CN110940732B - A method for online monitoring and evaluation of rail structural corrosion - Google Patents
A method for online monitoring and evaluation of rail structural corrosion Download PDFInfo
- Publication number
- CN110940732B CN110940732B CN201911404582.9A CN201911404582A CN110940732B CN 110940732 B CN110940732 B CN 110940732B CN 201911404582 A CN201911404582 A CN 201911404582A CN 110940732 B CN110940732 B CN 110940732B
- Authority
- CN
- China
- Prior art keywords
- corrosion
- rail
- rail structure
- steel rail
- degree
- 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.)
- Expired - Fee Related
Links
- 238000005260 corrosion Methods 0.000 title claims abstract description 229
- 230000007797 corrosion Effects 0.000 title claims abstract description 228
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011156 evaluation Methods 0.000 title claims abstract description 24
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 238000007635 classification algorithm Methods 0.000 claims abstract description 11
- 230000003044 adaptive effect Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 4
- 230000005284 excitation Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000003745 diagnosis Methods 0.000 claims description 11
- 230000002238 attenuated effect Effects 0.000 claims description 7
- 230000006378 damage Effects 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000007499 fusion processing Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims 1
- 230000003595 spectral effect Effects 0.000 claims 1
- 229910000831 Steel Inorganic materials 0.000 abstract description 124
- 239000010959 steel Substances 0.000 abstract description 124
- 238000001514 detection method Methods 0.000 abstract description 10
- 230000036541 health Effects 0.000 abstract description 4
- 238000001228 spectrum Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 3
- 239000010935 stainless steel Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
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
- G01N29/11—Analysing solids by measuring attenuation of acoustic waves
-
- 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
- G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
-
- 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
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/025—Change of phase or condition
- G01N2291/0258—Structural degradation, e.g. fatigue of composites, ageing of oils
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/26—Scanned objects
- G01N2291/262—Linear objects
- G01N2291/2623—Rails; Railroads
Landscapes
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
本发明公开了一种钢轨结构腐蚀在线监测与评价方法，涉及钢轨结构健康监测与智能检测领域。利用压电导波技术主动检测钢轨腐蚀结构，构建多主体的钢轨结构腐蚀程度识别框架，协同处理钢轨结构腐蚀数据，提高钢轨腐蚀数据的处理效率。运用钢轨腐蚀因子表示钢轨结构腐蚀特征信息，根据检测到的回波信号与导波信号之间的相位和幅值关系，提出自适应神经网络模糊分类算法实现钢轨腐蚀程度的计算，用于实现钢轨结构腐蚀程度的评价。本发明钢轨腐蚀在线监测与评价方法将推动智能检测技术在轨道交通工程的应用。
The invention discloses an on-line monitoring and evaluation method for steel rail structure corrosion, and relates to the field of steel rail structure health monitoring and intelligent detection. The piezoelectric guided wave technology is used to actively detect the corrosion structure of the rail, build a multi-subject identification framework for the corrosion degree of the rail structure, and collaboratively process the corrosion data of the rail structure to improve the processing efficiency of the rail corrosion data. The rail corrosion factor is used to represent the corrosion characteristic information of the rail structure. According to the phase and amplitude relationship between the detected echo signal and the guided wave signal, an adaptive neural network fuzzy classification algorithm is proposed to calculate the corrosion degree of the rail. Evaluation of the degree of structural corrosion. The online monitoring and evaluation method for rail corrosion of the present invention will promote the application of the intelligent detection technology in rail transit engineering.
Description
Technical Field
The invention relates to the field of steel rail structure health monitoring and intelligent detection, in particular to a steel rail structure corrosion online monitoring and evaluating method.
Background
The corrosion of the steel rail structure directly affects the running safety of trains, particularly, the corrosion has huge harm to rail traffic and high detection and maintenance cost every year in the recent rapid development of high-speed railways in China. The width of our country is vast, the complexity of geological and weather environments determines the complexity of the working environment of the steel rail structure, and great challenge is brought to the monitoring of the corrosion of the steel rail structure. How to apply intelligent sensing and advanced signal processing technology to the on-line monitoring of the corrosion of the steel rail structure is a current important subject, and the intelligent operation and maintenance level of the rail transit industry is improved.
At present, steel rail structure monitoring and corrosion monitoring technologies are receiving more and more attention, and rapid development of rail transit detection technologies and methods is promoted. Yuanjun, Guo Hua, Zhongming and ChenChong wood invent a corrosion-resistant steel rail for express train with excellent corrosion resistance and a production method thereof, the corrosion-resistant steel rail comprises a steel rail matrix and a corrosion-resistant layer arranged on the surface of the steel rail matrix (the corrosion-resistant steel rail for express train and the production method thereof, the publication number: CN 107779751A). The invention discloses a device and a method for monitoring the stress of a steel rail based on ultrasonic guided waves, which are based on Zhuliqiang, remainder Zymond and Scheining.A guided wave excitation source is arranged on the surface of the rail waist part of the steel rail, and at least one guided wave receiver is arranged on the steel rail and is spaced from the guided wave excitation source so as to receive the guided waves sent by the guided wave excitation source. The temperature stress of the seamless track steel rail is monitored in real time on line, the stress overrun interval is pre-warned in real time, and the safe operation of the seamless track is ensured (the monitoring device and the method of the steel rail stress based on ultrasonic guided waves, and the authorization notice number is CN 104614105B). At present, a unified data acquisition and processing frame is lacked in the on-line detection and the on-line detection of the steel rail structure, and how to construct the on-line monitoring and evaluation frame of the corrosion of the steel rail structure by using an intelligent sensing and signal processing technology improves the precision of the data acquisition of the steel rail structure and the distributed calculation and processing efficiency of the steel rail data.
In practice, the online monitoring of the steel rail corrosion structure plays a very great role in guaranteeing the rail transit industry, and the corresponding detection device, technology and method all receive high attention from the industry. The steel rail structure corrosion on-line monitoring and evaluating method based on the multi-body technology utilizes the distributed data processing technology to calculate and analyze the data characteristics of the steel rail structure corrosion on different levels, and realizes the on-line monitoring of the steel rail structure corrosion. The evaluation on the corrosion degree of the steel rail structure is realized by applying an advanced signal processing technology, the intelligent level of the steel rail structure is improved, and the safety performance of rail transit infrastructure is guaranteed.
Disclosure of Invention
In view of the above defects or improvement requirements of the prior art, a first object of the present invention is to provide a method for online monitoring of rail corrosion and evaluation of rail corrosion degree, which constructs a multi-body rail structure corrosion degree identification framework, including a sensing data acquisition body, a sensing data representation body, a rail structure corrosion diagnosis body, and a rail structure corrosion degree identification body. The multi-main-body system cooperatively processes the steel rail structure corrosion data, and the processing efficiency of the steel rail corrosion data is improved. The method comprises the steps of actively detecting the corrosion condition of the steel rail by adopting a guided wave technology, expressing structural corrosion characteristic information of the steel rail by using a steel rail corrosion factor according to the phase and amplitude relation between a detected echo signal and a guided wave signal, and providing a self-adaptive neural network fuzzy classification algorithm to reveal the relation between the corrosion degree of the steel rail and the corrosion factor for realizing the evaluation of the corrosion degree of the steel rail structure.
Aiming at the defects or the improvement requirements of the prior art, the second purpose of the invention is to invent a steel rail structure online monitoring and evaluation method realizing flow, a piezoelectric excitation module is used for actively exciting a guided wave signal and is used for actively detecting the corrosion condition of a steel rail structure, a piezoelectric sensing array is used for detecting an echo signal, different points between the echo signal and the guided wave signal are compared, a multi-main-body steel rail corrosion structure health monitoring frame is used for realizing the steel rail corrosion degree evaluation, and the steel rail structure online monitoring and evaluation method realizing flow mainly comprises the following steps:
(1) the piezoelectric excitation and sensing module and the corresponding circuit are arranged on the outer surface of the steel rail;
(2) the piezoelectric excitation module actively generates a guided wave signal under the action of an external signal;
(3) the guided wave signals are transmitted in the steel rail structure, and if corrosion exists in the steel rail structure, the guided wave signals are attenuated, reflected and refracted, so that the transmission of the guided wave signals in the steel rail is influenced;
(4) the piezoelectric sensing data acquisition main body acquires guided wave signals attenuated by a corrosion structure, and detected echo signals are used for analyzing the corrosion condition of the steel rail structure;
(5) comparing the difference of the echo signals and the guided wave signals in phase and amplitude, and providing a steel rail structure corrosion factor by the data interpretation main body for representing and extracting data characteristics of a steel rail corrosion structure;
(6) the steel rail structure corrosion diagnosis main body realizes the diagnosis of the steel rail structure corrosion according to the information of a plurality of corrosion factors representing the steel rail corrosion condition;
(7) the steel rail structure corrosion degree identification main body constructs a corresponding relation between the steel rail structure corrosion degree and a steel rail corrosion factor according to the proposed adaptive neural network fuzzy classification algorithm, and identifies the corrosion degree of the steel rail structure;
(8) the steel rail structure corrosion degree is calculated and monitored by using a multi-main-body system, and the method is applied to predicting the steel rail corrosion degree and development trend and improving the intelligent operation and maintenance level of the steel rail structure.
Furthermore, the steel rail structure corrosion on-line monitoring and evaluation method utilizes the piezoelectric excitation module to actively detect the corrosion condition of the steel rail structure, actively transmits the guided wave signal for detecting the corrosion condition of the steel rail, compares the difference of the echo signal and the guided wave signal in phase and amplitude, and improves the intelligent level of steel rail structure corrosion on-line monitoring.
Further, the method for on-line monitoring and evaluating steel rail structural corrosion compares the relationship between the echo and the guided wave signal from the angle of phase and amplitude, provides characteristic information of corrosion factor representing steel rail structural corrosion, and comprises the following steps: the method comprises the steps of cross-correlation corrosion factors, spatial phase corrosion factors, frequency spectrum amplitude difference corrosion factors, mean square error corrosion factors, comprehensive amplitude and phase characteristic corrosion factors, comprehensively analyzing the relation between various factors and steel rail structural corrosion, and providing a calculation basis of steel rail corrosion.
Further, the steel rail structure corrosion on-line monitoring and evaluating method utilizes an adaptive neural network fuzzy classification intelligent algorithm to reveal the relationship between various corrosion damage factors and the corrosion degree. The intelligent classification algorithm is a 5-layer structure, the corrosion factor is normalized by a layered calculation method, and the corresponding relation between the corrosion degree and the corrosion factor is disclosed, so that the calculation method of the corrosion degree of the steel rail structure is provided through an echo signal.
Generally, compared with the prior art, the steel rail structure corrosion on-line monitoring and evaluating method has the advantages that the piezoelectric excitation module is used for generating the excitation wave signal to actively detect the steel rail structure corrosion condition, the steel rail corrosion on-line monitoring frame based on multi-main-body technology cooperative monitoring is constructed, the corrosion factor is used for ensuring the corrosion characteristic signal condition of the steel rail, and the layered distributed signal processing frame is adopted, so that the calculation efficiency of the steel rail structure corrosion is improved; the intelligent classification algorithm is provided to reveal the relationship between various corrosion damage factors and the corrosion degree, and the corrosion degree of the steel rail structure is identified and evaluated.
In conclusion, according to the steel rail structure corrosion online monitoring and evaluating method, the calculation efficiency and accuracy of the hierarchical steel rail structure corrosion characteristic data are improved by adopting distributed calculation, the corrosion degree of the steel rail structure is evaluated by adopting a multi-characteristic data fusion method, an intelligent sensing and advanced signal technology is applied to the rail traffic industry, and the intelligent operation and maintenance level of rail traffic infrastructure is improved.
Drawings
Fig. 1 is a schematic diagram of online monitoring of steel rail corrosion based on a guided wave detection technology.
FIG. 2 is a multi-body system framework for rail corrosion monitoring and evaluation.
FIG. 3 is a relationship between guided wave signals and echo signals.
FIG. 4 is a structure of an adaptive neural network fuzzy classification algorithm, which employs a layered structure for evaluating the corrosion degree of a steel rail structure.
FIG. 5 is a detailed implementation flow of the steel rail structure corrosion online monitoring and evaluation method based on the multi-subject cooperation technology.
The symbolic meanings in the figures are as follows:
11-steel rail; 12-a piezoelectric excitation module; 13-a piezoelectric sensing module; 14-corrosion site of rail structure; 15-the piezoelectric excitation module actively excites the guided wave signal; and 16-the piezoelectric sensing module receives echo signals.
31-a piezoelectric excitation module; 32-a piezoelectric sensing module; 33-damage of the rail structure; 34-echo signals received by piezoelectric sensing; 35-guided wave signals emitted by the piezoelectric excitation module; 36-guided wave launch; 37-guided wave refraction.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1, a schematic diagram of online monitoring of rail corrosion based on a guided wave detection technology is given, a piezoelectric excitation module 12 and a piezoelectric sensing module 13 are respectively installed on the outer surface of a rail 11, the piezoelectric excitation module actively generates a guided wave signal 15 under the action of an external signal, the guided wave signal propagates in a rail structure, when the guided wave signal propagates to a corrosion part 14 of the rail structure, the guided wave signal is attenuated, reflected and refracted, and a corresponding echo signal 16 is generated and detected by the piezoelectric sensing module 13. And comparing different points between the phase and amplitude of the echo signal and the guided wave signal, and providing a feasible technical scheme for monitoring the corrosion of the steel rail structure.
In order to further analyze the relationship between the echo signals and the guided wave signals, a steel rail structure corrosion diagnosis method is invented, and the method is shown in figure 2. The invention relates to a multi-main-body system framework for monitoring and evaluating steel rail corrosion, which comprises a sensing data acquisition main body, a sensing data representation main body, a steel rail structure corrosion diagnosis main body and a steel rail structure corrosion degree identification main body. The multi-body system adopts distributed data to process the steel rail structure corrosion data, and the processing efficiency of the steel rail corrosion data is improved. The sensing data acquisition main body comprises a piezoelectric active excitation unit and a plurality of piezoelectric sensing units, the piezoelectric sensing units receive echo signals on the steel rail, the echo signals are stored in a database, and data of different piezoelectric sensing units are fused. The fused sensing data is transmitted to a sensing data main body, corresponding characteristic information is extracted according to corrosion factors representing the corrosion condition of the steel rail structure, the phase and amplitude difference of echo signals and guided wave signals is compared, and the characteristic information of cross-correlation corrosion factors, space phase corrosion factors, frequency spectrum amplitude difference corrosion factors, mean square error corrosion factors, comprehensive amplitudes and phase characteristic corrosion factors is extracted. The corrosion diagnosis main body comprehensively considers the characteristic information of different corrosion factors and fuses the characteristic information on the corrosion factor characteristic layer to realize the diagnosis of the steel rail structure. The corrosion degree identification main body utilizes the adaptive neural network fuzzy classification algorithm to reveal the relation between the steel rail corrosion degree and the corrosion factor, so as to realize the evaluation of the steel rail structure corrosion degree and finally output the damage degree result of the steel rail structure.
Fig. 3 is a relationship between guided wave signals and echo signals, in the method for monitoring and evaluating corrosion of a steel rail structure on line, the relationship between echo and guided wave signals is compared from phase and amplitude angles, characteristic information of corrosion factors representing corrosion of the steel rail structure is given, and the method includes: the method comprises the steps of cross-correlation corrosion factors, spatial phase corrosion factors, frequency spectrum amplitude difference corrosion factors, mean square error corrosion factors, comprehensive amplitude and phase characteristic corrosion factors, comprehensively analyzing the relation between various factors and steel rail structural corrosion, and providing a calculation basis of steel rail corrosion. The cross-correlation corrosion factor represents the difference between echo signals in a healthy state and a corrosion state of the structure, and represents the correlation degree between the steel rail corrosion echo signal and the signal in the healthy state. The spatial phase corrosion factor describes the magnitude of the phase angle between the normalized guided wave signal and the echo signal. The frequency spectrum amplitude difference corrosion factor reflects the change of the signal amplitude value, and the relation of signal frequency response is measured through the amplitude value. The mean square error corrosion factor is the relative difference between the mean square error of the healthy echo signal and the mean square error of the corrosion echo signal. And integrating the amplitude characteristic corrosion factor and the phase characteristic corrosion factor, and reflecting the change condition of the whole echo signal from the phase and the amplitude.
For example, fig. 4, the relation between various corrosion damage factors and the corrosion degree is revealed by using an adaptive neural network fuzzy classification intelligent algorithm. The intelligent classification algorithm is a 5-layer structure, the corrosion factor is normalized by a layered calculation method, and the corresponding relation between the corrosion degree and the corrosion factor is disclosed, so that the calculation method of the corrosion degree of the steel rail structure is provided through an echo signal.
A first layer: inputting 5 corrosion factors (relationship among wave signals, and characteristic information of the corrosion factors representing steel rail structural corrosion, including cross-correlation corrosion factors, spatial phase corrosion factors, frequency spectrum amplitude difference corrosion factors, mean square error corrosion factors, comprehensive amplitude values and phase characteristic corrosion factors), performing fuzzification processing (high and low) on a first layer, and performing fuzzification operation on the characteristics of the input corrosion factors by using a fuzzy membership function to obtain a membership degree between 0 and 1;
a second layer: multiplying the membership degree of each corrosion factor characteristic according to the corrosion factors representing the corrosion degree of the steel rail structure to obtain the triggering strength of each rule;
and a third layer: normalizing the triggering strength of each rule to represent the triggering proportion of the rule in the whole rule base;
a fourth layer: calculating a result of the rule using a linear combination of the input features;
and a fifth layer: and defuzzification is carried out to obtain the output of the corrosion degree of the steel rail structure, and the final output result of the corrosion degree of the steel rail structure is the weighted average value of each rule.
FIG. 5 is a flow for implementing the steel rail structure on-line monitoring and evaluation method, which utilizes a multi-main-body steel rail corrosion structure health monitoring frame to implement the steel rail corrosion degree evaluation, and the steel rail structure on-line monitoring and evaluation method implementation flow specifically comprises the following steps:
(1) the piezoelectric excitation, the plurality of sensing modules and corresponding circuits are all arranged on the outer side surface of the steel rail;
(2) the piezoelectric excitation module actively generates a guided wave signal under the action of an external signal, wherein a five-peak wave modulated by a sinusoidal signal is adopted as the guided wave signal and is used for actively detecting the corrosion condition of a steel rail structure;
(3) the guided wave signals (the quintuplex waves) are transmitted in the steel rail structure, if corrosion exists in the steel rail structure, the guided wave signals (the quintuplex waves) are attenuated, reflected and refracted, and the transmission of the guided wave signals (the quintuplex waves) in the steel rail is influenced;
(4) the piezoelectric sensing unit acquires a guided wave signal (quintuplex wave) attenuated by a corrosion structure, and the detected echo signal (quintuplex wave) is used for analyzing the corrosion condition of the steel rail structure;
(5) comparing the difference of the phase and the amplitude of the echo signal (quincuncial wave) and the guided wave signal (quincuncial wave), and providing a steel rail structure corrosion factor by a data interpretation main body for representing and extracting the data characteristics of a steel rail corrosion structure, wherein the corrosion factor adopts a cross-correlation corrosion factor, a space phase corrosion factor, a frequency spectrum amplitude difference corrosion factor, a mean square error corrosion factor, a comprehensive amplitude and a phase characteristic corrosion factor;
(6) the steel rail structure corrosion diagnosis main body adopts a characteristic fusion processing method according to various corrosion factor information representing the steel rail corrosion condition to realize the diagnosis of the steel rail structure corrosion;
(7) the steel rail structure corrosion degree identification main body adopts a self-adaptive neural network fuzzy classification algorithm to carry out pasting processing on different corrosion factors, fuses characteristic information of the different corrosion factors, constructs a corresponding relation between the steel rail structure corrosion degree and the steel rail corrosion factor, and identifies the corrosion degree of the steel rail structure;
(8) the steel rail structure corrosion degree is calculated and monitored by using a multi-main-body system, the steel rail corrosion degree and the development trend are predicted, and the intelligent operation and maintenance level of the steel rail structure is improved.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404582.9A CN110940732B (en) | 2019-12-30 | 2019-12-30 | A method for online monitoring and evaluation of rail structural corrosion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404582.9A CN110940732B (en) | 2019-12-30 | 2019-12-30 | A method for online monitoring and evaluation of rail structural corrosion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110940732A CN110940732A (en) | 2020-03-31 |
| CN110940732B true CN110940732B (en) | 2022-03-01 |
Family
ID=69913588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911404582.9A Expired - Fee Related CN110940732B (en) | 2019-12-30 | 2019-12-30 | A method for online monitoring and evaluation of rail structural corrosion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110940732B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115235877A (en) * | 2021-04-23 | 2022-10-25 | 中国石油化工股份有限公司 | Corrosion state monitoring system and stress corrosion state evaluation method and device |
| CN114510767B (en) * | 2022-02-22 | 2022-09-02 | 中交第四公路工程局有限公司 | Steel structure assembly effect evaluation method and system based on three-dimensional modeling |
| CN115586252B (en) * | 2022-09-15 | 2025-04-25 | 国网湖北省电力有限公司超高压公司 | Guided wave pulse echo detection method for corrosion damage of ground flat steel in different soil environments |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3978712A (en) * | 1971-11-17 | 1976-09-07 | Scanning Systems, Inc. | Method and apparatus for testing wear, size and residual stress conditions |
| CN101666783A (en) * | 2008-09-01 | 2010-03-10 | 中国科学院金属研究所 | Ultrasonic guided wave composite non-destructive testing method and device |
| CN109649432A (en) * | 2019-01-23 | 2019-04-19 | 浙江大学 | Cloud platform rail integrity monitoring systems and method based on guided wave technology |
| CN112906672A (en) * | 2021-04-08 | 2021-06-04 | 上海应用技术大学 | Steel rail defect identification method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6424150B2 (en) * | 1999-03-17 | 2002-07-23 | Southwest Research Institute | Magnetostrictive sensor rail inspection system |
| US9036861B2 (en) * | 2010-04-22 | 2015-05-19 | The University Of North Carolina At Charlotte | Method and system for remotely inspecting bridges and other structures |
-
2019
- 2019-12-30 CN CN201911404582.9A patent/CN110940732B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3978712A (en) * | 1971-11-17 | 1976-09-07 | Scanning Systems, Inc. | Method and apparatus for testing wear, size and residual stress conditions |
| CN101666783A (en) * | 2008-09-01 | 2010-03-10 | 中国科学院金属研究所 | Ultrasonic guided wave composite non-destructive testing method and device |
| CN109649432A (en) * | 2019-01-23 | 2019-04-19 | 浙江大学 | Cloud platform rail integrity monitoring systems and method based on guided wave technology |
| CN112906672A (en) * | 2021-04-08 | 2021-06-04 | 上海应用技术大学 | Steel rail defect identification method and system |
Non-Patent Citations (2)
| Title |
|---|
| 钢轨轨底斜裂纹的超声导波散射特性;卢超等;《无损检测》;20160510(第05期);23-27 * |
| 随机点蚀损伤钢板的极限强度预测;王仁华等;《工程力学》;20181220(第12期);258-266 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110940732A (en) | 2020-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A Bayesian probabilistic approach for acoustic emission‐based rail condition assessment | |
| CN110940732B (en) | A method for online monitoring and evaluation of rail structural corrosion | |
| CN105241660B (en) | Performance test method for large bridges of high-speed railway based on health monitoring data | |
| WO2019201177A1 (en) | Train component crack damage monitoring method and system | |
| Zhang et al. | Deep convolutional neural network probability imaging for plate structural health monitoring using guided waves | |
| Montalvao et al. | A review of vibration-based structural health monitoring with special emphasis on composite materials | |
| CN106006344B (en) | Staircase On-line Fault early warning system and method for diagnosing faults | |
| CN114166943B (en) | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves | |
| CN111896625A (en) | Real-time monitoring method and monitoring system for rail damage | |
| CN101566601B (en) | System for recognizing tensile damage state of 16Mn steel force-bearing part by adopting neural network and coupling iteration | |
| Nichols et al. | Use of data-driven phase space models in assessing the strength of a bolted connection in acomposite beam | |
| CN109649432B (en) | Cloud platform rail integrity monitoring system and method based on guided wave technology | |
| CN108318589A (en) | Fatigue crack length intelligence assessment method based on Gaussian process and monitoring method | |
| Peng et al. | One-dimensional residual convolutional neural network and percussion-based method for pipeline leakage and water deposit detection | |
| CN109443766A (en) | A kind of heavy-duty vehicle gearbox gear Safety Analysis Method | |
| CN102072789B (en) | Method for continuously processing wheel-track force of track vehicle by means of ground test | |
| CN119150154A (en) | Construction method, diagnosis method, system and equipment of bolt fault diagnosis model | |
| Liu et al. | Fuzzy pattern recognition of impact acoustic signals for nondestructive evaluation | |
| Lee et al. | De-bonding detection on a CFRP laminated concrete beam using self sensing-based multi-scale actuated sensing with statistical pattern recognition | |
| Biswas et al. | Acoustic emission-based damage detection and classification in steel frame structure using wavelet transform and random forest | |
| Silik et al. | Development of features for early detection of defects and assessment of bridge decks | |
| CN116484204A (en) | A Method for Identifying Defects of Aircraft Cable Insulation Layer Based on BP Neural Network | |
| Friedmann et al. | Monitoring and damage detection in structural parts of wind turbines | |
| Sidibé et al. | Signal processing and Gaussian neural networks for the edge and damage detection in immersed metal plate-like structures | |
| Liu et al. | An improved short-wave rail irregularity detection method based on frequency-related Recurrence Plot and Convolutional Neural Network |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220301 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |