Motor fault diagnosis and deterioration trend prediction method and system

Abstract

The invention provides a motor fault diagnosis and degradation trend prediction method and system, and the system comprises a data collection unit which is mainly used for collecting the voltage and current data of a motor, and marking the data at the same time; the server unit can be connected with a plurality of acquisition units and is mainly used for performing preprocessing, spectrum analysis, fault diagnosis, degradation trend prediction and the like on data; the database unit is used for storing typical fault samples of historical data. The system adopts a machine learning and manual intervention method to carry out monitoring and fault diagnosis on the motor. The method is not influenced by voltage grades and operation conditions, and can intelligently analyze the current state of the motor and predict the fault development trend. By adopting the motor fault diagnosis and deterioration trend prediction method and system, the severity of the motor fault can be judged, and the fault development trend can be predicted. A shutdown overhaul and maintenance plan is arranged in advance, production efficiency is improved, equipment operation and maintenance cost is reduced, and enterprise economic and safety benefits are increased.

Description

technical field [0001] The invention relates to the field of motor fault diagnosis, in particular to a motor fault diagnosis and deterioration trend prediction method and system. Background technique [0002] As an important auxiliary machine and source of power in industrial fields such as power generation, chemical industry, shipbuilding, steel, and cement, electric motors play a pivotal role in the production process. The failure of key equipment motors directly affects the normal production of the enterprise, and causes an increase in maintenance costs, which in turn affects the economic benefits of the enterprise. [0003] Common motor faults such as broken rotor bars, stator winding faults and bearing faults. Motor fault diagnosis technology has been developed for decades, and many principles and methods have emerged. Among them, the mainstream methods are based on the principle of motor vibration signal analysis, based on the principle of motor electrical quantity a...

AI Technical Summary

Problems solved by technology

In this way, it is impossible to explain whether the motor is faulty through the spectrum characteristics, and its accuracy is low, and it is impossible to automatically generate a detailed fault report

It can only be judged whether the motor has a fault and its severity by manually analyzing the data source by technical experts and evaluating the fault index based on experience

At the same time, the current motor diagnosis method can only analyze the current state of the motor, and cannot predict the fault development trend. Although some scientific research institutions have proposed to build a model based on the neural network method to predict the fault development trend, this method needs to use a large number of various types of motors in advance. Manually train the model on samples with known fault characteristics, but this method is difficult to implement in practical applications

Images