Fault diagnosis method of reciprocating compressor based on closed spherical solution of improved spherical vector machine

Abstract

The invention discloses a fault diagnosis method for a reciprocating compressor based on an improved spherical vector machine closure sphere solution. The data of different operating conditions of the reciprocating compressor are collected as a training set. When using the spherical vector machine algorithm to solve the closed sphere problem, When looking for the farthest point in the training set, the dot product of the cache point and the center of the sphere is used to calculate the distance between the same point and the center of the sphere after the center of the sphere is updated a certain number of times; when looking for the farthest point, some non-farthest points are excluded; point The change of the product solution method makes the solution of the distance between the point and the center of the sphere no longer related to the support vector, and chooses to update the support vector weight every certain number of times; when there are too many support vectors, increase the number of times to find the farthest point in the support vector set, Through these strategies, the establishment of the fault diagnosis classification model can be completed in a short period of time. The diagnostic model is tested by the collected test data, and the diagnostic model has high accuracy, which can efficiently complete the fault diagnosis of the reciprocating compressor.

Description

technical field [0001] The invention belongs to a fault diagnosis method, in particular to a fault diagnosis method for a reciprocating compressor based on an improved spherical vector machine closure sphere 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 once they fail, 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 diagnostic algorithms. The traditional fault diagnosis algorithm is difficult to meet the actual production needs, and the general intelligent diagnosis algorithm used in the fault diagnosis of the compressor usually has the disadvantages of long tr...

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