CN112229800B - Non-contact type railway bridge condition comprehensive detection method and system - Google Patents
Non-contact type railway bridge condition comprehensive detection method and system Download PDFInfo
- Publication number
- CN112229800B CN112229800B CN202011462055.6A CN202011462055A CN112229800B CN 112229800 B CN112229800 B CN 112229800B CN 202011462055 A CN202011462055 A CN 202011462055A CN 112229800 B CN112229800 B CN 112229800B
- Authority
- CN
- China
- Prior art keywords
- railway bridge
- apparent
- bridge
- steel rail
- rail
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/1702—Systems in which incident light is modified in accordance with the properties of the material investigated with opto-acoustic detection, e.g. for gases or analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The application discloses a non-contact type railway bridge condition comprehensive detection method and a non-contact type railway bridge condition comprehensive detection system, which comprise the following steps: acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle; the method comprises the following steps of (1) emitting laser by using a laser ultrasonic probe arranged on a rail detection vehicle and irradiating the laser to the surface of a steel rail so as to draw a sound pressure distribution diagram of apparent defects of the steel rail; reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; extracting characteristic parameters containing steel rail apparent defect information by using a modal decomposition method; classifying apparent defects of the steel rails by adopting a support vector machine and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge. Therefore, the arrangement of sensors on the railway bridge is effectively avoided, the data processing difficulty is reduced, the labor intensity of manual detection is reduced, and the detection cost is saved.
Description
Technical Field
The invention relates to the field of railway bridge detection, in particular to a non-contact comprehensive railway bridge condition detection method and system.
Background
With the rapid development of the high-speed railway in China, the total mileage of the high-speed railway in China exceeds 3.5 kilometers by 2019. The bridge is used as an important component of the high-speed railway, and has a very high proportion of the line, such as 86.6 percent of the Jingjin intercity bridge, 80.5 percent of the Jinghong high-speed railway and 94.0 percent of the Guangzhou intercity bridge. Under the conditions of continuous speed increasing, continuous load increasing and severe environment of high-speed rails, the working performance and the health condition of a high-speed rail bridge structure have a vital influence on the operation safety of a high-speed train. How to detect and evaluate high-speed rail bridges is a problem to be solved urgently in high-speed rail construction, operation, maintenance and management in China at present.
At present, most of detection methods for railway bridges are manual detection, so that detection omission or insufficient detection depth inevitably occurs, and the comprehensive elimination of potential safety hazards of railway bridge structures cannot be guaranteed; the manual detection operation needs to be carried out in skylight time, the skylight time is mostly at night, the operation time and the operation field are severely limited, the skylight time can be gradually shortened along with the high-efficiency operation of the railway, and greater pressure is caused to the detection of the railway bridge in the skylight time; the real-time performance is poor, and potential safety hazards cannot be found in time for prevention and early warning.
Disclosure of Invention
In view of the above, the present invention provides a non-contact comprehensive detection method and system for railway bridge conditions, which can quickly detect apparent diseases and internal damages, reduce labor intensity of manual detection, and improve detection intelligence. The specific scheme is as follows:
a non-contact comprehensive detection method for railway bridge conditions comprises the following steps:
acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle;
the laser ultrasonic probe arranged on the rail detection vehicle is used for emitting laser and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm;
extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information;
classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree;
and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
Preferably, in the method for comprehensively detecting a condition of a non-contact railroad bridge according to an embodiment of the present invention, the acquiring a dynamic characteristic parameter of the railroad bridge by an acceleration sensor mounted on a rail detection vehicle specifically includes:
acquiring a vibration response signal of a train-track-bridge coupled vibration system through an acceleration sensor arranged on a track detection vehicle;
enhancing and reconstructing the acquired vibration response signal to reduce noise;
extracting dynamic characteristic parameters of the railway bridge structure according to the reconstructed noise-reduced signals; the dynamic characteristic parameters comprise natural frequency, vibration mode and damping ratio of the railway bridge.
Preferably, in the method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the extracting, by using a modal decomposition method, the characteristic parameter including the rail apparent defect information from the reconstructed photoacoustic image specifically includes:
extracting and decomposing non-stationary random initial photoacoustic signals from the reconstructed photoacoustic image by using a modal decomposition method to obtain an eigenmode function containing steel rail apparent defect information;
and extracting characteristic parameters containing the apparent defect information of the steel rail from the time domain and the frequency domain according to the obtained eigenmode function.
Preferably, in the method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the method further includes:
bridge deck video information is obtained through a high-definition camera carried on the track detection vehicle, and apparent diseases of the railway bridge are identified and positioned according to the bridge deck video information.
Preferably, in the method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, identifying and locating an apparent defect of the railroad bridge according to the bridge deck video information specifically includes:
establishing an apparent disease database of the railway bridge as a data set;
processing detail information of the edge of the disease image in the railway bridge apparent disease database by adopting a Laplace operator;
constructing a deep convolutional neural network model, dividing the data set into a training set, a verification set and a test set, training the deep convolutional neural network model by taking the training set as a sample, checking a training result on the verification set, and continuously adjusting parameters until the recognition accuracy of the deep convolutional neural network model on the test set meets the requirement;
identifying the type and the characteristics of the railway bridge apparent diseases in the bridge deck video information by using the trained deep convolution neural network model;
according to the vehicle-mounted GPS and the video image processing method, the corresponding relation between the railway bridge apparent diseases and the key members and positions of the bridge structure is determined, so that the railway bridge apparent diseases are positioned and marked.
Preferably, in the method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the method further includes:
and measuring the side surface and the bottom of the railway bridge and the outer surface of the cable tower by adopting the unmanned aerial vehicle carried on the track detection vehicle so as to identify and locate the apparent diseases of the railway bridge.
The embodiment of the invention also provides a non-contact type comprehensive detection system for the condition of the railway bridge, which comprises the following steps:
the acceleration sensor is arranged on the rail detection vehicle and used for acquiring dynamic characteristic parameters of the railway bridge;
the laser ultrasonic probe is arranged on the rail detection vehicle and used for emitting laser and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
the processing chip is used for reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information; classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classified apparent defects of the steel rails and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
Preferably, in the system for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the system further includes:
the high-definition camera is carried on the track detection vehicle and is used for acquiring bridge deck video information;
the unmanned aerial vehicle is carried on the track detection vehicle and is used for measuring the side surface and the bottom of the railway bridge and the outer surface of the cable tower;
and the processing chip is also used for identifying and positioning the apparent diseases of the railway bridge according to the bridge deck video information and the unmanned aerial vehicle measurement result.
According to the technical scheme, the non-contact comprehensive detection method for the railway bridge condition, provided by the invention, comprises the following steps: acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle; the method comprises the following steps of (1) emitting laser by using a laser ultrasonic probe arranged on a rail detection vehicle and irradiating the laser to the surface of a steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser; reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information; classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
The invention utilizes the dynamic response of the rail detection vehicle to obtain the dynamic characteristics of the railway bridge structure, effectively avoids the arrangement of sensors on the railway bridge, reduces the required number of sensors and the data processing difficulty, simultaneously utilizes the laser ultrasonic probe carried on the rail detection vehicle to identify the type and the characteristics of the apparent defect of the steel rail, can simultaneously and quickly detect the apparent defect and the internal damage of the steel rail, lightens the labor intensity of manual detection, saves the detection cost, effectively avoids the problems of missing detection of manual detection or insufficient detection depth and the like, improves the intelligent level of the railway bridge detection, and promotes the development of the railway bridge detection to the direction of intellectualization, digitization and informatization. In addition, the invention also provides a corresponding system for the non-contact type comprehensive detection method of the railway bridge condition, so that the method has higher practicability and the system has corresponding advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a non-contact type comprehensive detection method for railway bridge conditions provided by the embodiment of the invention;
fig. 2 is a flowchart for identifying dynamic characteristic parameters and apparent defects of a railway bridge according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a non-contact type comprehensive detection method for railway bridge conditions, which comprises the following steps as shown in figure 1:
s101, acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle;
s102, emitting laser by using a laser ultrasonic probe arranged on a rail detection vehicle and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
it can be understood that when laser light is irradiated on the surface of the steel rail, an initial sound field is generated within a depth range of a few millimeters of the surface of the steel rail; the initial sound field generated by the steel rail with the surface defect is different from the steel rail without the surface defect, and the sound field is generated by irradiating the bottom of the steel rail defect by laser, so that different sound fields are generated by different steel rail surface defects, and the sound pressure distribution diagram of different steel rail apparent defects is drawn by the collected photoacoustic signals by adopting a reconstruction algorithm, so that the aim of identifying the steel rail apparent defects is fulfilled;
s103, reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm;
it should be noted that the time reversal reconstruction algorithm is based on the fundamental principle of the photoacoustic effect, and when the sound velocity in the steel rail is a uniform sound velocity, the fundamental equation of the photoacoustic effect is expressed by 3 acoustic linear equations as follows:
the initial conditions were:
wherein the content of the first and second substances,
representing the sound pressure at time t within the imaging region,
the vibration speed of the steel rail is shown,
the speed of the sound is indicated by the speed of sound,
which represents the density of the medium,
the change rate of the steel rail density. And when the photoacoustic image is reconstructed through time reversal, calculating the initial sound field distribution by considering the photoacoustic signal measured value acquired from 0-t of time.
The equation initial sound pressure value is taken to be 0, namely:
s104, extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information;
s105, classifying the apparent defects of the steel rails by adopting a Support Vector Machine (SVM) according to the constructed characteristic parameter database and determining the internal damage degree; in practical application, the method can firstly optimize kernel function parameters and punishment factors of the SVM by using a grid search method, then classify apparent defects of the steel rail by using the optimized SVM, and classification results can comprise cracks of a rail head, a rail waist and a rail bottom of the rail, looseness of the surface of the rail and mounting screws and the like;
and S106, evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
In the non-contact comprehensive detection method for the railway bridge condition, when a rail detection vehicle runs through the railway bridge, the dynamic response of the rail detection vehicle is utilized to obtain the dynamic characteristic of the railway bridge structure, the sensors are effectively prevented from being arranged on the railway bridge, the required number of the sensors and the data processing difficulty are reduced, meanwhile, the apparent defect type and the characteristic of the steel rail are identified by utilizing the laser ultrasonic probe carried on the rail detection vehicle, the apparent defect and the internal damage of the steel rail can be rapidly detected at the same time, the labor intensity of manual detection is reduced, the detection cost is saved, the problems of missing detection of manual detection or insufficient detection depth and the like are effectively avoided, the intelligent level of the railway bridge detection is improved, and the development of the railway bridge detection to the intelligent, digital and information directions is promoted.
Further, in a specific implementation, in the non-contact comprehensive detection method for a railroad bridge condition provided in the embodiment of the present invention, the step S101 of obtaining a dynamic characteristic parameter of the railroad bridge through an acceleration sensor mounted on a rail detection vehicle may specifically include the following steps:
acquiring a vibration response signal of a train-track-bridge coupled vibration system through an acceleration sensor arranged on a track detection vehicle;
step two, enhancing and reconstructing the acquired vibration response signals to reduce noise;
in practical application, vibration response signals obtained by measurement under the action of a rail detection vehicle are noisy nonstationary vibration signals, and the acquired vibration response signals can be enhanced, reconstructed and denoised through signal technology processing; specifically, the signal is preprocessed based on a Variational Modal Decomposition (VMD), the vibration response signal is enhanced, and the signal is reconstructed to reduce noise. On the basis of signal denoising, separating each mutually independent source signal component from a vehicle vibration signal based on Robustness Independent Component Analysis (RICA), and extracting dynamic characteristic parameters of a train and a bridge structure by combining methods such as spectrum analysis, continuous wavelet transform and the like;
thirdly, extracting dynamic characteristic parameters of the railway bridge structure according to the reconstructed noise-reduced signals; the dynamic characteristic parameters comprise natural frequency, vibration mode and damping ratio of the railway bridge;
specifically, the railway bridge vibration response obtained by inverting the vehicle vibration response signal is subjected to empirical mode decomposition and an improved method thereof (EMD/EEMD/VMD) and compression wavelet transform (SSWT) to obtain the natural frequency, the damping ratio and the high-resolution railway bridge one-dimensional vibration mode.
In specific implementation, in the non-contact comprehensive detection method for railway bridge conditions provided in the embodiment of the present invention, the step S104 may extract the characteristic parameters including the apparent defect information of the steel rail from the reconstructed photoacoustic image by using a modal decomposition method, and specifically include the steps of: firstly, extracting and decomposing a non-stationary random initial photoacoustic signal from a reconstructed photoacoustic image by using a modal Decomposition (EMD) method, thereby obtaining a plurality of finite eigen Mode functions (IMFs) and obtaining the IMF containing the apparent defect information of the steel rail; and then, extracting characteristic parameters containing the apparent defect information of the steel rail from the time domain and the frequency domain according to the obtained eigenmode function.
Further, in a specific implementation, in the method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the method may further include: bridge deck video information is obtained through a high-definition camera carried on a track detection vehicle, and apparent diseases of the railway bridge are identified and positioned according to the bridge deck video information. The high-definition camera is used for identifying the apparent defect type and the characteristics of the railway bridge structure, so that the apparent defects of the railway bridge can be quickly detected, the labor intensity of manual detection is further reduced, and the detection cost is saved.
In specific implementation, in the above step, the identifying and locating the apparent diseases of the railroad bridge according to the bridge deck video information may specifically include the following steps:
classifying and grading common disease types of the railway bridge, such as concrete honeycombs, peeling, cavities, exposed ribs, staggered platforms, steel structure coating cracking, rusting, weld cracks, loosening or falling of rivets and bolts and the like, so that a large number of disease images can be collected from various channels, and an apparent disease database of the railway bridge is established to be used as a data set for deep learning model training;
secondly, processing detail information of edges of the disease images in the railway bridge apparent disease database by adopting a Laplace operator;
in particular, the Laplace operator template matrixAAs shown in formula (6). The disease image in the database is processed through the Laplace operator, and a training database with prominent outline details and rich and various diseases of the disease image can be obtained.
Thirdly, constructing a deep convolutional neural network model, dividing a data set into a training set, a verification set and a test set, training the deep convolutional neural network model by taking the training set as a sample, checking a training result on the verification set, and continuously adjusting parameters until the recognition accuracy of the deep convolutional neural network model on the test set meets the requirement;
fourthly, recognizing the type and the characteristics of the apparent railway bridge diseases in the bridge deck video information by using the trained deep convolutional neural network model, and calculating the actual sizes of the diseases by adopting an image recognition method based on a contrast;
and fifthly, determining the corresponding relation between the apparent diseases of the railway bridge and key members and positions of the bridge structure according to the vehicle-mounted GPS and a video image processing method so as to position and mark the apparent diseases of the railway bridge.
Further, in practical implementation, in the above method for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, since the rail detection vehicle has an undetectable area, such as a side and a bottom of a bridge, an outer surface of a cable tower, and the like, the method may further include: the method comprises the steps of measuring the side face and the bottom of the railway bridge and the outer surface of a cable tower by adopting an unmanned aerial vehicle carried on a rail detection vehicle, and identifying based on a similar neural network model so as to identify and position the apparent diseases of the railway bridge. The acceleration sensor, the laser ultrasonic probe, the high-definition camera and the unmanned aerial vehicle are used for detecting apparent diseases of the interior of the steel rail and the railway bridge, so that comprehensive detection of the railway bridge, the steel rail, the bridge deck, the track plate and the support can be realized.
It should be noted that, the operation condition, the degradation behavior, the remaining life, the maintenance cost, and the like of the bridge in the whole area can be predicted regularly or regularly by the rail detection vehicle, so as to provide a scientific decision basis for the safety monitoring, the operation maintenance, the daily maintenance planning and the management of the road network bridge.
Based on the same invention concept, the embodiment of the invention also provides a non-contact type comprehensive detection system for the railway bridge condition, and as the problem solving principle of the system is similar to that of the non-contact type comprehensive detection method for the railway bridge condition, the implementation of the system can refer to the implementation of the non-contact type comprehensive detection method for the railway bridge condition, and repeated parts are not repeated.
In specific implementation, the non-contact comprehensive detection system for the railway bridge condition provided by the embodiment of the invention specifically comprises:
the acceleration sensor is arranged on the rail detection vehicle and used for acquiring dynamic characteristic parameters of the railway bridge;
the laser ultrasonic probe is arranged on the rail detection vehicle and used for emitting laser and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
the processing chip is used for reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information; classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classified apparent defects of the steel rails and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
In the non-contact comprehensive detection system for the railway bridge condition, provided by the embodiment of the invention, the dynamic response of the rail detection vehicle can be utilized to obtain the dynamic characteristics of the railway bridge structure, the arrangement of sensors on the railway bridge is effectively avoided, the required number of the sensors is reduced, and the data processing difficulty is reduced, meanwhile, the apparent defect type and the characteristic of the steel rail can be identified by utilizing the laser ultrasonic probe carried on the rail detection vehicle, the apparent defect and the internal damage of the steel rail are simultaneously and rapidly detected, the labor intensity of manual detection is reduced, the detection cost is saved, the problems of missing detection of manual detection or insufficient detection depth and the like are effectively avoided, the intelligent level of the railway bridge detection is improved, and the development of the railway bridge detection to the intelligent, digital and information directions is promoted.
In specific implementation, in the system for comprehensively detecting a condition of a non-contact railroad bridge provided in an embodiment of the present invention, the system may further include:
the high-definition camera is carried on the track detection vehicle and used for acquiring bridge deck video information;
the unmanned aerial vehicle is carried on the rail detection vehicle and used for measuring the side surface and the bottom of the railway bridge and the outer surface of the cable tower;
and the processing chip is also used for identifying and positioning the apparent diseases of the railway bridge according to the bridge deck video information and the measurement result of the unmanned aerial vehicle.
For more specific working processes of the above components, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not described herein again.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The embodiment of the invention provides a non-contact type comprehensive detection method for railway bridge conditions, which comprises the following steps: acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle; the method comprises the following steps of (1) emitting laser by using a laser ultrasonic probe arranged on a rail detection vehicle and irradiating the laser to the surface of a steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser; reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information; classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge. The dynamic response of the rail detection vehicle is utilized to obtain the dynamic characteristics of the railway bridge structure, the arrangement of sensors on the railway bridge can be effectively avoided, the required number of the sensors and the data processing difficulty are reduced, meanwhile, the laser ultrasonic probe carried on the rail detection vehicle is utilized to identify the type and the characteristics of the apparent defects of the steel rail, the apparent defects and the internal damage of the steel rail can be simultaneously and rapidly detected, the labor intensity of manual detection is reduced, the detection cost is saved, the problems of missing detection of manual detection or insufficient detection depth and the like are effectively avoided, the intelligent level of railway bridge detection is improved, and the development of the railway bridge detection to intellectualization, digitization and informatization is promoted. In addition, the invention also provides a corresponding system for the non-contact type comprehensive detection method of the railway bridge condition, so that the method has higher practicability and the system has corresponding advantages.
Finally, it should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The non-contact type comprehensive detection method and system for the railway bridge condition provided by the invention are described in detail, specific examples are applied in the method to explain the principle and the implementation mode of the invention, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A non-contact type comprehensive detection method for railway bridge conditions is characterized by comprising the following steps:
acquiring dynamic characteristic parameters of the railway bridge through an acceleration sensor arranged on a rail detection vehicle;
the laser ultrasonic probe arranged on the rail detection vehicle is used for emitting laser and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; the time reversal reconstruction algorithm adopted by reconstruction is a specific equation based on the photoacoustic effect; the particular equation comprises:
wherein the content of the first and second substances,
representing time of day within an imaging regiontThe sound pressure at the time of the operation,
the vibration speed of the steel rail is shown,
representing soundThe speed of the motor is controlled by the speed of the motor,
which represents the density of the medium,
representing the change rate of the steel rail density;
extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method, and constructing a characteristic parameter database containing the steel rail apparent defect information;
classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree;
and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classification result and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
2. The method for comprehensively detecting the condition of the non-contact railroad bridge according to claim 1, wherein the acquiring of the dynamic characteristic parameters of the railroad bridge through an acceleration sensor installed on a rail detection vehicle specifically comprises:
acquiring a vibration response signal of a train-track-bridge coupled vibration system through an acceleration sensor arranged on a track detection vehicle;
enhancing and reconstructing the acquired vibration response signal to reduce noise;
extracting dynamic characteristic parameters of the railway bridge structure according to the reconstructed noise-reduced signals; the dynamic characteristic parameters comprise natural frequency, vibration mode and damping ratio of the railway bridge.
3. The method for comprehensively detecting the condition of the non-contact railroad bridge according to claim 2, wherein a mode decomposition method is used for extracting characteristic parameters containing the apparent defect information of the steel rail from the reconstructed photoacoustic image, and the method specifically comprises the following steps:
extracting and decomposing non-stationary random initial photoacoustic signals from the reconstructed photoacoustic image by using a modal decomposition method to obtain an eigenmode function containing steel rail apparent defect information;
and extracting characteristic parameters containing the apparent defect information of the steel rail from the time domain and the frequency domain according to the obtained eigenmode function.
4. The method for comprehensively detecting the condition of the non-contact railroad bridge according to claim 3, further comprising:
bridge deck video information is obtained through a high-definition camera carried on the track detection vehicle, and apparent diseases of the railway bridge are identified and positioned according to the bridge deck video information.
5. The method for comprehensively detecting the condition of the non-contact railway bridge according to claim 4, wherein the identifying and positioning of the apparent diseases of the railway bridge according to the bridge deck video information specifically comprises the following steps:
establishing an apparent disease database of the railway bridge as a data set;
processing detail information of the edge of the disease image in the railway bridge apparent disease database by adopting a Laplace operator;
constructing a deep convolutional neural network model, dividing the data set into a training set, a verification set and a test set, training the deep convolutional neural network model by taking the training set as a sample, checking a training result on the verification set, and continuously adjusting parameters until the recognition accuracy of the deep convolutional neural network model on the test set meets the requirement;
identifying the type and the characteristics of the railway bridge apparent diseases in the bridge deck video information by using the trained deep convolution neural network model;
according to the vehicle-mounted GPS and the video image processing method, the corresponding relation between the railway bridge apparent diseases and the key members and positions of the bridge structure is determined, so that the railway bridge apparent diseases are positioned and marked.
6. The method for comprehensively detecting the condition of the non-contact railroad bridge according to claim 5, further comprising:
and measuring the side surface and the bottom of the railway bridge and the outer surface of the cable tower by adopting the unmanned aerial vehicle carried on the track detection vehicle so as to identify and locate the apparent diseases of the railway bridge.
7. A non-contact railway bridge condition comprehensive detection system is characterized by comprising:
the acceleration sensor is arranged on the rail detection vehicle and used for acquiring dynamic characteristic parameters of the railway bridge;
the laser ultrasonic probe is arranged on the rail detection vehicle and used for emitting laser and irradiating the laser to the surface of the steel rail so as to draw a sound pressure distribution diagram of the apparent defect of the steel rail under the irradiation of the laser;
the processing chip is used for reconstructing the photoacoustic image of the apparent defect of the steel rail by adopting a time inversion algorithm; the time reversal reconstruction algorithm adopted by reconstruction is a specific equation based on the photoacoustic effect; the particular equation comprises:
wherein the content of the first and second substances,
representing time of day within an imaging regiontThe sound pressure at the time of the operation,
the vibration speed of the steel rail is shown,
the speed of the sound is indicated by the speed of sound,
which represents the density of the medium,
representing the change rate of the steel rail density;
the processing chip is further used for extracting characteristic parameters containing steel rail apparent defect information from the reconstructed photoacoustic image by using a modal decomposition method and constructing a characteristic parameter database containing the steel rail apparent defect information; classifying apparent defects of the steel rails by adopting a support vector machine according to the constructed characteristic parameter database and determining the internal damage degree; and evaluating the operation condition of the railway bridge according to the acquired dynamic characteristic parameters, the classified apparent defects of the steel rails and the determined internal damage degree in combination with historical data of the condition of the railway bridge.
8. The system of claim 7, further comprising:
the high-definition camera is carried on the track detection vehicle and is used for acquiring bridge deck video information;
the unmanned aerial vehicle is carried on the track detection vehicle and is used for measuring the side surface and the bottom of the railway bridge and the outer surface of the cable tower;
and the processing chip is also used for identifying and positioning the apparent diseases of the railway bridge according to the bridge deck video information and the unmanned aerial vehicle measurement result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011462055.6A CN112229800B (en) | 2020-12-14 | 2020-12-14 | Non-contact type railway bridge condition comprehensive detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011462055.6A CN112229800B (en) | 2020-12-14 | 2020-12-14 | Non-contact type railway bridge condition comprehensive detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112229800A CN112229800A (en) | 2021-01-15 |
| CN112229800B true CN112229800B (en) | 2021-03-12 |
Family
ID=74124855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011462055.6A Active CN112229800B (en) | 2020-12-14 | 2020-12-14 | Non-contact type railway bridge condition comprehensive detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112229800B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450324A (en) * | 2021-06-23 | 2021-09-28 | 北京世纪东方通讯设备有限公司 | Method and system for analyzing length of internal defect of steel rail |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1010151A (en) * | 1996-06-26 | 1998-01-16 | Nissan Motor Co Ltd | Damage detection circuit for micromechanical sensor |
| US7103460B1 (en) * | 1994-05-09 | 2006-09-05 | Automotive Technologies International, Inc. | System and method for vehicle diagnostics |
| CN101900708A (en) * | 2010-08-18 | 2010-12-01 | 哈尔滨工业大学 | Vibration and audio signal-based high-speed train track defect detecting method |
| EP2430461A2 (en) * | 2009-05-15 | 2012-03-21 | Biomerieux, Inc | Combined detection instrument for culture specimen containers and instrument for identification and/or characterization of a microbial agent in a sample |
| CN105136908A (en) * | 2015-07-23 | 2015-12-09 | 彭凯 | Bridge structure damage positioning method based on indicated frequency space-time evolution |
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN111079323A (en) * | 2019-11-12 | 2020-04-28 | 湖南大学 | Power response prediction method and system based on human-vehicle-road coupling vibration model |
| CN211291730U (en) * | 2020-01-21 | 2020-08-18 | 湖南大学 | Detection vehicle device for bridge dynamic characteristic identification and damage diagnosis |
| CN111795978A (en) * | 2020-09-08 | 2020-10-20 | 湖南大学 | Steel bridge structure health state assessment method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10113951B2 (en) * | 2016-04-22 | 2018-10-30 | The Boeing Company | Apparatus, systems, and methods for inspecting a part |
-
2020
- 2020-12-14 CN CN202011462055.6A patent/CN112229800B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7103460B1 (en) * | 1994-05-09 | 2006-09-05 | Automotive Technologies International, Inc. | System and method for vehicle diagnostics |
| JPH1010151A (en) * | 1996-06-26 | 1998-01-16 | Nissan Motor Co Ltd | Damage detection circuit for micromechanical sensor |
| EP2430461A2 (en) * | 2009-05-15 | 2012-03-21 | Biomerieux, Inc | Combined detection instrument for culture specimen containers and instrument for identification and/or characterization of a microbial agent in a sample |
| CN101900708A (en) * | 2010-08-18 | 2010-12-01 | 哈尔滨工业大学 | Vibration and audio signal-based high-speed train track defect detecting method |
| CN105136908A (en) * | 2015-07-23 | 2015-12-09 | 彭凯 | Bridge structure damage positioning method based on indicated frequency space-time evolution |
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN111079323A (en) * | 2019-11-12 | 2020-04-28 | 湖南大学 | Power response prediction method and system based on human-vehicle-road coupling vibration model |
| CN211291730U (en) * | 2020-01-21 | 2020-08-18 | 湖南大学 | Detection vehicle device for bridge dynamic characteristic identification and damage diagnosis |
| CN111795978A (en) * | 2020-09-08 | 2020-10-20 | 湖南大学 | Steel bridge structure health state assessment method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| "A new fatigue reliability analysis method for steel bridges based on peridynamic";Yingkai Liu 等;《Engineering Fracture Mechanics》;20200901;第236卷;第1-35页 * |
| "公路车－桥耦合振动的理论和应用研究进展";邓露 等;《中国公路学报》;20180731;第31卷(第7期);第39-54页 * |
| "轨道交通桥梁检测技术发展趋势探讨";郭扬艳 等;《现代城市轨道交通》;20191231;第68-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112229800A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | A kNN algorithm for locating and quantifying stiffness loss in a bridge from the forced vibration due to a truck crossing at low speed | |
| US11055506B2 (en) | Method of analyzing a fingerprint | |
| Zhang et al. | Automatic visual detection system of railway surface defects with curvature filter and improved Gaussian mixture model | |
| Molodova et al. | Automatic detection of squats in railway infrastructure | |
| Zhang et al. | Acoustic emission detection of rail defect based on wavelet transform and Shannon entropy | |
| EP2697738B1 (en) | Method and system of rail component detection using vision technology | |
| US20170052060A1 (en) | Method and system for automatically detecting faults in a rotating shaft | |
| CN112411371A (en) | Highway bridge comprehensive detection method and system based on mobile sensing and vision | |
| JPWO2009139052A1 (en) | Signal determination method, signal determination apparatus, program, and signal determination system | |
| CN115758289B (en) | Rail wave mill identification method based on multitask learning neural network | |
| CN115311246A (en) | Bridge safety management method and system based on big data | |
| CN112229800B (en) | Non-contact type railway bridge condition comprehensive detection method and system | |
| Mohamadi et al. | Fusion and visualization of bridge deck nondestructive evaluation data via machine learning | |
| CN114544206A (en) | Method and device for detecting polygonal fault of wheel pair of rail transit rolling stock | |
| Ghiasi et al. | Damage detection of in-service steel railway bridges using a fine k-nearest neighbor machine learning classifier | |
| Wei et al. | Carriage interior noise-based inspection for rail corrugation on high-speed railway track | |
| Costa et al. | Combining wavelet analysis of track irregularities and vehicle dynamics simulations to assess derailment risks | |
| Shirzad-Ghaleroudkhani et al. | A crowdsensing-based platform for transportation infrastructure monitoring and management in smart cities | |
| CN113392874B (en) | Abnormal state diagnosis method and device for rail vehicle and terminal equipment | |
| Moreno-Gomez et al. | Fractal dimension analysis for assessing the health condition of a truss structure using vibration signals | |
| Van Hauwermeiren et al. | A scalable, self‐supervised calibration and confounder removal model for opportunistic monitoring of road degradation | |
| Uygun et al. | Acoustic monitoring of railway defects using deep learning with audio to spectrogram conversion | |
| Ma et al. | State-of-the-art of terrain profile characterisation models | |
| CN116680646B (en) | Method and device for identifying damage of aircraft load bridge, electronic equipment and storage medium | |
| Kumar et al. | Damage Detection in Concrete Slab Using Smart Sounding |
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 |