise signal during the operation of the range hood under test; extracting the sound pressure level (SPL) time-domain mean, sound pressure level (SPL) time-domain peak, sound pressure level (SPL) frequency-domain mean, sound pressure level (SPL) frequency-domain peak, and frequency superposition characteristics of the noise signal; determining the magnitudes of the SPL time-domain mean and SPL time-domain peak compared to a preset sound pressure envelope time-domain line, and determining and comparing the magnitudes of the SPL frequency-domain mean and SPL frequency-domain peak compared to the preset sound pressure envelope, to obtain a first determination result; further determining whether frequency superposition exists in the frequency superposition characteristics, to obtain a second determination result; and determining whether the range hood under test has objective abnormal noise based on the first determination result and the second determination result. This method improves the accuracy of abnormal noise detection of range hoods before they leave the factory by extracting and analyzing the SPL time-domain mean, SPL time-domain peak, SPL frequency-domain mean, SPL frequency-domain peak, and frequency superposition characteristics of the noise signal.

[0079] Example 3

[0080] Figure 5 This is a schematic diagram of the structure of an abnormal noise detection device for a range hood provided in an embodiment of the present invention.

[0081] Depend on Figure 5 As seen, the device includes:

[0082] The noise acquisition module 51 is used to acquire the noise signal of the range hood under test during operation.

[0083] The feature extraction module 52 is used to extract the time-frequency domain features and frequency superposition characteristics of the noise signal.

[0084] The judgment module 53 is used to judge the magnitude of the above time-frequency domain features and the preset time-frequency domain feature threshold to obtain a first judgment result; and to judge whether the above frequency superposition characteristics have frequency superposition to obtain a second judgment result.

[0085] The abnormal noise result output module 54 is used to determine whether the range hood to be tested has objective abnormal noise based on the first judgment result and the second judgment result.

[0086] The noise acquisition module 51, feature extraction module 52, judgment module 53, and abnormal noise result output module 54 are connected in sequence.

[0087] In one embodiment, the feature extraction module 52 is further used to extract the sound pressure time-domain mean, sound pressure time-domain peak, sound pressure frequency-domain mean, sound pressure frequency-domain peak, and frequency superposition characteristics of the noise signal; the judgment module 53 is further used to judge the magnitude of the sound pressure time-domain mean, the sound pressure time-domain peak and a preset sound pressure envelope time-domain line respectively, and to judge and compare the magnitude of the sound pressure frequency-domain mean, the sound pressure frequency-domain peak and a preset sound pressure frequency-domain envelope respectively, to obtain a first judgment result.

[0088] In one embodiment, the feature extraction module 52 is further used to analyze the frequency superposition characteristics of the noise signal using a preset wavelet analysis algorithm.

[0089] In one embodiment, the device further includes an envelope determination module; the envelope determination module is used to acquire first experimental noise from multiple experimental tobacco machines under different operating states; preprocess the first experimental noise to obtain first preprocessed noise; filter the first preprocessed noise into experimental time-domain noise and experimental frequency-domain noise; perform convolution calculations on the experimental time-domain noise and experimental frequency-domain noise respectively to obtain the sound pressure average and peak time-domain envelope and the sound pressure average and peak frequency-domain envelope; determine the sound pressure envelope time-domain line based on the sound pressure average and peak time-domain envelope, and determine the sound pressure frequency-domain envelope based on the sound pressure average and peak frequency-domain envelope.

[0090] In one embodiment, the device further includes a subjective noise determination module; the subjective noise determination module is used to input the noise signal into a preset sound subjective evaluation model and output a subjective score of the noise signal if it is determined that the range hood to be tested does not have objective abnormal noise; the sound subjective evaluation model is constructed based on the experimental noise and the subjective score corresponding to the experimental noise; and the presence or absence of subjective noise in the range hood to be tested is determined according to the relationship between the subjective score and the preset subjective score threshold.

[0091] In one embodiment, the device further includes a subjective noise determination module, which is used to acquire second experimental noise from multiple experimental smoke machines under different operating states; preprocess the second experimental noise to obtain second preprocessed noise; extract objective parameter values ​​from the second preprocessed noise and score the second preprocessed noise using preset noise analysis software to obtain a scoring result; the objective parameter values ​​are used to indicate the noise characteristic values ​​of the second preprocessed noise; perform correlation analysis between the objective parameter values ​​and the scoring result to obtain a correlation degree; select target objective parameter values ​​from the objective parameter values ​​whose correlation degree is greater than a preset threshold; and determine the sound subjective evaluation model based on the target objective parameter values.

[0092] In one embodiment, the above-mentioned device further includes a subjective noise determination module, which is also used to perform multivariate nonlinear fitting on the above-mentioned objective parameter values ​​to obtain a preliminary prediction model; perform correlation verification on the above-mentioned preliminary prediction model based on a preset verification noise to obtain a verification error; determine whether the above-mentioned verification error is less than or equal to a preset error threshold; if so, determine the above-mentioned preliminary prediction model as the above-mentioned subjective sound evaluation model.

[0093] The abnormal noise detection device for range hoods provided in this embodiment of the invention has the same technical features as the abnormal noise detection method for range hoods provided in the above embodiments, and therefore can solve the same technical problems and achieve the same technical effects. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0094] Example 4

[0095] This embodiment provides an electronic device, including a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the steps of a method for detecting abnormal noises from a range hood.

[0096] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of a method for detecting abnormal noises from a range hood.

[0097] See Figure 6 The diagram shows the structure of an electronic device, which includes a memory 61 and a processor 62. The memory 61 stores a computer program that can run on the processor 62. When the processor executes the computer program, it implements the steps provided by the above-mentioned method for detecting abnormal noises from a range hood.

[0098] like Figure 6As shown, the device also includes a bus 63 and a communication interface 64. The processor 62, the communication interface 64 and the memory 61 are connected via the bus 63. The processor 62 is used to execute executable modules, such as computer programs, stored in the memory 61.

[0099] The memory 61 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 64 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0100] Bus 63 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0101] The memory 61 stores the program, and the processor 62 executes the program after receiving the execution instruction. The method executed by the abnormal noise detection device of the range hood disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 62, or implemented by the processor 62. The processor 62 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 62 or by instructions in the form of software. The processor 62 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this invention can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 61, and processor 62 reads information from memory 61 and, in conjunction with its hardware, completes the steps of the above method.

[0102] Furthermore, this embodiment of the invention also provides a machine-readable storage medium storing machine-executable instructions. When these machine-executable instructions are invoked and executed by the processor 62, they cause the processor 62 to implement the above-mentioned method for detecting abnormal noises from a range hood.

[0103] The electronic devices and computer-readable storage media provided in the embodiments of the present invention have the same technical features, so they can also solve the same technical problems and achieve the same technical effects.

[0104] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0105] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

Claims

1. A method for detecting abnormal noise in a range hood, characterized in that, include: Acquire the noise signal of the range hood under test during operation; Extract the time-frequency domain features and frequency superposition characteristics of the noise signal; The first judgment result is obtained by determining the magnitude of the time-frequency domain feature and the preset time-frequency domain feature threshold; and the second judgment result is obtained by determining whether the frequency superposition characteristic has frequency superposition. Based on the first judgment result and the second judgment result, determine whether the range hood to be tested has any objective abnormal noise; The steps for extracting the time-frequency domain features and frequency superposition characteristics of the noise signal include: Extract the sound pressure time-domain mean, sound pressure time-domain peak, sound pressure frequency-domain mean, sound pressure frequency-domain peak, and frequency superposition characteristics of the noise signal; The step of determining the magnitude of the time-frequency domain feature and a preset time-frequency domain feature threshold to obtain a first determination result includes: The magnitudes of the sound pressure time-domain mean and the sound pressure time-domain peak are respectively compared with the preset sound pressure envelope time-domain line, and the magnitudes of the sound pressure frequency-domain mean and the sound pressure frequency-domain peak are respectively compared with the preset sound pressure frequency-domain envelope line to obtain a first judgment result; Before the steps of determining the magnitudes of the sound pressure time-domain mean and the sound pressure time-domain peak value relative to a preset sound pressure envelope time-domain line, and comparing the magnitudes of the sound pressure frequency-domain mean and the sound pressure frequency-domain peak value relative to a preset sound pressure frequency-domain envelope line to obtain a first determination result, the method includes: The first experimental noise of multiple experimental tobacco machines under different operating conditions was obtained; The first experimental noise is preprocessed to obtain the first preprocessed noise; The first preprocessed noise is filtered into experimental time-domain noise and experimental frequency-domain noise; Convolution calculations are performed on the experimental time-domain noise and experimental frequency-domain noise respectively to obtain the time-domain envelope of the mean sound pressure level and the peak sound pressure level, and the frequency-domain envelope of the mean sound pressure level and the peak sound pressure level. In the convolution calculation, the log-Mel spectrum after time-frequency masking is used as input, the convolution kernel is scanned on the spectrum, and the corresponding terms are multiplied to obtain the output. The sound pressure envelope time domain line is determined based on the sound pressure average and peak time domain envelope, and the sound pressure frequency domain envelope is determined based on the sound pressure average and peak frequency domain envelope.

2. The method for detecting abnormal noise in a range hood according to claim 1, characterized in that, The step of extracting the frequency superposition characteristics of the noise signal includes: The frequency superposition characteristics of the noise signal are analyzed using a preset wavelet analysis algorithm.

3. The method for detecting abnormal noise in a range hood according to claim 1, characterized in that, After determining whether the range hood to be tested has objective abnormal noise based on the first judgment result and the second judgment result, the method includes: If it is determined that the range hood under test does not have any objective abnormal noise, the noise signal is input into a preset subjective sound evaluation model, and the subjective score of the noise signal is output; the subjective sound evaluation model is constructed based on the experimental noise and the subjective score corresponding to the experimental noise; Based on the relationship between the subjective score and the preset subjective score threshold, it is determined whether the range hood to be tested has subjective noise.

4. The method for detecting abnormal noise in a range hood according to claim 3, characterized in that, The steps for constructing the subjective sound evaluation model include: Secondary experimental noise was obtained from multiple experimental tobacco machines under different operating conditions; The second experimental noise is preprocessed to obtain the second preprocessed noise; The objective parameter values ​​of the second preprocessed noise are extracted, and the second preprocessed noise is scored using preset noise analysis software to obtain the scoring result; the objective parameter values ​​are used to indicate the noise characteristic values ​​of the second preprocessed noise. A correlation analysis is performed between the objective parameter values ​​and the scoring results to obtain the correlation degree. From the objective parameter values, select target objective parameter values ​​whose relevance is greater than a preset threshold; The subjective evaluation model of the sound is determined based on the objective parameter values ​​of the target.

5. The method for detecting abnormal noise in a range hood according to claim 4, characterized in that, The steps for determining the subjective sound evaluation model based on the target objective parameter values ​​include: The target objective parameter values ​​are subjected to multivariate nonlinear fitting to obtain a preliminary prediction model; The correlation of the preliminary prediction model is verified based on the preset verification noise to obtain the verification error; Determine whether the verification error is less than or equal to a preset error threshold; If so, the preliminary prediction model is determined as the subjective sound evaluation model.

6. The method for detecting abnormal noise in a range hood according to claim 4, characterized in that, The objective parameter values ​​include: the loudness value, roughness value, sharpness value, jitter value, and noise mean value of the second experimental noise.

7. A noise detection device for a range hood, characterized in that, include: The noise acquisition module is used to acquire the noise signal of the range hood under test during operation; The feature extraction module is used to extract the time-frequency domain features and frequency superposition characteristics of the noise signal; The judgment module is used to judge the magnitude of the time-frequency domain feature and the preset time-frequency domain feature threshold to obtain a first judgment result; and to judge whether the frequency superposition characteristic has frequency superposition to obtain a second judgment result. The abnormal noise result output module is used to determine whether the range hood under test has objective abnormal noise based on the first judgment result and the second judgment result; The feature extraction module is also used to extract the sound pressure time-domain mean, sound pressure time-domain peak, sound pressure frequency-domain mean, sound pressure frequency-domain peak, and frequency superposition characteristics of the noise signal; The judgment module is further configured to judge the magnitudes of the sound pressure time-domain mean, the sound pressure time-domain peak value, and the preset sound pressure envelope time-domain line, respectively, and to judge and compare the magnitudes of the sound pressure frequency-domain mean, the sound pressure frequency-domain peak value, and the preset sound pressure frequency-domain envelope line, respectively, to obtain a first judgment result; The judgment module is further configured to acquire first experimental noise from multiple experimental tobacco machines under different operating states; preprocess the first experimental noise to obtain first preprocessed noise; filter the first preprocessed noise into experimental time-domain noise and experimental frequency-domain noise; perform convolution calculations on the experimental time-domain noise and experimental frequency-domain noise respectively to obtain the time-domain envelope of the sound pressure average and peak values ​​and the frequency-domain envelope of the sound pressure average and peak values; wherein, when performing the convolution calculation, the log-Mel spectrum after time-frequency masking is used as input, the convolution kernel is scanned on the spectrum, and the corresponding terms are multiplied to obtain the output; the sound pressure envelope time-domain line is determined based on the sound pressure average and peak value time-domain envelope, and the sound pressure frequency-domain envelope is determined based on the sound pressure average and peak value frequency-domain envelope.

8. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to achieve the abnormal noise detection of the range hood according to any one of claims 1 to 6.

Images