Abnormal sound recognition and audio injection control method and system for range hood

Abstract

The present invention provides a control method and system for abnormal sound recognition and audio injection of a range hood, including: obtaining a target sound signal generated by a target range hood during operation; performing wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; judging whether the target sound signal is abnormal noise based on the ratio between a preset feature vector and a target feature vector; if so, determining a target control sound corresponding to the target feature vector in a preset control sound database, and masking the target sound signal by playing the target control sound; the preset control sound database includes multiple control sounds, each of which corresponds to a feature vector range. The present invention alleviates the technical problems existing in the prior art that abnormal sounds cannot be effectively recognized and noise reduction processing cannot be performed on the generated abnormal sounds.

Description

Technical Field

[0001] The present invention relates to the technical field of range hood control, and in particular to a method and system for controlling abnormal sound recognition and audio injection of a range hood. Background Art

[0002] With the popularization and development of intelligent technology, more and more kitchen heating products are pursuing intelligence and high-end. As a member of household appliances that are closely related to people's lives, the performance of range hoods has gradually become the focus of people's attention. At present, during the operation of range hoods, other abnormal sound characteristics such as buzzing will be generated due to uncertain factors, and the range hoods in the existing technology cannot effectively identify abnormal sounds, and cannot perform noise reduction processing for the generated abnormal sounds. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a method and system for controlling abnormal sound recognition and audio injection of a range hood, so as to alleviate the technical problems existing in the prior art of being unable to effectively recognize abnormal sounds and unable to perform noise reduction processing on the generated abnormal sounds.

[0004] In the first aspect, an embodiment of the present invention provides a method for controlling abnormal sound recognition and audio injection of a range hood, comprising: obtaining a target sound signal generated by a target range hood during operation; the target sound signal comprises a target sound spectrum signal and a target vibration signal; performing wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector comprises a target sound spectrum peak value and a target vibration amplitude; based on a ratio between a preset feature vector and the target feature vector, determining whether the target sound signal is abnormal noise; if so, determining a target control sound corresponding to the target feature vector in a preset control sound database, and masking the target sound signal by playing the target control sound; the preset control sound database comprises multiple control sounds, each control sound corresponding to a feature vector range.

[0005] Furthermore, the method also includes: obtaining a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal; performing wavelet packet decomposition on the background sound signal based on wavelet packet analysis to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude.

[0006] Further, the preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude; based on the ratio between the preset feature vector and the target feature vector, judging whether the target sound signal is abnormal noise includes: judging whether the ratio of the preset sound spectrum peak to the target sound spectrum peak is less than a first preset threshold; if so, determining that the target sound signal is abnormal noise; if not, judging whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than a second preset threshold; if so, determining that the target sound signal is abnormal noise.

[0007] Furthermore, the method also includes: if the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold, and the ratio of the preset vibration amplitude to the target vibration amplitude is greater than or equal to the second preset threshold, then determining that the target sound signal is a normal sound signal.

[0008] In a second aspect, an embodiment of the present invention further provides a control system for abnormal sound recognition and audio injection of a range hood, comprising: an acquisition module, an analysis module, a judgment module and a playback module; wherein the acquisition module is used to acquire a target sound signal generated by a target range hood during operation; the target sound signal comprises a target sound spectrum signal and a target vibration signal; the analysis module is used to perform wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector comprises a target sound spectrum peak value and a target vibration amplitude; the judgment module is used to judge whether the target sound signal is abnormal noise based on a ratio between a preset feature vector and the target feature vector; the playback module is used to determine a target control sound corresponding to the target feature vector in a preset control sound database if the target sound signal is abnormal noise, and mask the target sound signal by playing the target control sound; the preset control sound database comprises a plurality of control sounds, each control sound corresponding to a feature vector range.

[0009] Furthermore, the acquisition module is also used to: acquire a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal; perform wavelet packet decomposition on the background sound signal based on wavelet packet analysis to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude.

[0010] Furthermore, the preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude; the judgment module is also used to: judge whether the ratio of the preset sound spectrum peak to the target sound spectrum peak is less than a first preset threshold; if so, determine that the target sound signal is abnormal noise; if not, judge whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than a second preset threshold; if so, determine that the target sound signal is abnormal noise.

[0011] Furthermore, the judgment module is also used to: if the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold, and the ratio of the preset vibration amplitude to the target vibration amplitude is greater than or equal to the second preset threshold, then determine that the target sound signal is a normal sound signal.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, wherein the program code enables the processor to execute the method described in the first aspect.

[0014] The present invention provides a method and system for controlling abnormal sound recognition and audio injection of a range hood. The sound signal generated by a target range hood during operation is processed by a wavelet packet analysis method to obtain a target feature vector. Then, a preset feature vector is set to determine whether the sound signal is abnormal noise, and a suitable control sound is selected to mask the abnormal noise. This can achieve the technical effect of reducing noise interference from the range hood and improving sound quality, and alleviates the technical problems in the prior art of being unable to effectively recognize abnormal sounds and being unable to perform noise reduction processing on the generated abnormal sounds. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for controlling abnormal sound recognition and audio injection of a range hood provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of a control system for abnormal sound recognition and audio injection of a range hood provided by an embodiment of the present invention;

[0018] Figure 3 A schematic diagram of another control system for abnormal sound recognition and audio injection of a range hood provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1:

[0021] Figure 1 1 is a flow chart of a method for controlling abnormal sound recognition and audio injection of a range hood according to an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:

[0022] Step S102, obtaining a target sound signal generated by a target range hood during operation; the target sound signal includes a target sound spectrum signal and a target vibration signal.

[0023] Optionally, a target sound spectrum signal and a target vibration signal of the target range hood when it is in operation are detected by a sound sensor and a piezoelectric acoustic vibration sensor installed on the target range hood.

[0024] Step S104, performing wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector includes a target sound spectrum peak value and a target vibration amplitude.

[0025] Specifically, the target sound signal is decomposed into wavelet packets based on wavelet packet analysis theory, and then the target feature vector can be extracted through a neural network algorithm.

[0026] Step S106: judging whether the target sound signal is abnormal noise based on the ratio between the preset feature vector and the target feature vector.

[0027] Step S108, if the target sound signal is abnormal noise, determine the target control sound corresponding to the target feature vector in the preset control sound database, and mask the target sound signal by playing the target control sound; the preset control sound database includes multiple control sounds, each control sound corresponds to a feature vector range.

[0028] In an embodiment of the present invention, a plurality of different types of control sounds are pre-stored in a preset control sound database, and the same type of control sound includes different small types of control sounds. For example, different water flow sounds (types) such as streams, waterfalls and springs (small types) can be stored, and there are more than 5 small types of sound samples under the same type, and then each small type of control sound corresponds to a feature vector range. After determining that the target sound signal is abnormal noise, the corresponding control sound is selected according to the corresponding relationship in the preset control sound database and the feature vector of the target sound signal, and the masking effect of the target sound signal is achieved by playing the control sound, thereby achieving the technical effect of reducing noise.

[0029] The present invention provides a method for controlling abnormal sound recognition and audio injection of a range hood. The sound signal generated by a target range hood during operation is processed by a wavelet packet analysis method to obtain a target feature vector. Then, a preset feature vector is set to determine whether the sound signal is abnormal noise, and a suitable control sound is selected to mask the abnormal noise. This can achieve the technical effect of reducing noise interference from the range hood and improving sound quality, and alleviates the technical problems in the prior art of being unable to effectively recognize abnormal sounds and being unable to perform noise reduction processing on the generated abnormal sounds.

[0030] Optionally, in the embodiment of the present invention, a step of setting a preset feature vector is further included, which specifically includes the following steps:

[0031] Acquire a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal;

[0032] The background sound signal is decomposed by wavelet packet based on wavelet packet analysis to obtain a preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude.

[0033] Specifically, step S106 also includes the following steps:

[0034] Step S1061, determining whether the ratio of the preset sound spectrum peak to the target sound spectrum peak is less than a first preset threshold; if yes, executing step S1062; if no, executing step S1063.

[0035] Step S1062: determine that the target sound signal is abnormal noise.

[0036] Step S1063, determining whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than a second preset threshold; if yes, executing step S1064; if no, executing step S1065.

[0037] Step S1064: determine that the target sound signal is abnormal noise.

[0038] Step S1065: determine whether the target sound signal is a normal sound signal.

[0039] Optionally, in the embodiment of the present invention, the sound spectrum peak value and vibration amplitude corresponding to the range hood when generating different abnormal noises are collected and recorded as Ln and Kn respectively, and the characteristic vector of the generated abnormal sound signal is compared and analyzed with the characteristic vector of the signal generated when the range hood is running normally, and its characteristics are recorded to provide a data comparison basis for the subsequent determination threshold, and then determine the first preset threshold and the second preset threshold. For example, the first preset threshold is set to 0.9 and the second preset threshold is set to 1, then the judgment process of whether the target sound signal is abnormal noise can be shown in Table 1:

[0040] Table 1 Abnormal noise judgment process

[0041]

[0042] In the table, L0 is the preset sound spectrum peak, LP is the target sound spectrum peak, K0 is the preset vibration amplitude, and KP is the target vibration amplitude.

[0043] From the above description, it can be seen that the embodiment of the present invention provides a method for identifying abnormal sounds of a range hood and controlling audio injection. In view of the problem that most of the methods for analyzing abnormal noise in the prior art mainly rely on human experience to judge the analysis method, and lack effective and scientific theoretical methods to guide the research basis, the embodiment of the present invention utilizes wavelet packet analysis theory combined with a neural network algorithm, which can decompose the signal into parts and extract effective values ​​with more accurate values; it plays and controls the sound by using audio injection to mask the abnormal sound, thereby reducing noise and improving sound quality; it alleviates the technical problems of the prior art in that abnormal sounds cannot be effectively identified and noise reduction processing cannot be performed on the generated abnormal sounds.

[0044] Embodiment 2:

[0045] Figure 2 Schematic diagram of a control system for abnormal sound recognition and audio injection of a range hood according to an embodiment of the present invention. Figure 2 As shown, the system includes: an acquisition module 10, an analysis module 20, a judgment module 30 and a playback module 40.

[0046] The acquisition module 10 is used to acquire a target sound signal generated by a target range hood during operation; the target sound signal includes a sound spectrum signal and a vibration signal.

[0047] The analysis module 20 is used to perform wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector includes a sound spectrum peak value and a vibration amplitude.

[0048] The judgment module 30 is used to judge whether the target sound signal is abnormal noise based on the ratio between the preset feature vector and the target feature vector.

[0049] The playing module 40 is used to determine the target control sound corresponding to the target feature vector in the preset control sound database if the target sound signal is abnormal noise, and mask the target sound signal by playing the target control sound; the preset control sound database includes multiple control sounds, each control sound corresponds to a feature vector range.

[0050] The present invention provides a control system for abnormal sound recognition and audio injection of a range hood. The sound signal generated by a target range hood during operation is processed by a wavelet packet analysis method to obtain a target feature vector. Then, a preset feature vector is set to determine whether the sound signal is abnormal noise, and a suitable control sound is selected to mask the abnormal noise. This can achieve the technical effect of reducing noise interference from the range hood and improving sound quality, and alleviates the technical problems in the prior art of being unable to effectively recognize abnormal sounds and being unable to perform noise reduction processing on the generated abnormal sounds.

[0051] Optionally, the acquisition module 10 is further used for:

[0052] Acquire a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal;

[0053] The background sound signal is decomposed by wavelet packet based on wavelet packet analysis to obtain a preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude.

[0054] Optionally, the judging module 30 is further configured to:

[0055] Determine whether the ratio of the preset sound spectrum peak to the target sound spectrum peak is less than a first preset threshold; if so, determine that the target sound signal is abnormal noise;

[0056] If not, it is determined whether the ratio of the preset vibration amplitude to the vibration amplitude is less than a second preset threshold; if yes, it is determined that the target sound signal is abnormal noise.

[0057] Optionally, the judging module 30 is further configured to:

[0058] If the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold, and the ratio of the preset vibration amplitude to the vibration amplitude is greater than or equal to the second preset threshold, the target sound signal is determined to be a normal sound signal.

[0059] Embodiment three:

[0060] Figure 3FIG. 1 is a schematic diagram of another control system for abnormal sound recognition and audio injection of a range hood according to an embodiment of the present invention. Figure 3 As shown, the system includes a wavelet packet analysis module, an audio injection module, an audio playback module, a vibration receiver and a noise sensor.

[0061] Specifically, Figure 3 As shown, the wavelet packet analysis module and the audio injection module are both integrated and installed on the integrated panel of the range hood. The wavelet packet analysis module is connected to the audio injection module, the noise sensor, and the vibration receiver respectively, while the audio injection module is connected to the audio playback module.

[0062] The noise sensor and vibration receiver are integrated and installed at the upper part of the inner shell of the range hood, and are also installed on the other three sides. The audio playback module is located at the four bottom corners of the top, all in the shape of a rectangular parallelepiped.

[0063] Specifically, the wavelet packet analysis module has a built-in neural network algorithm, which mainly collects the vibration amplitude and noise peak of the sound in the time domain and frequency domain analysis states as the main feature vectors.

[0064] The audio injection module integrates most of the audible audio frequencies, such as natural sounds like running water, rain, wind, and various artificial synthetic sounds like musical instruments like piano and guitar. Each audio frequency corresponds to different vibration peak and noise peak characteristics.

[0065] The audio playback module includes speakers, which are installed on the four corners of the top of the range hood and are in the shape of a rectangular parallelepiped, with the sound diffusion direction all facing outwards.

[0066] The vibration receiver is a piezoelectric acoustic vibration sensor, which is arranged around the inner wall of the range hood and is used to detect the vibration amplitude.

[0067] The noise sensor is arranged at one side of the vibration receiver and is used to collect the noise spectrum generated by the operation of the range hood.

[0068] First, based on the wavelet packet theory, the vibration amplitude and noise peak value of the normal operation of the range hood are collected as feature vectors through the neural network algorithm, recorded as L0 and K0 and stored in the module. At the same time, based on the same method, the vibration amplitude and noise peak signals of the range hood with different abnormal sounds are recorded as L1-Ln and K1-Kn respectively, and the recorded abnormal sound feature vectors Ln and Kn are compared with L0 and K0 respectively. Based on this, the threshold judgment condition is determined and set in the built-in core module;

[0069] When the range hood is running, the vibration characteristics of the range hood structure are collected through the vibration receiver set on the inner shell of the range hood, and the noise value generated is collected in real time through the noise sensor, and the collected information is passed to the wavelet packet analysis module. The wavelet packet analysis module extracts the signals therein, mainly the noise peak value LP and the vibration amplitude KP, and decomposes and extracts the two signal feature vectors step by step, and analyzes and compares them with the built-in initial values ​​L0 and K0;

[0070] Then the collected LP and KP characteristic vector signal values ​​are compared and analyzed with the initial values ​​one by one. When the ratio of L0 / LP is greater than or equal to 0.9 and satisfies K0 / KP>=1, it is determined that no abnormal sound is generated; otherwise, it is determined that an abnormal sound is generated, and the wavelet packet analysis module will pass the signal characteristics to the audio injection module. The control program in the audio injection module will play the corresponding characteristic control sound (such as flowing water sound, musical instrument sound, bird singing, etc.) according to the signal characteristics. The audio injection module will pass the selected control sound signal to the audio playback module. The speaker in the audio playback module located on the top of the range hood will play the selected control sound. The control sound will mask the generated abnormal sound in the time domain or frequency domain, thereby reducing the operating noise of the range hood, greatly reducing the probability of abnormal sound entering the human ear, reducing the physical and mental interference of abnormal sound on personnel, and improving the sound quality of the range hood operation.

[0071] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method in the first embodiment when executing the computer program.

[0072] The embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, wherein the program code enables the processor to execute the method in the above-mentioned embodiment 1.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling abnormal sound recognition and audio injection of a range hood, characterized in that: include: Acquire a target sound signal generated by a target range hood during operation; The target sound signal includes a target sound spectrum signal and a target vibration signal; Based on wavelet packet analysis, the target sound signal is decomposed by wavelet packet to obtain a target feature vector; the target feature vector includes a target sound spectrum peak value and a target vibration amplitude; Based on the ratio between the preset feature vector and the target feature vector, determining whether the target sound signal is abnormal noise; If yes, determining a target control sound corresponding to the target feature vector in a preset control sound database, and masking the target sound signal by playing the target control sound; The preset control sound database includes a plurality of control sounds, each of which corresponds to a feature vector range; The preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude; and the step of judging whether the target sound signal is abnormal noise based on the ratio between the preset feature vector and the target feature vector includes: Determine whether the ratio of the preset sound spectrum peak to the target sound spectrum peak is less than a first preset threshold; if yes, determine that the target sound signal is abnormal noise; If not, it is determined whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than a second preset threshold; if yes, it is determined that the target sound signal is abnormal noise.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal; The background sound signal is subjected to wavelet packet decomposition based on wavelet packet analysis to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude.

3. The method according to claim 1, characterized in that The method further comprises: If the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold, and the ratio of the preset vibration amplitude to the target vibration amplitude is greater than or equal to the second preset threshold, the target sound signal is determined to be a normal sound signal.

4. A control system for abnormal sound recognition and audio injection of a range hood, characterized in that: include: Acquisition module, analysis module, judgment module and playback module; wherein, The acquisition module is used to acquire a target sound signal generated by a target range hood during operation; the target sound signal includes a target sound spectrum signal and a target vibration signal; The analysis module is used to perform wavelet packet decomposition on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector includes a target sound spectrum peak value and a target vibration amplitude; The judging module is used to judge whether the target sound signal is abnormal noise based on the ratio between the preset feature vector and the target feature vector; The playing module is used to determine a target control sound corresponding to the target feature vector in a preset control sound database if the target sound signal is abnormal noise, and mask the target sound signal by playing the target control sound; the preset control sound database includes multiple control sounds, each control sound corresponds to a feature vector range; Wherein, the preset feature vector includes a preset sound spectrum peak and a preset vibration amplitude; and the judgment module includes: A comparison and judgment module, used to judge whether the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is less than a first preset threshold value; A first determination module, configured to determine that the target sound signal is abnormal noise when a ratio of a peak value of the preset sound spectrum to a peak value of the target sound spectrum is less than a first preset threshold; The second judgment module is used to judge whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than a second preset threshold when the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold; if so, determine that the target sound signal is abnormal noise.

5. The system according to claim 4, characterized in that The acquisition module is further used for: Acquire a background sound signal generated by the target range hood during normal operation; the background sound signal includes a background sound spectrum signal and a background vibration signal; The background sound signal is subjected to wavelet packet decomposition based on wavelet packet analysis to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude.

6. The system according to claim 4, characterized in that The judging module is further used for: If the ratio of the preset sound spectrum peak to the target sound spectrum peak is greater than or equal to the first preset threshold, and the ratio of the preset vibration amplitude to the target vibration amplitude is greater than or equal to the second preset threshold, the target sound signal is determined to be a normal sound signal.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

8. A computer-readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the method according to any one of claims 1 to 3.

Images