Method and system for predictive maintenance based on motor parameters

Abstract

The invention discloses a method and a system for predictive maintenance based on motor parameters. The method starts from the local operation condition of the motor; two non-electrical acquisition parameters of temperature and vibration of the motor without direct connection are acquired for cross calculation. The real-time working state of the motor is mapped by adopting the matrix eigenvalue vector; the function relationship among the temperature, the vibration and the health degree of the motor can be realized, the linear change relationship between the local and comprehensive health degrees of the motor can be obtained, predictive maintenance is realized by judging the change trend of the health degree within a period of time, the diagnosis time of traditional motor fault diagnosis isadvanced, and irreversible damage to the motor can be well prevented. According to the method, the abnormal working state of the motor can be obtained more accurately, the statistical calculation flow is independent of the real-time calculation flow, the edge calculation pressure of acquisition equipment is reduced, and unnecessary hardware cost is avoided; and predictive maintenance can be positioned to a part of the motor, so that the manual detection cost is reduced.

Description

technical field [0001] The invention relates to a method and system for predictive maintenance based on motor parameters, belongs to the field of information, and is suitable for maintenance of industrial sites, engineering teaching equipment and equipment with motor devices. Background technique [0002] In terms of predictive maintenance of motors, the country is still in the tentative stage, and there is no outstanding solution that can realize a unified predictive maintenance platform for motors of various types and industries. In order to realize the construction of the predictive platform, the daily operating health of the motor must first be determined, which requires statistics and analysis of the daily operating parameters of the motor. The current motor maintenance is mostly based on fault diagnosis algorithms, and the relevant electrical parameters of the motor can be derived mathematically to judge its operating status. This kind of algorithm, first, requires hi...

AI Technical Summary

Problems solved by technology

This kind of algorithm, first, requires high real-time performance, requires real-time collection and real-time calculation, and requires a large number of mathematical calculations in the collection equipment. The calculation here includes not only calculating the input data of the algorithm from the collected data, but also Including the calculation of the algorithm itself, in order to better maintain the effect, this kind of calculation has high requirements on the hardware of the acquisition equipment. If a large number of equipment needs to be collected, the cost will be doubled; second, this type of algorithm often produces acute Fault diagnosis can only be performed when there is a sudden fault. If the health of the motor is regarded as a value between 0 and 100, when the traditional fault diagnosis algorithm is applied, the change of the health of the motor is often a sudden decrease of a discrete value, which makes the equipment diagnosis The time from failure to irreversible damage to the equipment is too short, which is not conducive to the fault tolerance of the motor; third, the traditional fault diagnosis method often only judges the threshold value of one parameter, its accuracy is not high, and its robustness is poor

Images