CN108600984B - Remote monitoring device and method for running state of locomotive bogie - Google Patents
Remote monitoring device and method for running state of locomotive bogie Download PDFInfo
- Publication number
- CN108600984B CN108600984B CN201810377804.1A CN201810377804A CN108600984B CN 108600984 B CN108600984 B CN 108600984B CN 201810377804 A CN201810377804 A CN 201810377804A CN 108600984 B CN108600984 B CN 108600984B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- data center
- locomotive bogie
- remote
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/42—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for mass transport vehicles, e.g. buses, trains or aircraft
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a device and a method for remotely monitoring the running state of a locomotive bogie, wherein a single chip microcomputer is electrically connected with a wireless module, the wireless module is in communication connection with a vehicle-mounted data center, the single chip microcomputer transmits data collected by a data acquisition module to the vehicle-mounted data center through a data wireless module, and the vehicle-mounted data center is in communication connection with a remote data center. The method comprises the steps of data acquisition, vehicle-mounted data center establishment, remote data center establishment, sensitive feature extraction, model training and remote monitoring, so that the monitoring of the running state of the locomotive bogie is completed remotely. The method comprises the steps that a remote monitoring method is adopted, and information data of running characteristics of a locomotive bogie are obtained through a plurality of groups of sensors; the method is combined with a remote data center, the remote monitoring of the running state of the locomotive bogie is realized by utilizing a neural network model mode identification method, the running state of key parts of the locomotive bogie is remotely monitored by utilizing the neural network model mode identification method, the running safety of the whole locomotive bogie is further evaluated in time, and the method has very important significance in providing necessary theoretical guidance for ensuring the safe and reliable running and maintenance of the locomotive.
Description
Technical Field
The invention relates to the field of remote monitoring systems in railway industry, in particular to a device and a method for remotely monitoring the running state of a locomotive bogie.
Background
The bogie is an important mechanism for inter-city rail trains. Because the existing bogie is welded by adopting gas metal arc welding, the welding line energy is large, the welding line is dense, the number of welding lines is large, and in addition, a large amount of tooling and pre-compression treatment are required to ensure the dimensional precision. Therefore, the bogie has large residual stress, and even part of the part exceeds the yield limit of the bogie material. Residual stress not only affects structural accuracy and dimensional stability, but also reduces the rigidity, breaking strength, fatigue strength and stress corrosion resistance of the welded component. The various parameters of the bogie also directly determine the stability of the vehicle and the ride comfort of the vehicle.
The locomotive bogie plays roles of guiding, bearing and damping in operation, is also a final executor of traction and braking, and is a key part of a locomotive. The locomotive bears frequent random alternating dynamic loads during operation, so that the structural member of the locomotive bogie can be failed, the operation quality of the locomotive is further reduced, and even serious safety accidents such as derailment and turnover can be caused. Therefore, the design of a remote monitoring device for the running state of the locomotive bogie is particularly important.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a remote monitoring device and method for the operation state of a locomotive bogie, which can automatically acquire key data, wirelessly transmit data, and perform identification and monitoring by combining a neural network model.
In order to realize the technical purpose, the scheme of the invention is as follows: a remote monitoring device for the running state of a locomotive bogie comprises a data acquisition module, a single chip microcomputer, a wireless module, a vehicle-mounted data center and a remote data center;
the data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance sensor and a Hall speed sensor, wherein the acceleration sensor is used for acquiring running vibration data of the locomotive bogie;
the acceleration sensor, the acoustic emission sensor, the thermal resistance sensor and the Hall speed sensor are respectively and electrically connected with the single chip microcomputer, the single chip microcomputer is electrically connected with the wireless module, the wireless module is in communication connection with the vehicle-mounted data center, the single chip microcomputer transmits data collected by the data acquisition module to the vehicle-mounted data center through the data wireless module, and the vehicle-mounted data center is in communication connection with the remote data center.
Preferably, the vehicle-mounted data center is further electrically connected with a wireless router, the vehicle-mounted data center forms a basic vehicle-mounted server, the vehicle-mounted data center and the wireless router form a local area network, a TCP/IP communication protocol is adopted, the vehicle-mounted data center is connected with the mobile base station in a wireless mode and then is accessed to the Internet for data transmission, and data of the vehicle-mounted server is acquired through the router on the remote data center.
Preferably, the wireless module is a 2.4G wireless communication module.
Preferably, the remote data center is further connected to a remote monitoring platform, and the remote monitoring platform analyzes and processes the acquired data of the vehicle-mounted server, so that remote monitoring of the running state of the locomotive bogie is completed.
A remote monitoring method for the running state of a locomotive bogie comprises the following specific steps:
the method comprises the steps that firstly, data are obtained, a vehicle-mounted data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance temperature measurement sensor and a Hall speed sensor, wherein the acceleration sensor is used for obtaining an operation vibration signal of a locomotive bogie, the acoustic emission sensor is used for obtaining an operation noise signal of the locomotive bogie, the thermal resistance sensor is used for obtaining an operation temperature of the locomotive bogie, and the Hall speed sensor is used for obtaining the revolution number of the locomotive bogie;
acquiring corresponding data of the locomotive bogie in operation through a data acquisition module;
secondly, establishing a vehicle-mounted data center, acquiring the acquired locomotive bogie running data through a single chip microcomputer, transmitting the acquired data to the vehicle-mounted data center in real time by using a wireless transmission technology, and storing the acquired data in real time, so that the vehicle-mounted data are acquired and stored in real time, and forming a vehicle-mounted server on the basis of the vehicle-mounted data center;
thirdly, establishing a remote data center, connecting the vehicle-mounted server to a wireless router to form a local area network, connecting the wireless router with a mobile tower in a wireless network mode, and then accessing the Internet for data transmission, wherein a communication protocol adopts a TCP/IP communication protocol; in TCP communication, one end of the two communication ends is a vehicle-mounted server end, the other end of the two communication ends is a remote data center, and meanwhile, data of the vehicle-mounted server are obtained in the remote data through a router, so that the operation data of the locomotive bogie can be obtained remotely;
and fourthly, sensitive feature extraction, namely performing time-frequency analysis processing on the data acquired by the remote data center to extract the sensitive features of the operation of the locomotive bogie: the method comprises the steps of obtaining a sensitive characteristic quantity of the locomotive bogie in operation by using a time domain sensitive characteristic, a frequency domain sensitive characteristic or a time-frequency domain sensitive characteristic;
fifthly, model training, namely constructing an initial neural network model by taking the acquired sensitive characteristic quantity of the locomotive bogie in operation as the input of the neural network model and taking the operation state of the bogie as the output of the neural network model; using a part of acquired data of the sensitive characteristic quantity of the locomotive bogie in operation as a training sample, and training an initial neural network model by adopting a gradient descent iteration method until the initial neural network model is optimized, so as to obtain an optimized neural network model;
and sixthly, remotely monitoring, namely substituting the acquired residual data of the sensitive characteristic quantity of the locomotive bogie in the operation process as a test sample into the optimized neural network model, calculating the output of the optimized neural network model, wherein the state corresponding to the maximum output value is the identification state, so that the operation state of the locomotive bogie is remotely monitored.
Preferably, the sensitive feature in the fourth step may be one or more of a time-domain sensitive feature, a frequency-domain sensitive feature or a time-frequency-domain sensitive feature;
the extracted time-domain sensitive features may be: root mean square value, probability density function or kurtosis, etc.; the extracted frequency-domain sensitive features may be: center of gravity frequency, root mean square frequency, or frequency standard deviation, etc.; the extracted time-frequency domain sensitive features may be: and selecting one or more of wavelet packet energy, wavelet packet coefficients, ensemble empirical mode decomposition and singular spectrums as a sensitive feature extraction method to obtain the sensitive feature quantity required by the operation of the locomotive bogie as the input of a subsequent identification model.
Preferably, in the first step, the measured values { x ] of the vibration signal, the noise signal, the temperature, and the number of revolutions obtained by the data acquisition module1，x2，K，xk1, 2, m and m are the number of data acquired by each sensor, and the data are combined to form a signal data set (X) in the operation of the locomotive bogieiIn which X isi＝{x1，x2，K，xkN, n is the number of measurement values obtained by the sensor.
The method has the advantages that the remote monitoring method is adopted, the operation characteristic information data of the locomotive bogie is obtained through a plurality of groups of sensors, and the data are transmitted to the vehicle-mounted data center by utilizing a wireless transmission technology; the data of the vehicle-mounted server is remotely acquired by combining a TCP/IP communication protocol through a vehicle-mounted server and a wireless network transmission technology, and a remote data center for the operation of the locomotive bogie is established; the method is combined with a remote data center, the remote monitoring of the running state of the locomotive bogie is realized by utilizing a neural network model mode identification method, the running state of key parts of the locomotive bogie is remotely monitored by utilizing the neural network model mode identification method, the running safety of the whole locomotive bogie is further evaluated in time, and the method has very important significance in providing necessary theoretical guidance for ensuring the safe and reliable running and maintenance of the locomotive.
Drawings
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific embodiments.
As shown in fig. 1-2, a specific embodiment of the present invention is a remote monitoring device for an operating state of a locomotive bogie, comprising a data acquisition module, a single chip microcomputer, a wireless module, a vehicle-mounted data center, and a remote data center;
the data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance sensor and a Hall speed sensor, wherein the acceleration sensor is used for acquiring running vibration data of the locomotive bogie;
the acceleration sensor, the acoustic emission sensor, the thermal resistance sensor and the Hall speed sensor are respectively and electrically connected with the single chip microcomputer, the single chip microcomputer is electrically connected with the wireless module, the wireless module is in communication connection with the vehicle-mounted data center, the single chip microcomputer transmits data collected by the data acquisition module to the vehicle-mounted data center through the data wireless module, and the vehicle-mounted data center is in communication connection with the remote data center.
In order to realize the stable remote wireless transmission of data, the vehicle-mounted data center is also electrically connected with a wireless router, the vehicle-mounted data center forms a basic vehicle-mounted server, the vehicle-mounted data center and the wireless router form a local area network, a TCP/IP communication protocol is adopted, the vehicle-mounted data center is connected with a mobile base station in a wireless mode and then is accessed to an Internet network for data transmission, and the data of the vehicle-mounted server is acquired through the router on the remote data center. The wireless router and the mobile base station can adopt a 4G wireless router and a 4G mobile base station which are commonly used at present, can also adopt a 3G network, and can also adopt a 5G network in the future.
In order to facilitate the short-distance data transmission, the wireless module is a 2.4G wireless communication module. The data are transmitted to the vehicle-mounted data center by utilizing a wireless transmission technology, so that the problem that the data cannot be transmitted remotely in real time is solved
In order to realize real-time dynamic monitoring, the remote data center is also connected to a remote monitoring platform, and the remote monitoring platform analyzes and processes the acquired data of the vehicle-mounted server, so that the remote monitoring of the running state of the locomotive bogie is completed. The remote monitoring platform realizes remote monitoring of the running state of the locomotive bogie, remotely monitors the running state of key components of the locomotive bogie, and further timely evaluates the running safety of the whole locomotive bogie,
a remote monitoring method for the running state of a locomotive bogie comprises the following specific steps:
the method comprises the steps that firstly, data are obtained, a vehicle-mounted data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance temperature measurement sensor and a Hall speed sensor, wherein the acceleration sensor is used for obtaining an operation vibration signal of a locomotive bogie, the acoustic emission sensor is used for obtaining an operation noise signal of the locomotive bogie, the thermal resistance sensor is used for obtaining an operation temperature of the locomotive bogie, and the Hall speed sensor is used for obtaining the revolution number of the locomotive bogie;
acquiring corresponding data of the locomotive bogie in operation through a data acquisition module;
secondly, establishing a vehicle-mounted data center, acquiring the acquired locomotive bogie running data through a single chip microcomputer, transmitting the acquired data to the vehicle-mounted data center in real time by using a wireless transmission technology, and storing the acquired data in real time, so that the vehicle-mounted data are acquired and stored in real time, and forming a vehicle-mounted server on the basis of the vehicle-mounted data center;
thirdly, establishing a remote data center, connecting the vehicle-mounted server to a wireless router to form a local area network, connecting the wireless router with a mobile tower in a wireless network mode, and then accessing the Internet for data transmission, wherein a communication protocol adopts a TCP/IP communication protocol; in TCP communication, one end of the two communication ends is a vehicle-mounted server end, the other end of the two communication ends is a remote data center, and meanwhile, data of the vehicle-mounted server are obtained in the remote data through a router, so that the operation data of the locomotive bogie can be obtained remotely;
and fourthly, sensitive feature extraction, namely performing time-frequency analysis processing on the data acquired by the remote data center to extract the sensitive features of the operation of the locomotive bogie: the method comprises the steps of obtaining a sensitive characteristic quantity of the locomotive bogie in operation by using a time domain sensitive characteristic, a frequency domain sensitive characteristic or a time-frequency domain sensitive characteristic;
fifthly, model training, namely constructing an initial neural network model by taking the acquired sensitive characteristic quantity of the locomotive bogie in operation as the input of the neural network model and taking the operation state of the bogie as the output of the neural network model; using a part of acquired data of the sensitive characteristic quantity of the locomotive bogie in operation as a training sample, and training an initial neural network model by adopting a gradient descent iteration method until the initial neural network model is optimized, so as to obtain an optimized neural network model;
and sixthly, remotely monitoring, namely substituting the acquired residual data of the sensitive characteristic quantity of the locomotive bogie in the operation process as a test sample into the optimized neural network model, calculating the output of the optimized neural network model, wherein the state corresponding to the maximum output value is the identification state, so that the operation state of the locomotive bogie is remotely monitored.
For better division of the sensitive features, the sensitive features in the fourth step may be one or more of time-domain sensitive features, frequency-domain sensitive features or time-frequency-domain sensitive features;
the extracted time-domain sensitive features may be: root mean square value, probability density function or kurtosis, etc.; the extracted frequency-domain sensitive features may be: center of gravity frequency, root mean square frequency, or frequency standard deviation, etc.; the extracted time-frequency domain sensitive features may be: wavelet packet energy, wavelet packet coefficients, ensemble empirical mode decomposition, singular spectra, and the like. One or more of the sensitive characteristic extraction methods are selected as sensitive characteristic extraction methods, and the sensitive characteristic quantity required by the operation of the locomotive bogie is obtained and used as the input of a subsequent identification model.
For better data acquisition, measured values { x ] of vibration signal, noise signal, temperature, number of revolutions acquired by the data acquisition module in the first step1，x2，K，xk1, 2, m and m are the number of data acquired by each sensor, and the data are combined to form a signal data set (X) in the operation of the locomotive bogieiIn which X isi＝{x1，x2，K，xkN, n is the number of measurement values obtained by the sensor.
Model training and neural network models, for example, are as follows:
taking the acquired sensitive characteristic quantity in the operation of the locomotive bogie bearing as an input of a neural network model, preferably 10 characteristic quantities: root mean square value, frequency standard deviation and 8 wavelet packet decomposition energy characteristics, the running state of the bogie bearing is output as a neural network model, and 4 states are preferably selected: when the neural network model is normal, the inner ring is in fault, the outer ring is in fault, and the neural network model is not centered; and taking a part of the acquired data of the sensitive characteristic quantity of the locomotive bogie bearing in operation as a training sample, and training the initial neural network model by adopting a gradient descent iteration method until the initial neural network model is optimized, thereby obtaining the optimized neural network model.
In the initial neural network model in this embodiment, the input layer and the hidden layer use tangent S-type transfer functions, and the output layer uses linear transfer functions; hidden layer number is composed of
Determining, wherein: a is1Is the number of hidden layer neurons, a is the number of output layer neurons, b is the number of input layer neurons, α ∈ [1, 10 ]]Thus constituting an initial neural network model.
In this embodiment, it is preferable that the number a of input layer neurons is 10, the number b of output layer neurons is 4, and the number a of hidden layer neurons is1The number is 13.
The remote monitoring device adopts a plurality of groups of sensors to acquire the running characteristic information data of the locomotive bogie, and transmits the data to the vehicle-mounted data center by utilizing a wireless transmission technology, so that the problem that the data cannot be transmitted remotely in real time is solved; the data of the vehicle-mounted server is remotely acquired by combining a TCP/IP communication protocol through a vehicle-mounted server and a wireless network transmission technology, and a remote data center for the operation of the locomotive bogie is established; the remote monitoring of the running state of the locomotive bogie is finally realized by combining a remote data center and analyzing and processing signals, so that the running safety of the whole locomotive bogie is evaluated in time, and the important significance is provided for providing necessary theoretical guidance for ensuring the safe and reliable running and maintenance of the locomotive.
The remote monitoring method obtains and obtains locomotive bogie running characteristic information data through a plurality of groups of sensors, and transmits the data to a vehicle-mounted data center by utilizing a wireless transmission technology; the data of the vehicle-mounted server is remotely acquired by combining a TCP/IP communication protocol through a vehicle-mounted server and a wireless network transmission technology, and a remote data center for the operation of the locomotive bogie is established; the method is combined with a remote data center, the remote monitoring of the running state of the locomotive bogie is realized by utilizing a neural network model mode identification method, the running state of key parts of the locomotive bogie is remotely monitored by utilizing the neural network model mode identification method, the running safety of the whole locomotive bogie is further evaluated in time, and the method has very important significance in providing necessary theoretical guidance for ensuring the safe and reliable running and maintenance of the locomotive.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and any minor modifications, equivalent replacements and improvements made to the above embodiment according to the technical spirit of the present invention should be included in the protection scope of the technical solution of the present invention.
Claims (2)
1. A remote monitoring device and method for the running state of a locomotive bogie are characterized in that: the remote monitoring system comprises a data acquisition module, a single chip microcomputer, a wireless module, a vehicle-mounted data center, a remote data center and a remote monitoring method for the running state of a locomotive bogie;
the data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance sensor and a Hall speed sensor, wherein the acceleration sensor is used for acquiring running vibration data of the locomotive bogie;
the acceleration sensor, the acoustic emission sensor, the thermal resistance sensor and the Hall speed sensor are respectively and electrically connected with the single chip microcomputer, the single chip microcomputer is electrically connected with the wireless module, the wireless module is in communication connection with the vehicle-mounted data center, the single chip microcomputer transmits data collected by the data acquisition module to the vehicle-mounted data center through the data wireless module, and the vehicle-mounted data center is in communication connection with the remote data center;
the vehicle-mounted data center is also electrically connected with a wireless router, the vehicle-mounted data center forms a basic vehicle-mounted server, the vehicle-mounted data center and the wireless router form a local area network, a TCP/IP communication protocol is adopted, the vehicle-mounted data center is connected with the mobile base station in a wireless mode and then is accessed to an Internet network for data transmission, and the data of the vehicle-mounted server is obtained on the remote data center through the router;
the locomotive bogie running state remote monitoring device is characterized in that: the wireless module is a 2.4G wireless communication module;
the locomotive bogie running state remote monitoring device is characterized in that: the remote data center is further connected to a remote monitoring platform, and the remote monitoring platform analyzes and processes the acquired data of the vehicle-mounted server, so that remote monitoring of the running state of the locomotive bogie is completed.
2. A remote monitoring device and method for the running state of a locomotive bogie are also characterized in that: the method comprises the following specific steps:
the method comprises the steps that firstly, data are obtained, a vehicle-mounted data acquisition module comprises an acceleration sensor, an acoustic emission sensor, a thermal resistance temperature measurement sensor and a Hall speed sensor, wherein the acceleration sensor is used for obtaining an operation vibration signal of a locomotive bogie, the acoustic emission sensor is used for obtaining an operation noise signal of the locomotive bogie, the thermal resistance sensor is used for obtaining an operation temperature of the locomotive bogie, and the Hall speed sensor is used for obtaining the revolution number of the locomotive bogie;
acquiring corresponding data of the locomotive bogie in operation through a data acquisition module;
secondly, establishing a vehicle-mounted data center, acquiring the acquired locomotive bogie running data through a single chip microcomputer, transmitting the acquired data to the vehicle-mounted data center in real time by using a wireless transmission technology, and storing the acquired data in real time, so that the vehicle-mounted data are acquired and stored in real time, and forming a vehicle-mounted server on the basis of the vehicle-mounted data center;
thirdly, establishing a remote data center, connecting the vehicle-mounted server to a wireless router to form a local area network, connecting the wireless router with a mobile tower in a wireless network mode, and then accessing the Internet for data transmission, wherein a communication protocol adopts a TCP/IP communication protocol; in TCP communication, one end of the two communication ends is a vehicle-mounted server end, the other end of the two communication ends is a remote data center, and meanwhile, data of the vehicle-mounted server are obtained in the remote data through a router, so that the operation data of the locomotive bogie can be obtained remotely;
and fourthly, sensitive feature extraction, namely performing time-frequency analysis processing on the data acquired by the remote data center to extract the sensitive features of the operation of the locomotive bogie: the method comprises the steps of obtaining a sensitive characteristic quantity of the locomotive bogie in operation by using a time domain sensitive characteristic, a frequency domain sensitive characteristic or a time-frequency domain sensitive characteristic;
fifthly, model training, namely constructing an initial neural network model by taking the acquired sensitive characteristic quantity of the locomotive bogie in operation as the input of the neural network model and taking the operation state of the bogie as the output of the neural network model; using a part of acquired data of the sensitive characteristic quantity of the locomotive bogie in operation as a training sample, and training an initial neural network model by adopting a gradient descent iteration method until the initial neural network model is optimized, so as to obtain an optimized neural network model;
and sixthly, remotely monitoring, namely substituting the acquired residual data of the sensitive characteristic quantity of the locomotive bogie in the operation process as a test sample into the optimized neural network model, calculating the output of the optimized neural network model, wherein the state corresponding to the maximum output value is the identification state, so that the operation state of the locomotive bogie is remotely monitored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810377804.1A CN108600984B (en) | 2018-04-18 | 2018-04-18 | Remote monitoring device and method for running state of locomotive bogie |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810377804.1A CN108600984B (en) | 2018-04-18 | 2018-04-18 | Remote monitoring device and method for running state of locomotive bogie |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108600984A CN108600984A (en) | 2018-09-28 |
| CN108600984B true CN108600984B (en) | 2020-12-22 |
Family
ID=63609150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810377804.1A Active CN108600984B (en) | 2018-04-18 | 2018-04-18 | Remote monitoring device and method for running state of locomotive bogie |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108600984B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109556864A (en) * | 2018-12-17 | 2019-04-02 | 衢州职业技术学院 | A kind of motor bearings defect detecting system |
| CN111516711B (en) * | 2019-02-02 | 2021-08-20 | 株洲中车时代电气股份有限公司 | Safety monitoring method and device for running gear of motor train unit |
| CN110411766A (en) * | 2019-07-30 | 2019-11-05 | 中国神华能源股份有限公司神朔铁路分公司 | The snakelike unstability detection method of train bogie, device, system and storage medium |
| CN113159179B (en) * | 2021-04-22 | 2023-04-18 | 中车株洲电力机车有限公司 | Subway and subway bogie running state identification method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102053016A (en) * | 2010-11-08 | 2011-05-11 | 江苏大学 | System for monitoring vibration of rotating machinery rolling bearing in wireless mode |
| CN102497393A (en) * | 2011-11-28 | 2012-06-13 | 浙江网新技术有限公司 | High-speed train intelligent system and communication method thereof |
| CN104571079A (en) * | 2014-11-25 | 2015-04-29 | 东华大学 | Wireless long-distance fault diagnosis system based on multiple-sensor information fusion |
| CN104807639A (en) * | 2015-04-23 | 2015-07-29 | 广西大学 | Fault diagnosis method and device for rolling bearing of running gear of locomotive |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7549327B2 (en) * | 2001-02-16 | 2009-06-23 | Automotive Technologies International, Inc. | Tire-mounted energy generator and monitor |
-
2018
- 2018-04-18 CN CN201810377804.1A patent/CN108600984B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102053016A (en) * | 2010-11-08 | 2011-05-11 | 江苏大学 | System for monitoring vibration of rotating machinery rolling bearing in wireless mode |
| CN102497393A (en) * | 2011-11-28 | 2012-06-13 | 浙江网新技术有限公司 | High-speed train intelligent system and communication method thereof |
| CN104571079A (en) * | 2014-11-25 | 2015-04-29 | 东华大学 | Wireless long-distance fault diagnosis system based on multiple-sensor information fusion |
| CN104807639A (en) * | 2015-04-23 | 2015-07-29 | 广西大学 | Fault diagnosis method and device for rolling bearing of running gear of locomotive |
Non-Patent Citations (1)
| Title |
|---|
| 基于广义BP 神经网络的切削颤振识别研究;谢锋云，江炜文，陈红年，谢三毛，李雪萌，刘博文;《振动与冲击》;20180315;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108600984A (en) | 2018-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108600984B (en) | Remote monitoring device and method for running state of locomotive bogie | |
| KR101864860B1 (en) | Diagnosis method of automobile using Deep Learning | |
| CN103852271B (en) | High-speed train running gear fault diagnosis and remote monitoring system based on Internet of Things | |
| CN107380202B (en) | Based on NB-IoT net rail vehicle Spindle Status monitoring method and system | |
| Hodge et al. | Wireless sensor networks for condition monitoring in the railway industry: A survey | |
| US7705743B2 (en) | Self-assembling wireless network, vehicle communications system, railroad wheel and bearing monitoring system and methods therefor | |
| CN106441893B (en) | Train rolling bearing fault vibrates differentiating method with impurity | |
| CN103592122B (en) | Fault diagnosis device and method for urban rail transit train running gear | |
| CN105527104B (en) | A kind of bearing running abnormal sound detecting system | |
| CN104833534A (en) | Train running fault diagnosis device based on multi-source information fusion, and method | |
| CN105923014B (en) | A kind of track transition Amplitude Estimation method based on evidential reasoning rule | |
| CN107380201B (en) | Based on wide area network and local area network axle health status monitoring method and monitoring system | |
| US11697442B2 (en) | Monitoring an axle of a railway vehicle | |
| CN206255021U (en) | A kind of lorry intelligent online monitoring device | |
| CN206132406U (en) | High -speed rail train health condition monitoring devices | |
| CN104458252A (en) | Method for monitoring running state of high-speed train gear box | |
| CN209505760U (en) | A kind of railway freight-car operating status wireless monitor system | |
| CN107941533A (en) | EMU unstability detecting system and method based on Industrial Ethernet | |
| Cong et al. | Subway rail transit monitoring by built-in sensor platform of smartphone | |
| CN105988460B (en) | Vehicle runway dynamic testing method, device and system | |
| CN109238713A (en) | A kind of device for railway truck bearing Incipient Fault Diagnosis | |
| CN105424387B (en) | Tooth sector real time remote intelligent monitor system | |
| CN116767307A (en) | Dynamic irregularity measuring system for rail transit and wheel track relation evaluation method | |
| CN207528466U (en) | EMU unstability detecting system based on Industrial Ethernet | |
| CN108981818B (en) | Online detection device and method for high-speed wheel set |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Yi Inventor after: Xie Fengyun Inventor after: Xiao Qian Inventor after: Zhu Haiyan Inventor after: Zhou Shengtong Inventor after: Shen Longjiang Inventor after: Xie Sanmao Inventor after: Liu Kun Inventor after: Feng Chunyu Inventor before: Liu Yi Inventor before: Xie Fengyun Inventor before: Shen Longjiang Inventor before: Xie Sanmao Inventor before: Liu Kun Inventor before: Feng Chunyu |