Filtering-based intelligent fault detection method for motors in industrial field

Abstract

The invention discloses a filtering-based intelligent fault detection method for motors in the industrial field and belongs to the technical field of fault detection. According to the method, a set membership estimation method is utilized to represent a state feasible set by using vectors, so that prior knowledge of model disturbance and noise does not need to be known in advance, and the practicability and accuracy of the fault detection method are improved; in the solving process of an inversion filtering problem, vectors are used for representing interval boxes; the interval boxes belongingto the feasible set are searched for through the Boolean operation of vector sets, so that the problems of large calculated amount, and the exponential-level increase of calculation time along with increase of interval dimensions of a traditional interval filtering algorithm are solved, and a state interval is estimated more efficiently and accurately. Different from a traditional method for realizing fault detection by utilizing the upper and lower boundaries of estimation residual error, the method provided by the invention obtains the estimated interval of a fault, thereby providing guarantee for subsequent fault diagnosis of the motor by estimating the fault range.

Description

technical field [0001] The invention relates to a filter-based intelligent motor fault detection method in the industrial field, and belongs to the technical field of fault detection. Background technique [0002] The motor realizes the mechanization of production and manufacturing by converting electrical energy into mechanical energy, and is an indispensable part of current industrial production equipment. In order to meet the requirements of increasingly complex and integrated modern automatic control production equipment, real-time and accurate detection of motor faults is required to minimize losses. [0003] Traditional fault detection methods assume that noise and disturbance are variables that are known or satisfy a certain probability distribution when performing fault detection. On this basis, fault values ​​are estimated for fault detection. Noise is not a variable that is known or satisfies a certain probability distribution, but it is difficult to describe with...

AI Technical Summary

Problems solved by technology

[0003] Traditional fault detection methods assume that noise and disturbance are variables that are known or satisfy a certain probability distribution when performing fault detection. On this basis, fault values ​​are estimated for fault detection. Noise is not a variable that is known or satisfies a certain probability distribution, but it is difficult to describe with specific statistical characteristics, so it will lead to inaccurate detection results

[0004] In order to overcome the problem of inaccurate detection results caused by the fact that the disturbance and noise in the actual operating environment are not variables that are known or satisfy a certain probability distribution, the existing fault detection uses the set membership estimation method for fault detection, using spatial geometry, such as Intervals, ellipsoids, polytopes, etc. describe measurement data, disturbances, and noises, and judge faults by monitoring the consistency between the measured output of the motor and the predicted output of the motor model system, but this method has a large amount of calculation, low accuracy, and real-time gender issues

Images