CN109387565A - A method of brake block internal flaw is detected by analysis voice signal - Google Patents
A method of brake block internal flaw is detected by analysis voice signal Download PDFInfo
- Publication number
- CN109387565A CN109387565A CN201811186178.4A CN201811186178A CN109387565A CN 109387565 A CN109387565 A CN 109387565A CN 201811186178 A CN201811186178 A CN 201811186178A CN 109387565 A CN109387565 A CN 109387565A
- Authority
- CN
- China
- Prior art keywords
- brake pad
- sound
- time
- signal
- neural network
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000003745 diagnosis Methods 0.000 claims abstract description 3
- 230000007547 defect Effects 0.000 claims description 22
- 230000005236 sound signal Effects 0.000 claims description 22
- 238000010079 rubber tapping Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 7
- 238000002474 experimental method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000032798 delamination Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002783 friction material Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of methods for detecting brake block internal flaw by analysis voice signal, comprising the following steps: obtains voice signal；Interception pretreatment；Wavelet time-frequency analysis；Extract gray level image feature；Characteristic quantity input neural network is trained；Brake block internal flaw is determined.This method is scientific and reasonable, and accuracy rate of diagnosis is high.
Description
Technical Field
The invention relates to the field of defect detection, and particularly relates to a method for detecting internal defects of a brake pad based on time-frequency characteristics and a neural network, wherein the internal defects of the brake pad are judged by processing sound signals.
Background
The quality of the brake pad is an important guarantee for driving safety, and the friction material absorbs and transmits power so as to achieve the purposes of speed reduction and braking. The service life of the brake pad has a plurality of influencing factors, the defects of the brake pad product are key reasons, and the internal defects are expressed as foreign matters, delamination and lateral cracks. At present, most of domestic enterprises adopt more traditional experienced worker-masters visual observation method and manual tapping method to judge whether internal defects exist, and the detection mode is too dependent on experience, time-consuming and labor-consuming and has no good accuracy. Therefore, it is very necessary to research the brake pad detection method and improve the detection efficiency and accuracy of the brake pad.
At present, researches for distinguishing the internal defects of the brake pad through sound signals are few, scholars such as the champion apply an acoustic detection technology to the aspect of the brake pad, and the on-line detection of the brake pad is realized by using a DSP (digital signal processor), but only a frequency domain analysis method is used in a signal analysis stage, phase information is lost when the sound signals are analyzed, a judgment equation is established by only using Fisher to distinguish whether the brake pad is good or bad, and the parameters of a judgment factor are relatively fuzzy when the judgment equation is discussed.
Disclosure of Invention
In order to overcome the defects of the traditional detection mode and improve the detection efficiency and the detection precision, the invention provides a method for detecting the internal defects of the brake pad by analyzing the sound signals, the method can effectively detect the internal defects of the brake pad, and the specific steps are as follows:
(1) collecting the sound signal of the brake pad to be detected through a capacitive sound sensor, and directly inputting the time domain signal into a computer connected with a vibration testing system after collection;
(2) preprocessing the collected sound signals, wherein a plurality of signals irrelevant to knocking are obtained in the knocking process, so that effective sound signals need to be intercepted, and multiple experiments show that the effective signals containing wave peak values of knocking sound can be obtained when the intercepting length is 256 points; loading data to form a one-dimensional vector, finding the maximum value of the one-dimensional vector (namely the peak value of the propagation of the tapping sound), taking 1/3 points of the peak value as a threshold value of a tapping effective signal, and intercepting 10 points before and 245 points after the time of the threshold value (peak value of 1/3) as effective tapping signals;
(3) and performing time-frequency analysis, selecting wavename = 'cmor1-1' to analyze and draw a time-frequency graph for a wavelet basis function, converting an image matrix into a gray image for conveniently extracting characteristics, generating a co-occurrence matrix for the obtained gray image, and calculating four characteristics of contrast, homogeneity, correlation and energy. Contrast (Contrast) describes the brightness Contrast between a pixel and its neighboring pixels in the return image. Homogeneity (Homogemetiy) describes the return metric GLCM for distribution of elements to a diagonal degree of closeness. Correlation (Correlation) describes a measure of how well a pixel is correlated with its neighbors throughout the image. The Energy (Energy) is calculated by the sum of squares of the elements in the returned glcm, and the specific formula is as follows:
formula of contrast
Wherein,；
homogeneity formula
Correlation formula
Formula of energy
Where p is the total pixels of the entire region,is an arbitrary coordinate within the area and,is composed ofA color value of the point;
(4) according to experimental data, a neural network is constructed to carry out pattern recognition, and according to experimental data generated by experiments, the invention constructs a three-layer neural network which comprises an input layer, a middle layer and an output layer. Inputting the four characteristic quantities into a neural network for training to obtain fault recognition capability, carrying out fault diagnosis according to logic output and fault corresponding states, and respectively representing fault types by output binary values: 01 a flawless brake pad; 10 have defective brake pads.
The method analyzes the internal defects of the brake pad through the collected sound signals, intercepts effective signals for time-frequency analysis, extracts four static characteristics to construct a neural network and identifies the quality and the internal defect types of the brake pad. Compared with the existing detection mode, the method has the following characteristics:
1. the brake pad is detected by adopting a mode of collecting sound signals, so that the interference of human factors is reduced, and the influence of the experience of detection personnel is eliminated; the invention improves the detection efficiency and precision, can cover all products and reduce the problem that the brake pad with defects cannot be accurately detected due to sampling inspection;
2. the method extracts time-frequency characteristics from the sound signals of the brake pad, and takes the four characteristics of contrast, homogeneity, correlation and energy as the detection basis of the internal defects of the brake pad;
3. the neural network pattern recognition method improves the detection accuracy.
Drawings
FIG. 1 is a diagram of the general steps of the method of the present invention;
FIG. 2 is a sound collection device for use with the present invention;
FIG. 3 is a diagram of an acquired original sound signal;
FIG. 4 is a sound signal after being pre-processed;
FIG. 5 is a time-frequency diagram drawn by time-frequency analysis performed by matlab
FIG. 6 is a gray scale image converted from the obtained time-frequency image;
fig. 7 is a summary of extracted features.
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
The hardware environment for implementation is a general computer, and the software environment is: matlab 2014a and windows 8. The method provided by the invention is realized by Matlab software.
Referring to fig. 1, fig. 1 is a flow chart of the present invention, and the implementation includes the following steps;
(1) collecting the sound signal of the brake pad to be detected through a sensor, and directly inputting the time domain signal into a computer connected with a vibration testing system after collection; the data acquisition system adopts a vibration test system, so that the knocking signals can be collected in real time in the experimental process and stored in a computer connected with the data acquisition system, and the sound acquisition device is shown in figure 2. The sampling frequency of the tapping signal was set to 9000 Hz. The knocking device adopts an LC-1 type force hammer, and a hammer handle of the knocking device consists of a force sensor for transmitting a signal cable, an impact hammer, an impact cushion seat and an elastic impact cushion seat. The raw signal obtained by the data acquisition system is shown in fig. 3;
(2) because the different positions of each brake pad are knocked for multiple times during the experiment, the system recording equipment records the whole knocking process, and a plurality of signals irrelevant to knocking are collected to the computer, so that the subsequent signal processing is troublesome and the memory of the computer is seriously wasted. Therefore, the effective sound signal needs to be intercepted, and multiple experiments show that the peak value of the knocking sound can be obtained when the interception length is 256 points, and the memory of a computer can be saved. After the data is loaded, the data is in the form of a one-dimensional vector, the maximum value of the one-dimensional vector (namely the peak value of the travel of the tapping sound) is found, 1/3 points of the peak value are taken as the threshold value of the tapping effective signal, and 10 points before and 245 points after the time of the threshold value (the peak value of 1/3) are intercepted as the effective tapping signals, as shown in fig. 4;
(3) and performing time-frequency analysis on the intercepted signals, wherein a wavelet function wavename = 'cmor1-1' is selected for analysis, and a time-frequency graph (shown in figure 5) of the brake pad is drawn by using MATLAB and converted into a gray graph (shown in figure 6). The resulting gray image is then used to generate a co-occurrence matrix GLCM by means of the graycotatrix function provided by MATLAB, which graycospros normalizes the gray co-occurrence matrix so that the sum of the elements equals 1. The normalized glcm was used to calculate four static properties of contrast, homogeneity, correlation, energy. 6 samples of the test, three good brake pads, and three layered brake pads were taken. Extracting the characteristics of 'Contrast', 'homogeexist', 'Correlation' and 'Energy'. As shown in FIG. 7, samples Nos. 1 to 3 are layered brake pads, and samples Nos. 4 to 6 are good brake pads. From the contrast, the contrast value of a sample of the layered brake pad is larger than the good brake pad contrast, and the values of the three characteristics of the homogeneity, the correlation and the energy of the layered brake pad are smaller than those of the good brake pad;
(4) according to experimental data generated by experiments, the invention constructs a three-layer neural network, wherein the three-layer neural network comprises an input layer, a middle layer and an output layer. And importing test data, adjusting parameters and inputting an objective function by using a MATLAB self-contained pattern recognition tool box (nprtool), and then obtaining a pattern recognition result. Taking experimental brake pad samples (80 experimental samples), and taking 20 good brake pads; brake pads with 20 foreign matters; 20 layered brake pads; 20 brake pads with side cracks. The brake pads in all the experimental samples are divided into three classes, 60 samples are used for training, 10 samples are used for verification, and 10 samples are used for testing. Through experimental analysis, the success rate of defect detection is 98.75%, and whether the brake pad has defects or not can be basically detected.
Claims (4)
1. A method for detecting internal defects of a brake pad by analyzing sound signals is characterized by comprising the following steps:
acquiring a sound signal; pre-treating; extracting time-frequency characteristics; state identification;
(1) acquiring a sound signal: collecting the sound signal of the brake pad to be detected through a sensor, and directly inputting the time domain signal into a computer connected with a vibration testing system after collection;
(2) pretreatment: preprocessing the collected sound signals and intercepting effective sound signals;
(3) extracting time-frequency characteristics: drawing a time-frequency graph by utilizing wavelet analysis, converting the time-frequency graph into a gray-scale graph, and extracting 4 attribute characteristics of the gray-scale graph;
(4) and (3) state identification: inputting the characteristic quantity into a neural network for training; and judging internal defects of the brake pad.
2. A method for detecting internal defects of a brake pad by analyzing an acoustic signal according to claim 1, wherein: in the step (2), a plurality of signals irrelevant to knocking are acquired to the computer in the knocking process, so that troubles are caused to subsequent signal processing, and the memory of the computer is seriously wasted; therefore, effective sound signals need to be intercepted, and multiple experiments show that the peak value of knocking sound can be obtained when the interception length is 256 points, and the memory of a computer can be saved; in the specific method, after data is loaded, the data is in a one-dimensional vector form, the maximum value of the one-dimensional vector (namely the peak value of the travel of the tapping sound) is found, 1/3 points of the peak value are taken as the threshold value of the tapping effective signal, and 10 points before and 245 points after the time of the threshold value (1/3 peak value) are intercepted to be taken as the effective tapping signal.
3. A method for detecting internal defects of a brake pad by analyzing an acoustic signal according to claim 1, wherein: in the step (3), a time-frequency graph is drawn by utilizing wavelet analysis and converted into a gray-scale graph, and four characteristics of contrast, homogeneity, correlation and energy of the gray-scale graph are extracted; the specific formula is as follows:
formula of contrast
Wherein,；
homogeneity formula
Correlation formula
Formula of energy
Where p is the total pixels of the entire region,is an arbitrary coordinate within the area and,is composed ofThe color value of the point.
4. A method for detecting internal defects of a brake pad by analyzing an acoustic signal according to claim 1, wherein: in the step (4), a three-layer neural network is constructed, wherein the three-layer neural network comprises an input layer, a middle layer and an output layer; inputting the four characteristic quantities of contrast, homogeneity, correlation and energy in the step (3) into a neural network for training to obtain fault recognition capability, and performing fault diagnosis according to logic output and fault corresponding states, wherein the output binary values respectively represent fault types: 01 a flawless brake pad; 10 have defective brake pads.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811186178.4A CN109387565A (en) | 2018-10-12 | 2018-10-12 | A method of brake block internal flaw is detected by analysis voice signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811186178.4A CN109387565A (en) | 2018-10-12 | 2018-10-12 | A method of brake block internal flaw is detected by analysis voice signal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109387565A true CN109387565A (en) | 2019-02-26 |
Family
ID=65427355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811186178.4A Pending CN109387565A (en) | 2018-10-12 | 2018-10-12 | A method of brake block internal flaw is detected by analysis voice signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109387565A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006664A (en) * | 2019-04-03 | 2019-07-12 | 上海好耐电子科技有限公司 | Automobile brake noise expert's detection method neural network based |
| CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Automatic inspection method and platform for transformer substation |
| CN111257415A (en) * | 2020-01-17 | 2020-06-09 | 同济大学 | Tunnel damage detection management system based on mobile train vibration signal |
| CN111983020A (en) * | 2020-08-25 | 2020-11-24 | 绍兴市特种设备检测院 | Metal component internal defect knocking detection and identification system and identification method |
| CN113514547A (en) * | 2021-07-05 | 2021-10-19 | 哈尔滨理工大学 | High-speed rail brake pad nondestructive testing method based on sound vibration method |
| CN116300837A (en) * | 2023-05-25 | 2023-06-23 | 山东科技大学 | Fault diagnosis method and system for unmanned surface vehicle actuator |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592631A (en) * | 2009-07-10 | 2009-12-02 | 浙江大学 | Automatic detection device for quality of brake pad |
| CN102419347A (en) * | 2011-08-17 | 2012-04-18 | 江苏安捷汽车配件有限公司 | Brake pad quality detection control device, its usage method and application |
| CN103489446A (en) * | 2013-10-10 | 2014-01-01 | 福州大学 | Twitter identification method based on self-adaption energy detection under complex environment |
| CN103646135A (en) * | 2013-11-28 | 2014-03-19 | 哈尔滨医科大学 | Computer-assisted ultrasonic diagnosis method for left atrium/left auricle thrombus |
| CN105225223A (en) * | 2015-08-27 | 2016-01-06 | 南京市计量监督检测院 | Based on the damage Detection of Smart Composite Structure method of wavelet analysis and BP neural network |
| CN106297770A (en) * | 2016-08-04 | 2017-01-04 | 杭州电子科技大学 | The natural environment sound identification method extracted based on time-frequency domain statistical nature |
| CN106326826A (en) * | 2015-10-10 | 2017-01-11 | 北京控制与电子技术研究所 | Visible-image-based autonomous landing zone selection method for deep space detector |
| CN106600612A (en) * | 2016-12-27 | 2017-04-26 | 重庆大学 | Damage identification and detection method for electric automobile before and after renting |
| CN106680371A (en) * | 2016-12-30 | 2017-05-17 | 陕西科技大学 | Electric porcelain body online flaw detection device and electric porcelain body online flaw detection method |
| CN108508088A (en) * | 2018-03-22 | 2018-09-07 | 清华大学 | A kind of antenna house non-destructive testing device and method based on percussion sonic method |
-
2018
- 2018-10-12 CN CN201811186178.4A patent/CN109387565A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592631A (en) * | 2009-07-10 | 2009-12-02 | 浙江大学 | Automatic detection device for quality of brake pad |
| CN102419347A (en) * | 2011-08-17 | 2012-04-18 | 江苏安捷汽车配件有限公司 | Brake pad quality detection control device, its usage method and application |
| CN103489446A (en) * | 2013-10-10 | 2014-01-01 | 福州大学 | Twitter identification method based on self-adaption energy detection under complex environment |
| CN103646135A (en) * | 2013-11-28 | 2014-03-19 | 哈尔滨医科大学 | Computer-assisted ultrasonic diagnosis method for left atrium/left auricle thrombus |
| CN105225223A (en) * | 2015-08-27 | 2016-01-06 | 南京市计量监督检测院 | Based on the damage Detection of Smart Composite Structure method of wavelet analysis and BP neural network |
| CN106326826A (en) * | 2015-10-10 | 2017-01-11 | 北京控制与电子技术研究所 | Visible-image-based autonomous landing zone selection method for deep space detector |
| CN106297770A (en) * | 2016-08-04 | 2017-01-04 | 杭州电子科技大学 | The natural environment sound identification method extracted based on time-frequency domain statistical nature |
| CN106600612A (en) * | 2016-12-27 | 2017-04-26 | 重庆大学 | Damage identification and detection method for electric automobile before and after renting |
| CN106680371A (en) * | 2016-12-30 | 2017-05-17 | 陕西科技大学 | Electric porcelain body online flaw detection device and electric porcelain body online flaw detection method |
| CN108508088A (en) * | 2018-03-22 | 2018-09-07 | 清华大学 | A kind of antenna house non-destructive testing device and method based on percussion sonic method |
Non-Patent Citations (5)
| Title |
|---|
| 张国强 等: "基于敲击信号的刹车片内部缺陷检测", 《组合机床与自动化加工技术》 * |
| 张益杰 等: "磁共振图像的纹理分析在界定高级别脑胶质瘤边界中的应用", 《临床放射学杂志》 * |
| 陈刚 等: "一种食管癌内镜图像识别算法", 《计算机科学》 * |
| 陈彩文 等: "基于图像纹理特征的养殖鱼群摄食活动强度评估", 《农业工程学报》 * |
| 隋文涛 等: "平稳小波变换在轴承振动信号去噪中的应用", 《轴承》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006664A (en) * | 2019-04-03 | 2019-07-12 | 上海好耐电子科技有限公司 | Automobile brake noise expert's detection method neural network based |
| CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Automatic inspection method and platform for transformer substation |
| CN111257415A (en) * | 2020-01-17 | 2020-06-09 | 同济大学 | Tunnel damage detection management system based on mobile train vibration signal |
| CN111257415B (en) * | 2020-01-17 | 2021-08-10 | 同济大学 | Tunnel damage detection management system based on mobile train vibration signal |
| CN111983020A (en) * | 2020-08-25 | 2020-11-24 | 绍兴市特种设备检测院 | Metal component internal defect knocking detection and identification system and identification method |
| CN111983020B (en) * | 2020-08-25 | 2023-08-22 | 绍兴市特种设备检测院 | System and method for detecting and identifying internal defects of metal component through knocking |
| CN113514547A (en) * | 2021-07-05 | 2021-10-19 | 哈尔滨理工大学 | High-speed rail brake pad nondestructive testing method based on sound vibration method |
| CN116300837A (en) * | 2023-05-25 | 2023-06-23 | 山东科技大学 | Fault diagnosis method and system for unmanned surface vehicle actuator |
| CN116300837B (en) * | 2023-05-25 | 2023-08-18 | 山东科技大学 | Fault diagnosis method and system for unmanned surface vehicle actuator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109387565A (en) | A method of brake block internal flaw is detected by analysis voice signal | |
| CN109782274B (en) | Water damage identification method based on time-frequency statistical characteristics of ground penetrating radar signals | |
| CN102621150B (en) | Airplane skin damage identification method based on gray level co-occurrence matrix and support vector machine | |
| CN112858473B (en) | Turnout switch blade damage state monitoring method based on feature fusion | |
| Sun et al. | On-line detection of eggshell crack based on acoustic resonance analysis | |
| US6213958B1 (en) | Method and apparatus for the acoustic emission monitoring detection, localization, and classification of metabolic bone disease | |
| CN110363746B (en) | Ultrasonic nondestructive detection signal classification method based on convolutional neural network | |
| CN102928435A (en) | Aircraft skin damage identification method and device based on image and ultrasound information fusion | |
| CN108680796B (en) | Electromagnetic information leakage detection system and method for computer display | |
| Posilović et al. | Flaw detection from ultrasonic images using YOLO and SSD | |
| CN103745239B (en) | A kind of forest reserves measuring method based on satellite remote sensing technology | |
| WO2021248962A1 (en) | Non-destructive testing method and device for testing and distinguishing internal and external defects of steel wire rope | |
| CN104008551B (en) | A kind of Citrus Huanglongbing pathogen detection method based on visible images | |
| CN101852768A (en) | Workpiece flaw identification method based on compound characteristics in magnaflux powder inspection environment | |
| Xi et al. | Bearing diagnostics based on pattern recognition of statistical parameters | |
| CN110967409A (en) | Method for extracting and identifying original data features based on multi-channel ultrasonic flaw detection | |
| CN103593668B (en) | Automatic crack identification method in metal plate stamping connector mechanical property test | |
| Xu et al. | Rail defect detection method based on recurrent neural network | |
| CN111783616B (en) | Nondestructive testing method based on data-driven self-learning | |
| CN111753877B (en) | Product quality detection method based on deep neural network migration learning | |
| CN110020637A (en) | A kind of analog circuit intermittent fault diagnostic method based on more granularities cascade forest | |
| CN115656335A (en) | Method for quickly detecting and identifying internal defects of bearing ring | |
| CN112302061A (en) | Intelligent rapid interpretation method for integrity detection signal of low-strain foundation pile | |
| Li et al. | Non-destructive detection on the egg crack based on wavelet transform | |
| CN104833724B (en) | A kind of bird egg crack detecting method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190226 |
|
| WD01 | Invention patent application deemed withdrawn after publication |