阅读说明：本技术 一种道岔监测方法及系统 (Turnout monitoring method and system ) 是由 王伟 刘超 于 2019-11-07 设计创作，主要内容包括：本发明实施例公开了一种道岔监测方法及系统,包括：采集当前线路中每个道岔的实时数据,对所述每个道岔的实时数据进行预处理,得到所述每个道岔对应的预处理数据；对所述每个道岔对应的预处理数据进行分析处理,确定所述每个道岔对应的健康状态,其中,所述健康状态至少包括健康、亚健康及故障；若存在故障状态的道岔,则确定每个故障状态的道岔对应的目标故障类型；基于所述每个道岔对应的健康状态及每个故障状态的道岔对应的目标故障类型,生成所述当前线路对应的监测结果,并将所述监测结果发送至终端。采用本发明可以提高列车的运行效率。(The embodiment of the invention discloses a switch monitoring method and a system, comprising the following steps: acquiring real-time data of each turnout in a current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout; analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises health, sub-health and failure; if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state; and generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal. The invention can improve the running efficiency of the train.)

1. A switch monitoring method, comprising:

acquiring real-time data of each turnout in a current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout;

analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises health, sub-health and failure;

if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state;

and generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal.

2. The switch monitoring method according to claim 1, wherein the collecting real-time data of each switch in the current line, and preprocessing the real-time data of each switch comprises:

the real-time data of each turnout is collected through a current sensor corresponding to each turnout in the current line, and the real-time data of each turnout is converted into a digital signal through an analog signal, wherein the real-time data at least comprises the real-time action current of the turnout.

3. The switch monitoring method according to claim 1, characterized in that the method further comprises:

acquiring a fault type and fault data corresponding to each fault of each turnout in a preset historical time period, and clustering the fault type and the fault data corresponding to each fault to obtain fault characteristic clustering big data;

and acquiring a processing mode corresponding to each fault type, and constructing a fault processing mode set based on the processing mode corresponding to each fault type.

4. The switch monitoring method according to claim 3, wherein the analyzing the preprocessed data corresponding to each switch to determine the health status of each switch comprises:

determining the health state of each turnout according to the preprocessed data corresponding to each turnout by combining a preset health value and a preset sub-health value;

if the turnout in the fault state exists, determining a target fault type corresponding to the turnout in each fault state, wherein the target fault type comprises the following steps:

if the turnout in the fault state exists, determining a target fault type corresponding to the turnout in each fault state based on the fault feature clustering big data and the preprocessing data corresponding to the turnout in each fault state;

determining a fault processing mode corresponding to each target fault type based on the fault processing mode set and the target fault type corresponding to the turnout in each fault state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, wherein the monitoring result comprises:

and generating a monitoring result corresponding to the current line based on the target fault type corresponding to the turnout in each fault state and the fault processing mode corresponding to each target fault type.

5. The switch monitoring method according to claim 4, wherein after said determining the health status of each switch, further comprising:

if the turnouts in the sub-health states exist, determining a target trend fault type corresponding to the turnouts in each sub-health state based on the fault feature clustering big data and the preprocessing data corresponding to the turnouts in each sub-health state;

determining a fault processing mode corresponding to each target trend fault type based on the fault processing mode set and the target trend fault type corresponding to the turnout in each sub-health state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, wherein the monitoring result comprises the following steps:

and generating a monitoring result corresponding to the current line based on each target trend fault type, the fault processing mode corresponding to each target trend fault type, each target fault type and the fault processing mode corresponding to each target fault type.

6. The method according to claim 1, wherein after determining the health status corresponding to each switch, further comprising:

counting the occurrence frequency of each fault type in the preset counting time length of each unit and the sub-health state frequency of each turnout in the preset counting time length before the current time of all turnouts in the current line;

and generating a monitoring result corresponding to the current line based on the health state of each turnout, the occurrence frequency of each fault type and the sub-health state frequency of each turnout, and sending the monitoring result to the terminal.

7. The switch monitoring method according to claim 5, wherein after determining the health status corresponding to each switch, further comprising:

and generating a health state report corresponding to each turnout in the current line based on the preprocessed data corresponding to each turnout, the health state of each turnout, each target fault type and each target trend fault type, and sending the health state report to the terminal.

8. The method of claim 1, further comprising:

if a health detection instruction is received, determining a target line corresponding to the health detection instruction, acquiring real-time data of each turnout in the target line, and acquiring the historical moment of the last health detection instruction reception;

determining health values corresponding to all switches in the target line and health values of the target line based on real-time data of all switches in the target line, and determining a current detection period based on the historical time of the last received health detection instruction and the current time;

and generating a health report of the target line based on the health value corresponding to each turnout in the target line, the health value of the target line, the real-time data of each turnout in the target line and the current detection period, and sending the health report to the terminal.

9. The turnout monitoring method according to claim 1, wherein the method for constructing the fault handling manner set based on the handling manner corresponding to each fault type at least comprises a fault tree analysis method, a failure mode and an influence analysis method.

10. A switch monitoring system, the system comprising a sensing layer, a platform layer and an application layer, wherein:

the sensing layer is used for acquiring real-time data of each turnout in a current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout;

the platform layer is used for:

analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises a health state, a sub-health state and a fault state;

if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal

And the application layer is used for receiving the monitoring result sent by the platform layer.

Technical Field

The invention relates to the technical field of rail transit, in particular to a turnout monitoring method and system.

Background

The turnout serves as important connecting equipment in urban rail transit, and a train can be switched from one track to another track. The health state of the turnout can directly affect the running safety and efficiency of the train, so that the monitoring of the equipment state of the turnout is particularly important.

At present, operators usually adopt microcomputer monitoring systems to monitor the state of turnouts. Specifically, the microcomputer monitoring system can acquire the action current of each turnout in the line in real time, and generate a relation curve graph of the action current and the time by combining historical action current data acquired by each turnout in a previous period (such as 20 seconds). Then, the health state of each turnout can be determined according to the relation graph, all fault types which may occur to each turnout are judged, all fault types which may occur to each turnout are used as monitoring results and sent to the terminal, so that an operator can check the monitoring results on the basis of the terminal, and maintain each turnout on the basis of all fault types which may occur to each turnout in the monitoring results.

Disclosure of Invention

Because the existing method has the problems, the embodiment of the invention provides a switch monitoring method and a switch monitoring device.

In a first aspect, an embodiment of the present invention provides a switch monitoring method, including:

acquiring real-time data of each turnout in a current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout;

analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises health, sub-health and failure;

if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state;

and generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal.

Optionally, the acquiring real-time data of each switch in the current line, and preprocessing the real-time data of each switch includes:

the real-time data of each turnout is collected through a current sensor corresponding to each turnout in the current line, and the real-time data of each turnout is converted into a digital signal through an analog signal, wherein the real-time data at least comprises the real-time action current of the turnout.

Optionally, the method further includes:

acquiring a fault type and fault data corresponding to each fault of each turnout in a preset historical time period, and clustering the fault type and the fault data corresponding to each fault to obtain fault characteristic clustering big data;

and acquiring a processing mode corresponding to each fault type, and constructing a fault processing mode set based on the processing mode corresponding to each fault type.

Optionally, the analyzing and processing the preprocessed data corresponding to each switch to determine the health status corresponding to each switch includes:

determining the health state of each turnout according to the preprocessed data corresponding to each turnout by combining a preset health value and a preset sub-health value;

if the turnout in the fault state exists, determining a target fault type corresponding to the turnout in each fault state, wherein the target fault type comprises the following steps:

if the turnout in the fault state exists, determining a target fault type corresponding to the turnout in each fault state based on the fault feature clustering big data and the preprocessing data corresponding to the turnout in each fault state;

determining a fault processing mode corresponding to each target fault type based on the fault processing mode set and the target fault type corresponding to the turnout in each fault state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, wherein the monitoring result comprises:

and generating a monitoring result corresponding to the current line based on the target fault type corresponding to the turnout in each fault state and the fault processing mode corresponding to each target fault type.

Optionally, after determining the health status of each switch, the method further includes:

if the turnouts in the sub-health states exist, determining a target trend fault type corresponding to the turnouts in each sub-health state based on the fault feature clustering big data and the preprocessing data corresponding to the turnouts in each sub-health state;

determining a fault processing mode corresponding to each target trend fault type based on the fault processing mode set and the target trend fault type corresponding to the turnout in each sub-health state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, wherein the monitoring result comprises the following steps:

and generating a monitoring result corresponding to the current line based on each target trend fault type, the fault processing mode corresponding to each target trend fault type, each target fault type and the fault processing mode corresponding to each target fault type.

Optionally, after determining the health status corresponding to each switch, the method further includes:

counting the occurrence frequency of each fault type in the preset counting time length of each unit and the sub-health state frequency of each turnout in the preset counting time length before the current time of all turnouts in the current line;

and generating a monitoring result corresponding to the current line based on the health state of each turnout, the occurrence frequency of each fault type and the sub-health state frequency of each turnout, and sending the monitoring result to the terminal.

Optionally, after determining the health status corresponding to each switch, the method further includes:

and generating a health state report corresponding to each turnout in the current line based on the preprocessed data corresponding to each turnout, the health state of each turnout, each target fault type and each target trend fault type, and sending the health state report to the terminal.

Optionally, the method further includes:

if a health detection instruction is received, determining a target line corresponding to the health detection instruction, acquiring real-time data of each turnout in the target line, and acquiring the historical moment of the last health detection instruction reception;

determining health values corresponding to all switches in the target line and health values of the target line based on real-time data of all switches in the target line, and determining a current detection period based on the historical time of the last received health detection instruction and the current time;

and generating a health report of the target line based on the health value corresponding to each turnout in the target line, the health value of the target line, the real-time data of each turnout in the target line and the current detection period, and sending the health report to the terminal.

Optionally, the method for constructing the fault handling manner set based on the handling manner corresponding to each fault type at least includes a fault tree, a failure mode, and an impact analysis method.

In a second aspect, an embodiment of the present invention further provides a switch monitoring system, where the system includes a sensing layer, a platform layer, and an application layer, where:

the sensing layer is used for acquiring real-time data of each turnout in a current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout;

the platform layer is used for:

analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises a health state, a sub-health state and a fault state;

if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal

And the application layer is used for receiving the monitoring result sent by the platform layer.

According to the technical scheme, the target fault type corresponding to the turnout in each fault state is determined according to the real-time data of each turnout in the line, and the monitoring result containing the target fault type corresponding to the turnout in each fault state is generated. Therefore, each turnout is only corresponding to one fault type, so that an operator can maintain the turnout in a fault state in a more targeted manner, the maintenance time of the turnout can be effectively reduced, and the running efficiency of a train can be improved. Meanwhile, the monitoring results sent to the terminal in the method provided by the invention also comprise the health state of each turnout, such as the health state, the sub-health state and the fault state, so that an operator can selectively maintain the turnout in the sub-health state in advance according to the health state of each turnout, the turnout fault probability can be reduced, and the running efficiency of the train can be further improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a switch monitoring method according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a switch monitoring system according to an embodiment of the present invention.

Detailed Description

The following further describes embodiments of the present invention with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.

Fig. 1 shows a schematic flow chart of a switch monitoring method provided in this embodiment, including:

s101, acquiring real-time data of each turnout in the current line, and preprocessing the real-time data of each turnout to obtain preprocessed data corresponding to each turnout.

The preprocessing data refers to data obtained after preprocessing the real-time data of each turnout.

In implementation, the real-time data of each turnout in the current line can be collected in real time, the real-time data of each turnout is analyzed and processed, the health state of each turnout in the current line is determined, such as the health state, the sub-health state, the fault state and the like, the fault type corresponding to the turnout in each fault state can be determined, and the monitoring result corresponding to the current line at the current moment is generated based on the health state of each turnout in the current line and the fault type of each faulted turnout, so that an operator can know the health state of each turnout and the fault type of the faulted turnout in the current line according to the monitoring result to perform targeted maintenance. Specifically, the real-time data of each switch in the current line can be collected in real time, for example, the real-time data of the corresponding switch, such as the real-time action current of each switch, can be collected through a current sensor installed on a cable of each switch. Then, the acquired real-time data of each switch in the current line may be subjected to data preprocessing to obtain preprocessed data, such as analog-to-digital conversion and the like.

And S102, analyzing and processing the preprocessing data corresponding to each turnout, and determining the health state corresponding to each turnout.

The health state at least comprises health, sub-health and faults, the health state can be used for indicating the running state of the turnout, and if the turnout runs normally and works well, the turnout is healthy; if the operation can be performed but the working state is not good, the operation is sub-healthy; if the system can not operate normally, the system is in failure.

In implementation, after the preprocessed data corresponding to each switch is obtained, the preprocessed data corresponding to each switch may be further subjected to statistical analysis, for example, a health state corresponding to each switch in the current line may be determined by methods such as cloud platform application software and an artificial intelligence algorithm, for example, the health state corresponding to each switch may be one of three states, i.e., health, sub-health, and failure.

And S103, if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state.

The target fault type refers to a fault type corresponding to each turnout in a fault state, such as a point rail fault, a switch machine fault and the like.

In implementation, after the health status corresponding to each switch in the current route is determined, it may be determined whether there is a switch with a fault health status in all switches in the current route. If there is a switch whose health state is a fault (i.e., a fault state), all switches whose health states are faults can be determined from all switches of the current route. Then, a target failure type corresponding to each switch of the failure state can be determined. It can be understood that the target fault types corresponding to the switches in different fault states can be the same or different.

And S104, generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to the terminal.

In implementation, after the target fault type corresponding to the switch in each fault state is determined, a monitoring result of the current line at the current time may be generated based on the health state corresponding to each switch in the current line and the target fault type corresponding to the switch in each fault state, that is, the monitoring result may include the health state corresponding to each switch in the current line and the target fault type corresponding to the switch in each fault state. Then, the monitoring result may be sent to a terminal, which may be a computer, a tablet computer, or another mobile terminal, as long as the communication address of the terminal is pre-stored in the switch monitoring system. Then, the operator can receive and check the monitoring result through the terminal, so as to maintain the turnout in the current line based on the monitoring result, for example, the turnout in the fault state can be repaired or replaced slightly, and the turnout in the sub-health state can also be maintained.

According to the technical scheme, the target fault type corresponding to the turnout in each fault state is determined according to the real-time data of each turnout in the line, and the monitoring result containing the target fault type corresponding to the turnout in each fault state is generated. Therefore, each turnout is only corresponding to one fault type, so that an operator can maintain the turnout in a fault state in a more targeted manner, the maintenance time of the turnout can be effectively reduced, and the running efficiency of a train can be improved. Meanwhile, the monitoring results sent to the terminal in the method provided by the invention also comprise the health state of each turnout, such as the health state, the sub-health state and the fault state, so that an operator can selectively maintain the turnout in the sub-health state in advance according to the health state of each turnout, the turnout fault probability can be reduced, and the running efficiency of the train can be further improved.

Further, on the basis of the above method embodiment, analog-to-digital conversion may be performed on the real-time data of each switch, and the corresponding processing of step S101 may be as follows: the real-time data of each turnout is collected through a current sensor corresponding to each turnout in the current line, and the real-time data of each turnout is converted into a digital signal through an analog signal.

Wherein, the real-time data of each switch at least comprises the real-time action current of the switch.

In the implementation, considering that the acquired real-time data of each switch is usually an analog signal, and the data processing cannot be directly performed, the analog signal can be converted into an electronic signal when the real-time data of each switch is preprocessed. Specifically, real-time data of each switch in the current line, such as at least real-time action current of each switch, can be acquired through a current sensor installed on a cable of each switch in the current line. After the real-time data of each turnout is collected, the real-time data of each turnout can be subjected to analog-to-digital conversion through the A/D converter, and the real-time data of each turnout is converted into an electronic signal from an analog signal.

Further, on the basis of the above method embodiment, a fault feature cluster big data and fault processing mode set may also be constructed, and the corresponding processing may be as follows: acquiring a fault type and fault data corresponding to each fault of a turnout in a preset historical time period, and clustering the fault type and the fault data corresponding to each fault to obtain fault characteristic clustering big data; and acquiring a processing mode corresponding to each fault type, and constructing a fault processing mode set based on the processing mode corresponding to each fault type.

The preset historical time period refers to a time period corresponding to historical data for constructing fault feature cluster big data.

The fault data refers to real-time data when each turnout in the current line has a fault.

The real-time fault feature clustering big data refers to a classification set of the fault types and the corresponding fault data which are constructed based on the fault types and the fault data corresponding to the faults of each turnout in a preset historical period, for example, the classification set can be a fault data range x corresponding to the fault type A₁-x₂(ii) a Fault type B corresponds to fault data range y₁-y₂。

The fault processing mode set refers to a set constructed based on the processing modes corresponding to the fault types.

In implementation, the type of the fault corresponding to each failed switch in the current line within a preset historical time period (for example, the past week) and the corresponding fault data may be obtained, where the fault data may be the real-time operating current of each failed switch. Then, clustering processing can be carried out on the obtained fault type and fault data corresponding to each turnout when the turnout fails in a preset historical period, and fault characteristic clustering big data are constructed and obtained. And the processing modes corresponding to various existing fault types can be obtained, for example, the processing modes corresponding to each fault type provided by an authority engineer or the processing modes with higher power in the historical processing modes can be obtained. Then, a Fault handling manner set can be constructed based on the handling manners corresponding to the various Fault types, for example, a Fault Tree Analysis (FTA) and a Failure Mode and Effects Analysis (FMEA) can be used. Therefore, a fault feature clustering big data and fault processing mode set is constructed, more accurate data basis can be provided for turnout monitoring, the accuracy of the monitoring result of each turnout in the current line can be further improved, a corresponding fault processing mode can be provided, the maintenance time of an operator for each turnout of the current line can be further shortened, the maintenance efficiency is improved, and the running efficiency of a train can be further improved.

Further, on the basis of the above method embodiment, the fault processing method corresponding to the fault type of each failed switch may be sent to the terminal together, and the corresponding processing in step S102 may be as follows: determining the health state of each turnout according to the preprocessed data corresponding to each turnout by combining a preset health value and a preset sub-health value; the corresponding processing of step S103 described above may be as follows: if the turnout in the fault state exists, determining a target fault type corresponding to the turnout in each fault state based on the fault feature clustering big data and the preprocessing data corresponding to the turnout in each fault state; determining a fault processing mode corresponding to each target fault type based on the fault processing mode set and the target fault type corresponding to the turnout in each fault state; the corresponding processing of step S104 described above may be as follows: and generating a monitoring result corresponding to the current line based on the target fault type corresponding to the turnout in each fault state and the fault processing mode corresponding to each target fault type.

The preset health value and the preset sub-health value pointer set for the operation state of the turnout are used for judging the value of the operation health state of each turnout, and the health value and the sub-health value are determined according to historical operation data of the turnout, such as the storable data.

In implementation, after preprocessing data corresponding to each turnout in a current line is obtained, a real-time health value of each turnout can be determined by combining the preprocessing data of each turnout, and a health state of each turnout in the current line is determined by combining a preset health value and a preset sub-health value, if the preset health value is 90 and the preset sub-health value is 70, and if the real-time health value of a certain turnout is greater than or equal to 90, the turnout is considered to be in a health state; and if the real-time health value of the turnout is greater than or equal to 70 and less than 90, the turnout is considered to be in a sub-health state, otherwise, the turnout is considered to be in a fault state. Then, it can be determined whether there is a switch in a fault state in the current line at the current time, if there is a switch in a fault state, the target fault type corresponding to the switch in each fault state can be determined by combining the above-mentioned fault feature cluster big data and the preprocessed data corresponding to the switch in each fault state, if the action current range corresponding to the fault type a is a₁～a₂Suppose that the action current of a certain turnout at the current moment is a₁～a₂And then, the target fault type of the turnout can be determined to be the fault type A. Then, by combining the above fault processing mode set, a fault processing mode corresponding to the target fault type of the faulty turnout is determined in the fault processing mode set. Then, based on the determined health state corresponding to each switch in the current route, the target fault type of the switch in each fault state, and the fault processing manner corresponding to each target type, a monitoring result corresponding to the current route at the current moment can be generated. Like this, can make operating personnel can be according to the target fault type and the corresponding processing mode of the switch of fault state among the monitoring result, carry out the pertinence maintenance to the switch of fault state to can further shorten switch maintenance time, and then further improve the operating efficiency of train, simultaneously, can also make operating personnel according to the monitoring result, to the switch of fault stateThe turnout in the sub-health state is maintained in advance, so that the turnout can be prevented from being broken down, and the running safety and the running efficiency of the train can be further improved.

Further, on the basis of the above method embodiment, the target trend fault type and the corresponding fault handling manner of each sub-health turnout may also be sent to the terminal, and after the corresponding step S102, the following processing may also be performed: if the turnouts in the sub-health states exist, determining a target trend fault type corresponding to the turnouts in the sub-health states based on the fault feature clustering big data and the preprocessing data corresponding to the turnouts in each sub-health state; determining a fault processing mode corresponding to each target trend fault type based on the fault processing mode set and the target trend fault type corresponding to each subhealth turnout; the corresponding processing of step S104 described above may be as follows: and generating a monitoring result corresponding to the current line based on each target trend fault type, a fault processing mode corresponding to each target trend fault type, each target fault type and a fault processing mode corresponding to each target fault type.

Wherein the target trend fault type refers to a fault type which can occur in the switch in the sub-health state.

In implementation, after obtaining the preprocessed data corresponding to each switch in the current route and determining the health state of each switch in the current route, it may be determined whether there is a switch in a sub-health state in the current route. If the turnout in the sub-health state exists, the target trend fault type corresponding to the turnout in each sub-health state can be determined by combining the fault feature cluster big data and the preprocessed data corresponding to the turnout in each sub-health state, for example, the target trend fault type of the turnout in each sub-health state can be determined by determining the real-time data corresponding to the turnout in each sub-health state is closer to the fault data range of which fault type according to the real-time data corresponding to the turnout in each sub-health state and the fault data range corresponding to each fault type in the fault feature cluster big data. Then, a fault handling manner corresponding to the target trend fault type corresponding to each sub-health state turnout can be determined based on the target trend fault type of each sub-health state turnout and the fault handling manner set. And then, generating a monitoring result corresponding to the current line by using each target trend fault type, a fault processing mode corresponding to each target trend fault type, each target fault type and a fault processing mode corresponding to each target fault type, and sending the monitoring result to the terminal. Therefore, the operation personnel can perform targeted maintenance on the turnout in the fault state according to the target fault type and the corresponding processing mode of the turnout in the fault state in the monitoring result, so that the turnout maintenance time is further shortened, and the operation efficiency of the train is further improved. Meanwhile, fault early warning can be realized, so that an operator can perform targeted maintenance on the turnout in each sub-health state in advance according to a fault processing mode corresponding to each target fault type, corrective maintenance after the fault is reduced, the turnout can be further prevented from being broken down, the turnout maintenance time is shortened, and the running safety and the running efficiency of the train can be further improved.

Further, on the basis of the above method embodiment, the health status of each switch in the current route may be monitored for a period of time, and the following processing may be performed after step S102: counting the occurrence frequency of each fault type in the preset counting time length of each unit and the sub-health state frequency of each turnout in the preset counting time length before the current moment of all turnouts in the current line; and generating a monitoring result corresponding to the current line based on the health state of each turnout, the occurrence frequency of each fault type and the sub-health state frequency of each turnout, and sending the monitoring result to the terminal.

The preset statistics duration refers to the interval duration of the number of faults of all switches in the current line, and if the preset statistics duration is one week and the current time is 10 months and 15 days in 2019 at 10:00, the number of faults of all switches in the current line can be counted within 10 months and 8 days in 2019 at 10:00 and 10 months and 15 days in 2019 at 10: 00.

The unit preset statistic duration refers to a small statistic duration divided by the preset statistic duration, and if the preset statistic duration is one week, the unit preset statistic duration may be one day.

In the implementation, the times of occurrence of various fault types in the preset statistical time of each unit and the times of occurrence of sub-health state of each turnout in the preset statistical time before the current time of all turnouts in the current line can be counted. Then, based on the health state of each turnout, the occurrence frequency of each target fault type and the sub-health state frequency of each turnout, a monitoring result corresponding to the current line is generated and sent to the terminal. Taking the preset statistical time as 1 week, the unit preset statistical time as 1 day, and the current time as 10 months and 15 days in 2019 and 10:00 days in 2019, it can be determined that what needs to be counted at the current time are the times of sub-health state and fault of each turnout in 2019 and 10 months and 8 days in 2019 and 10 months and 15 days in 10 months and 10:00 of 2019 and the times of occurrence of each fault type every day, and it is assumed that the times of occurrence of faults and the fault types of each turnout (only turnout 1-5 is assumed) in the current line are respectively 3 (fault a occurs for 2 times and fault B occurs for 1 time), 2 (fault C occurs for 1 time and fault B occurs for 1 time), 0, 1 (fault C occurs for 1 time) and 1 (fault D occurs for 1 time). Then, the number of healthy turnouts, the number of sub-healthy turnouts and the number of faulty turnouts at the current moment can be determined based on the health state of each turnout determined at the current moment, a corresponding fault trend graph is drawn based on the number of times of faults of each turnout occurring in 2019, 10/8/10/00-2019, 10/15/10/00, the corresponding sub-healthy turnout and faulty turnout ranking is determined based on the number of times of sub-health and fault occurring in each turnout in 2019, 10/8/10/00-2019, 10/15/10/00, and the corresponding fault distribution graph can be drawn based on the number of times of faults occurring in each turnout and the fault type. And then, generating a monitoring result based on the healthy turnout number, the sub-healthy turnout number, the fault trend graph, the sub-healthy turnout ranking and the fault turnout ranking at the current moment and the fault distribution graph, and sending the monitoring result to the terminal. Like this, can make operating personnel can be audio-visual to know the switch condition in current moment and a period before to can carry out the total accuse to the running state of each switch in the current circuit, carry out holistic maintenance arrangement to all switches of current circuit, and then further the improvement operating efficiency of train.

Further, on the basis of the above method embodiment, the health status of each switch and the corresponding related information may be sent to the terminal, and the corresponding processing may be as follows: and generating a health state report corresponding to each turnout in the current line based on the preprocessed data corresponding to each turnout, the health state of each turnout, each target fault type and each target trend fault type, and sending the health state report to the terminal.

In implementation, after the health state of each switch in the current line is determined, the health trend corresponding to each switch can be further determined based on the preprocessed data corresponding to each switch. Then, a health state report corresponding to each turnout in the current line can be generated based on the health state of each turnout, the target fault type corresponding to each faulty turnout and the target trend fault type corresponding to each sub-healthy turnout, and the health state report can be sent to the terminal. Taking the current line including the turnout 1, the turnout 2 and the turnout 3 as an example, assuming that the health states corresponding to the turnouts are respectively healthy, sub-healthy and faulty, the health trend of each turnout can be determined, such as the health, the fault and the fault, and the corresponding target fault type or the target trend fault type, and then, the monitoring result can be generated based on the health state, the preprocessing data, the health trend and the fault type corresponding to each turnout, and sent to the terminal. Therefore, the operating personnel can visually know the operating state and the operating trend of each turnout, and can perform targeted maintenance on each turnout, further reduce the maintenance time, reduce the failure occurrence frequency and improve the safety and the operating efficiency of train operation.

Further, on the basis of the above method embodiment, the switches in the line may be monitored according to the health detection instruction, and the corresponding processing may be as follows: if the health detection instruction is received, determining a target line corresponding to the health detection instruction, acquiring real-time data of each turnout in the target line, and acquiring the historical moment of the last health detection instruction reception; determining a health value corresponding to each turnout in a target line and a health value of the target line based on real-time data of each turnout in the target line, and determining a current detection period based on a historical moment of last receiving of a health detection instruction and a current moment; and generating a health report of the target line based on the health value corresponding to each turnout in the target line, the health value of the target line, the real-time data of each turnout in the target line and the current detection period, and sending the health report to the terminal.

Wherein the target line refers to a line corresponding to the health detection instruction.

In implementation, when receiving a health detection command, the target line corresponding to the health detection command may be detected, and the health detection command may be automatically generated by the system according to a set period or manually input by an operator. Specifically, if a health detection instruction is received, a target line corresponding to the health detection instruction may be determined. Then, real-time data of each turnout in the target line can be collected, and the historical time of the health detection instruction received last time can be determined. And then, preprocessing the real-time data of each turnout of the target line to determine the corresponding health value of each turnout. Then, the overall health value of the target route may be determined based on the health values of the switches, and the interval duration between the previous historical time when the health detection instruction was received and the current time may be calculated and determined as the current detection period. And then, based on the health value corresponding to each turnout in the target line, the health value of the target line, the real-time data of each turnout in the target line and the current detection period, generating a health report corresponding to the target line, and sending the health report to the terminal. It is understood that the manual detection content, such as the appearance of the switch, etc., can also be input into the system in advance, and when the health report is generated, the health report can also be generated by combining the manual detection content with the above data. Therefore, the whole operation condition of the whole line and the operation condition of each turnout in the line can be determined according to the health report, so that the whole control of the whole line and the operation condition of each turnout can be realized, the whole line is maintained or some turnouts are maintained in a targeted manner, the maintenance time can be further shortened, the failure occurrence frequency is reduced, and the train operation safety and the operation efficiency are improved.

It will be appreciated that the executing entity of the above method embodiments of the present invention may be a switch monitoring system, which may include a perception layer, a platform layer and an application layer. The sensing layer can realize the collection and transmission of data. The platform layer can realize the storage and processing of data. The application layer can receive and graphically display the data analysis result. The sensing layer may include: the device comprises a current sensor, a data acquisition module and a communication transmission module. The current sensor is used for acquiring real-time data of the turnout; the data acquisition module is used for preprocessing acquired data, and comprises analog-to-digital conversion, data caching, data sending and the like, can provide 12V direct current power supply by adopting a direct current power supply, and can be connected to communication transmission equipment by adopting a WIFI wireless interface, an RS485 or an Ethernet; the communication transmission module is used for transmitting turnout preprocessing data, the communication transmission module can select an industrial-grade 4G wireless router, the router can adopt a WIFI interface and is placed in a signal machine room together with the acquisition module, a power supply mode can adopt a direct-current power supply to provide 12V direct-current power supply, the communication transmission module can also establish a virtual private network on a public network and carry out encryption communication, the communication mode can adopt WIFI, and RS485 or Ethernet transmission can also be used. The platform layer can be a server or a server cluster, can receive data sent by the data acquisition module through the communication transmission equipment, and can process the data by combining with a characteristic fault clustering big data and an artificial intelligence algorithm. The application layer comprises a display terminal, such as a mobile phone, a computer and the like, and can complete data sent by the platform layer and display the data so that an operator can check real-time monitoring results, health status reports, health reports and the like of the turnout at the display terminal.

Fig. 2 shows a switch monitoring system provided in this embodiment, the system includes a sensing layer 201, a platform layer 202, and an application layer 203, where:

the sensing layer 201 is configured to acquire real-time data of each turnout in a current line, and preprocess the real-time data of each turnout to obtain preprocessed data corresponding to each turnout;

the platform layer 202 is configured to:

analyzing and processing the preprocessed data corresponding to each turnout, and determining the health state corresponding to each turnout, wherein the health state at least comprises a health state, a sub-health state and a fault state;

if the turnouts in the fault states exist, determining a target fault type corresponding to each turnout in the fault state;

generating a monitoring result corresponding to the current line based on the health state corresponding to each turnout and the target fault type corresponding to the turnout in each fault state, and sending the monitoring result to a terminal

The application layer 203 is configured to receive the monitoring result sent by the platform layer.

The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

It should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.