Rotary motor state monitoring method based on support vector machine and data driving

Abstract

The invention discloses a rotary motor state monitoring method based on a support vector machine and data driving. The method comprises a step of collecting a rotary motor vibration signal, using curve fitting vibration information to predict rotary motor acceleration and speed operation states, and evaluating a motor state according to indexes of an error, motor performance and the like, a step of installing an acquisition node on a shell of rotary motor, obtaining a three-axis vibration signal of a monitoring motor and environment temperature and humidity in real time, transmitting the signal and the environment temperature and humidity to a receiving end through the IOT (Internet of things) wireless communication technology, storing the signal and the environment temperature and humidity to a database from the receiving end, and calculating each node speed spectrogram and other information by using wavelet analysis and an ARIMA model or other time series prediction methods to obtain a prediction curve, a step of adding historical error compensation to get an accurate prediction value, and comparing the prediction value with a true value to get an error at the moment. The error is taken as a main characteristic of the support vector machine, and a fault judgment is made with the combination of temperature, motor power, rotation speed and other auxiliary characteristics.

Description

technical field [0001] The invention relates to a state monitoring method of a rotating electrical machine based on a support vector machine and data drive, which is used for detection, diagnosis and early warning of vibration signals of rotating electrical equipment in various factories. Background technique [0002] As the core component, the electric motor is widely used in various occasions of the production site. There are many classifications of motors, such as servo motors, stepper motors, DC motors, etc., and the basic principle is to convert electrical energy into mechanical energy to generate drive torque and apply it in all aspects of production. In actual production and use, a factory often needs to use several large, medium and small motors. There are motors ranging from 100 to 10,000 revolutions per minute, and the working environment of the same type of motor may be different, so The difference in the model of the motor and the use environment of the motor wi...

AI Technical Summary

Problems solved by technology

This method relies on the experience of the maintenance personnel and the understanding of the rotating motor. The disadvantage is that it also increases the production cost of the enterprise, and the maintenance personnel cannot make different judgments according to different types of motors, and cannot save the data to the server. Comprehensive management consumes a lot of manpower and material resources, and it is impossible to predict and deal with failures in time

Images