Reciprocating compressor fault diagnosis method based on improved ball vector machine closure ball solution acquisition

Abstract

The invention discloses a reciprocating compressor fault diagnosis method based on improved ball vector machine closure ball solution acquisition. Data of a reciprocating compressor operated under different working conditions are acquired to serve as a training set, when a ball vector machine algorithm is used for solving a closure ball problem, the dot product between a dot and a sphere center is cached when the training set is searched for the farthest dot, and the dot product is used for calculating the distance between the same dot and the sphere center after the sphere center is updated certain times; when the training set is searched for the farthest dot, part of non-farthest dots are eliminated; the solution of the distance between the dot and the sphere center is not related to support vectors any more through the change of a dot product solution mode and the support vector weights are updated once every certain times; when the number of the support vectors is too large, the times of searches for the farthest dot in a support vector set are increased. Through the strategies, a fault diagnosis classification model can be established within short time, the diagnosis model is detected through the acquired test data, it can be known that the diagnosis model is high in accuracy, and fault diagnosis of the reciprocating compressor can be finished efficiently.

Description

Technical field [0001] The invention belongs to a fault diagnosis method, and in particular relates to a fault diagnosis method for a reciprocating compressor based on an improved ball vector machine closed ball solution (IEBVM). Background technique [0002] As a key mechanical equipment in the production process, reciprocating compressors may fail to operate normally, shut down or even cause serious production accidents, causing huge economic losses, environmental losses, and even casualties. Due to the increasingly complex structure of reciprocating compressors, the state information required for fault diagnosis increases, and the detection data increases, which increases the difficulty of establishing models through diagnosis algorithms. Traditional fault diagnosis algorithms are difficult to meet actual production needs, while general intelligent diagnosis algorithms used for compressor fault diagnosis usually have the disadvantages of long training time and insufficient dia...

AI Technical Summary

Problems solved by technology

However, when the data scale is too large, the training time is still relatively long. When the BVM algorithm is used for the fault diagnosis of reciprocating compressors, the training effect needs to be further improved to meet the actual diagnosis needs.

In the process of solving the closure sphere, the most time-consuming part of the BVM algorithm is the distance from the solution point to the center of the closure sphere. A certain number of points are sampled in the training set each time to determine the point farthest from the center of the sphere. Update the center of the ball, and after updating the center of the ball several times, the distance from the same point to the center of the ball needs to be solved again, and the original distance has not been fully utilized

The solution of the distance is directly related to the number of support vectors. When the scale of the data set is large, the number of support vectors is bound to be large, which makes the calculation of the distance more time-consuming. Due to the complex structure of the reciprocating compressor, The fault data has a high dimension and a large number, and the time required for fault diagnosis using the ball vector machine algorithm is also relatively large

Images