CN112215411B

CN112215411B - Switch operation and maintenance quality prediction analysis system

Info

Publication number: CN112215411B
Application number: CN202011026478.3A
Authority: CN
Inventors: 王立军; 顾重清
Original assignee: Hangzhou Yifan Technology Co ltd
Current assignee: Hangzhou Yifan Technology Co ltd
Priority date: 2020-09-25
Filing date: 2020-09-25
Publication date: 2021-07-27
Anticipated expiration: 2040-09-25
Also published as: CN112215411A

Abstract

The application discloses switch operation and maintenance quality prediction analysis system includes: the turnout monitoring system comprises a plurality of turnout monitoring subsystems, a server and a plurality of monitoring terminals. The turnout monitoring subsystem is used for monitoring quality data of turnouts, and the turnout monitoring subsystem is arranged at each turnout and used for monitoring data of each turnout. The server is used for storing and processing the monitoring data of the turnout monitoring subsystem. The monitoring terminal is used for being used by maintenance personnel to obtain data from the server. The application has the advantages that: the switch operation and maintenance quality prediction analysis system is diversified and more intelligent in monitoring data.

Description

Switch operation and maintenance quality prediction analysis system

Technical Field

The application relates to a switch operation and maintenance quality prediction analysis system.

Background

Switches are necessary devices when trains turn into or cross tracks and are important components of railways. The switch rail is positioned at the bent rail part of the turnout. The train needs to turn when passing through the switch rail, the train can bring huge transverse impact force to the steel rail in the process, various different damages can occur to the switch rail in the process, such as deformation, abrasion, cracks, corrosion and even breakage, and a plurality of train derailment accidents are caused, and the safe operation of the train is seriously influenced. Therefore, the state of the switch blade needs to be continuously detected, maintained and maintained to ensure the safety performance of the switch blade. At present, methods for detecting stock rails in steel rails include a construction method, an ultrasonic flaw detection method and a steel rail flaw detection vehicle, and although the problem of detecting switch rails can be solved, the methods cannot carry out real-time operation on the operation states of the switch rails.

In the related art, although the method of electrode detection can realize online early warning and reminding of damage, it cannot prevent the damage in advance because the alarm threshold is given according to general experience, the actual working condition of the turnout is not always combined, and after the alarm occurs, unless very obvious damage is confirmed by a human or video online and then repaired or replaced by a maintenance person, when the damage is not obvious but possibly develops into danger, the method often depends on the experience and historical data of a supervision person.

On the other hand, because current switch damage monitoring is often directed at switch itself, aim at in time maintaining and changing the switch, but do not explore the vehicle reason that causes the switch damage, in case the vehicle itself has the trouble that causes the switch damage, then can't in time acquire data and maintain.

On the other hand, due to the fact that the track of the turnout needs to be maintained and replaced, the monitoring equipment needs to be re-arranged, the existing scheme usually adopts a manual input mode to conduct networking and arrangement, the workload is undoubtedly increased, and meanwhile, arrangement data are prone to being mistakenly and mistakenly arranged due to human reasons.

Disclosure of Invention

A switch operation and maintenance quality prediction analysis system, comprising: the turnout monitoring subsystems are used for monitoring quality data of turnouts; the server is used for storing and processing the monitoring data of the turnout monitoring subsystem; the monitoring terminals are used for being used by maintenance personnel in a work section to acquire data from the server; wherein, the switch monitoring subsystem includes: the damage monitoring unit is used for being installed on the track to detect the quality parameters of the track; the damage monitoring extension is used for carrying out signal interaction with the rail damage monitoring unit to acquire the quality data of the rail; the damage monitoring unit includes: the electrode is used for being arranged on the track to form an equivalent circuit required by monitoring the track; the first type UWB tag module is used for sending or receiving UWB signals; the RFID tag module is used for storing the identification data of the damage monitoring unit; the IMU detection module is used for detecting the inertial data of the damage monitoring unit; the damage monitoring extension includes: an electrical detection module for electrical connection to the electrodes to obtain electrical data relating to track quality; the UWB base station module is used for detecting the position of the first type UWB tag module; the RFID reading and writing module is used for reading or writing the identification data in the RFID label module; the extension processor is used for processing the data of the electrical detection module, the UWB base station module and the RFID read-write module; the extension processor is used for matching the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertia data of the IMU detection module and transmitting the matching data to the server.

Further, the switch operation and maintenance quality prediction analysis system comprises: and the vehicle detection subsystem is arranged on vehicles running on the railway and used for interacting data or signals with the damage monitoring extension set.

Further, the damage monitoring extension also comprises: the vehicle detection module is used for detecting the speed of a vehicle passing through the turnout at present; the vehicle identification module is used for acquiring identification information of a vehicle passing through a turnout at present; and the vehicle interaction module is used for interacting data with the vehicle detection subsystem which passes through the turnout at present.

Further, the vehicle detection module, the vehicle identification module and the vehicle interaction module are electrically connected with the extension processor.

Further, the vehicle detection subsystem includes: and the second type UWB tag module is used for forming signal interaction with the UWB base station module so as to enable the extension processor to acquire the position data of the second type UWB tag module.

Further, the second type UWB tag module is plural and is respectively installed to different positions of the vehicle.

Further, the server includes: and the neural network system takes the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag, the inertial data of the IMU detection module and the turnout maintenance data as data for training an artificial neural network in the neural network system, wherein one or a combination of more of the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertial data of the IMU detection module is used as input layer data, and the turnout maintenance data is used as output layer data.

Further, the switch maintenance data includes service life, damage condition or alarm level.

Further, the server predicts the turnout maintenance data according to one or more of the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertial data of the IMU detection module by using the neural network system.

Further, the server is divided into a data server and an application server, and the neural network system is arranged in the application server.

The application has the advantages that: the switch operation and maintenance quality prediction analysis system is diversified and more intelligent in monitoring data.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:

FIG. 1 is a block diagram of a switch operation and maintenance quality prediction analysis system according to an embodiment of the present application;

fig. 2 is a schematic block diagram of a structure of a damage monitoring unit in a switch operation and maintenance quality prediction analysis system according to an embodiment of the present application;

fig. 3 to fig. 8 are schematic diagrams of an operation interface in the switch operation and maintenance quality prediction analysis system according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but 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 application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.

Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.

Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

As shown in fig. 1, the switch operation and maintenance quality prediction analysis system of the present application includes: the turnout monitoring system comprises a plurality of turnout monitoring subsystems, a server and a plurality of monitoring terminals.

The turnout monitoring subsystem is used for monitoring quality data of turnouts, and the turnout monitoring subsystem is arranged at each turnout and used for monitoring data of each turnout. The server is used for storing and processing the monitoring data of the turnout monitoring subsystem. The monitoring terminal is used for being used by maintenance personnel of a workshop section to acquire data from the server.

As a specific solution, the monitoring terminal may be formed by a dedicated device, or may be implemented by using a smart phone or a tablet computer.

As a specific solution, the server may adopt a cloud server.

As a specific scheme, the switch monitoring subsystem comprises: the damage monitoring unit and the damage monitoring extension, a damage monitoring extension can correspond a plurality of damage monitoring unit, and damage monitoring unit can be constructed or be connected with bolt structure or centre gripping mounting structure to make damage monitoring unit can combine to the track department of switch, for example combine to switch tongue, point rail and the wing rail department of switch. Therefore, the damage monitoring unit may be classified into a point rail damage monitoring unit, and a wing rail damage monitoring unit.

As a specific scheme, the damage monitoring unit is used for being mounted on a track to detect the quality parameters of the track; and the damage monitoring extension is used for carrying out signal interaction with the track damage monitoring unit to acquire the quality data of the track. Track quality data as referred to herein includes, but is not limited to, damage data for the track.

Specifically, the damage monitoring unit includes: the device comprises an electrode, a first UWB tag module, an RFID tag module and an IMU detection unit. Preferably, the damage monitoring unit may further comprise a means for detecting temperature or other parameters.

As a preferable scheme, the damage monitoring unit comprises two parts, wherein one part of the damage monitoring unit forms an electrode or a thread structure and the like for realizing physical contact and installing a disposable structure part, the disposable structure part can be discarded or replaced when the track is replaced, and a reusable multiplexing structure part formed by packaging the first type UWB tag module, the RFID tag module and the IMU detection unit can be replaced on different disposable structure parts by adopting a physical interface and an electrical interface so as to form the damage monitoring unit for replacement, in other words, the damage monitoring unit can be formed by two parts of disposable use and multiple use, so that the structural strength after replacement is not influenced on the basis of saving cost.

The electrode is used for being arranged on the track to form an equivalent circuit required by monitoring the track; the state of the steel rail is monitored on line by adopting an electric measurement principle, when the switch rail (or the point rail and the wing rail) is damaged, cracks can be generated in the switch rail, or the volume and the quality of the switch rail are changed due to surface damage. Whether a crack or a loss of volume (surface damage) of the point rail, changes in impedance, capacitive reactance, and inductive reactance occur electrically. Monitoring electrodes are arranged in the conventional screw holes of the switch rail, the point rail and the wing rail, and the monitoring and collecting extension set sends out proper frequency to find out and measure the impedance sensitive change generated by the equivalent circuit of the steel rail section when the crack is damaged. The damage can be qualitatively judged by comparing the change of the impedance before and after the damage, and the damage degree can be quantitatively reported.

The first type of UWB tag module is used for sending or receiving UWB signals; the first type of UWB tag mainly has the function of positioning the position data of the damage monitoring unit, and the RFID tag module is used for storing the identification data of the damage monitoring unit, namely storing the RFID tag used for identifying the identification data of the damage monitoring unit; the IMU detection module is used for detecting inertial data of the damage monitoring unit, mainly used for detecting vibration conditions of the damage monitoring unit, mainly used for detecting that a track moves in the changing of turnout and monitoring impact and vibration of the track when a railway vehicle passes by.

The damage monitoring extension includes: the system comprises an electrical detection module, a UWB base station module and an RFID read-write module, wherein the electrical detection module is electrically connected to an electrode to acquire electrical data related to the track quality; the UWB base station module is used for detecting the position of the first type of UWB tag module; the RFID read-write module is used for reading or writing the identification data in the RFID tag module; and the extension processor is used for processing data of the electrical detection module, the UWB base station module and the RFID read-write module.

The extension processor is used for matching the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertia data of the IMU detection module and transmitting the data to the server.

Specifically, extension treater matches and encapsulates each item data of every damage monitoring unit, then transmits to the server, UWB location data and RFID identification data mainly used discernment and distinguish damage monitoring unit, and the impaired condition of electricity data mainly used analysis track, and the data that IMU detection module acquireed are used for reflecting the condition that the track received the impact, compare through inertial data and electricity data and further get rid of electricity and detect the noise that produces, improve the accuracy.

As a concrete scheme, when maintenance personnel replace and lay, the recording and data resetting of the whole track replacement process can be realized through data acquisition of the handheld RFID reading device and the damage monitoring extension, when the maintenance or replacement is carried out, the damage monitoring extension is in a maintenance recording state, and when the damage monitoring extension detects that the damage monitoring unit generates large displacement and detects that the damage monitoring unit resets, the replacement is determined on site through schemes such as online video and the like.

As a technical direction of the technical solution of the present application, a railroad switch quality monitoring analysis system includes: a vehicle detection subsystem. The vehicle detection subsystem is arranged on vehicles running on the railway and used for interacting data or signals with the damage monitoring extension set.

Specifically, the rail vehicle passes through the vehicle detection subsystem, and data when the vehicle passes through a turnout is bound with vehicle operation data and fed back to the server.

As a specific scheme, the damage monitoring extension further comprises: the vehicle identification system comprises a vehicle detection module, a vehicle identification module and a vehicle interaction module. The vehicle detection module is used for detecting the speed of a vehicle passing through a turnout at present; the vehicle identification module is used for acquiring identification information of a vehicle passing through a turnout at present; the vehicle interaction module is used for interacting data with a vehicle detection subsystem which passes through a turnout at present.

The vehicle detection module can be composed of modules such as a velocimeter and the like, and the modules detect the speed of the vehicle. The vehicle identification module and the vehicle interaction module can be formed by a device or a chip with a wireless communication function, and when the vehicle enters a set range, the vehicle identification module and the vehicle interaction module perform data interaction with the vehicle so as to achieve the purposes of vehicle identification and data exchange at the same time.

The server can acquire the vehicle as the data set of data collection like this, then compares electricity data and inertial data of other vehicles of the same motorcycle type when passing through same switch to judge whether there is comparatively unusual vehicle to cause the loss to the switch easily, avoid dangerous emergence probability, reduce simultaneously and maintain the change track loss.

In order to more accurately acquire the influence of the specific position of the vehicle on the turnout, the vehicle detection subsystem comprises: a second type of UWB tag module. The second type UWB tag module is used for forming signal interaction with the UWB base station module so that the extension processor can acquire the position data of the second type UWB tag module.

The vehicle detection subsystem further includes: and the vehicle processor is used for processing the data of the second type UWB tag module, and has a wireless communication function, can form data interaction with other systems of the vehicle, and can upload the data to the server through remote wireless communication.

As a preferred solution, the server may be a cloud server, and as an extension, the server may include an application server and a data server according to functions. Which are used for implementing application functions and data storage, respectively.

Specifically, every carriage at the vehicle is equipped with second type UWB tag module, and as more accurate scheme, second type UWB tag module is a plurality of and installs respectively to the different positions of vehicle, for example can set up second type UWB tag module corresponding every wheel position to when the vehicle passes through the switch region, obtain the data that corresponds every carriage position, thereby the data that just so detect through the position and cut the data of gathering according to the vehicle corresponds the position through the switch time quantum, thereby learn the track quality data that corresponds the carriage.

Specifically, when a vehicle enters a preset range of a distance turnout, a damage monitoring extension starts a vehicle detection module, a vehicle identification module and a vehicle interaction module; and begin to carry out UWB signal interaction to when the vehicle passes through the switch, obtain the location data, the speed of vehicle speed module measurement vehicle, vehicle interaction module sends location data and vehicle speed data to the vehicle, and the vehicle uploads to the server again, then through all corresponding the time when examining with data, thereby will damage data and vehicle data and correspond.

As an extension, the server comprises: a neural network system. The neural network system can acquire data according to the system to perform deep learning, and a judgment result of maintenance personnel according to manual experience corresponds to the neural network system.

As an alternative, the neural network system is a convolutional neural network that takes the detected monitoring data as input and the point in time of the loss as output.

As a specific scheme, the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag, the inertial data of the IMU detection module, and the switch maintenance data are used as data for training an artificial neural network in a neural network system, wherein one or a combination of several of the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag, and the inertial data of the IMU detection module is used as input layer data, and the switch maintenance data is used as output layer data. Switch maintenance data includes service life, damage condition or alarm level.

When a system is configured, a data server is arranged, the data server is provided with a neural network, before the data server is started, a large amount of data input and results are firstly trained to form a training set, then data which are not input are adopted for verification to form a verification set, the verification result is evaluated, the neural network is put into use after the verification result meets the requirement of accuracy, and when the verification result accurately predicts the fault release time point, the group of detection data is collected into the training set or the verification set so as to be retrained after some parameters of the neural network are adjusted.

As an alternative, two different servers may be provided to arrange two neural networks, one for daily monitoring and the other as a backup, the backup neural network being turned on to work when the daily monitored neural network is adjusted. In daily work, the standby neural network can also share the daily monitored neural network data for training and outputting, and when the results given by the two neural networks are different greatly, manual judgment intervention is needed.

As a further scheme, the information and data of the vehicle can also be input into the neural network as learning data, after the neural network learns and establishes the data model, the data is input into the neural network of the server, reference data can be obtained, the occurrence of the damage risk is predicted in advance, and then after manual confirmation, the data neural network model is corrected again, so that the accuracy of the neural network evaluation is improved.

Therefore, a large number of experience of maintenance personnel is solidified in the server, so that the risk condition is predicted more accurately and in advance, and the risk is prevented from occurring due to timely maintenance or replacement.

Referring to fig. 3 to 8, as an application layer of the present application, fig. 3 to 8 illustrate an operation interface according to an embodiment of the present application.

Specifically, as shown in fig. 3, when the system enters a normal monitoring state, the monitoring panel stays in the line segment monitoring interface, and when an alarm occurs, an alarm prompt appears at the position of the corresponding site and the upper right corner, and a voice alarm is sent.

As shown in FIG. 4, the alarm device is checked, the corresponding icons on the monitoring graph are clicked, the station graph is entered in sequence, and the switch graph is used for checking the alarm position.

As shown in fig. 5, clicking the alarm steel rail section or the upper right corner, jumping to unconfirmed alarm information to observe the damage index of the damage alarm, wherein 0-100 indicates the damage degree, and when the damage index is larger than 100, the steel rail is completely broken.

As shown in fig. 6, if the site survey finds that the steel rail can still be used normally, the alarm is confirmed, and a damage tracking tag is filled in the alarm confirmation information, so that the historical damage of the steel rail can be tracked later.

And as shown in fig. 7, continuing to enter a normal monitoring state, and checking historical damage tracking information of the steel rail through a historical alarm function when an alarm occurs.

As shown in FIG. 8, if the track needs to be changed, the alarm is confirmed in the system after the track change is finished.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A switch operation and maintenance quality prediction analysis system is characterized in that:

the switch operation and maintenance quality prediction analysis system comprises:

the turnout monitoring subsystems are used for monitoring quality data of turnouts;

the server is used for storing and processing the monitoring data of the turnout monitoring subsystem;

the monitoring terminals are used for being used by maintenance personnel in a work section to acquire data from the server;

wherein, the switch monitoring subsystem includes:

the damage monitoring unit is used for being installed on the track to detect the quality parameters of the track;

the damage monitoring extension is used for carrying out signal interaction with the rail damage monitoring unit to acquire the quality data of the rail;

the damage monitoring unit includes:

the electrode is used for being arranged on the track to form an equivalent circuit required by monitoring the track;

the first type UWB tag module is used for sending or receiving UWB signals;

the RFID tag module is used for storing the identification data of the damage monitoring unit;

the IMU detection module is used for detecting the inertial data of the damage monitoring unit;

the damage monitoring extension includes:

an electrical detection module for electrical connection to the electrodes to obtain electrical data relating to track quality;

the UWB base station module is used for detecting the position of the first type UWB tag module;

the RFID reading and writing module is used for reading or writing the identification data in the RFID label module;

the extension processor is used for processing the data of the electrical detection module, the UWB base station module and the RFID read-write module;

the extension processor is used for matching the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertia data of the IMU detection module and transmitting the matching data to the server;

the vehicle detection subsystem is arranged on vehicles running on the railway and used for interacting data or signals with the damage monitoring extension set;

the injury monitoring extension further comprises:

the vehicle detection module is used for detecting the speed of a vehicle passing through the turnout at present;

the vehicle identification module is used for acquiring identification information of a vehicle passing through a turnout at present;

the vehicle interaction module is used for interacting data with a vehicle detection subsystem which passes through a turnout at present;

the vehicle detection module, the vehicle identification module and the vehicle interaction module are electrically connected with the extension processor;

the vehicle detection subsystem includes:

the second type UWB tag module is used for forming signal interaction with the UWB base station module so as to enable the extension processor to acquire the position data of the second type UWB tag module;

the second type UWB tag modules are multiple and are respectively installed at different positions of the vehicle;

the server includes: and the neural network system takes the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag, the inertial data of the IMU detection module and the turnout maintenance data as data for training an artificial neural network in the neural network system, wherein one or a combination of more of the electrical data of the electrical detection module, the position data of the first UWB tag module, the identification data of the RFID tag and the inertial data of the IMU detection module is used as input layer data, and the turnout maintenance data is used as output layer data.

2. The switch operation and maintenance quality prediction analysis system according to claim 1, characterized in that:

the switch maintenance data includes service life, damage condition or alarm level.

3. The switch operation and maintenance quality prediction analysis system according to claim 2, characterized in that:

and the server predicts the turnout maintenance data according to one or more of the electrical data of the electrical detection module, the position data of the first type UWB tag module, the identification data of the RFID tag and the inertia data of the IMU detection module by using the neural network system.

4. The switch operation and maintenance quality prediction analysis system according to claim 3, characterized in that:

the server is divided into a data server and an application server, and the neural network system is arranged on the application server.