A Method for Prediction and Evaluation of Service Life of Computer Interlocking System

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 present invention: first of all, aiming at the computer interlocking systems of the dual-computer hot standby type and the two-by-two-out type, respectively design a life prediction neural network structure model; secondly, by controlling the neuron transfer function and output of the life prediction neural network function, and the optimization of the width of the central neuron to improve the prediction accuracy; finally, based on the operating equipment failure data, the input vector format constraints of the life prediction neural network are performed to predict and evaluate the service life of the interlocking system. Through example verification, the results show that: compared with other methods, it is more in line with the actual operation of the interlocking system, with high prediction accuracy, which can effectively support the operation safety of the system and improve the return on investment of interlocking equipment.

Description

Technical field[0001]The invention belongs to the technical field of rail transit control, operation and maintenance, and relates to the life prediction evaluation of control equipment, in particular to the service life prediction evaluation of a railway signal computer interlocking system.Background technique[0002]The computer interlocking system is the core technical equipment of railway signal, which plays a key role in the production of railway transportation. Its main function is to control the operation and operation of trains (or shunting trains) at stations, and ensure that trains (or trains) Column) operation safety. At present, the computer interlocking used in my country's railways mainly includes two systems: dual machine hot standby and two by two out of two. At this stage, the life cycle management of computer interlocking systems in our country is not standardized enough and lacks scientific and reasonable basis. In 2009, the "Railway Signal Maintenance Regulations" i...

AI Technical Summary

Problems solved by technology

The method based on probability and statistics, due to some uncertain factors in the system, leads to a large deviation in the life prediction results; at this stage, the life prediction method based on information technology lacks attention to the structure of the control system, and is more common in technical systems in the aerospace field

The railway signal computer interlocking system has a unique hardware redundancy structure, which is quite different from the conventional industrial control system

Images