CN112033674A - Train fault online detection system and method - Google Patents

Train fault online detection system and method Download PDF

Info

Publication number
CN112033674A
CN112033674A CN202010786738.0A CN202010786738A CN112033674A CN 112033674 A CN112033674 A CN 112033674A CN 202010786738 A CN202010786738 A CN 202010786738A CN 112033674 A CN112033674 A CN 112033674A
Authority
CN
China
Prior art keywords
input end
signal
output end
port
train
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.)
Granted
Application number
CN202010786738.0A
Other languages
Chinese (zh)
Other versions
CN112033674B (en
Inventor
王宇
马诗洋
靳宝全
高妍
张红娟
白清
刘昕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taiyuan University of Technology
Original Assignee
Taiyuan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Taiyuan University of Technology filed Critical Taiyuan University of Technology
Priority to CN202010786738.0A priority Critical patent/CN112033674B/en
Publication of CN112033674A publication Critical patent/CN112033674A/en
Application granted granted Critical
Publication of CN112033674B publication Critical patent/CN112033674B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00Testing of machine parts
    • G01M13/04Bearings
    • G01M13/045Acoustic or vibration analysis
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/165Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00Testing of vehicles
    • G01M17/08Railway vehicles
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/01Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/03Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers
    • G01S19/10Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers providing dedicated supplementary positioning signals
    • G01S19/12Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers providing dedicated supplementary positioning signals wherein the cooperating elements are telecommunication base stations
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42Determining position
    • G01S19/45Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
    • G01S19/47Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Automation & Control Theory (AREA)
  • Acoustics & Sound (AREA)
  • Optical Communication System (AREA)

Abstract

The invention relates to a train fault on-line detection system and a method, which can detect and locate a train fault point in real time by using a distributed optical fiber vibration sensing system, and can shorten the locating period of a global positioning system and identify faults by combining a three-axis accelerometer with the global positioning system; the method is characterized in that a weighted fusion algorithm of a least square method is designed to complete fusion of three types of signals, more accurate detection and positioning of a fault axle during train operation are realized through multidimensional modeling analysis, and the system has the advantages of flexible layout, simple structure, electromagnetic interference resistance, no detection blind area and the like.

Description

Train fault online detection system and method
Technical Field
The invention relates to the technical field of optical fiber sensing, in particular to a train fault online detection system and method.
Background
The high-speed train is used as a national great infrastructure and a popular vehicle, and plays an important role in the national economic development and the safety of people in journey by ensuring the normal and safe operation of the high-speed train. After a high-speed train runs for a long time, a bottom axle is easy to break down, and safety accidents are easy to cause. However, the traditional detection means still has certain limitations, such as manual investigation cannot be performed in all weather in real time, the detection period of the wheel sensor is long, and timely alarming cannot be performed. Under the background, the continuously developed distributed optical fiber vibration sensing technology can be applied to the field of detection of a failed axle of a high-speed train due to the advantages of electromagnetic interference resistance, high sensitivity, no detection blind area and the like.
When the high-speed train runs, the wheel axle fails, and abnormal vibration can be generated on the rail. A distributed optical fiber vibration sensing system based on a coherent optical time domain reflection technology detects optical phase change caused by abnormal vibration through a sensing optical fiber laid along a rail, and realizes positioning and alarming of a train fault wheel shaft. The train is combined with a three-axis accelerometer and a global positioning system of the train, and meanwhile, the acceleration and position signals of the train are wirelessly transmitted and are fused with the vibration signals of the optical fiber vibration system, so that the safety detection of the train and the accurate positioning and real-time alarming of fault points when the train breaks down are realized.
Disclosure of Invention
The invention provides an on-line train fault detection system and method, which utilize coherent optical time domain reflection technology to detect and position a vibration signal generated by a fault axle when a train runs, and combine a three-axis accelerometer and a global positioning system of the train to perform algorithm fusion on an acceleration signal and a geographic position signal through wireless transmission and an optical fiber vibration signal, so as to realize accurate positioning and real-time alarm of the train fault axle.
The technical scheme adopted by the invention for solving the technical problems is as follows: constructing a train fault online detection system comprising:
the device comprises a narrow-linewidth laser, a first optical fiber coupler, an acousto-optic modulator, a wavelength division multiplexer, a circulator, an optical cable connecting box, an optical cable, a tail fiber terminal box, a second optical fiber coupler, a balanced photoelectric detector, a band-pass filter, a sine wave generator, an orthogonal demodulator, a low-pass filter, an amplitude operator, a three-axis accelerometer, a first signal modulator, a first wireless signal generator, a high-speed analog-to-digital conversion module, a microcontroller, a global positioning system, a first data converter, a second signal modulator, a second wireless signal transmitter, a first wireless signal receiver, a first signal demodulator, a Kalman filtering module, a second wireless signal receiver, a second signal demodulator, a second data converter, a high-speed data acquisition card, a multi-source data fusion module, a feature extraction module and an upper computer;
wherein the output end of the narrow linewidth laser is connected with the input end of the first optical fiber coupleraPort, output of first optical fiber couplerbThe port is connected with the input end of the acousto-optic modulator and the other output end of the first optical fiber couplercWith ports connecting to second fibre-optic couplersaA terminal; the output end of the acousto-optic modulator is connected with the input end of the wavelength division multiplexer, and the output end of the wavelength division multiplexer is connected with the circulatoraOf port, circulatorbThe port is connected with the input end of the optical cable connection box, the optical cable is laid at a position close to the rail, the output end of the optical cable connection box is connected with one end of the optical cable, and the other end of the optical cable is connected with the input end of the tail fiber terminal box; of circulatorscWith ports connecting to second fibre-optic couplersbOf ports, second fibre-optic couplersc、dWith ports respectively connected to balanced photodetectorsa、bPort, balanced photodetectorcThe port is connected with the input end of a band-pass filter, and the output end of the band-pass filter and the output end of a sine wave generator are respectively connected with the input end of the band-pass filterConnected to quadrature demodulatorsa、bOf port, quadrature demodulatorsc、dWith ports connected to low-pass filtersa、 bPort, output of low pass filtercThe port is connected to the input end of the amplitude arithmetic unit, and the output end of the amplitude arithmetic unit is connected with the high-speed data acquisition cardaA terminal; of three-axis accelerometersaTerminals connected to input terminals of a first signal modulator, output terminals of the first signal modulator connected to input terminals of a first radio signal transmitter, of a triaxial accelerometerbThe end of the first wireless signal modulator is connected with the input end of a first wireless signal transmitter; the output end of the first wireless signal receiver is connected with the input end of a first signal demodulator, the output end of the first signal demodulator is connected with the input end of a Kalman filtering module, and the output end of the Kalman filtering module is connected with a high-speed data acquisition cardbThe output end of the second wireless signal receiver is connected with the input end of a second signal demodulator, the output end of the second signal demodulator is connected with the input end of a second data converter, and the output end of the second data converter is connected with a high-speed data acquisition cardcOf port, high-speed data acquisition cardsd、e、fWith ends respectively connected to multiple-source data fusion modulesa、b、cPort, multi-source data fusion moduledThe port is connected with the input end of the characteristic extraction module; the output end of the characteristic extraction module is connected with the input end of the upper computer.
Wherein, the output end of the narrow linewidth laser and the input end of the first optical fiber coupleraAn optical fiber isolator is arranged between the ports.
An optical fiber amplifier is arranged between the output end of the acousto-optic modulator and the input end of the wavelength division multiplexer.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method for detecting the train fault on line is constructed, the train fault on line detection system in the technical scheme is used for detecting, and the method comprises the following steps:
preprocessing a vibration signal detected and transmitted by the optical cable, a train wheel axle acceleration signal received by the first wireless signal receiver and the second wireless signal receiver and a train geographical position signal;
after the three types of data are preprocessed, carrying out weighted average on redundant information of each type of data by using a weighted average fusion algorithm, and taking the result as a fusion value;
performing feature extraction transformation on the fused data by using empirical mode decomposition, and extracting a feature vector representing the data;
and performing pattern recognition processing on the characteristic vectors by using a support vector machine, and realizing more accurate detection and positioning of the fault wheel axle during the operation of the train through multidimensional modeling analysis.
In the step of preprocessing the three types of data, noise interference generated when a fault wheel axle operates is removed and filtered by utilizing wavelet denoising.
Different from the prior art, the train fault online detection system and the method adopt the distributed optical fiber vibration sensing technology to detect the train wheel shaft all the way, can position the fault point in real time when the fault occurs, and have the advantages of flexible layout, simple structure, electromagnetic interference resistance, no detection blind area and the like; the detection of the fault point and the train running position is realized by utilizing a three-axis accelerometer, a global positioning system and a wireless transmission module and combining an acceleration signal and a geographical position signal; meanwhile, the method adopts a weighted fusion algorithm of a least square method to fuse the vibration signal, the acceleration signal and the geographic position signal, and realizes more accurate detection and positioning of the fault axle during the operation of the train through multidimensional modeling analysis.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic structural diagram of an online train fault detection system provided by the invention.
FIG. 2 is a schematic flow chart of a method for measuring the bending degree of a scraper optical fiber according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Referring to fig. 1, the present invention provides an online train fault detection system, which includes:
a narrow-linewidth laser 1, a first optical fiber coupler 3, an acousto-optic modulator 4, a wavelength division multiplexer 6, a circulator 7, an optical cable connection box 8, an optical cable 9, a pigtail termination box 10, a second optical fiber coupler 11, a balanced photodetector 12, a band-pass filter 13, a sine wave generator 14, a quadrature demodulator 15, a low-pass filter 16, an amplitude operator 17, a three-axis accelerometer 18, a first signal modulator 19, a first wireless signal generator 20, a high-speed analog-to-digital conversion module 21, a microcontroller 22, a global positioning system 23, a first data converter 24, a second signal modulator 25, a second wireless signal transmitter 26, a first wireless signal receiver 28, a first signal demodulator 29, a Kalman filtering module 30, a second wireless signal receiver 31, a second signal demodulator 32, a second data converter 33, a high-speed data acquisition card 34, a multi-source data fusion module 35, A feature extraction module 36 and an upper computer 37;
the output end of the narrow linewidth laser 1 is connected with the input end a port of the first optical fiber coupler 3, the output end b port of the first optical fiber coupler 3 is connected with the input end of the acousto-optic modulator 4, and the other output end c port of the first optical fiber coupler 3 is connected with the end a of the second optical fiber coupler 11; the output end of the acoustic optical modulator 4 is connected with the input end of the wavelength division multiplexer 6, the output end of the wavelength division multiplexer 6 is connected with the port a of the circulator 7, the port b of the circulator 7 is connected with the input end of the optical cable connection box 8, the optical cable 9 is laid at a position close to the rail 27, the output end of the optical cable connection box 8 is connected with one end of the optical cable 9, and the other end of the optical cable 9 is connected with the input end of the tail fiber terminal box 10; the port c of the circulator 7 is connected with the port b of the second optical fiber coupler 11, the ports c and d of the second optical fiber coupler 11 are respectively connected with the ports a and b of the balanced photoelectric detector 12, the port c of the balanced photoelectric detector 12 is connected with the input end of the band-pass filter 13, the output end of the band-pass filter 13 and the output end of the sine wave generator 14 are respectively connected with the ports a and b of the quadrature demodulator 15, the ports c and d of the quadrature demodulator 15 are connected with the ports a and b of the low-pass filter 16, the port c of the output end of the low-pass filter 16 is connected with the input end of the amplitude arithmetic unit 17, and the output end of the amplitude arithmetic unit 17 is connected with the end a of the high; the a end of the triaxial accelerometer 18 is connected with the input end of a first signal modulator 19, the output end of the first signal modulator 19 is connected with the input end of a first wireless signal transmitter 20, the b end of the triaxial accelerometer 18 is connected with the input end of a high-speed analog-to-digital conversion module 21, the output end of the high-speed analog-to-digital conversion module 21 is connected with the input end of a microcontroller 22, the output end of the microcontroller 22 is connected with the input end of a global positioning system 23, the output end of the global positioning system 23 is connected with the input end of a first data converter 24, the output end of the first data converter 24 is connected with the input end of a second signal modulator 25, and the output end of the second signal modulator 25 is connected with the; the output end of the first wireless signal receiver 28 is connected with the input end of the first signal demodulator 29, the output end of the first signal demodulator 29 is connected with the input end of the Kalman filtering module 30, the output end of the Kalman filtering module 30 is connected with the port b of the high-speed data acquisition card 34, the output end of the second wireless signal receiver 31 is connected with the input end of the second signal demodulator 32, the output end of the second signal demodulator 32 is connected with the input end of the second data converter 33, the output end of the second data converter 33 is connected with the port c of the high-speed data acquisition card 34, the ends d, e and f of the high-speed data acquisition card 34 are respectively connected with the ports a, b and c of the multi-source data fusion module 35, and the port d of the multi-source data fusion module 35 is connected with the; the output end of the feature extraction module 36 is connected with the input end of the upper computer 37.
An optical fiber isolator 2 is arranged between the output end of the narrow linewidth laser 1 and the input end a port of the first optical fiber coupler 3.
Wherein, an optical fiber amplifier 5 is arranged between the output end of the acousto-optic modulator 4 and the input end of the wavelength division multiplexer 6.
The narrow linewidth laser 1 outputs light with the central wavelength of 1550nm to the input end of the optical fiber isolator 2; the optical fiber isolator 2 is in one-way transmission, and the output light is transmitted to the port a of the first optical fiber coupler 3; the first optical fiber coupler 3 divides the signal into two parts of 99:1, and the two parts are respectively output from two ports b and c; the light output from the port b of the first optical fiber coupler 3 is transmitted to the input end of the acousto-optic modulator 4; the acousto-optic modulator 4 modulates light into pulse light and outputs the pulse light to the input end of the optical fiber amplifier 5; the optical fiber amplifier 5 amplifies the optical power and outputs the amplified optical power to the input end of the wavelength division multiplexer 6; the wavelength division multiplexer 6 filters the input light and outputs the filtered light to the port a of the optical circulator 7; the b end of the optical circulator 8 is output to the input end of the optical cable connecting box 8; the optical cable connection box 8 outputs optical fiber and optical cable connection from the output port to the input end of the optical cable 9, and the optical cable 9 is laid along the rail 27 for detecting and transmitting vibration signals on the rail; the output end of the optical cable 9 is connected with the input end of the tail fiber terminal box 10 and is used for realizing the tail end treatment of the optical cable; backward Rayleigh scattered light generated by the optical cable 9 returns to the port b of the optical circulator 7 through the optical cable connecting box 8; the c port of the optical circulator 7 outputs return light to the b port of the second optical fiber coupler 11; the intrinsic light output from the c port of the first optical fiber coupler 3 is transmitted to the a port of the second optical fiber coupler 11; the second optical fiber coupler 11 generates coherent beat frequency and outputs the frequency to ports a and b of the balanced photoelectric detector 12 through ports c and d; the balanced photoelectric detector 12 converts the optical signal into an electrical signal and outputs the electrical signal to the input end of the band-pass filter 13 through the port c, and the center frequency of the band-pass filter is 200MHz and is used for filtering noise signals outside a pass band; the band-pass filter 13 filters the signal and outputs the filtered signal to a port a of the quadrature demodulator 15; the sine wave generator 14 generates a standard sine wave signal and outputs the standard sine wave signal to a port b of the quadrature demodulator 15; the signal after quadrature demodulation by the quadrature demodulator 15 is output to the ports a and b of the low-pass filter 16 through the ports c and d, the frequency range of the low-pass filter is 0-50MHz, and noise except the frequency of 0-50MHz is filtered; the port c of the low-pass filter 16 outputs the filtered signal to the input end of the amplitude arithmetic unit 17, the position information of the vibration point is obtained through amplitude arithmetic, the output port of the amplitude arithmetic unit 17 is output to the end a of the high-speed data acquisition card 34, and the position information data acquisition of the vibration point is carried out; the end a of the triaxial accelerometer 18 outputs a vibration acceleration signal generated by a train wheel shaft to the input end of the first signal modulator 19, and the vibration acceleration signal is modulated into a high-frequency signal; the output end of the first signal modulator 19 transmits the modulated signal to the input end of the first wireless signal transmitter 20 for wireless transmission; the b end of the triaxial accelerometer 18 is connected with the input end of the high-speed analog-to-digital conversion module 21, and converts an analog signal into a digital signal; the output end of the high-speed analog-to-digital conversion module 21 transmits a digital signal to the input end of the microcontroller 22, the microcontroller 22 is driven to generate an instruction for starting the global positioning system 23, and the three-axis accelerometer 18 is used for controlling and triggering the global positioning system 23 to perform positioning, so that the positioning period of a train track can be shortened, and the positioning accuracy is improved; the global positioning system 23 outputs the positioning signal to the input end of the first data converter 24, and converts the asynchronous data of the global positioning system 23 into synchronous data; the output end of the first data converter 24 transmits the synchronous data to the input end of the second signal modulator 25, and performs error correction coding on the synchronous data to form a baseband signal which can be transmitted by a channel; the output end of the second signal modulator 25 transmits the baseband signal to the input end of the second wireless signal transmitter 26 for wireless transmission; the first wireless signal receiver 28 receives the signal transmitted by the first wireless signal transmitter 20 and transmits the signal to the input end of the first signal demodulator 29, so as to demodulate the vibration acceleration signal from the high-frequency signal; the first signal demodulator 29 transmits a vibration acceleration signal generated by a train axle to the input end of the kalman filtering module 30, so as to filter noise generated during train operation; the kalman filtering module 30 transmits the processed signals to the b end of the high-speed data acquisition card 34, and performs data acquisition on the vibration acceleration signals generated by the train axle; the second wireless signal receiver 31 receives the train geographical position signal transmitted by the second wireless signal transmitter 26 and transmits the train geographical position signal to the input end of the second signal demodulator 32, and 2 psk demodulation is performed on the baseband signal to recover the synchronous data; the second signal demodulator 32 transmits the synchronous data to the input end of the second data converter 33, and converts the synchronous data into asynchronous data; the second data converter 33 transmits asynchronous data to the c end of the high-speed data acquisition card 34 to acquire the train geographical position signals; the d, e and f ends of the high-speed data acquisition card are respectively connected with the a, b and c ends of the multi-source data fusion module, and algorithm fusion is carried out on the acquired vibration signals, acceleration signals and train geographical position signals; the d end of the multi-source data fusion module transmits the fused signal to the input end of the feature extraction module 36 for feature extraction; the feature extraction module 36 transmits the feature vector to the input end of the upper computer 37 for signal identification processing.
When a train passes through a rail 27 laid with an optical cable 9, return light carrying vibration information is output to a port b of an optical circulator 7 through a sensing optical fiber, namely an optical cable connecting box 8, the port c of the optical circulator 7 outputs return light to a port b of a second optical fiber coupler 11, intrinsic light output by the port c of a first optical fiber coupler 3 is output to a port a of the second optical fiber coupler 11, coherent beat frequency is generated in the second optical fiber coupler 11 and is output to ports a and b of a balanced photoelectric detector 12 through ports c and d, the balanced photoelectric detector 12 converts an optical signal into an electric signal and outputs the electric signal to an input end of a band-pass filter 13, the electric signal is filtered by the band-pass filter 13 and is output to a port a of an orthogonal demodulator 15, a sine wave signal generated by a sine wave generator 14 is output to a port b of the orthogonal demodulator 15, and a signal subjected to orthogonal demodulation by the orthogonal demodulator 15 is output from c, The port d is output to ports a and b of the low-pass filter 16, filtered by the low-pass filter 16 and output to the input end of the amplitude arithmetic unit 16 through the port c, the position information of the vibration point is obtained through amplitude arithmetic, and the position information is output to the port a of the high-speed data acquisition card 34 through the output end of the amplitude arithmetic unit 17; the end a of the triaxial accelerometer 18 outputs the generated vibration acceleration signal to the input end of the first signal modulator 19, and modulates the vibration acceleration signal into a high-frequency signal, and the output end of the first signal modulator 19 transmits the modulated signal to the input end of the first wireless signal transmitter 20 for wireless transmission; the b end of the triaxial accelerometer 18 is connected with the input end of the high-speed analog-to-digital conversion module 21, the analog signal is converted into a digital signal, the output end of the high-speed analog-to-digital conversion module 21 transmits the digital signal to the input end of the microcontroller 22, the microcontroller 22 is driven to send out an instruction to start the global positioning system 23 and output the positioning signal to the input end of the first data converter 24, the first data converter 24 converts asynchronous data of the global positioning system 23 into synchronous data and transmits the synchronous data to the input end of the second signal modulator 25, the second signal modulator 25 performs error correction coding on the synchronous data to form a baseband signal which can be transmitted by a channel and then transmits the baseband signal to the input end of the second wireless signal transmitter 26 for wireless transmission; the first wireless signal receiver 28 receives the signal transmitted by the first wireless signal transmitter 20 and transmits the signal to the input end of the first signal demodulator 29, the first signal demodulator 29 demodulates the vibration acceleration signal from the high-frequency signal and transmits the signal to the input end of the kalman filtering module 30, and the signal is transmitted to the b end of the high-speed data acquisition card 34 after the noise generated during the operation of the train is filtered; the second wireless signal receiver 31 receives the signal transmitted by the second wireless signal transmitter 26 and transmits the signal to the input end of the second signal demodulator 32, performs 2 psk demodulation on the baseband signal to recover synchronous data, and then transmits the synchronous data to the input end of the second data converter 33, converts the synchronous data into asynchronous data and transmits the asynchronous data to the c end of the high-speed data acquisition card 34; the high-speed data acquisition card 34 acquires and processes vibration signals detected and transmitted by the optical cable, train axle acceleration signals and train geographical position signals received by the wireless signal receiver, and outputs the signals to the multi-source data fusion module 35, the multi-source data fusion module 35 performs algorithm fusion on the three signals and transmits the fused signals to the input end of the feature extraction module 36 for feature extraction, and finally the feature extraction module 36 transmits feature vectors to the upper computer 37 for signal identification processing and display.
Referring to fig. 2, the present invention further provides an online train fault detection method, which uses the online train fault detection system according to the foregoing technical solution to perform detection, and includes:
preprocessing the vibration signal detected and transmitted by the optical cable 9, the train axle acceleration signal and the train geographical position signal received by the first wireless signal receiver 28 and the second wireless signal receiver 31;
after the three types of data are preprocessed, carrying out weighted average on redundant information of each type of data by using a weighted average fusion algorithm, and taking the result as a fusion value;
performing feature extraction transformation on the fused data by using empirical mode decomposition, and extracting a feature vector representing the data;
and performing pattern recognition processing on the characteristic vectors by using a support vector machine, and realizing more accurate detection and positioning of the fault wheel axle during the operation of the train through multidimensional modeling analysis.
In the step of preprocessing the three types of data, noise interference generated when a fault wheel axle operates is removed and filtered by utilizing wavelet denoising.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (5)

1. An on-line train fault detection system, comprising:
the device comprises a narrow-linewidth laser (1), a first optical fiber coupler (3), an acoustic-optical modulator (4), a wavelength division multiplexer (6), a circulator (7), an optical cable connecting box (8), an optical cable (9), a tail fiber terminal box (10), a second optical fiber coupler (11), a balanced photoelectric detector (12), a band-pass filter (13), a sine wave generator (14), an orthogonal demodulator (15), a low-pass filter (16), an amplitude calculator (17), a three-axis accelerometer (18), a first signal modulator (19), a first wireless signal generator (20), a high-speed analog-to-digital conversion module (21), a microcontroller (22), a global positioning system (23), a first data converter (24), a second signal modulator (25), a second wireless signal transmitter (26), a first wireless signal receiver (28), and a first signal demodulator (29), The system comprises a Kalman filtering module (30), a second wireless signal receiver (31), a second signal demodulator (32), a second data converter (33), a high-speed data acquisition card (34), a multi-source data fusion module (35), a feature extraction module (36) and an upper computer (37);
wherein, the output end of the narrow linewidth laser (1) is connected with the input end of the first optical fiber coupler (3)aPort, output of the first fiber coupler (3)bThe port is connected with the input end of the acousto-optic modulator (4) and the other output end of the first optical fiber coupler (3)cThe ports being connected to a second fibre-optic coupler (11)aA terminal; the output end of the acousto-optic modulator (4) is connected with the input end of the wavelength division multiplexer (6), and the output end of the wavelength division multiplexer (6) is connected with the circulator (7)aOf port, circulator (7)bThe port is connected with the input end of an optical cable connection box (8), an optical cable (9) is laid at a position close to a rail (27), the output end of the optical cable connection box (8) is connected with one end of the optical cable (9), and the other end of the optical cable (9) is connected to the input end of a tail fiber terminal box (10); of circulators (7)cThe ports being connected to a second fibre-optic coupler (11)bOf ports, second fibre-optic couplers (11)c、dWith ports respectively connected to balanced photodetectors (12)a、bPort, balanced photodetector (12)cThe port is connected with the input end of a band-pass filter (13), the output end of the band-pass filter (13) and the output end of a sine wave generator (14) are respectively connected with the quadrature demodulator (15)a、bOf port, quadrature demodulator (15)c、dWith ports connected to low-pass filters (16)a、bPort, output of low pass filter (16)cThe port is connected with the input end of an amplitude arithmetic unit (17), and the output end of the amplitude arithmetic unit (17) is connected with a high-speed data acquisition card (34)aA terminal; of three-axis accelerometers (18)aThe terminal of the first signal modulator (19) is connected with the input terminal of the first signal modulator (19), and the output terminal of the first signal modulator (19) is connected with the input terminal of the first wireless signal transmitter (20)At the input, of three-axis accelerometers (18)bThe end of the high-speed analog-to-digital conversion module is connected with the input end of the high-speed analog-to-digital conversion module (21), the output end of the high-speed analog-to-digital conversion module (21) is connected with the input end of the microcontroller (22), the output end of the microcontroller (22) is connected with the input end of the global positioning system (23), the output end of the global positioning system (23) is connected with the input end of the first data converter (24), the output end of the first data converter (24) is connected with the input end of the second signal modulator (25), and the output end of the second signal modulator (25) is connected with the input end of the second wireless; the output end of the first wireless signal receiver (28) is connected with the input end of a first signal demodulator (29), the output end of the first signal demodulator (29) is connected with the input end of a Kalman filtering module (30), and the output end of the Kalman filtering module (30) is connected with the input end of a high-speed data acquisition card (34)bThe output end of the second wireless signal receiver (31) is connected with the input end of a second signal demodulator (32), the output end of the second signal demodulator (32) is connected with the input end of a second data converter (33), and the output end of the second data converter (33) is connected with the input end of a high-speed data acquisition card (34)cOf port, high-speed data acquisition cards (34)d、e、fWith ends respectively connected to multiple source data fusion modules (35)a、b、cOf port, multisource data fusion modules (35)dThe port is connected with the input end of the characteristic extraction module (36); the output end of the feature extraction module (36) is connected with the input end of the upper computer (37).
2. The train fault on-line detection system according to claim 1, characterized in that the narrow linewidth laser (1) output end and the first fiber coupler (3) input endaAn optical fiber isolator (2) is arranged between the ports.
3. The train fault on-line detection system according to claim 1, characterized in that an optical fiber amplifier (5) is arranged between the output end of the acousto-optic modulator (4) and the input end of the wavelength division multiplexer (6).
4. An on-line train fault detection method, which is used for detection by the on-line train fault detection system according to any one of claims 1 to 4, and is characterized by comprising the following steps:
preprocessing a vibration signal detected and transmitted by an optical cable (9), a train wheel axle acceleration signal and a train geographical position signal received by a first wireless signal receiver (28) and a second wireless signal receiver (31);
after the three types of data are preprocessed, carrying out weighted average on redundant information of each type of data by using a weighted average fusion algorithm, and taking the result as a fusion value;
performing feature extraction transformation on the fused data by using empirical mode decomposition, and extracting a feature vector representing the data;
and performing pattern recognition processing on the characteristic vectors by using a support vector machine, and realizing more accurate detection and positioning of the fault wheel axle during the operation of the train through multidimensional modeling analysis.
5. The on-line train fault detection method as claimed in claim 4, wherein in the step of preprocessing the three types of data, noise interference generated when the fault axle operates is removed and filtered by wavelet denoising.
CN202010786738.0A 2020-08-07 2020-08-07 Train fault online detection system and method Active CN112033674B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010786738.0A CN112033674B (en) 2020-08-07 2020-08-07 Train fault online detection system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010786738.0A CN112033674B (en) 2020-08-07 2020-08-07 Train fault online detection system and method

Publications (2)

Publication Number Publication Date
CN112033674A true CN112033674A (en) 2020-12-04
CN112033674B CN112033674B (en) 2022-03-15

Family

ID=73582656

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010786738.0A Active CN112033674B (en) 2020-08-07 2020-08-07 Train fault online detection system and method

Country Status (1)

Country Link
CN (1) CN112033674B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1510429A1 (en) * 1966-01-21 1971-01-21 Schlumberger Cie N Rotary funnel arrangement for winding fiber ribbons into cross-wound bobbins
US20130110414A1 (en) * 2011-11-02 2013-05-02 Vestas Wind Systems A/S Methods and systems for detecting sensor fault modes
CN103175849A (en) * 2013-04-17 2013-06-26 黑龙江大学 Optical fiber on-line vehicle bearing fault detection device
CN103332207A (en) * 2013-06-11 2013-10-02 大连理工大学 Method and device for on-line acquisition of steel rail temperature, strain and acceleration data
CN106323442A (en) * 2016-08-18 2017-01-11 南京发艾博光电科技有限公司 Railway health monitoring method based on distributed optical fiber vibration sensing system
CN106347416A (en) * 2016-10-24 2017-01-25 南京派光信息技术有限公司 Distributed optical fiber-based train compartment separation real-time early warning system and method
CN209296054U (en) * 2019-01-15 2019-08-23 广东聚源管业实业有限公司 A kind of distributed fiber grating detection pipeline and system
CN110281984A (en) * 2019-02-03 2019-09-27 中铁二院工程集团有限责任公司 High-speed maglev train positioning system and localization method based on optical frequency domain reflection technology
CN111071300A (en) * 2020-02-12 2020-04-28 太原理工大学 High-speed train rail transit fault safety monitoring and early warning system and signal processing method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1510429A1 (en) * 1966-01-21 1971-01-21 Schlumberger Cie N Rotary funnel arrangement for winding fiber ribbons into cross-wound bobbins
US20130110414A1 (en) * 2011-11-02 2013-05-02 Vestas Wind Systems A/S Methods and systems for detecting sensor fault modes
CN103175849A (en) * 2013-04-17 2013-06-26 黑龙江大学 Optical fiber on-line vehicle bearing fault detection device
CN103332207A (en) * 2013-06-11 2013-10-02 大连理工大学 Method and device for on-line acquisition of steel rail temperature, strain and acceleration data
CN106323442A (en) * 2016-08-18 2017-01-11 南京发艾博光电科技有限公司 Railway health monitoring method based on distributed optical fiber vibration sensing system
CN106347416A (en) * 2016-10-24 2017-01-25 南京派光信息技术有限公司 Distributed optical fiber-based train compartment separation real-time early warning system and method
CN209296054U (en) * 2019-01-15 2019-08-23 广东聚源管业实业有限公司 A kind of distributed fiber grating detection pipeline and system
CN110281984A (en) * 2019-02-03 2019-09-27 中铁二院工程集团有限责任公司 High-speed maglev train positioning system and localization method based on optical frequency domain reflection technology
CN111071300A (en) * 2020-02-12 2020-04-28 太原理工大学 High-speed train rail transit fault safety monitoring and early warning system and signal processing method

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
XIA, LIXUE等: "Fault-Tolerant Training Enabled by On-Line Fault Detection for RRAM-Based Neural Computing Systems", 《IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS》 *
周松: "基于 FBG 的铁路安全监测传感网络的复用技术应用", 《信息通信》 *
邹捷 等: "一种基于相干光时域反射的分布式光纤振动传感系统研制", 《中国测试》 *
郭雅婕 等: "分布式光纤传感技术在接触网附加导线的应用", 《电气化铁道》 *

Also Published As

Publication number Publication date
CN112033674B (en) 2022-03-15

Similar Documents

Publication Publication Date Title
CN111071300B (en) High-speed train rail transit fault safety monitoring and early warning system and signal processing method
CN106052842A (en) Distributed fiber vibration sensing system capable of eliminating declining noises and demodulation method of system
CN104467984B (en) A kind of distribution type fiber-optic sound wave communication method and device
CN104819741B (en) A kind of relevant Brillouin optical time domain analysis sensor-based system based on single sideband modulation detection light
CN111147133B (en) Real-time monitoring system and method for traffic flow based on phi-OTDR
CN103115633B (en) Utilize phase generated carrier to reduce and interfere path loose (instead) to penetrate the method for light interference
CN104296783A (en) Sensor detecting method and device for enhanced coherent optical time domain reflection
CN103983342A (en) Method for determining shaking position of sensing optical fiber and optical fiber sensing system
CN112833929A (en) Disturbance monitoring system of heterodyne phi-OTDR technology based on local optical frequency shift
CN205120239U (en) Vibration detection device based on optical frequency domain reflectometer
CN106482822A (en) A kind of phase sensitive optical time domain reflection system of the detection that is concerned with based on double homologous heterodyne
CN112033674B (en) Train fault online detection system and method
JPH0627861B2 (en) Initial setting method and device for seismic data collection device
CN103472485B (en) Array frequency domain electromagnetic detection system quality of data monitoring device and monitoring method
CN108592963A (en) A kind of suppressing method and its system of time division multiplexing optical fiber sensing system multiplicative noise
CN108489517A (en) Based on the digitally coded COTDR sensing devices of polarization state in pulse and method
CN201224417Y (en) Distribution type stress sensing train locating and real time trace system based on Raman amplification
CN107314823A (en) The Method for Phase Difference Measurement and device of interferometric optical fiber sensor
CN112532337B (en) Distributed high-precision optical fiber vibration invasion and online monitoring detector
CN115901043A (en) Power cable external force monitoring system and method based on distributed optical fiber sensing
CN207132906U (en) Optical fiber perimeter sensing positioning system
CN103292831B (en) The single-ended Brillouin optical time domain analysis sensor of fiber grating reflection filter structure
CN206496836U (en) A kind of phase sensitive optical time domain reflection system based on the relevant detection of double homologous heterodyne
CN205785493U (en) A kind of distributed optical fiber vibration sensing device
CN113390449A (en) Optical fiber sensing device

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