Electromechanical equipment state data completion and prediction method based on multi-scale sampling

Abstract

The invention discloses an electromechanical equipment state data completion and prediction method based on multi-scale sampling, and relates to the technical field of data processing. The electromechanical equipment state data completion and prediction method based on multi-scale sampling comprises the following steps: S1, acquiring working condition data in a working process of electromechanicalequipment by adopting an intelligent sensor, and constructing a working condition data set D. According to the electromechanical equipment state data completion and prediction method based on multi-scale sampling, a multi-scale sampling thought is adopted to extract a plurality of time sequences from the data set, feature learning is carried out from different time scales; the prediction precision and stability are improved through a voting scoring strategy, meanwhile, a generative adversarial network is adopted, sample completion is conducted on a data set, a loss function of the generativeadversarial network is improved, training stability and efficiency are improved, completed samples are selected based on the voting scoring strategy, and low-quality generated samples are removed.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for complementing and predicting state data of electromechanical equipment based on multi-scale sampling. Background technique [0002] Electromechanical equipment usually works in a normal state, and there are few sample data in the fault state that can be collected, which is prone to the problem of unbalanced data sets, that is, the sample data set DG in the normal state is much larger than the sample data set DF in the fault state. The problem of data imbalance caused by the lack of fault state sample data seriously affects the accuracy of equipment state prediction. [0003] The traditional way to expand the sample data set is over-sampling, but over-sampling just completely copy and reuse a small amount of sample information in DF, and cannot automatically learn the data distribution characteristics of samples. Therefore, how to expand and complement the sa...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the existing technology, the present invention provides a method for complementing and predicting the status data of electromechanical equipment based on multi-scale sampling, which solves the problem that the traditional method of expanding sample data sets is oversampling, but oversampling is just copying and reusing DF A small amount of sample information in the system cannot automatically learn the data distribution characteristics of the sample, and it is difficult to expand and complement the sample data in the fault state.

Images