Electric locomotive writing pole permanent magnet synchronous traction system based on guiding of expert system

Abstract

The invention discloses a technology of using artificial intelligence such as an expert system, a neural network and the like to diagnose a fault of a writing pole permanent magnet synchronous traction system. The specific technical implementation process comprises the steps of firstly extracting a fault symptom, searching cases that are the same as or similar to the current symptom, and if the symptoms are successfully matched, listing similar cases according to similarity; then matching the feature values of the similar cases with the status value of a current traction motor, to acquire thebest case, so as to diagnosis the transaction system, wherein such a process is named as backward verification. The inference mechanism also can be used for correcting the case, and the corrected casecan be used as a new case to be added into a case library. According to the system provided by the invention, the fault diagnosis of the electric locomotive traction system is relatively high in accuracy.

Description

technical field [0001] The invention relates to a traction system of an electric locomotive. In the field of utilization of electric locomotives in which pole-write permanent magnet synchronous motors are applied, expert experience is effectively used to form heuristic knowledge to quickly, effectively and accurately identify faults and solve the problem of fault diagnosis of pole-write traction motors. [0002] technical background [0003] During the actual operation of the electric locomotive, the traction motor is affected by the external complex working environment, such as temperature, grid voltage fluctuation, electromagnetic radiation, rapid start / stop of the vehicle, etc., so that the traction motor is subjected to alternating stress, including air resistance, Electromagnetic force, centrifugal force, etc. In addition, it also includes defects in the manufacture of the traction motor itself, which also leads to the failure of the stator winding, rotor guide bar and o...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the traditional traction motor fault diagnosis is to analyze various parameters of the motor by means of experiments to obtain the diagnosis results, the efficiency is low and the accuracy is not high, the present invention discloses and invents an electric locomotive write pole permanent magnet synchronization based on an expert system traction system such as figure 2

Images