CN114299990A - Abnormal sound recognition and audio injection control method and system for range hood - Google Patents
Abnormal sound recognition and audio injection control method and system for range hood Download PDFInfo
- Publication number
- CN114299990A CN114299990A CN202210105179.1A CN202210105179A CN114299990A CN 114299990 A CN114299990 A CN 114299990A CN 202210105179 A CN202210105179 A CN 202210105179A CN 114299990 A CN114299990 A CN 114299990A
- Authority
- CN
- China
- Prior art keywords
- target
- sound
- preset
- sound signal
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000002347 injection Methods 0.000 title claims abstract description 26
- 239000007924 injection Substances 0.000 title claims abstract description 26
- 230000005236 sound signal Effects 0.000 claims abstract description 97
- 239000013598 vector Substances 0.000 claims abstract description 70
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 9
- 238000001228 spectrum Methods 0.000 claims description 52
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 230000001276 controlling effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000873 masking effect Effects 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 5
- 239000000243 solution Substances 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Ventilation (AREA)
Abstract
本发明提供了一种吸油烟机的异音识别及音频注入的控制方法和系统，包括：获取目标吸油烟机在运行时产生的目标声音信号；基于小波包分析对目标声音信号进行小波包分解，得到目标特征向量；基于预设特征向量与目标特征向量之间的比值，判断目标声音信号是否为异常噪音；如果是，则在预设调控声数据库中确定与目标特征向量对应的目标调控声，并通过播放目标调控声对目标声音信号进行掩蔽；预设调控声数据库包括多个调控声，每个调控声对应一个特征向量范围。本发明缓解了现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。
The invention provides a method and a system for the control of abnormal sound recognition and audio injection of a range hood, including: acquiring a target sound signal generated by a target range hood during operation; and performing wavelet packet decomposition on the target sound signal based on wavelet packet analysis. , obtain the target feature vector; based on the ratio between the preset feature vector and the target feature vector, determine whether the target sound signal is abnormal noise; if so, determine the target sound control sound corresponding to the target feature vector in the preset sound control sound database , and mask the target sound signal by playing the target control sound; the preset control sound database includes a plurality of control sounds, and each control sound corresponds to a feature vector range. The invention alleviates the technical problems existing in the prior art that abnormal sounds cannot be effectively identified and noise reduction processing cannot be performed for the generated abnormal sounds.
Description
技术领域technical field
本发明涉及吸油烟机控制技术领域，尤其是涉及一种吸油烟机的异音识别及音频注入的控制方法和系统。The invention relates to the technical field of range hood control, in particular to a control method and system for abnormal sound recognition and audio injection of a range hood.
背景技术Background technique
随着智能化技术的普及和发展，越来越多的厨热产品追求智能化、高端化。吸油烟机作为与人们生活密切的家电一员，其性能已经逐渐成为人们关注的重点。目前，吸油烟机运行过程中会由于不确定因素会产生嗡嗡等其他异音特征，而现有技术中的吸油烟机还不能有效识别异音，以及不能针对产生的异音进行降噪处理。With the popularization and development of intelligent technology, more and more kitchen heating products are pursuing intelligent and high-end products. As a household appliance that is closely related to people's lives, the performance of the range hood has gradually become the focus of people's attention. At present, during the operation of the range hood, other abnormal sound features such as buzzing may be generated due to uncertain factors, and the range hood in the prior art cannot effectively identify the abnormal sound, and cannot perform noise reduction processing for the generated abnormal sound. .
发明内容SUMMARY OF THE INVENTION
有鉴于此，本发明的目的在于提供一种吸油烟机的异音识别及音频注入的控制方法和系统，以缓解现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。In view of this, the purpose of the present invention is to provide a kind of abnormal sound recognition of a range hood and a control method and system for audio injection, so as to alleviate the inability to effectively identify the abnormal sound in the prior art and to reduce the abnormal sound generated. Technical issues of noise processing.
第一方面，本发明实施例提供了一种吸油烟机的异音识别及音频注入的控制方法，包括：获取目标吸油烟机在运行时产生的目标声音信号；所述目标声音信号包括目标声音频谱信号和目标振动信号；基于小波包分析对所述目标声音信号进行小波包分解，得到目标特征向量；所述目标特征向量包括目标声音频谱峰值和目标振动幅值；基于预设特征向量与所述目标特征向量之间的比值，判断所述目标声音信号是否为异常噪音；如果是，则在预设调控声数据库中确定与所述目标特征向量对应的目标调控声，并通过播放所述目标调控声对所述目标声音信号进行掩蔽；所述预设调控声数据库包括多个调控声，每个调控声对应一个特征向量范围。In a first aspect, an embodiment of the present invention provides a method for recognizing abnormal sound and audio injection of a range hood, including: acquiring a target sound signal generated by a target range hood during operation; the target sound signal includes a target sound Spectral signal and target vibration signal; wavelet packet decomposition is performed on the target sound signal based on wavelet packet analysis to obtain a target feature vector; the target feature vector includes the target sound spectrum peak value and the target vibration amplitude; Determine whether the target sound signal is abnormal noise; if so, determine the target sound control sound corresponding to the target feature vector in the preset sound control sound database, and play the target sound signal by playing the target sound signal. The control sound masks the target sound signal; the preset control sound database includes a plurality of control sounds, and each control sound corresponds to a feature vector range.
进一步地，所述方法还包括：获取目标吸油烟机在正常运行时产生的背景声音信号；所述背景声音信号包括背景声音频谱信号和背景振动信号；基于小波包分析对所述背景声音信号进行小波包分解，得到所述预设特征向量；所述预设特征向量包括预设声音频谱峰值和预设振动幅值。Further, the method further includes: acquiring 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; and performing a wavelet packet analysis on the background sound signal. The wavelet packet is decomposed to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value.
进一步地，所述预设特征向量包括预设声音频谱峰值和预设振动幅值；基于预设特征向量与所述目标特征向量之间的比值，判断所述目标声音信号是否为异常噪音，包括：判断所述预设声音频谱峰值与所述目标声音频谱峰值的比值是否小于第一预设阈值；如果是，则确定所述目标声音信号为异常噪音；如果否，则判断所述预设振动幅值与所述目标振动幅值的比值是否小于第二预设阈值；如果是，则确定所述目标声音信号为异常噪音。Further, the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value; based on the ratio between the preset feature vector and the target feature vector, it is determined whether the target sound signal is abnormal noise, including : determine whether the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is less than the first preset threshold; if so, determine that the target sound signal is abnormal noise; if not, determine the preset vibration Whether the ratio of the amplitude to the target vibration amplitude is less than a second preset threshold; if so, it is determined that the target sound signal is abnormal noise.
进一步地，所述方法还包括：若所述预设声音频谱峰值与所述目标声音频谱峰值的比值大于等于所述第一预设阈值，且所述预设振动幅值与所述目标振动幅值的比值大于等于所述第二预设阈值，则确定所述目标声音信号为正常声音信号。Further, the method further includes: if the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is greater than or equal to the first preset threshold value, and the preset vibration amplitude value is equal to the target vibration amplitude value. If the ratio of the values is greater than or equal to the second preset threshold, it is determined that the target sound signal is a normal sound signal.
第二方面，本发明实施例还提供了一种吸油烟机的异音识别及音频注入的控制系统，包括：获取模块，分析模块，判断模块和播放模块；其中，所述获取模块，用于获取目标吸油烟机在运行时产生的目标声音信号；所述目标声音信号包括目标声音频谱信号和目标振动信号；所述分析模块，用于基于小波包分析对所述目标声音信号进行小波包分解，得到目标特征向量；所述目标特征向量包括目标声音频谱峰值和目标振动幅值；所述判断模块，用于基于预设特征向量与所述目标特征向量之间的比值，判断所述目标声音信号是否为异常噪音；所述播放模块，用于若所述目标声音信号为异常噪音，则在预设调控声数据库中确定与所述目标特征向量对应的目标调控声，并通过播放所述目标调控声对所述目标声音信号进行掩蔽；所述预设调控声数据库包括多个调控声，每个调控声对应一个特征向量范围。In the second aspect, the embodiment of the present invention also provides a control system for abnormal sound recognition and audio injection of a range hood, including: an acquisition module, an analysis module, a judgment module and a playback module; wherein, the acquisition module is used for Obtain the target sound signal generated by the target range hood during operation; the target sound signal includes the target sound spectrum signal and the target vibration signal; the analysis module is configured to perform wavelet packet decomposition on the target sound signal based on wavelet packet analysis , obtain the target feature vector; the target feature vector includes the target sound spectrum peak value and the target vibration amplitude value; the judgment module is used to judge the target sound based on the ratio between the preset feature vector and the target feature vector Whether the signal is abnormal noise; the playback module 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 play the target sound by playing the target sound. The control sound masks the target sound signal; the preset control sound database includes a plurality of control sounds, and each control sound corresponds to a feature vector range.
进一步地，所述获取模块，还用于：获取目标吸油烟机在正常运行时产生的背景声音信号；所述背景声音信号包括背景声音频谱信号和背景振动信号；基于小波包分析对所述背景声音信号进行小波包分解，得到所述预设特征向量；所述预设特征向量包括预设声音频谱峰值和预设振动幅值。Further, the acquisition module is also used to: acquire the 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; based on wavelet packet analysis, the background sound signal is analyzed. The sound signal is subjected to wavelet packet decomposition to obtain the preset feature vector; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value.
进一步地，所述预设特征向量包括预设声音频谱峰值和预设振动幅值；所述判断模块，还用于：判断所述预设声音频谱峰值与所述目标声音频谱峰值的比值是否小于第一预设阈值；如果是，则确定所述目标声音信号为异常噪音；如果否，则判断所述预设振动幅值与所述目标振动幅值的比值是否小于第二预设阈值；如果是，则确定所述目标声音信号为异常噪音。Further, the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value; the judgment module is further configured to: determine whether the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is less than the first preset threshold; if yes, determine that the target sound signal is abnormal noise; if not, determine whether the ratio of the preset vibration amplitude to the target vibration amplitude is less than the second preset threshold; if If yes, it is determined that the target sound signal is abnormal noise.
进一步地，所述判断模块，还用于：若所述预设声音频谱峰值与所述目标声音频谱峰值的比值大于等于所述第一预设阈值，且所述预设振动幅值与所述目标振动幅值的比值大于等于所述第二预设阈值，则确定所述目标声音信号为正常声音信号。Further, the judging module is further configured to: if the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is greater than or equal to the first preset threshold value, and the preset vibration amplitude value is the same as the If the ratio of the target vibration amplitude is greater than or equal to the second preset threshold, it is determined that the target sound signal is a normal sound signal.
第三方面，本发明实施例还提供了一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述第一方面所述的方法的步骤。In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program When implementing the steps of the method described in the first aspect above.
第四方面，本发明实施例还提供了一种具有处理器可执行的非易失的程序代码的计算机可读介质，所述程序代码使所述处理器执行上述第一方面所述方法。In a fourth aspect, an embodiment of the present invention further provides a computer-readable medium having non-volatile program code executable by a processor, where the program code enables the processor to execute the method in the first aspect.
本发明提供了一种吸油烟机的异音识别及音频注入的控制方法和系统，通过小波包分析的方法对目标吸油烟机运行时产生的声音信号进行处理，得到目标特征向量，然后通过设定预设特征向量判断该声音信号是否是异常噪音，并选择合适的调控声对异常噪音进行掩蔽，可以达到降低吸油烟机噪音干扰和提升声品质的技术效果，缓解了现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。The invention provides a method and a system for the control of abnormal sound recognition and audio injection of a range hood. A wavelet packet analysis method is used to process the sound signal generated when a target range hood is running to obtain a target feature vector. The preset feature vector is determined to determine whether the sound signal is abnormal noise, and the appropriate control sound is selected to mask the abnormal noise, which can achieve the technical effect of reducing noise interference of the range hood and improving sound quality, and alleviates the existing problems in the prior art. The technical problem that the abnormal sound cannot be effectively identified and the noise reduction processing cannot be performed for the generated abnormal sound.
附图说明Description of drawings
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.
图1为本发明实施例提供的一种吸油烟机的异音识别及音频注入的控制方法的流程图；1 is a flowchart of a method for controlling abnormal sound and audio injection of a range hood provided by an embodiment of the present invention;
图2为本发明实施例提供的一种吸油烟机的异音识别及音频注入的控制系统的示意图；2 is 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;
图3为本发明实施例提供的另一种吸油烟机的异音识别及音频注入的控制系统的示意图。FIG. 3 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.
具体实施方式Detailed ways
下面将结合附图对本发明的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
实施例一：Example 1:
图1是根据本发明实施例提供的一种吸油烟机的异音识别及音频注入的控制方法的流程图。如图1所示，该方法具体包括如下步骤：FIG. 1 is a flowchart of a method for controlling abnormal sound and audio injection of a range hood according to an embodiment of the present invention. As shown in Figure 1, the method specifically includes the following steps:
步骤S102，获取目标吸油烟机在运行时产生的目标声音信号；目标声音信号包括目标声音频谱信号和目标振动信号。Step S102, acquiring a target sound signal generated by the target range hood during operation; the target sound signal includes a target sound spectrum signal and a target vibration signal.
可选地，通过安装在目标吸油烟机上的声音传感器和压电式声振传感器检测目标吸油烟机在运行时的目标声音频谱信号和目标振动信号。Optionally, the target sound spectrum signal and the target vibration signal of the target range hood during operation are detected by a sound sensor and a piezoelectric acoustic vibration sensor installed on the target range hood.
步骤S104，基于小波包分析对目标声音信号进行小波包分解，得到目标特征向量；目标特征向量包括目标声音频谱峰值和目标振动幅值。Step S104, the target sound signal is decomposed by wavelet packet based on the wavelet packet analysis to obtain a target feature vector; the target feature vector includes the target sound spectrum peak value and the target vibration amplitude.
具体的，基于小波包分析理论对目标声音信号进行小波包分解，然后可以通过神经网络算法提取目标特征向量。Specifically, the target sound signal is decomposed by wavelet packet based on the theory of wavelet packet analysis, and then the target feature vector can be extracted by the neural network algorithm.
步骤S106，基于预设特征向量与目标特征向量之间的比值，判断目标声音信号是否为异常噪音。Step S106, based on the ratio between the preset feature vector and the target feature vector, determine whether the target sound signal is abnormal noise.
步骤S108，如果目标声音信号为异常噪音，则在预设调控声数据库中确定与目标特征向量对应的目标调控声，并通过播放目标调控声对目标声音信号进行掩蔽；预设调控声数据库包括多个调控声，每个调控声对应一个特征向量范围。Step S108, if the target sound signal is abnormal noise, determine the target sound control sound corresponding to the target feature vector in the preset sound control sound database, and mask the target sound signal by playing the target sound control sound; Each control sound corresponds to a range of eigenvectors.
在本发明实施例中，在预设调控声数据库中，预先存放多种不同类型的调控声，同一类型的调控声包括不同小种类的调控声，例如，可以存放溪流、瀑布和泉水(小种类)等不同的水流声(类型)，同一类型下的小种类的声音样本多于5个，然后将每个小种类的调控声对应于一个特征向量范围。再确定目标声音信号为异常噪音后，根据预设调控声数据库中的对应关系，和目标声音信号的特征向量，选择对应的调控声，并通过播放该调控声实现对目标声音信号的掩蔽效果，进而达到减弱噪音的技术效果。In the embodiment of the present invention, in the preset control sound database, a variety of different types of control sounds are stored in advance, and the same type of control sounds includes different small types of control sounds, for example, streams, waterfalls and springs (small types of control sounds can be stored ) and other different water flow sounds (types), there are more than 5 small types of sound samples under the same type, and then each small type of regulated sound corresponds to a feature vector range. After determining that the target sound signal is abnormal noise, select the corresponding regulation sound according to the corresponding relationship in the preset regulation sound database and the feature vector of the target sound signal, and realize the masking effect on the target sound signal by playing the regulation sound, In order to achieve the technical effect of reducing noise.
本发明提供了一种吸油烟机的异音识别及音频注入的控制方法，通过小波包分析的方法对目标吸油烟机运行时产生的声音信号进行处理，得到目标特征向量，然后通过设定预设特征向量判断该声音信号是否是异常噪音，并选择合适的调控声对异常噪音进行掩蔽，可以达到降低吸油烟机噪音干扰和提升声品质的技术效果，缓解了现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。The invention provides a method for recognizing abnormal sound of a range hood and controlling audio injection. The sound signal generated when a target range hood is running is processed by a method of wavelet packet analysis to obtain a target feature vector, and then by setting a preset Set the feature vector to determine whether the sound signal is abnormal noise, and select the appropriate control sound to mask the abnormal noise, which can achieve the technical effect of reducing the noise interference of the range hood and improving the sound quality, alleviating the ineffectiveness of the existing technology. Identify the abnormal sound and the technical problem that the noise reduction cannot be performed for the generated abnormal sound.
可选地，在本发明实施例中，还包括设定预设特征向量的步骤，具体的包括如下步骤：Optionally, in the embodiment of the present invention, the step of setting a preset feature vector is further included, which specifically includes the following steps:
获取目标吸油烟机在正常运行时产生的背景声音信号；背景声音信号包括背景声音频谱信号和背景振动信号；Obtain the background sound signal generated by the target range hood during normal operation; the background sound signal includes the background sound spectrum signal and the background vibration signal;
基于小波包分析对背景声音信号进行小波包分解，得到预设特征向量；预设特征向量包括预设声音频谱峰值和预设振动幅值。The background sound signal is decomposed by wavelet packet based on the wavelet packet analysis, and a preset feature vector is obtained; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value.
具体的，步骤S106还包括如下步骤：Specifically, step S106 further includes the following steps:
步骤S1061，判断预设声音频谱峰值与目标声音频谱峰值的比值是否小于第一预设阈值；如果是，则执行步骤S1062；如果否，则执行步骤S1063。Step S1061, judging whether the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is smaller than the first preset threshold; if yes, go to step S1062; if not, go to step S1063.
步骤S1062，确定目标声音信号为异常噪音。Step S1062, it is determined that the target sound signal is abnormal noise.
步骤S1063，判断预设振动幅值与目标振动幅值的比值是否小于第二预设阈值；如果是，则执行步骤S1064；如果否，则执行步骤S1065。Step S1063, judging whether the ratio of the preset vibration amplitude value to the target vibration amplitude value is smaller than the second preset threshold value; if yes, go to step S1064; if not, go to step S1065.
步骤S1064，确定目标声音信号为异常噪音。Step S1064, it is determined that the target sound signal is abnormal noise.
步骤S1065，确定目标声音信号为正常声音信号。Step S1065, it is determined that the target sound signal is a normal sound signal.
可选地，在本发明实施例中，采集吸油烟机在产生不同异常噪音时对应的声音频谱峰值和振动幅值，分别依次记录为Ln和Kn，并将产生的异音信号特征向量与正常吸油烟机运行下产生的信号的特征向量进行比对分析，记录其特征，为后续判定阈值提供数据比对依据，进而确定第一预设阈值和第二预设阈值。例如，第一预设阈值设定为0.9，第二预设阈值设定为1，则对目标声音信号是否为异常噪音的判断过程可以如表1所示：Optionally, in the embodiment of the present invention, the peak value of the sound spectrum and the vibration amplitude corresponding to the range hood when different abnormal noises are generated are collected, recorded as Ln and Kn respectively, and the characteristic vector of the generated abnormal sound signal is compared with the normal value. The characteristic vectors of the signals generated under the operation of the range hood are compared and analyzed, their characteristics are recorded, and the data comparison basis is provided for the subsequent determination of the threshold value, and the first preset threshold value and the second preset threshold value are further determined. For example, if the first preset threshold is set to 0.9 and the second preset threshold is set to 1, the process of judging whether the target sound signal is abnormal noise can be as shown in Table 1:
表1异常噪音的判断过程Table 1 Judgment process of abnormal noise
表格中的L0为预设声音频谱峰值，LP为目标声音频谱峰值，K0为预设振动幅值，KP为目标振动幅值。In the table, L0 is the preset sound spectrum peak value, LP is the target sound spectrum peak value, K0 is the preset vibration amplitude, and KP is the target vibration amplitude.
由以上描述可知，本发明实施例提供了一种吸油烟机的异音识别及音频注入的控制方法，针对与现有技术中大部分分析异常噪音的方法主要依靠人为经验去判断分析的方式、而缺乏有效和科学的理论方法指导研究依据的问题，本发明实施例利用了小波包分析理论结合神经网络算法，可以针对信号进行分部拆解，提取有效值，数值更为精准；通过利用音频注入的方式播放调控声掩蔽异音，进而降低噪声提高声品质；缓解了现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。It can be seen from the above description that the embodiment of the present invention provides a method for recognizing abnormal noise and audio injection of a range hood, and most of the methods for analyzing abnormal noise in the prior art mainly rely on human experience to determine the analysis method, However, for the problem of lack of effective and scientific theoretical methods to guide the research, the embodiment of the present invention uses the wavelet packet analysis theory combined with the neural network algorithm to disassemble the signal in parts, extract the effective value, and the value is more accurate; by using the audio frequency The injection method plays and controls the sound to mask the abnormal sound, thereby reducing the noise and improving the sound quality; alleviating the technical problems existing in the prior art that the abnormal sound cannot be effectively identified and the noise reduction processing cannot be performed for the generated abnormal sound.
实施例二：Embodiment 2:
图2是根据本发明实施例提供的一种吸油烟机的异音识别及音频注入的控制系统的示意图。如图2所示，该系统包括：获取模块10，分析模块20，判断模块30和播放模块40。2 is a 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. As shown in FIG. 2 , the system includes: an acquisition module 10 , an analysis module 20 , a judgment module 30 and a playback module 40 .
获取模块10，用于获取目标吸油烟机在运行时产生的目标声音信号；目标声音信号包括声音频谱信号和振动信号。The acquisition module 10 is used for acquiring a target sound signal generated by the target range hood during operation; the target sound signal includes a sound spectrum signal and a vibration signal.
分析模块20，用于基于小波包分析对目标声音信号进行小波包分解，得到目标特征向量；目标特征向量包括声音频谱峰值和振动幅值。The analysis module 20 is configured 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 sound spectrum peaks and vibration amplitudes.
判断模块30，用于基于预设特征向量与目标特征向量之间的比值，判断目标声音信号是否为异常噪音。The judgment module 30 is configured to judge whether the target sound signal is abnormal noise based on the ratio between the preset feature vector and the target feature vector.
播放模块40，用于若目标声音信号为异常噪音，则在预设调控声数据库中确定与目标特征向量对应的目标调控声，并通过播放目标调控声对目标声音信号进行掩蔽；预设调控声数据库包括多个调控声，每个调控声对应一个特征向量范围。The playing module 40 is used for determining the target sound control sound corresponding to the target feature vector in the preset sound control sound database if the target sound signal is abnormal noise, and masking the target sound signal by playing the target sound control sound; the preset sound control sound The database includes multiple regulated sounds, each of which corresponds to a range of eigenvectors.
本发明提供了一种吸油烟机的异音识别及音频注入的控制系统，通过小波包分析的方法对目标吸油烟机运行时产生的声音信号进行处理，得到目标特征向量，然后通过设定预设特征向量判断该声音信号是否是异常噪音，并选择合适的调控声对异常噪音进行掩蔽，可以达到降低吸油烟机噪音干扰和提升声品质的技术效果，缓解了现有技术中存在的不能有效识别异音和不能针对产生的异音进行降噪处理的技术问题。The invention provides a control system for abnormal sound recognition and audio injection of a range hood. The sound signal generated when a target range hood is running is processed by a method of wavelet packet analysis to obtain a target feature vector. Set the feature vector to determine whether the sound signal is abnormal noise, and select the appropriate control sound to mask the abnormal noise, which can achieve the technical effect of reducing the noise interference of the range hood and improving the sound quality, alleviating the ineffectiveness of the existing technology. Identify the abnormal sound and the technical problem that the noise reduction cannot be performed for the generated abnormal sound.
可选地，获取模块10，还用于：Optionally, the obtaining module 10 is further used for:
获取目标吸油烟机在正常运行时产生的背景声音信号；背景声音信号包括背景声音频谱信号和背景振动信号；Obtain the background sound signal generated by the target range hood during normal operation; the background sound signal includes the background sound spectrum signal and the background vibration signal;
基于小波包分析对背景声音信号进行小波包分解，得到预设特征向量；预设特征向量包括预设声音频谱峰值和预设振动幅值。The background sound signal is decomposed by wavelet packet based on the wavelet packet analysis, and a preset feature vector is obtained; the preset feature vector includes a preset sound spectrum peak value and a preset vibration amplitude value.
可选地，判断模块30，还用于：Optionally, the judgment module 30 is further configured to:
判断预设声音频谱峰值与目标声音频谱峰值的比值是否小于第一预设阈值；如果是，则确定目标声音信号为异常噪音；Determine whether the ratio of the preset sound spectrum peak value to the target sound spectrum peak value is less than the first preset threshold; if so, determine that the target sound signal is abnormal noise;
如果否，则判断预设振动幅值与振动幅值的比值是否小于第二预设阈值；如果是，则确定目标声音信号为异常噪音。If not, it is determined whether the ratio of the preset vibration amplitude to the vibration amplitude is smaller than the second preset threshold; if so, it is determined that the target sound signal is abnormal noise.
可选地，判断模块30，还用于：Optionally, the judgment module 30 is further configured to:
若预设声音频谱峰值与目标声音频谱峰值的比值大于等于第一预设阈值，且预设振动幅值与振动幅值的比值大于等于第二预设阈值，则确定目标声音信号为正常声音信号。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 .
实施例三：Embodiment three:
图3是根据本发明实施例提供的另一种吸油烟机的异音识别及音频注入的控制系统的示意图。如图3所示，该系统包括小波包分析模块、音频注入模块、声频播放模块、振动接收器和噪声传感器。3 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. As shown in Figure 3, the system includes a wavelet packet analysis module, an audio injection module, an audio playback module, a vibration receiver and a noise sensor.
具体的，如图3所示，小波包分析模块与音频注入模块都集成安装在吸油烟机的集成面板上，小波包分析模块分别与音频注入模块、噪声传感器、振动接收器相连，而音频注入模块与声频播放模块进行相连。Specifically, as shown in Figure 3, the wavelet packet analysis module and the audio injection module are integrated and installed on the integrated panel of the range hood. The wavelet packet analysis module is respectively connected with the audio injection module, the noise sensor, and the vibration receiver, while the audio injection The module is connected with the audio playback module.
其中，噪声传感器和振动接收器集成安装在吸油烟机的内壳上部位置，其余三侧均有设置。声频播放模块则在顶部的四个底角处，均呈长方体形状。Among them, the noise sensor and the vibration receiver are integrated and installed in the upper part of the inner shell of the range hood, and the other three sides are arranged. The audio playback module is in the shape of a rectangular parallelepiped at the four bottom corners of the top.
具体的，小波包分析模块内置神经网络算法，主要采集时域、频域分析状态下的声音的振动幅值及噪音峰值作为主要特征向量。Specifically, the wavelet packet analysis module has a built-in neural network algorithm, which mainly collects the vibration amplitude and noise peak value of the sound in the time domain and frequency domain analysis state as the main feature vectors.
音频注入模块中集成了大部分的可听声频，诸如流水声、雨声、风声等自然声以及钢琴、吉他等乐器声等各种人工合成声声频，每种声频对应了不同的振动峰值及噪音峰值特征。The audio injection module integrates most of the audible audio frequencies, such as natural sounds such as flowing water, rain, wind, and various synthetic sounds such as piano, guitar and other musical instruments. Each audio frequency corresponds to different vibration peaks and noises Peak characteristics.
声频播放模块包括扬声器，扬声器设置安装在吸油烟机的顶部四个角上，呈长方体形状，声音扩散方向皆朝外侧。The audio playback module includes speakers, and the speakers are arranged and installed on the top four corners of the range hood, in the shape of a rectangular parallelepiped, and the sound diffusion directions are all outward.
振动接收器为压电式声振传感器，设置于烟机内壁的四周，用于检测振动幅值大小。The vibration receiver is a piezoelectric acoustic vibration sensor, which is arranged around the inner wall of the hood and is used to detect the magnitude of the vibration amplitude.
噪声传感器设置于振动接收器的一侧，用于采集吸油烟机工作产生的噪声频谱。The noise sensor is arranged on one side of the vibration receiver and is used to collect the noise spectrum generated by the operation of the range hood.
首先，基于小波包理论，通过神经网络算法采集烟机正常运行的振动幅值与噪声峰值作为特征向量，记录为L0和K0存储到模块中，同时基于同等方法记录烟机产生不同异音的振动幅值与噪声峰值信号分别依次记录为L1-Ln和K1-Kn，并将记录的异音特征向量Ln和Kn分别与L0、K0进行比对，基于此确定阈值判定条件,并将其设置到内置核心模块中；First, based on the wavelet packet theory, the vibration amplitude and noise peak value of the normal operation of the hood are collected as eigenvectors through the neural network algorithm, recorded as L0 and K0 and stored in the module, and the vibration of the hood with different abnormal sounds is recorded based on the same method. The amplitude and noise peak signals 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 to In the built-in core module;
当烟机运行时，通过烟机内壳上设置的振动接收器采集烟机结构的振动特征，并通过噪声传感器实时采集产生的噪音值，将采集的信息传递给小波包分析模块，小波包分析模块将其中的信号进行提取，主要是噪声峰值LP和振动幅值KP，将这两个信号特征向量进行逐级分解提取，与内置初始值L0和K0进行分析比对；When the hood is running, the vibration characteristics of the hood structure are collected by the vibration receiver set on the inner shell of the hood, and the generated noise value is collected in real time through the noise sensor, and the collected information is transmitted to the wavelet packet analysis module. The module extracts the signals, mainly the noise peak LP and the vibration amplitude KP, and decomposes and extracts the feature vectors of these two signals step by step, and analyzes and compares them with the built-in initial values L0 and K0;
然后将采集的LP和KP的特征向量信号值与初始值一一进行比对分析，当L0/LP的比值大于等于0.9时，且满足K0/KP>＝1时，则判定没有异音产生；否则判定有异音出现，小波包分析模块会将该信号特征传递给音频注入模块中，音频注入模块中的控制程序会根据信号特征播放相对应特征的调控声(如流水声、乐器声、鸟鸣声等)，音频注入模块将选择好的调控声信号传递给声频播放模块，位于烟机顶部的声频播放模块中的扬声器会选择的调控声进行播放，调控声将对产生的异音在时域或者频域上进行掩蔽，进而降低烟机运行噪声，大幅度削弱异音进入人耳的概率，减小异音对人员的身心干扰，提升了烟机运行的声品质。Then compare and analyze the collected eigenvector signal values of LP and KP with the initial value. When the ratio of L0/LP is greater than or equal to 0.9, and K0/KP>=1, it is determined that no abnormal sound is generated; Otherwise, it is determined that there is abnormal sound, and the wavelet packet analysis module will pass the signal feature to the audio injection module, and the control program in the audio injection module will play the corresponding characteristic regulation sound (such as the sound of running water, musical instruments, birds, etc.) according to the signal characteristics. sound, etc.), the audio injection module transmits the selected control sound signal to the audio playback module, the speaker in the audio playback module located on the top of the hood will play the selected control sound, and the control sound will generate abnormal sound when Masking is performed in the frequency domain or frequency domain, thereby reducing the operating noise of the hood, greatly reducing the probability of abnormal sound entering the human ear, reducing the physical and mental interference of the abnormal sound on personnel, and improving the sound quality of the hood operation.
本发明实施例还提供了一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行计算机程序时实现上述实施例一中的方法的步骤。An embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of the method in the first embodiment when the processor executes the computer program.
本发明实施例还提供了一种具有处理器可执行的非易失的程序代码的计算机可读介质，程序代码使处理器执行上述实施例一中的方法。An embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, and the program code enables the processor to execute the method in the first embodiment above.
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. scope.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210105179.1A CN114299990B (en) | 2022-01-28 | 2022-01-28 | Abnormal sound recognition and audio injection control method and system for range hood |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210105179.1A CN114299990B (en) | 2022-01-28 | 2022-01-28 | Abnormal sound recognition and audio injection control method and system for range hood |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114299990A true CN114299990A (en) | 2022-04-08 |
| CN114299990B CN114299990B (en) | 2024-12-31 |
Family
ID=80978256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210105179.1A Active CN114299990B (en) | 2022-01-28 | 2022-01-28 | Abnormal sound recognition and audio injection control method and system for range hood |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299990B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118629383A (en) * | 2024-08-08 | 2024-09-10 | 宁波方太厨具有限公司 | Active noise reduction system and control method thereof, abnormal sound detection method and device |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110010192A (en) * | 2009-07-24 | 2011-02-01 | 한국과학기술원 | Noise control device and method |
| CN104344535A (en) * | 2013-08-02 | 2015-02-11 | 广东美的制冷设备有限公司 | Method and device for adaptively adjusting frequency of conditioner motor and air conditioner |
| US20150043744A1 (en) * | 2013-08-09 | 2015-02-12 | GM Global Technology Operations LLC | Masking vehicle noise |
| CN105203318A (en) * | 2015-10-23 | 2015-12-30 | 珠海格力电器股份有限公司 | Method and device for monitoring running state of range hood in real time |
| JP2016052049A (en) * | 2014-09-01 | 2016-04-11 | 三菱電機株式会社 | Sound environment control device and sound environment control system using the same |
| CN106286362A (en) * | 2016-07-22 | 2017-01-04 | 国家电网公司 | Fan for cooling transformer evaluation of running status method and system based on noise |
| CN206210382U (en) * | 2016-11-01 | 2017-05-31 | 比亚迪股份有限公司 | Noise reduction system and electric automobile |
| CN108734933A (en) * | 2017-04-13 | 2018-11-02 | 广东美的智美科技有限公司 | Range hood and control method |
| CN110827852A (en) * | 2019-11-13 | 2020-02-21 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device and equipment for detecting effective voice signal |
| CN111457434A (en) * | 2020-04-15 | 2020-07-28 | 宁波方太厨具有限公司 | Range hood and resonance abnormal sound eliminating method thereof |
| CN113497849A (en) * | 2020-03-20 | 2021-10-12 | 华为技术有限公司 | Sound masking method and device and terminal equipment |
| CN113883671A (en) * | 2021-09-13 | 2022-01-04 | Tcl空调器(中山)有限公司 | Abnormal noise shielding control method for air conditioner, air conditioner and readable storage medium |
| CN113949956A (en) * | 2020-07-16 | 2022-01-18 | Oppo广东移动通信有限公司 | Noise reduction processing method, device, electronic device, earphone and storage medium |
| CN216849306U (en) * | 2022-01-28 | 2022-06-28 | 杭州老板电器股份有限公司 | Audio injection device of range hood and range hood |
-
2022
- 2022-01-28 CN CN202210105179.1A patent/CN114299990B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110010192A (en) * | 2009-07-24 | 2011-02-01 | 한국과학기술원 | Noise control device and method |
| CN104344535A (en) * | 2013-08-02 | 2015-02-11 | 广东美的制冷设备有限公司 | Method and device for adaptively adjusting frequency of conditioner motor and air conditioner |
| US20150043744A1 (en) * | 2013-08-09 | 2015-02-12 | GM Global Technology Operations LLC | Masking vehicle noise |
| JP2016052049A (en) * | 2014-09-01 | 2016-04-11 | 三菱電機株式会社 | Sound environment control device and sound environment control system using the same |
| CN105203318A (en) * | 2015-10-23 | 2015-12-30 | 珠海格力电器股份有限公司 | Method and device for monitoring running state of range hood in real time |
| CN106286362A (en) * | 2016-07-22 | 2017-01-04 | 国家电网公司 | Fan for cooling transformer evaluation of running status method and system based on noise |
| CN206210382U (en) * | 2016-11-01 | 2017-05-31 | 比亚迪股份有限公司 | Noise reduction system and electric automobile |
| CN108734933A (en) * | 2017-04-13 | 2018-11-02 | 广东美的智美科技有限公司 | Range hood and control method |
| CN110827852A (en) * | 2019-11-13 | 2020-02-21 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device and equipment for detecting effective voice signal |
| CN113497849A (en) * | 2020-03-20 | 2021-10-12 | 华为技术有限公司 | Sound masking method and device and terminal equipment |
| CN111457434A (en) * | 2020-04-15 | 2020-07-28 | 宁波方太厨具有限公司 | Range hood and resonance abnormal sound eliminating method thereof |
| CN113949956A (en) * | 2020-07-16 | 2022-01-18 | Oppo广东移动通信有限公司 | Noise reduction processing method, device, electronic device, earphone and storage medium |
| CN113883671A (en) * | 2021-09-13 | 2022-01-04 | Tcl空调器(中山)有限公司 | Abnormal noise shielding control method for air conditioner, air conditioner and readable storage medium |
| CN216849306U (en) * | 2022-01-28 | 2022-06-28 | 杭州老板电器股份有限公司 | Audio injection device of range hood and range hood |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118629383A (en) * | 2024-08-08 | 2024-09-10 | 宁波方太厨具有限公司 | Active noise reduction system and control method thereof, abnormal sound detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114299990B (en) | 2024-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112820291B (en) | Smart home control method, smart home control system and storage medium | |
| WO2013060079A1 (en) | Record playback attack detection method and system based on channel mode noise | |
| CN101393660A (en) | An intelligent access control system based on footstep recognition | |
| CN113689888B (en) | Abnormal sound classification method, system, device and storage medium | |
| CN117294985B (en) | TWS Bluetooth headset control method | |
| KR20060021299A (en) | Parameterized Time Characterization | |
| CN104992712B (en) | It can identify music automatically at the method for spectrum | |
| CN111964226B (en) | Air conditioner control method and device and air conditioner | |
| CN111128167B (en) | Far-field voice awakening method and device, electronic product and storage medium | |
| CN115762516B (en) | Man-machine interaction control method, device and storage medium | |
| CN112992153B (en) | Audio processing method, voiceprint recognition device and computer equipment | |
| CN114299990B (en) | Abnormal sound recognition and audio injection control method and system for range hood | |
| WO2000077772A2 (en) | Speech and voice signal preprocessing | |
| CN110197663B (en) | Control method and device and electronic equipment | |
| CN114400009B (en) | Voiceprint recognition method and device and electronic equipment | |
| CN114238849B (en) | False audio detection method and system based on complex spectrum sub-band fusion | |
| CN216849306U (en) | Audio injection device of range hood and range hood | |
| CN116935835A (en) | Tooth sound identification and elimination method, system, medium and equipment | |
| CN119274582A (en) | Unsupervised industrial abnormal sound detection method and system based on selective learning of time-frequency features | |
| CN118645101A (en) | A smart speaker control system | |
| CN112992131A (en) | Method for extracting ping-pong command of target voice in complex scene | |
| Noh et al. | Smart home with biometric system recognition | |
| CN109712635B (en) | Sound data processing method, intelligent terminal and storage medium | |
| CN117198300A (en) | A bird sound recognition method and device based on attention mechanism | |
| TWI779261B (en) | Wind shear sound filtering device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |