Vibration signal compression method and device

Abstract

The invention provides a vibration signal compression method and device. The vibration signal compression method is applied to the technical field of data signal compression, and comprises the steps of: acquiring he first vibration signal data of a target mechanical part; and compressing the first vibration signal data based on a trained preset stacked auto-encoder to obtain compressed vibration signal data of the target mechanical part, wherein the preset stacked auto-encoder comprises a plurality of auto-encoders, each auto-encoder comprises an encoder and a decoder, and a processing layer of each encoder comprises a first convolution layer, a first activation function layer, a first batch standardization layers, a second convolution layer, a second activation function layer, a second batch standardization layers and a Flatten layer which are connected in sequence, and a processing layer of each decoder comprises a first full connection layer, a third activation function layer, a third batch standardization layer and a second full connection layer which are connected in sequence. According to the vibration signal compression method and the device provided by the invention, the vibration signal compression precision can be improved while the calculation workload of the auto-encoders is reduced.

Description

technical field [0001] The invention belongs to the technical field of signal data compression, and more specifically relates to a vibration signal compression method and device. Background technique [0002] With the development of high-speed and large-scale mechanical equipment, the vibration frequency of mechanical equipment is getting higher and higher, and the vibration signal is nonlinear and non-stationary. According to the Nyquist sampling theorem, the sampling frequency cannot be lower than twice the vibration signal of the original mechanical equipment. Therefore, mechanical equipment will generate massive amounts of data during health testing, which poses challenges to real-time transmission, synchronous storage and real-time fault diagnosis. With the development of deep learning, many scholars consider applying stacked autoencoders to the compression of vibration signal data. [0003] However, the vibration signal compression method based on stacked autoencoder...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a vibration signal compression method and device, aiming at reducing the calculation amount of the stacked autoencoder and improving the vibration signal compression accuracy, and solving the large calculation amount and large error technology of the vibration signal data compression in the prior art question

Images