Novel high-reliability slewing bearing service life evaluation method

Abstract

The invention discloses a novel high-reliability slewing bearing service life evaluation method. The method comprises the following steps of: extracting an effective average value of positive and negative vibration signals in a short time according to a denoised slewing bearing vibration acceleration signal to obtain time-space information data, and determining actual balance position informationof the slewing bearing; determining whether the average value of the positive and negative vibration signals has false fluctuation or not according to the obtained information of the actual balance position, if so, repairing the signal data, and subsequently obtaining two groups of time indexes through adoption of a smooth curve method; and establishing a relationship between the obtained index and the residual service life by utilizing the obtained high-quality time index and the fault index of the slewing bearing through a time and fault index hybrid embedded long-short-term memory network based on the generative adversarial network. According to the method, high-quality sample data are obtained under complex working conditions, the number of samples is increased, the reliability of lifeprediction under the complex working conditions is effectively improved, and the method has a certain application value.

Description

technical field [0001] The invention relates to a new high-reliability slewing bearing life evaluation method, which is a high-precision residual service life prediction method based on FT-LSTM. Specifically, it is combined with the spatial information of the slewing bearing to accurately identify the wrong fault information, and repair the false fluctuations to obtain high-quality vibration signal data, and then use the FT-LSTM method to obtain three sets of effective and reliable time and fault indicators. Establish a life model with space-time characteristics. The proposed GAN-FT-LSTM method can enhance the adaptive adjustment ability of the life prediction model and make the life prediction model of FT-LSTM more accurate. Background technique [0002] Slewing bearings are widely used in mechanical equipment and are called mechanical joints. Due to the large size of the slewing bearing, it will cause more serious problems when it fails. Minor failures can lead to reduc...

AI Technical Summary

Problems solved by technology

Accurate data and sufficient samples cannot be provided under complex working conditions, resulting in low reliability of the prediction results of existing technologies

Images