CN114861830A - Automatic fault diagnosis method for vehicle-mounted equipment of subway signal system - Google Patents

Abstract

The invention discloses a fault automatic diagnosis method for vehicle-mounted equipment of a subway signal system, which comprises the following steps that (1) a data acquisition device acquires equipment state information in real time and transmits the equipment information to a maintenance center through a mobile communication facility; (2) the maintenance center analyzes the equipment information received from the mobile communication facility and carries out real-time data display, storage record and fault diagnosis on the equipment information; (3) sending the fault diagnosis result to maintenance personnel mobile equipment; (4) the maintenance personnel process the fault by means of a fault processing manual and experience according to the diagnosis information or the early warning information; (5) storing a fault processing result database; compared with the prior art, the method has the advantages of automatic diagnosis, accurate fault location, timely early warning and alarming when the working state of the signal equipment is monitored to be abnormal, and the like, and improves the fault diagnosis accuracy and the fault processing efficiency of the vehicle-mounted signal equipment.

Description

A method for automatic fault diagnosis of vehicle equipment in subway signal system

technical field

The invention relates to the technical field of fault diagnosis of vehicle-mounted signal equipment, in particular to an automatic fault diagnosis method for vehicle-mounted equipment of a subway signal system.

Background technique

The equipment involved in ATP and ATO on the train is called on-board signal equipment. The on-board signal system is a key component of the rail traffic signal system and is responsible for the operation control of the train. Its failure has a significant impact on the safe operation and transportation efficiency of the train. The subway runs for a long time and has a high intensity, and the aging and failure of the equipment are inevitable. At present, the maintenance and fault diagnosis of subway on-board signal equipment have the following problems:

First, troubleshooting is not efficient. The downloading, recording, statistics and summarization of fault information are all done manually, and the processing efficiency is low. The fault maintenance method is generally based on the fault performance and then refer to the past experience for maintenance.

Secondly, the fault data records are not standardized and the fault data records are incomplete. The format of the fault maintenance record is not standardized. The fault record focuses on the accident result, and does not record too much the cause of the fault, so the fault record lacks rigor.

On the other hand, fault diagnosis based on expert knowledge has a certain one-sidedness. Its accuracy depends on the size of the knowledge base and its correct rate, and the diagnostic rules given by different experts are quite different.

Finally, the replacement and repair of vehicle-mounted signal equipment generally refers to the equipment maintenance cycle table issued by the superior to replace the equipment. For some frequently damaged and faulty equipment, there is no corresponding life cycle prediction and estimation, and replacement is only based on experience, and a comprehensive inspection of key equipment is carried out every few days. Although such a maintenance method can ensure the safety of the pens involved, it consumes a lot of manpower and material resources.

To sum up, the faults of in-vehicle signal equipment are complex and uncertain, and the diagnosis system still needs to be improved. In order to solve these problems, the present invention proposes an automatic fault diagnosis method for on-board equipment of a subway signal system. By collecting fault data in real time, and carrying out fault diagnosis, fault information and early warning information are given in time to improve diagnostic accuracy and diagnostic efficiency.

SUMMARY OF THE INVENTION

To achieve the above object, the present invention provides the following technical solutions: a method for automatic fault diagnosis of on-board equipment in a subway signal system, comprising the following steps:

S1, the data collection device collects the equipment status information in real time, and transmits the equipment information to the maintenance center through the mobile communication facility;

S2, the maintenance center parses the device information received from the mobile communication facility, and performs real-time data display, storage record and fault diagnosis of the device information;

S3: Send the fault diagnosis result to the mobile device of the maintenance personnel;

S4: The maintenance personnel handle the fault with the help of the fault handling manual and experience according to the diagnosis information or early warning information;

S5: Save the fault handling result database;

S6: According to the fault processing result database, the K2 algorithm is used for structure learning and the maximum likelihood estimation method for parameter learning, so as to establish an optimal fault diagnosis model.

As a preferred technical manner of the present invention, in step S1, the state information of the automatic on-board train operation system ATO at the control end and the automatic protection system ATP of the on-board train at the control end are collected through two sets of interfaces.

As a preferred technical manner of the present invention, in step S2, a fault diagnosis model is used to generate diagnostic information or early warning information to realize fault diagnosis of the signal vehicle-mounted equipment.

As a preferred technical manner of the present invention, in step S5, the fault handling result database is composed of complete fault data and fault handling means.

As a preferred technical mode of the present invention, in step S6, the establishment of the optimal fault diagnosis model includes the following steps:

a. By analyzing the fault record information of the maintenance center, determine the network node information, that is, the fault processing result database; the network nodes are divided into three levels: fault phenomenon, fault location and fault cause; Combined with the fault processing result database, determine the Dependencies to build Bayesian networks based on expert knowledge;

b. Take an appropriate amount of data from the historically stored fault data as sample data;

c. Use sample data for structure learning and parameter learning;

d. The optimal fault diagnosis model that is more in line with the actual problem can be obtained by properly reducing the learned network structure.

As a preferred technical mode of the present invention, the failure phenomenon is the phenomenon after the hardware module causing the signal failure in the ATO and ATP systems fails; the failure parts are the ATP system and the ATO system; the failure cause is in the ATO and ATP systems Hardware modules in the system that cause signal failures.

As a preferred technical manner of the present invention, the fault diagnosis method is to use the fault phenomenon as an input to estimate the probability of each node of the fault cause.

As a preferred technical manner of the present invention, the early warning information method is to use the fault phenomenon as an input to calculate the probability of each node at the fault location layer.

Compared with the prior art, the beneficial effects of the present invention are as follows:

The automatic fault diagnosis method of the on-board equipment of the subway signal system of the present invention realizes the real-time monitoring of the fault state of the on-board equipment of the signal, the constructed fault diagnosis model realizes the fault early warning and diagnosis before and after the fault occurs, and transmits the fault information to the maintenance personnel in time. It plays an important role in diagnosis efficiency and troubleshooting efficiency.

Description of drawings

Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments with reference to the following drawings:

Fig. 1 is a step diagram of a method for automatic fault diagnosis of vehicle-mounted equipment in a subway signal system of the present invention;

Fig. 2 is the structure diagram of the collector of the present invention;

FIG. 3 is a schematic diagram of the structure of the Bayesian network of the present invention.

Detailed ways

In order to make the technical means, creative features, achievement goals and effects realized by the present invention easy to understand, the present invention will be further described below with reference to the specific embodiments.

As shown in Figure 1, the present invention is a kind of automatic fault diagnosis method of on-board equipment of subway signal system, a kind of automatic fault diagnosis method of on-board equipment of subway signal system comprises the following steps:

Step 1, the data acquisition device collects equipment status information in real time, and transmits the equipment information to the maintenance center through the mobile communication facility; as shown in Figure 2, the acquisition device collects the automatic operation system ATO of the on-board train at the control end and the on-board train at the control end through two sets of interfaces. The status information of the automatic protection system ATP is stored locally, and then uploaded to the maintenance center through the mobile communication facility;

Step 2, the maintenance center parses the device information received from the mobile communication facility, and performs real-time data display, storage record and fault diagnosis on the device information;

Step 3: Send the fault diagnosis result in Step 2 to the mobile device of the maintenance personnel;

Step 4: According to the diagnosis information or early warning information, the maintenance personnel handle the fault in time with the help of the fault handling manual and experience;

Step 5: After the fault is handled, save the fault handling result database;

Step 6: According to the fault processing result database, the K2 algorithm is used for structural learning and the maximum likelihood estimation method for parameter learning to establish an optimal fault diagnosis model (Bayesian network) as shown in Figure 3, which is the Bayesian of the present invention. The schematic diagram of the network structure, in order to make the drawing concise, the figure only schematically shows the structure of the fault diagnosis model of the present invention, and is not regarded as the actual structure;

The establishment of the model includes the following steps:

a. By analyzing the fault record information of the maintenance center, determine the network node information, that is, the fault processing result database; the network nodes are divided into three levels: fault phenomenon, fault location and fault cause; Combined with the fault processing result database, determine the Dependencies to build Bayesian networks based on expert knowledge;

b. Take an appropriate amount of data from the historically stored fault data as sample data;

c. Use sample data for structure learning and parameter learning;

d. By doing a proper and simplified treatment of the learned network structure, an optimal fault diagnosis model more in line with the actual problem is obtained;

Troubleshooting example:

The FAM mode of the 15001# car on the line 15 Luoxiu Road station cannot be converted, and the ATO cannot move the car. After the fault data is collected by the acquisition device, it is sent to the maintenance center in real time for fault diagnosis, and the diagnosis information is generated through the fault diagnosis model diagnosis. The fault diagnosis result is locked as : The FAM unavailable room is due to the driver's key not being turned to the position, and the ATO is unavailable because the button pressing time is too short; the fault diagnosis results are promptly transmitted to the relevant maintenance personnel to move the equipment, and the overhaul and maintenance will be carried out after the train returns to the warehouse.

Example of failure warning:

The connection of the vehicle network port 101# of the control center station of Line 10 is lost. After the fault data is collected by the acquisition device, it is sent to the maintenance center in real time for fault diagnosis, and early warning information is generated through the fault diagnosis model diagnosis. The alarm reason is (1) The port is enabled However, the network cable or optical fiber of the port is not well connected; (2) the network cable or optical fiber is faulty; (3) the sending part of the port is faulty; (4) the local receiving part is faulty. The fault warning information is transmitted to the mobile equipment of the relevant maintenance personnel in time. After the train returns to the warehouse, the maintenance personnel use this information to maintain and repair the train, thereby avoiding the possibility of major failures.

The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the above-mentioned embodiments. Therefore, any changes made to the present invention, and these changes belong to the scope of the claims of the present invention and the technical equivalents thereof, are all within the protection scope of the present invention.

While the basic principles and main features and advantages of the present invention have been shown and described above, it will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but without departing from the spirit or essential aspects of the present invention. In the case of the characteristic features, the present invention can be implemented in other specific forms. Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the appended claims. All changes within the meaning and range of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim.

In addition, it should be understood that although this specification is described in terms of embodiments, not each embodiment only includes an independent technical solution, and this description in the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole , the technical solutions in each embodiment can also be appropriately combined to form other implementations that can be understood by those skilled in the art.

Claims (8)

1. The automatic fault diagnosis method for the vehicle-mounted equipment of the subway signal system is characterized by comprising the following steps of:

s1, the data acquisition device acquires the equipment state information in real time and transmits the equipment information to the maintenance center through the mobile communication facility;

s2, the maintenance center analyzes the equipment information received from the mobile communication facility and carries out real-time data display, storage record and fault diagnosis on the equipment information;

s3: sending the fault diagnosis result to maintenance personnel mobile equipment;

s4: the maintenance personnel process the fault by means of a fault processing manual and experience according to the diagnosis information or the early warning information;

s5: storing a fault processing result database;

s6: and according to the fault processing result database, performing structure learning by adopting a K2 algorithm and performing parameter learning by adopting a maximum likelihood estimation algorithm to establish an optimal fault diagnosis model.

2. The method for automatically diagnosing the fault of the equipment on the train of the subway signal system as claimed in claim 1, wherein in step S1, the status information of the automatic operation system ATO of the train on the control side and the automatic protection system ATP of the train on the control side is collected through two sets of interfaces.

3. The method for automatically diagnosing the fault of the on-board equipment of the subway signal system as claimed in claim 1, wherein in step S2, the fault diagnosis model is used to generate the diagnosis information or the early warning information to diagnose the fault of the on-board equipment.

4. The method for automatically diagnosing the fault of the equipment carried in the subway signal system as claimed in claim 1, wherein in step S5, the fault processing result database is composed of complete fault data and fault handling means.

5. The method for automatically diagnosing the fault of the equipment on board the subway signal system as claimed in claim 1, wherein in step S6, the establishment of the optimal fault diagnosis model comprises the following steps:

a, determining network node information, namely a fault processing result database, by analyzing fault record information of a maintenance center; the network nodes are divided into 3 levels of fault phenomena, fault positions and fault reasons; determining the dependency relationship among the nodes by combining a fault processing result database, and establishing a Bayesian network based on expert knowledge;

b, taking a proper amount of data from the historical fault data as sample data;

c, performing structure learning and parameter learning by using the sample data;

and d, carrying out appropriate reduction treatment on the learned network structure to obtain an optimal fault diagnosis model which is more in line with practical problems.

6. The method for automatically diagnosing the fault of the vehicle-mounted equipment of the subway signal system as claimed in claim 1, wherein the fault phenomenon is a phenomenon after a hardware module causing signal fault in an ATO and ATP system is in fault; the fault positions are an ATP system and an ATO system; the cause of the failure is a hardware module that causes signal failure in the ATO and ATP systems.

7. The method for automatically diagnosing the fault of the equipment on board the subway signal system as claimed in claim 3, wherein the fault diagnosis method is to calculate the probability of each node of the fault reason by using the fault phenomenon as input.

8. The method for automatically diagnosing the fault of the equipment on board the subway signal system as claimed in claim 3, wherein the early warning information method is to calculate the probability of each node of the fault location layer by taking the fault phenomenon as input.

Images