CN112101301B - A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit - Google Patents
A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit Download PDFInfo
- Publication number
- CN112101301B CN112101301B CN202011207414.3A CN202011207414A CN112101301B CN 112101301 B CN112101301 B CN 112101301B CN 202011207414 A CN202011207414 A CN 202011207414A CN 112101301 B CN112101301 B CN 112101301B
- Authority
- CN
- China
- Prior art keywords
- model
- audio data
- training
- feature point
- data
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
本发明提供一种螺杆水冷机组的好音稳定预警方法、装置及存储介质，方法包括：导入多个原始音频数据，并对多个所述原始音频数据进行数据清洗，经数据清洗后剩余的原始音频数据作为目标音频数据，得到多个目标音频数据，所述原始音频数据是通过螺杆水冷机组设备得到的；分别对各个所述目标音频数据进行特征提取，得到对应的特征点，并集合提取到的所有的特征点得到特征点数据集。本发明能够进一步提高了音频识别准确率，克服了传统好音稳定预警的工作量大、效率低下和准确率不够的缺陷，能自动对大量的音频数据进行智能检测和识别，实时检测出的音频数据，为好音稳定预警做及时地干预，具有了效率高，稳定性强以及准确率高的特点。
The invention provides a good sound stability early warning method, device and storage medium for a screw water-cooled unit. The method includes: importing a plurality of original audio data, and performing data cleaning on the plurality of original audio data, and the remaining original audio data after data cleaning The audio data is used as the target audio data to obtain a plurality of target audio data, and the original audio data is obtained by the screw water-cooling unit equipment; the feature extraction is performed on each of the target audio data respectively to obtain the corresponding feature points, and collectively extract them. All the feature points get the feature point dataset. The invention can further improve the accuracy of audio recognition, overcome the defects of large workload, low efficiency and insufficient accuracy of traditional good-sound stability early warning, and can automatically perform intelligent detection and recognition on a large amount of audio data, and real-time detected audio It has the characteristics of high efficiency, strong stability and high accuracy.
Description
Technical Field
The invention mainly relates to the technical field of audio identification, in particular to a good sound stability early warning method and device for a screw water cooling unit and a storage medium.
Background
The good sound stability early warning essentially belongs to a mode recognition technology, in the application of actual life, the visual sensory recognition of audio by people is based on the semantic layer of the highest audio level, and the audio is easily influenced by the environment and transmission and conversion equipment.
Audio data is not very reliable due to the risk of non-humanization, remote control, low accuracy and complexity. There are many other factors that affect the accuracy of a sound sample, such as the quality of the sound sample, mood, background noise, and changes in sound over time. At present, automatic identification and recognition of instruments are difficult to rely on, higher identification accuracy cannot be guaranteed, and meanwhile real-time judgment and timely early warning are difficult to achieve.
Disclosure of Invention
The invention aims to solve the technical problem of the prior art and provides a good sound stability early warning method and device for a screw water cooling unit and a storage medium.
The technical scheme for solving the technical problems is as follows: a good sound stability early warning method for a screw water cooling unit comprises the following steps:
importing a plurality of original audio data, performing data cleaning on the original audio data, and taking the remaining original audio data after the data cleaning as target audio data to obtain a plurality of target audio data, wherein the original audio data are obtained through a screw water cooling unit device;
respectively extracting the characteristics of each target audio data to obtain corresponding characteristic points, and collecting all the extracted characteristic points to obtain a characteristic point data set;
constructing a training model, and training the training model according to the feature point data set to obtain an audio recognition model;
optimizing the audio recognition model to obtain an audio recognition optimization model;
and identifying the audio data to be identified according to the audio identification optimization model to obtain an identification result of the audio data.
Another technical solution of the present invention for solving the above technical problems is as follows: the utility model provides a good sound of screw rod water chilling unit stabilizes early warning device, includes:
the data cleaning module is used for importing a plurality of original audio data, cleaning the original audio data, and obtaining a plurality of target audio data by taking the residual original audio data after the data cleaning as the target audio data, wherein the original audio data are obtained through a screw water cooling unit device;
the feature extraction module is used for respectively extracting features of the target audio data to obtain corresponding feature points, and collecting all the extracted feature points to obtain a feature point data set;
the model training module is used for constructing a training model and training the training model according to the feature point data set to obtain an audio recognition model;
the optimization processing module is used for optimizing the audio recognition model to obtain an audio recognition optimization model;
and the good tone stability early warning module is used for identifying and processing the audio data to be identified according to the audio identification optimization model to obtain an identification result of the audio data.
Another technical solution of the present invention for solving the above technical problems is as follows: the good sound stability early warning device of the screw water chiller comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein when the processor executes the computer program, the good sound stability early warning method of the screw water chiller is realized.
Another technical solution of the present invention for solving the above technical problems is as follows: a computer-readable storage medium storing a computer program which, when executed by a processor, implements the good-sound stability warning method for a screw water chiller as described above.
The invention has the beneficial effects that: the method comprises the steps of obtaining a plurality of target audio data by respectively cleaning data of a plurality of original audio data, screening out data containing missing values, analyzing data with more useful information and information with larger influence on identification and recognition, conveniently manufacturing a data set according to the obtained target audio data so as to conveniently obtain a recognition model with higher identification and recognition accuracy, respectively extracting the characteristics of the plurality of target audio data to obtain a characteristic point data set, constructing a training model, obtaining an audio recognition model according to the training of the training model by the characteristic point data set, effectively improving the reliability and stability of good sound stability early warning, obtaining an audio recognition optimization model according to the optimization processing of a preset adjustment parameter on the audio recognition model, obtaining the recognition result of the audio data according to the recognition optimization model on the audio data to be recognized, the method can further improve the audio identification accuracy, overcomes the defects of large workload, low efficiency and insufficient accuracy of the traditional good sound stability early warning, can automatically carry out intelligent detection and identification on a large amount of audio data, and intervenes in time for the good sound stability early warning according to the audio data detected in real time, and has the characteristics of high efficiency, strong stability and high accuracy.
Drawings
Fig. 1 is a schematic flow chart of a good sound stability early warning method for a screw water-cooling unit according to an embodiment of the present invention;
fig. 2 is a block diagram of a good-sound stability early warning device of a screw water chiller according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a schematic flow chart of a good sound stability early warning method for a screw water chiller according to an embodiment of the present invention.
As shown in fig. 1, a good sound stability early warning method for a screw water chiller unit includes the following steps:
importing a plurality of original audio data, performing data cleaning on the original audio data, and taking the remaining original audio data after the data cleaning as target audio data to obtain a plurality of target audio data, wherein the original audio data are obtained through a screw water cooling unit device;
respectively extracting the characteristics of each target audio data to obtain corresponding characteristic points, and collecting all the extracted characteristic points to obtain a characteristic point data set;
constructing a training model, and training the training model according to the feature point data set to obtain an audio recognition model;
optimizing the audio recognition model to obtain an audio recognition optimization model;
and identifying the audio data to be identified according to the audio identification optimization model to obtain an identification result of the audio data.
It should be understood that data cleansing refers to the last procedure to find and correct recognizable errors in a data file, including checking data consistency, processing invalid and missing values, and the like.
And optimizing the audio recognition model according to the preset adjusting parameters to obtain an audio recognition optimization model.
Specifically, parameter tuning is performed by using a manual parameter tuning method, so that the optimal parameters corresponding to the audio recognition model can be obtained, the recognition accuracy of the audio recognition optimization model on audio can be further ensured, audio data of audio sample discharge can be detected in real time, and timely intervention can be performed for clinic.
In the above embodiment, the data of the original audio data are respectively cleaned to obtain a plurality of target audio data, data containing missing values can be screened out, more useful information data and information having larger influence on identification and recognition can be analyzed, a data set can be conveniently manufactured according to the obtained target audio data, so that a recognition model with higher recognition and recognition accuracy can be conveniently obtained, the features of the target audio data are respectively extracted to obtain a feature point data set, a training model is constructed, an audio recognition model is obtained according to the training of the feature point data set on the training model, the reliability and stability of good sound stability early warning can be effectively improved, an audio recognition optimization model is obtained according to the optimization processing of preset adjustment parameters on the audio recognition model, and the recognition result of the audio data is obtained according to the recognition processing of the audio recognition optimization model to be recognized, the method can further improve the audio identification accuracy, overcomes the defects of large workload, low efficiency and insufficient accuracy of the traditional good sound stability early warning, can automatically carry out intelligent detection and identification on a large amount of audio data, and intervenes in time for the good sound stability early warning according to the audio data detected in real time, and has the characteristics of high efficiency, strong stability and high accuracy.
Optionally, as an embodiment of the present invention, the process of respectively performing feature extraction on each target audio data to obtain corresponding feature points includes:
respectively carrying out dimensionality reduction on the target audio data to obtain a plurality of audio data subjected to dimensionality reduction;
and respectively extracting the features of the plurality of audio data subjected to dimension reduction by using a preset spectrogram to obtain a plurality of feature points.
It should be understood that in the field of machine learning and statistics, dimensionality reduction refers to the process of reducing the number of random variables under certain defined conditions to yield a set of "uncorrelated" principal variables. The dimension reduction of the data can save the storage space of a computer on one hand, and can eliminate the noise in the data and improve the performance of a machine learning algorithm on the other hand; the root of data dimension reduction: the data dimensionality is reduced, and the data after dimensionality reduction can represent the original data as much as possible.
It should be understood that, the LDA linear discriminant analysis algorithm is used to perform dimension reduction on a plurality of target audio data, so as to obtain a plurality of audio data after dimension reduction.
Specifically, a plurality of target audio data are projected on a low dimension respectively, so that an audio text is reduced from thousands of dimensions to k dimensions, the intra-class variance of the projected target audio data is minimum, and the inter-class variance is maximum; and compressing the target audio data which is reduced to the new feature space, and reserving information as much as possible to obtain a plurality of audio data after dimension reduction.
It should be understood that a Spectrogram (Spectrogram), whose abscissa is time, ordinate is frequency, and whose coordinate points are voice data energy, is a display image of time-series-related fourier analysis, which can reflect the transformation of the music signal spectrum with time. Because the three-dimensional information is expressed by adopting the two-dimensional plane, the size of the energy value is expressed by the color, and the deeper the color, the stronger the voice energy for expressing the point is.
The spectrogram displays a great deal of information related to the characteristics of the music signal, such as the change of frequency domain parameters such as formants, energy and the like along with time, and has the characteristics of a time domain waveform and a spectrogram. That is, the spectrogram itself contains all the spectral information of the music signal without any processing, so that the information of the spectrogram about the music is lossless.
The patterns in the spectrogram comprise transverse lines, random lines, vertical strips and the like, the transverse lines are black bands parallel to the time axis and are formants, the corresponding formant frequency and bandwidth can be determined according to the frequency and bandwidth corresponding to the transverse lines, and whether the transverse lines appear in the spectrogram of a section of audio is an important mark for judging whether the spectrogram is voiced sound or not is judged; the vertical bars are narrow black bars perpendicular to the time axis, each vertical bar corresponding to a fundamental tone, the start of a stripe corresponding to the start of a voiceprint pulse, the distance between stripes representing the fundamental tone, the denser the stripes representing the higher the frequency of the fundamental tone.
In the above embodiment, the dimension reduction processing on the target audio data is performed respectively to obtain the reduced audio data, the preset spectrogram is used to extract the features of the reduced audio data to obtain the feature points, so that the main features having a greater influence on the sound stability early warning of the screw water-cooling unit can be obtained, the calculation amount of the subsequent steps is reduced, and the subsequent support vector machine can obtain a higher accuracy rate only by using less training data.
Optionally, as an embodiment of the present invention, the training model according to the feature point data set to obtain an audio recognition model includes:
s1: randomly dividing the feature point data set into a feature point training set and a feature point testing set;
s2: constructing a model based on a support vector machine algorithm to obtain a support vector machine structure;
s3: inputting the feature point training set and the feature point testing set into the support vector machine structure together to search for an optimal recognition hyperplane, so as to obtain an optimal recognition hyperplane, and obtaining a support vector set and VC (virtual component interconnect) credibility according to the optimal recognition hyperplane;
s4: carrying out discrimination processing on the support vector set according to the VC credibility to obtain a discrimination function, and generating a training model according to the discrimination function;
s5: and carrying out model screening processing on the training model according to the feature point training set and the feature point testing set to obtain an audio recognition model.
It should be understood that, since the feature point data set is randomly divided into the feature point training set and the feature point testing set each time, the random proportion of each time is different, and the train _ test _ split function may be invoked for random division.
The Support Vector Machine (SVM) is a supervised learning algorithm, the SVM theory provides complexity for avoiding a high-dimensional space, an inner product function (namely a kernel function) of the space is directly used, and a solving method under the condition of linear divisibility is utilized to directly solve a decision problem of the corresponding high-dimensional space.
It should be understood that the VC credibility is the VC dimensional confidence or confidence risk, and the VC dimension is a measure for the function class, which can be simply understood as the complexity of the problem, and the higher the VC dimension is, the more complex a problem is. For example: many classification functions can easily achieve 100% accuracy on a sample set, but are confusing (i.e., so-called poor generalization ability, or poor generalization ability) when classified in reality. In this case, a classification function is selected that is complex enough (i.e. its VC dimension is high) to accurately remember each sample, but uniformly classify the data outside the sample in error.
Specifically, the feature point training set and the feature point testing set are input into the structure of the support vector machine, and the sample feature space of the support vector machine is used to find out the optimal identification hyperplane of each class of feature sample and other feature samples, so as to obtain the support vector set representing each class of sample and the corresponding VC credibility, form the discriminant function for distinguishing each feature, and obtain the training model.
In the embodiment, the feature point data set is randomly divided into a feature point training set and a feature point testing set, so that the objectivity of data can be ensured, human factors are reduced, the accuracy of a subsequent identification model is effectively improved, the feature point training set and the feature point testing set are input into an optimal identification hyperplane of a support vector machine structure together to search for an optimal identification hyperplane, a support vector set and VC reliability are obtained according to the optimal identification hyperplane, and a training model is obtained by performing discrimination processing on the support vector set according to the VC reliability; the audio recognition model is obtained by screening the training model according to the feature point training set and the feature point testing set, so that the accuracy of the audio data to be recognized can be kept at a higher level all the time, and the stability and reliability of audio recognition are improved.
Optionally, as an embodiment of the present invention, the process of step S5 includes:
s51: inputting the feature point training set into the training model according to preset iterative training times to perform iterative training to obtain a first detection model;
s52: inputting the feature point test set into the first detection model for detection to obtain a first accuracy, and judging whether the first accuracy reaches a preset expected value, if so, taking the first detection model as an audio recognition model, then performing optimization processing on the audio recognition model, and if not, executing the step S53;
s53: inputting the feature point test set into the training model for iterative training according to the preset iterative training times to obtain a second detection model;
s54: inputting the feature point training set into the second detection model for detection to obtain a second accuracy;
s55: and judging whether the second accuracy reaches the preset expected value, if so, taking the second detection model as the audio recognition model, then carrying out optimization processing on the audio recognition model, and if not, returning to the step S1.
Preferably, the preset expected value is 0.90.
In the above embodiment, a higher recognition accuracy can be ensured through the obtained first detection model and the second detection model, and an audio recognition model meeting expectations is obtained, when the first accuracy of the first detection model does not reach an expected value, the second detection model is obtained through training of the feature point test set, and the second accuracy is obtained through detection by using the feature point training set, which is equivalent to exchanging the training set and the test set, and the recognition model meeting expectations can be further ensured to be obtained, so that the accuracy of detecting audio data to be recognized by the audio recognition model meeting the expected value can be always kept at a higher level, and the stability and reliability of audio recognition are improved.
Fig. 2 is a block diagram of a good-sound stability early warning device of a screw water chiller according to an embodiment of the present invention.
Optionally, as another embodiment of the present invention, as shown in fig. 2, a good sound stability early warning device for a screw water chiller includes:
the data cleaning module is used for importing a plurality of original audio data, cleaning the original audio data, and obtaining a plurality of target audio data by taking the residual original audio data after the data cleaning as the target audio data, wherein the original audio data are obtained through a screw water cooling unit device;
the feature extraction module is used for respectively extracting features of the target audio data to obtain corresponding feature points, and collecting all the extracted feature points to obtain a feature point data set;
the model training module is used for constructing a training model and training the training model according to the feature point data set to obtain an audio recognition model;
the optimization processing module is used for optimizing the audio recognition model to obtain an audio recognition optimization model;
and the good tone stability early warning module is used for identifying and processing the audio data to be identified according to the audio identification optimization model to obtain an identification result of the audio data.
Optionally, as an embodiment of the present invention, the feature extraction module is specifically configured to:
respectively carrying out dimensionality reduction on the target audio data to obtain a plurality of audio data subjected to dimensionality reduction;
and respectively extracting the features of the plurality of audio data subjected to dimension reduction by using a preset spectrogram to obtain a plurality of feature points.
Optionally, as an embodiment of the present invention, the model training module is specifically configured to:
randomly dividing the feature point data set into a feature point training set and a feature point testing set;
constructing a model based on a support vector machine algorithm to obtain a support vector machine structure;
inputting the feature point training set and the feature point testing set into the support vector machine structure together to search for an optimal recognition hyperplane, so as to obtain an optimal recognition hyperplane, and obtaining a support vector set and VC (virtual component interconnect) credibility according to the optimal recognition hyperplane;
carrying out discrimination processing on the support vector set according to the VC credibility to obtain a discrimination function, and generating a training model according to the discrimination function;
and carrying out model screening processing on the training model according to the feature point training set and the feature point testing set to obtain an audio recognition model.
Optionally, as an embodiment of the present invention, the model training module is specifically configured to:
inputting the feature point training set into the training model according to preset iterative training times to perform iterative training to obtain a first detection model;
inputting the feature point test set into the first detection model for detection to obtain a first accuracy rate, judging whether the first accuracy rate reaches a preset expected value, if so, taking the first detection model as an audio recognition model, then carrying out optimization processing on the audio recognition model, and if not, inputting the feature point test set into the training model for iterative training according to the preset iterative training times to obtain a second detection model;
inputting the feature point training set into the second detection model for detection to obtain a second accuracy;
and judging whether the second accuracy reaches the preset expected value, if so, taking the second detection model as the audio recognition model, then carrying out optimization processing on the audio recognition model, and if not, randomly dividing the feature point data set into a feature point training set and a feature point testing set again.
Optionally, another embodiment of the present invention provides a good sound stability early warning device for a screw water chiller, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the good sound stability early warning method for the screw water chiller is implemented as described above. The device may be a computer or the like.
Optionally, another embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for early warning of sound stability of a screw water chiller according to the above is implemented.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. It will be understood that the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011207414.3A CN112101301B (en) | 2020-11-03 | 2020-11-03 | A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011207414.3A CN112101301B (en) | 2020-11-03 | 2020-11-03 | A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101301A CN112101301A (en) | 2020-12-18 |
| CN112101301B true CN112101301B (en) | 2021-02-26 |
Family
ID=73784513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011207414.3A Active CN112101301B (en) | 2020-11-03 | 2020-11-03 | A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101301B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170843A (en) * | 2007-11-30 | 2008-04-30 | 清华大学 | On-line Pure Tone Fault Diagnosis Method for Loudspeakers |
| CN104573355A (en) * | 2014-12-30 | 2015-04-29 | 北华大学 | Photoacoustic spectroscopy-based transformer fault diagnosis method employing parameter optimization SVM (support vector machine) |
| CN106404388A (en) * | 2016-09-13 | 2017-02-15 | 西安科技大学 | Scraper conveyor chain fluttering fault diagnosis method |
| WO2017112591A1 (en) * | 2015-12-20 | 2017-06-29 | Prophecy Sensors, Llc | Machine fault detection based on a combination of sound capture and on spot feedback |
| CN110992985A (en) * | 2019-12-02 | 2020-04-10 | 中国科学院声学研究所东海研究站 | Identification model determining method, identification method and identification system for identifying abnormal sounds of treadmill |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936818B (en) * | 2010-08-27 | 2012-09-05 | 上海交通大学 | Diagnostic system of non-contact type rotary mechanical failure |
| CN102819730A (en) * | 2012-07-23 | 2012-12-12 | 常州蓝城信息科技有限公司 | Method for extracting and recognizing facial features |
| CN106558318B (en) * | 2015-09-24 | 2020-04-28 | 阿里巴巴集团控股有限公司 | Audio recognition method and system |
| CN106053074B (en) * | 2016-08-02 | 2019-12-20 | 北京航空航天大学 | Rolling bearing sound signal fault feature extraction method based on STFT and rotational inertia entropy |
| CN108269249A (en) * | 2017-12-11 | 2018-07-10 | 深圳市智能机器人研究院 | A kind of bolt detecting system and its implementation |
| CN109117719B (en) * | 2018-07-02 | 2020-04-14 | 东南大学 | Driving attitude recognition method based on fusion features of local deformable component models |
| CN110837768B (en) * | 2018-08-16 | 2023-06-20 | 武汉大学 | An online detection and identification method for rare animal protection |
| CN110503131B (en) * | 2019-07-22 | 2023-10-10 | 北京工业大学 | Wind turbine health monitoring system based on big data analysis |
-
2020
- 2020-11-03 CN CN202011207414.3A patent/CN112101301B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170843A (en) * | 2007-11-30 | 2008-04-30 | 清华大学 | On-line Pure Tone Fault Diagnosis Method for Loudspeakers |
| CN104573355A (en) * | 2014-12-30 | 2015-04-29 | 北华大学 | Photoacoustic spectroscopy-based transformer fault diagnosis method employing parameter optimization SVM (support vector machine) |
| WO2017112591A1 (en) * | 2015-12-20 | 2017-06-29 | Prophecy Sensors, Llc | Machine fault detection based on a combination of sound capture and on spot feedback |
| CN106404388A (en) * | 2016-09-13 | 2017-02-15 | 西安科技大学 | Scraper conveyor chain fluttering fault diagnosis method |
| CN110992985A (en) * | 2019-12-02 | 2020-04-10 | 中国科学院声学研究所东海研究站 | Identification model determining method, identification method and identification system for identifying abnormal sounds of treadmill |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101301A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11467570B2 (en) | Anomalous sound detection apparatus, anomaly model learning apparatus, anomaly detection apparatus, anomalous sound detection method, anomalous sound generation apparatus, anomalous data generation apparatus, anomalous sound generation method and program | |
| CN119360278A (en) | A dangerous behavior identification and early warning method based on multimodal analysis | |
| CN104887224A (en) | Epileptic feature extraction and automatic identification method based on electroencephalogram signal | |
| CN117116290B (en) | Method and related equipment for locating defects of CNC machine tool parts based on multi-dimensional features | |
| CN112378942B (en) | White spirit grade classification and identification method based on nuclear magnetic resonance fingerprint | |
| CN119943384A (en) | A method for constructing a depression risk prediction model based on multimodal sample information | |
| CN114700587A (en) | A real-time detection method and system for solder leakage defects based on fuzzy reasoning and edge computing | |
| CN119377902B (en) | Multidimensional data fusion analysis method for detecting abnormal financial transaction | |
| CN115510909A (en) | Unsupervised algorithm for DBSCAN to perform abnormal sound features | |
| CN118866368A (en) | An impact quantification method and system for acute kidney injury assessment | |
| CN118016055A (en) | Heart sound classification method based on bidirectional long short-term memory network and multi-head attention mechanism | |
| CN110675858A (en) | Terminal control method and device based on emotion recognition | |
| CN112101301B (en) | A kind of good sound stability early warning method, device and storage medium of screw water-cooling unit | |
| Neili et al. | Gammatonegram based pulmonary pathologies classification using convolutional neural networks | |
| CN114781492B (en) | A network traffic data enhancement method for sample imbalance | |
| Cheng et al. | A novel chicken voice recognition method using the orthogonal matching pursuit algorithm | |
| CN114692693A (en) | Distributed optical fiber signal identification method, device and storage medium based on fractal theory | |
| CN118351886A (en) | Method, apparatus, electronic device, storage medium and computer program for voice quality inspection | |
| CN114781252A (en) | SVM band saw blade abrasion identification method based on improved artificial bee colony algorithm | |
| US20220027779A1 (en) | Value over replacement feature (vorf) based determination of feature importance in machine learning | |
| CN119837542B (en) | A method and system for EEG signal preprocessing and feature extraction | |
| CA3162546C (en) | Value over replacement feature (vorf) based determination of feature importance in machine learning | |
| CN118794532B (en) | Abnormal sound detection method and abnormal sound detection device | |
| CN118861529B (en) | Precise data acquisition system based on multi-parameter sensor | |
| CN119848427B (en) | Vacuum dry pump multi-fault prediction method and system based on improved C4.5 |
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 |