CN114972205A - Track bolt looseness detection method and device - Google Patents
Track bolt looseness detection method and device Download PDFInfo
- Publication number
- CN114972205A CN114972205A CN202210479654.1A CN202210479654A CN114972205A CN 114972205 A CN114972205 A CN 114972205A CN 202210479654 A CN202210479654 A CN 202210479654A CN 114972205 A CN114972205 A CN 114972205A
- Authority
- CN
- China
- Prior art keywords
- bolt
- vibration
- detected
- information
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The invention discloses a track bolt looseness detection method, a track bolt looseness detection device, track bolt looseness detection equipment, a computer readable storage medium, a looseness track bolt detector and a track detection vehicle, wherein an activation signal is sent to an excitation assembly; acquiring vibration video information of the bolt to be detected from a photographic assembly; according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information. According to the invention, the bolt to be tested is forced to vibrate by an active excitation means, and then the conclusion whether the bolt to be tested is loosened is obtained by comparing the vibration frequency with the vibration threshold value, so that the safe, efficient and accurate identification of the looseness of the track bolt is realized.
Description
Technical Field
The invention relates to the field of rail safety inspection, in particular to a rail bolt looseness detection method, a rail bolt looseness detection device, rail bolt looseness detection equipment, a computer readable storage medium, a looseness rail bolt detector and a rail detection vehicle.
Background
Along with the increase of the service life of rail trains (railways, subways, light rails and the like), frequent vibration of the trains can cause the fastener bolts of the rails to loosen in different degrees, so that great potential safety hazards are brought to the running operation of the rail trains.
The existing mainstream detection method is a manual knocking detection method, namely, a detector carries a small knocking hammer to knock the rail fasteners one by one, the knocking tool is a wooden stick, a nylon stick or a small nylon hammer with an elastic handle and the like, fastener bolts are slightly and continuously knocked, and whether the bolts are loosened or not is judged according to visual observation and clear and crisp or clunking of acoustic echo. The accuracy of the tapping method depends on the experience of the detection personnel, and the missed detection is easy to occur when the workload is large. For the subway, the method can be used only at night of the subway outage period, the detection efficiency is extremely low, and the personal and property safety of detection personnel is difficult to guarantee.
Therefore, how to find a technical means which is convenient to operate, high in detection precision and independent of manpower is a problem to be solved urgently by technical personnel in the field.
Disclosure of Invention
The invention aims to provide a track bolt looseness detection method, a track bolt looseness detection device, track bolt looseness detection equipment, a computer readable storage medium, a looseness track bolt detector and a track detection vehicle, and aims to solve the problems that in the prior art, looseness bolt detection efficiency is low, detection is easy to miss, and labor cost is high.
In order to solve the technical problem, the invention provides a rail bolt looseness detection method, which comprises the following steps:
sending an activation signal to an excitation assembly to enable the excitation assembly to vibrate the bolt to be tested;
acquiring vibration video information of the bolt to be detected from a photographic assembly;
according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm;
obtaining frequency domain information according to the time domain information;
judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information;
and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
Optionally, in the track bolt looseness detection method, when the excitation assembly and the camera assembly are both disposed on the track detection vehicle, the marking of the bolt to be detected as a loosened bolt, and the recording of the corresponding positioning information includes:
and marking the bolt to be detected as a loose bolt, and recording mileage information corresponding to the track inspection vehicle.
Optionally, in the track bolt looseness detection method, obtaining, according to the vibration video information, time domain information of the vibration of the bolt to be detected through a target tracking algorithm includes:
performing video motion amplification on the vibration video information to obtain amplified video information;
and obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the amplified video information.
Optionally, in the track bolt looseness detection method, the obtaining frequency domain information according to the time domain information includes:
and obtaining frequency domain information through a Fourier transform algorithm according to the time domain information.
A track bolt looseness detection device, comprising:
the activation module is used for sending an activation signal to the excitation assembly to enable the excitation assembly to vibrate the bolt to be tested;
the video acquisition module is used for acquiring vibration video information of the bolt to be detected from a camera assembly;
the time domain module is used for obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information;
the frequency domain module is used for obtaining frequency domain information according to the time domain information;
the judging module is used for judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value according to the frequency domain information;
and the loosening marking module is used for marking the bolt to be detected as a loosening bolt when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, and recording corresponding positioning information.
A track bolt looseness detection apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the rail bolt looseness detection method according to any one of the above when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of detecting a loosening of a track bolt as defined in any of the previous claims.
A loose track bolt detector comprises an excitation component, a camera component and a signal processor;
the excitation assembly is used for vibrating the bolt to be tested during activation;
the camera assembly is used for covering the bolt to be detected in a vision field and shooting vibration video information of the bolt to be detected;
the signal processor is used for sending an activation signal to the excitation assembly, acquiring the vibration video information from the camera assembly, and obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
Optionally, in the loose track bolt detector, the excitation component is a sound wave resonance component;
the sound wave resonance assembly is used for emitting sound waves of a first frequency, and the difference value between the first frequency and the resonance frequency of the bolt to be tested in the loosening state is smaller than a preset permission threshold value.
A rail inspection vehicle comprising a loose rail bolt detector as claimed in any one of the above.
According to the track bolt looseness detection method provided by the invention, the excitation assembly vibrates the bolt to be detected by sending an activation signal to the excitation assembly; acquiring vibration video information of the bolt to be detected from a photographic assembly; according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency (namely, the frequency domain information) of the bolt to be detected is derived from the collected vibration video information by a machine vision related algorithm, and the result of whether the bolt to be detected is loosened or not is obtained after the vibration frequency is compared with the preset vibration threshold value, so that the manual detection which too depends on the experience of workers is eliminated, and the safe, efficient and accurate identification of the looseness of the track bolt is realized. The invention also provides a track bolt looseness detection device, equipment, a computer readable storage medium, a looseness track bolt detector and a track detection vehicle with the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an embodiment of a track bolt looseness detection method provided by the present invention;
FIG. 2 is a schematic flow chart of another embodiment of the track bolt looseness detection method provided by the present invention;
fig. 3 is a schematic structural diagram of an embodiment of the track bolt looseness detecting apparatus provided in the present invention;
FIG. 4 is a schematic structural diagram of one embodiment of a loose track bolt detector provided in the present invention;
FIG. 5 is a schematic structural diagram of another embodiment of a loose track bolt detector provided by the present invention;
fig. 6 is a schematic structural diagram of a motion amplification algorithm based on deep learning, which is used in an embodiment of the loose track bolt detector provided in the present invention.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It should be apparent that the described embodiments are only some embodiments of the present invention, and not all 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 core of the invention is to provide a track bolt looseness detection method, a flow schematic diagram of a specific embodiment of which is shown in fig. 1, and is called as a first specific embodiment, and the method comprises the following steps:
s101: and sending an activation signal to the vibration excitation assembly to enable the vibration excitation assembly to vibrate the bolt to be tested.
The vibration excitation component is a component which can force the bolt to be tested to vibrate after being activated, such as a sound wave resonance component or an impact hammer component, and of course, other components which can cause the bolt to be tested to vibrate can be adopted according to actual needs.
S102: and acquiring vibration video information of the bolt to be detected from a photographic assembly.
The vibration video information also comprises video information of the vibration process of the bolt to be detected. During the percussion hammer striking or the sound wave excitation equipment emitting sound waves, the real-time recording of high-frame-rate and high-resolution videos in the bolt area is kept.
S103: and according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm.
And extracting time domain information of bolt vibration through a target tracking algorithm, and converting video information obtained by shooting into vibration time domain information of the characteristic points.
The extraction of the time domain information may be achieved by classical tracking algorithms (such as region matching, feature tracking, optical flow, particle filtering, etc.), tracking algorithms based on kernel-correlation filtering (MOSSE), target tracking algorithms based on deep learning, etc.
Preferably, bolt tracking is carried out based on deep learning and feature point matching, time domain information of bolt vibration is extracted through a target tracking algorithm, and video information obtained through shooting is converted into time domain information such as displacement of feature points along with time change. The deep learning target tracking algorithm adopts a YooloX algorithm, the target prediction part adopts a prediction method based on Kalman filtering, the data association part adopts a Hungarian algorithm, and the characteristic point detection algorithm adopts SURF.
S104: and obtaining frequency domain information according to the time domain information.
Furthermore, the step is to obtain frequency domain information by fourier transform algorithm according to the time domain information, and of course, other technical means, such as wavelet transform algorithm, may be adopted to obtain the frequency domain information.
The frequency domain information is information such as amplitude and waveform change of bolt vibration along with frequency change, and the time domain signals collected in the last step are transformed into frequency domain signals through mathematical processing by utilizing Fourier transform or wavelet transform.
S105: and judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information.
S106: and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
The positioning information may be direct positioning information such as GPS, or indirect positioning information such as mileage.
When the excitation assembly and the camera assembly are arranged on the track detection vehicle, mileage information can be used as positioning information, the bolt to be detected is marked to be a loose bolt, and the recording of corresponding positioning information comprises:
and marking the bolt to be detected as a loose bolt, and recording mileage information corresponding to the track inspection vehicle.
In the above preferred embodiment, since the track is fixed, as long as the starting position and mileage information (may be mileage or number of rolling turns of the wheel) of the track detection vehicle are known, the corresponding position of the loose bolt can be determined, and further, the mileage of the track detection vehicle at the starting position can be returned to zero when the detection is started, so that the position of the loose bolt can be conveniently calculated.
Of course, as a preferred embodiment, the mileage with the loose bolt marking information may be summarized after the detection of the whole track is completed, the corresponding relationship between the mileage and the on-site geographic position is established, the loose bolt distribution table is output, and the loose bolt distribution table is remotely transmitted to the cloud platform or the PC end in real time.
According to the track bolt looseness detection method provided by the invention, the excitation assembly vibrates the bolt to be detected by sending an activation signal to the excitation assembly; acquiring vibration video information of the bolt to be detected from a photographic assembly; according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information. According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency of the bolt to be detected is derived from the collected vibration video information by a machine vision related algorithm, and the result of whether the bolt to be detected is loosened is obtained after the vibration frequency is compared with a preset vibration threshold value, so that the manual detection which too depends on the experience of workers is eliminated, and the safe, efficient and accurate identification of the looseness of the track bolt is realized.
On the basis of the first specific embodiment, the method of image processing is further limited to obtain a second specific embodiment, a flowchart of which is shown in fig. 2, and includes:
s201: and sending an activation signal to the vibration excitation assembly to enable the vibration excitation assembly to vibrate the bolt to be tested.
S202: and acquiring vibration video information of the bolt to be detected from a photographic assembly.
S203: and carrying out video motion amplification on the vibration video information to obtain amplified video information.
Motion amplification can be performed by a Video Motion amplification technology (LVMM) Based on deep Learning, and other Video amplification technologies, such as Eulerian Video amplification (EVM), Phase-Based Video Motion Processing (PBVM), and the like, can also be used.
S204: and obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the amplified video information.
S205: and obtaining frequency domain information according to the time domain information.
S206: and judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information.
S207: and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
In the specific embodiment, vibration generated by the bolt is amplified through a video motion amplification technology so as to facilitate capturing and visualization of vibration information, and preferably, a motion amplification algorithm based on deep learning is adopted in the application.
The overall structure of the motion amplification algorithm based on deep learning is shown in fig. 6, and the whole network mainly comprises three parts: encoder, decoder, modulator. The algorithm inputs images and magnification factors in a video, an encoder extracts shape features and texture features in the video images by using a full convolution neural network and outputs the shape features and the texture features, and then shape features of front and rear frames are sent to a modulator; the modulator obtains an interested signal by passing the difference characteristic between two frames through a convolutional layer, and then multiplying the interested signal by the amplification factor alpha, and adding the amplified signal and the image characteristic of the previous frame to obtain an amplified image; the decoder restores the amplified shape characteristics and fuses the shape characteristics with the texture characteristics, and then the final amplified image is obtained through the convolution mobile phone network.
In the following, the track bolt looseness detecting device provided by the embodiment of the present invention is introduced, and the track bolt looseness detecting device described below and the track bolt looseness detecting method described above may be referred to correspondingly.
Fig. 3 is a block diagram of a track bolt looseness detection apparatus according to an embodiment of the present invention, which is referred to as a third embodiment, and referring to fig. 3, the track bolt looseness detection apparatus may include:
the activation module 100 is used for sending an activation signal to the excitation assembly to enable the excitation assembly to vibrate the bolt to be tested;
the video acquisition module 200 is used for acquiring vibration video information of the bolt to be detected from a photographic assembly;
the time domain module 300 is configured to obtain time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information;
a frequency domain module 400, configured to obtain frequency domain information according to the time domain information;
the judging module 500 is configured to judge whether the vibration frequency of the bolt to be tested exceeds a preset vibration threshold according to the frequency domain information;
and the loosening marking module 600 is used for marking the bolt to be detected as a loosening bolt when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, and recording corresponding positioning information.
In a preferred embodiment, when the excitation module and the camera module are both disposed on a track inspection vehicle, the looseness marking module 600 includes:
and the mileage recording unit is used for marking the bolt to be detected as a loose bolt and recording mileage information corresponding to the track inspection vehicle.
As a preferred embodiment, the time domain module 300 includes:
the motion amplification unit is used for carrying out video motion amplification on the vibration video information to obtain amplified video information;
and the time domain amplifying unit is used for obtaining the time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the amplified video information.
As a preferred embodiment, the frequency domain module 400 includes:
and the Fourier unit is used for obtaining frequency domain information through a Fourier transform algorithm according to the time domain information.
The track bolt looseness detection device provided by the invention comprises an activation module 100, a vibration excitation component and a detection module, wherein the activation module is used for sending an activation signal to the vibration excitation component so that the vibration excitation component vibrates a bolt to be detected; the video acquisition module 200 is used for acquiring vibration video information of the bolt to be detected from a photographic component; the time domain module 300 is configured to obtain time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information; a frequency domain module 400, configured to obtain frequency domain information according to the time domain information; the judging module 500 is configured to judge whether the vibration frequency of the bolt to be tested exceeds a preset vibration threshold according to the frequency domain information; and the loosening marking module 600 is used for marking the bolt to be detected as a loosening bolt when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, and recording corresponding positioning information. According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency of the bolt to be detected is derived from the collected vibration video information by a relevant algorithm of machine vision, and the vibration frequency is compared with a preset vibration threshold value to draw a conclusion whether the bolt to be detected is loosened or not, so that the manual detection which excessively depends on the experience of workers is avoided, and the safe, efficient and accurate identification of the looseness of the track bolt is realized.
The track bolt looseness detecting device of this embodiment is used for implementing the track bolt looseness detecting method, and therefore a specific implementation manner of the track bolt looseness detecting device can be seen in the foregoing example portions of the track bolt looseness detecting method, for example, the activating module 100, the video acquiring module 200, the time domain module 300, the frequency domain module 400, the judging module 500, and the looseness marking module 600 are respectively used for implementing steps S101, S102, S103, S104, S105, and S106 in the track bolt looseness detecting method, so that the specific implementation manner thereof may refer to descriptions of corresponding partial examples, and is not repeated herein.
A track bolt looseness detection apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the track bolt looseness detection method according to any one of the above when executing the computer program. According to the track bolt looseness detection method provided by the invention, the excitation assembly vibrates the bolt to be detected by sending an activation signal to the excitation assembly; acquiring vibration video information of the bolt to be detected from a photographic assembly; according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information. According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency of the bolt to be detected is derived from the collected vibration video information by a machine vision related algorithm, and the result of whether the bolt to be detected is loosened is obtained after the vibration frequency is compared with a preset vibration threshold value, so that the manual detection which too depends on the experience of workers is eliminated, and the safe, efficient and accurate identification of the looseness of the track bolt is realized.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of detecting a loosening of a track bolt as defined in any of the previous claims. According to the track bolt looseness detection method provided by the invention, the excitation assembly vibrates the bolt to be detected by sending an activation signal to the excitation assembly; acquiring vibration video information of the bolt to be detected from a photographic assembly; according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information. According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency of the bolt to be detected is derived from the collected vibration video information by a machine vision related algorithm, and the result of whether the bolt to be detected is loosened is obtained after the vibration frequency is compared with a preset vibration threshold value, so that the manual detection which too depends on the experience of workers is eliminated, and the safe, efficient and accurate identification of the looseness of the track bolt is realized.
The invention also provides a loose track bolt detector, the structural schematic diagram of which is shown in fig. 4, and the detector comprises an excitation component 02, a camera component 03 and a signal processor 01;
the excitation assembly 02 is used for vibrating the bolt to be tested during activation;
the camera component 03 is used for covering the bolt to be detected in a vision field and shooting vibration video information of the bolt to be detected;
the signal processor 01 is configured to send an activation signal to the excitation assembly 02, acquire the vibration video information from the camera assembly 03, and obtain time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
The loose track bolt detector provided by the invention corresponds to the track bolt loose detection method in the foregoing, so reference may be made to the description of the track bolt loose detection method in the foregoing, and the technical details are not described herein again.
As a specific implementation mode, cameras are installed on two sides of each track, 4 cameras are arranged in total, the camera shooting area covers the whole bolt area, and the fact that the camera can shoot the bolt vibration position is guaranteed.
Preferably, the excitation assembly 02 is an acoustic wave resonance assembly;
the sound wave resonance assembly is used for emitting sound waves of a first frequency, and the difference value between the first frequency and the resonance frequency of the bolt to be tested in the loosening state is smaller than a preset permission threshold value.
The more the bolt to be measured loosens, the closer its resonance frequency that corresponds is to the resonance frequency under the not hard up state, therefore, the sound wave resonance subassembly of this application launches the sound wave of the first frequency near the resonance frequency under the not hard up state, the threshold value of obtaining permission can be decided according to actual conditions.
Of course, the excitation method of the excitation component 02 includes steady-state sinusoidal excitation, transient excitation (fast sinusoidal scanning excitation, pulse excitation, step excitation), random excitation, and the like; the excitation assembly 02 may include a mechanical type, an electric type, a hydraulic type, an electromagnetic type, an impact hammer, and the like, in addition to the acoustic wave resonance assembly.
The photographing component 03 includes a monocular camera, an RGBD depth camera (binocular camera, structured light depth camera, time of flight TOF depth camera, multi-view camera (oblique photography)), and the like.
Preferably, the camera component 03 is a depth camera, and the depth camera can obtain the distance between each pixel of the picture and the shooting lens, that is, a depth measurement is added on the basis of the basic function of a common camera to obtain the three-dimensional coordinate of each pixel, so that a real scene can be restored better.
The invention also provides a track detection vehicle which comprises the loose track bolt detector.
The loose track bolt detector can detect all track bolts below the track detection vehicle in the running process of the track detection vehicle, and a partial structure schematic diagram of one specific embodiment is shown in fig. 5.
The loose track bolt detector provided by the invention comprises an excitation component 02, a camera component 03 and a signal processor 01; the excitation assembly 02 is used for vibrating the bolt to be tested during activation; the camera component 03 is used for covering the bolt to be detected in a vision field and shooting vibration video information of the bolt to be detected; the signal processor 01 is configured to send an activation signal to the excitation assembly 02, acquire the vibration video information from the camera assembly 03, and obtain time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information. According to the invention, the bolt to be detected is forced to vibrate by an active excitation means, the vibration frequency of the bolt to be detected is derived from the collected vibration video information by a relevant algorithm of machine vision, and the vibration frequency is compared with a preset vibration threshold value to draw a conclusion whether the bolt to be detected is loosened or not, so that the manual detection which excessively depends on the experience of workers is avoided, and the safe, efficient and accurate identification of the looseness of the track bolt is realized.
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. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is to be noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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.
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 invention.
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 track bolt looseness detection method, device, equipment, computer readable storage medium, looseness track bolt detector and track detection vehicle provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A rail bolt looseness detection method is characterized by comprising the following steps:
sending an activation signal to an excitation assembly to enable the excitation assembly to vibrate the bolt to be tested;
acquiring vibration video information of the bolt to be detected from a photographic assembly;
according to the vibration video information, obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm;
obtaining frequency domain information according to the time domain information;
judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information;
and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
2. The track bolt looseness detection method according to claim 1, wherein when the excitation assembly and the camera assembly are both disposed on the track inspection vehicle, the marking of the bolt to be inspected as a loosened bolt and recording of corresponding positioning information includes:
and marking the bolt to be detected as a loose bolt, and recording mileage information corresponding to the track inspection vehicle.
3. The track bolt looseness detection method of claim 1, wherein the obtaining, according to the vibration video information, time domain information of the vibration of the bolt to be detected through a target tracking algorithm includes:
performing video motion amplification on the vibration video information to obtain amplified video information;
and obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the amplified video information.
4. The track bolt looseness detection method of claim 1, wherein said obtaining frequency domain information from said time domain information comprises:
and obtaining frequency domain information through a Fourier transform algorithm according to the time domain information.
5. The utility model provides a track bolt looseness detection device which characterized in that includes:
the activation module is used for sending an activation signal to the excitation assembly to enable the excitation assembly to vibrate the bolt to be tested;
the video acquisition module is used for acquiring vibration video information of the bolt to be detected from a camera assembly;
the time domain module is used for obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information;
the frequency domain module is used for obtaining frequency domain information according to the time domain information;
the judging module is used for judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value according to the frequency domain information;
and the loosening marking module is used for marking the bolt to be detected as a loosening bolt when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, and recording corresponding positioning information.
6. The utility model provides a track bolt check out test set that becomes flexible which characterized in that includes:
a memory for storing a computer program;
a processor for implementing the steps of the rail bolt looseness detection method according to any one of claims 1 to 4 when executing said computer program.
7. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the rail bolt looseness detection method according to any one of claims 1 to 4.
8. A loose track bolt detector is characterized by comprising an excitation component, a camera component and a signal processor;
the excitation assembly is used for vibrating the bolt to be tested during activation;
the camera assembly is used for covering the bolt to be detected in a vision field and shooting vibration video information of the bolt to be detected;
the signal processor is used for sending an activation signal to the excitation assembly, acquiring the vibration video information from the photographic assembly, and obtaining time domain information of the vibration of the bolt to be detected through a target tracking algorithm according to the vibration video information; obtaining frequency domain information according to the time domain information; judging whether the vibration frequency of the bolt to be detected exceeds a preset vibration threshold value or not according to the frequency domain information; and when the vibration frequency of the bolt to be detected exceeds the vibration threshold value, marking the bolt to be detected as a loose bolt, and recording corresponding positioning information.
9. The loose track bolt detector of claim 8, wherein the excitation component is an acoustic resonance component;
the sound wave resonance assembly is used for emitting sound waves of a first frequency, and the difference value between the first frequency and the resonance frequency of the bolt to be tested in the loosening state is smaller than a preset permission threshold value.
10. A rail inspection vehicle, characterized in that it comprises a loose rail bolt detector as claimed in claim 8 or 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210479654.1A CN114972205A (en) | 2022-05-05 | 2022-05-05 | Track bolt looseness detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210479654.1A CN114972205A (en) | 2022-05-05 | 2022-05-05 | Track bolt looseness detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114972205A true CN114972205A (en) | 2022-08-30 |
Family
ID=82979632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210479654.1A Pending CN114972205A (en) | 2022-05-05 | 2022-05-05 | Track bolt looseness detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972205A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937165A (en) * | 2022-12-19 | 2023-04-07 | 中交公路长大桥建设国家工程研究中心有限公司 | Mobile bolt loosening intelligent detection and identification method and system |
| CN117782403A (en) * | 2024-02-27 | 2024-03-29 | 北京谛声科技有限责任公司 | Loose bolt positioning method, device and medium based on separation network |
| CN118090109A (en) * | 2024-04-26 | 2024-05-28 | 河南工学院 | Online auscultation system for monitoring abnormal vibration table and monitoring method thereof |
-
2022
- 2022-05-05 CN CN202210479654.1A patent/CN114972205A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937165A (en) * | 2022-12-19 | 2023-04-07 | 中交公路长大桥建设国家工程研究中心有限公司 | Mobile bolt loosening intelligent detection and identification method and system |
| CN115937165B (en) * | 2022-12-19 | 2023-08-25 | 中交公路长大桥建设国家工程研究中心有限公司 | Intelligent detection and identification method and system for loosening of movable bolt |
| CN117782403A (en) * | 2024-02-27 | 2024-03-29 | 北京谛声科技有限责任公司 | Loose bolt positioning method, device and medium based on separation network |
| CN117782403B (en) * | 2024-02-27 | 2024-05-10 | 北京谛声科技有限责任公司 | Loose bolt positioning method, device and medium based on separation network |
| CN118090109A (en) * | 2024-04-26 | 2024-05-28 | 河南工学院 | Online auscultation system for monitoring abnormal vibration table and monitoring method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114972205A (en) | Track bolt looseness detection method and device | |
| CN114596525B (en) | Dynamic bridge form recognition method based on computer vision | |
| CN113808096B (en) | Non-contact bolt loosening detection method and system | |
| Ngeljaratan et al. | System identification of large-scale bridges using target-tracking digital image correlation | |
| Jiang et al. | A detailed investigation of uplift and damping of a railway catenary span in traffic using a vision-based line-tracking system | |
| CN115791803B (en) | Deep-buried tunnel surrounding rock blasting damage test system and test method | |
| CN115014617B (en) | Cable-stayed bridge cable force synchronous monitoring method based on ground radar | |
| KR102139987B1 (en) | Slope monitoring method using vibration synthesized image | |
| CN115761487A (en) | Method for quickly identifying vibration characteristics of small and medium-span bridges based on machine vision | |
| Morlier et al. | Virtual vibration measurement using KLT motion tracking algorithm | |
| CN114550037A (en) | Hydropower station video data digital safety early warning method and device | |
| CN115876365B (en) | Visual testing method, device and medium for inhaul cable force based on motion comprehensive brightness spectrum | |
| Chen et al. | Video camera-based vibration measurement for Condition Assessment of Civil Infrastructure | |
| CN116386302A (en) | Intelligent monitoring and early warning system for side slope | |
| Shen et al. | Video-based vibration measurement for large structure: A spatiotemporal disturbance-adaptive morphological component analysis | |
| US20170169576A1 (en) | Crowd intelligence on flow velocity measurement | |
| Shariati et al. | Oversampling in virtual visual sensors as a means to recover higher modes of vibration | |
| CN110930447A (en) | Android-based unattended snow depth measurement method | |
| McCarthy et al. | 3D case studies of monitoring dynamic structural tests using long exposure imagery | |
| Jeon et al. | Multi-point measurement of structural vibration using pattern recognition from camera image | |
| JP2016161453A (en) | Signal analyzer and knocking detector | |
| CN110969875A (en) | Method and system for road intersection traffic management | |
| Bao et al. | Motion magnification for quantifying aeroelastic modes from high-speed videos | |
| CN113538580B (en) | Vibration measurement method and system based on visual processing | |
| CN114295058B (en) | Method for measuring whole-face dynamic displacement of building structure |
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 |