Noise platform analysis method based on feature extraction

Abstract

The invention discloses a noise platform analysis method based on feature extraction, and the method comprises the following steps: obtaining target noise data information, carrying out the preprocessing of the noise information, carrying out the feature extraction of the processed noise information, cleaning the extracted features, constructing a noise classification and recognition model according to the feature data, constructing a sample set, and training the model. And optimizing the model. Compared with the prior art, the noise platform analysis method based on feature extraction has the advantages that targeted feature extraction analysis can be conveniently carried out, so that noise analysis is completed, and the noise category can be output.

Description

Technical Field

[0001] The present invention relates to the technical field of noise analysis, and in particular to a noise platform analysis method based on feature extraction. Background Art

[0002] Noise environments are often very complex, encompassing a wide variety of noise sources and characteristics. These noises can originate from mechanical equipment, electronic equipment, the natural environment, and other sources, each with varying characteristics such as frequency, amplitude, and phase.

[0003] To obtain accurate measurements, it is necessary to accurately evaluate the characteristics of the measurement equipment, measurement methods, and noise during the measurement process. This allows for the correct evaluation and precise measurement of the measured values, laying a solid foundation for improving equipment performance and refining test methods.

[0004] Therefore, in order to effectively identify and process these noises, a method that can extract the key features of the noise is needed to accurately classify and identify the noise. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the above-mentioned extreme speed defects and provide a noise platform analysis method based on feature extraction that is convenient for targeted feature extraction analysis, thereby completing noise analysis and outputting noise categories.

[0006] To solve the above technical problems, the present invention provides a technical solution: a noise platform analysis method based on feature extraction, comprising the following steps: obtaining target noise data information, preprocessing the noise information, extracting features from the processed noise information, cleaning the extracted features, constructing a noise classification and recognition model based on the feature data, constructing a sample set to train the model, and optimizing the model.

[0007] Preferably, the feature extraction includes frequency features, amplitude features, phase features, and energy features.

[0008] Preferably, the sample set includes noise data samples related to the target obtained based on the Internet.

[0009] Preferably, the target noise data information includes time domain and frequency domain information, and feature extraction includes using Fourier transform to convert the time domain signal into a frequency domain signal, extracting the frequency domain information, and combining the obtained time domain and frequency domain features to obtain a time-frequency distribution matrix.

[0010] Preferably, the extracted features are used to classify the noise into mechanical noise, electronic noise, and environmental noise using a classifier.

[0011] Preferably, noise data related to the target is collected, including using sensors, recording equipment and Internet data, and the preprocessing of the noise information includes data cleaning, denoising and normalization.

[0012] Preferably, the cleaning and extracting of features includes removing redundant features, processing missing values, and then standardizing feature values.

[0013] The advantages of the present invention over the prior art are as follows: in the present invention, by constructing a noise classification and recognition model, by collecting target noise data information, preprocessing the noise information, and extracting features, and constructing a noise parameter relationship based on the extracted features, the noise classification and recognition model is completed, and the model is trained using the constructed sample set to obtain high-precision noise analysis results. DETAILED DESCRIPTION

[0014] Reference will now be made in detail to embodiments of the present invention, one or more examples of which are described below. Each example is provided to illustrate, not to limit, the present invention. Indeed, it will be apparent to those skilled in the art that various modifications and variations may be made to the present invention without departing from the scope or spirit of the invention. For example, features illustrated or described as part of one embodiment may be used in another embodiment to produce further embodiments.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0016] The terms "comprise", "include" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In the description of the present invention, the meaning of "several" is at least one, such as one, two, etc., unless otherwise clearly and specifically defined.

[0017] Except as shown in the operating examples or otherwise indicated, all numbers used in the specification and claims to express the amount of ingredients, physicochemical properties, etc. are understood to be adjusted by the term "about" in all cases. For example, therefore, unless otherwise indicated, the numerical parameters listed in the above specification and the appended claims are approximate values, and those skilled in the art will be able to appropriately change these approximate values ​​using the teachings disclosed herein to seek to obtain the desired properties. The use of numerical ranges expressed as endpoints includes all numbers within the range and any range within the range, for example, 1 to 5 includes 1, 1.1, 1.3, 1.5, 2, 2.75, 3, 3.80, 4 and 5, etc.

[0018] As shown in the figure, a noise platform analysis method based on feature extraction includes the following steps: obtaining target noise data information, preprocessing the noise information, extracting features from the processed noise information, cleaning the extracted features, building a noise classification and recognition model based on the feature data, building a sample set to train the model, and optimizing the model.

[0019] Collecting noise data related to the target includes using sensors, recording equipment and Internet data. The preprocessing of the noise information includes data cleaning, denoising and normalization. Among them, feature extraction includes frequency features, amplitude features, phase features and energy features. The sample set includes noise data samples related to the target obtained based on the Internet. The target noise data information includes time domain and frequency domain information. Feature extraction includes using Fourier transform to convert the time domain signal into a frequency domain signal, extracting the frequency domain information, and combining the obtained time domain and frequency domain features to obtain a time-frequency distribution matrix. Cleaning the extracted features includes removing redundant features, processing missing values ​​and then standardizing the feature values.

[0020] The extracted features are used to classify the noise into mechanical noise, electronic noise, and environmental noise.

[0021] Noise information acquisition includes sensors, recording equipment, environmental monitoring stations or Internet data information, including information in both time domain and frequency domain.

[0022] After obtaining the original noise data, the data is cleaned, denoised, and filtered to eliminate outliers, noise interference, and redundant information in the data. Representative, stable, and distinguishable features are extracted from the preprocessed noise data, including frequency features, amplitude features, phase features, and energy features.

[0023] Through the Fourier transform frequency domain analysis method, the time domain signal is converted into a frequency domain signal, so as to extract the frequency characteristics of the noise. At the same time, the amplitude of the noise signal is measured and the amplitude characteristics are extracted. At the same time, the phase characteristics of the noise signal are analyzed to understand the phase difference and phase delay between the noise signals, and the phase characteristics are extracted. Combining the characteristics of the time domain and frequency domain, the time-frequency distribution matrix is ​​obtained.

[0024] Cleaning the extracted features includes processing missing values ​​and standardizing feature values. A noise classification and recognition model is constructed based on the cleaned feature data. A convolutional neural network is used, and a sample set containing multiple noise types is constructed to optimize the model training.

[0025] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0026] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection claimed in the present invention is defined by the attached claims and their equivalents. Therefore, based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0028] In the present invention, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; they may refer to direct connection or indirect connection through an intermediate medium; they may refer to internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0029] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0030] The above description of the present invention and its embodiments is non-limiting. In short, if a person skilled in the art is inspired by the above description and designs a similar structure and embodiment to the technical solution without departing from the purpose of the present invention, they should fall within the scope of protection of the present invention.

Claims

1. A noise platform analysis method based on feature extraction, characterized in that: The following steps are involved: Obtain target noise data information, preprocess the noise information, extract features from the processed noise information, clean and extract features, build a noise classification and recognition model based on the feature data, build a sample set to train the model, and optimize the model.

2. The noise platform analysis method based on feature extraction according to claim 1, characterized in that: The feature extraction includes frequency feature, amplitude feature, phase feature and energy feature.

3. The noise platform analysis method based on feature extraction according to claim 1, characterized in that: The sample set includes noise data samples related to the target obtained based on the Internet.

4. The noise platform analysis method based on feature extraction according to claim 1, characterized in that: The target noise data information includes time domain and frequency domain information, and feature extraction includes using Fourier transform to convert the time domain signal into a frequency domain signal, extracting the frequency domain information, and combining the obtained time domain and frequency domain features to obtain a time-frequency distribution matrix.

5. The noise platform analysis method based on feature extraction according to claim 4 is characterized in that: The extracted features are used to classify the noise into mechanical noise, electronic noise, and environmental noise.

6. The noise platform analysis method based on feature extraction according to claim 1, characterized in that: Noise data related to the target is collected, including using sensors, recording equipment and Internet data. The preprocessing of the noise information includes data cleaning, denoising and normalization.

7. The noise platform analysis method based on feature extraction according to claim 1, characterized in that: The cleaning and extraction of features includes removing redundant features, processing missing values, and then standardizing feature values.