Method for predicting and evaluating service life of computer interlocking system

A technology of computer interlocking and service life, which is applied in general control systems, control/regulation systems, test/monitoring control systems, etc., can solve problems such as large deviations in life prediction results, concerns, and lack of control system structures, etc., to improve Operational Safety and Equipment ROI, Effects of Improved Accuracy

CN108107864AInactive Publication Date: 2018-06-01CHINA RAILWAYS CORPORATION +1
17 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2018-06-01
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention belongs to the technical field of rail traffic control operation and maintenance, and provides a method for predicting and evaluating the service life of a railway signal computer interlocking system based on a neural network. The method comprises the following steps: first, designing life prediction neural network structure models for double-machine hot standby and double 2-vote-2 computer interlocking systems respectively; then, improving the accuracy of prediction by controlling the neuron transfer function and output function of a life prediction neural network and optimizingthe center neuron width; and finally, constraining the format of the input vector of the life prediction neural network based on operation equipment fault data, and predicting and evaluating the service life of the interlocking systems. The results of example verification show that compared with other methods, the method of the invention is more in line with the actual operation of the interlocking systems, has high prediction accuracy and can effectively support the operation safety of the systems and improve the rate of return on investment of interlocking equipment.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of rail traffic control operation and maintenance, and relates to life prediction and evaluation of control equipment, in particular to a service life prediction and evaluation of a railway signal computer interlocking system. Background technique

[0002] The computer interlocking system is the core technical equipment of railway signals, which plays a key role in the production of railway transportation. column) is safe to operate. At present, the computer interlocking used in my country's railways mainly includes two systems of hot backup and two-by-two. At this stage, the life cycle management of computer interlocking systems in my country is not standardized enough and lacks scientific and reasonable basis. The "Railway Signal Maintenance Rules" issued by the former Ministry of Railways in 2009 stipulates that the overhaul cycle of general signal equipment is 15 years. In actual operation, the overhau...

Examples

specific example

[0056] Based on the fault data of a two-by-two computer interlocking system obtained from a railway bureau in my country, the life prediction and evaluation of it are carried out. The failure data of the system collected from 2012 to 2016 are as follows:

[0057]

[0058]

[0059] The data in the table is classified according to the data constraint format of the present invention, and the input vector [x1, x2, ... x23] of the life prediction and evaluation neural network is obtained, and the calculation is performed, and the life of the interlocking system components obtained by the network calculation is as follows :

[0060] Failure Data Predictors

[0061] use the formula Find the mean time between failure index of the computer interlocking system,

[0062]

[0063] According to the average remaining life of the system, that is, the mean time between failures (MTBF) of the system, when the value does not meet the MTBF stipulated in my country's ...