A Life Prediction Method for Air Compressor

Abstract

The present invention provides a life prediction method for an air compressor, including: S1, collecting vibration data and current data of the air compressor, the vibration data is the total energy value OA, OA is the total energy value Overall l Value, and the current data Including the maximum value, minimum value and average value of the current per unit time; S2, processing vibration data and current data; S3, performing feature engineering on the processed vibration data and current data to generate training data; S4, training data Carry out the training of the convolutional neural network algorithm CNN and the long-term short-term memory artificial neural network algorithm LSTM; S5, save the trained life prediction model to an H5 file, which is the fifth generation version of the hierarchical data format; S6, use Python The Flask framework packages the life prediction model into a Web service for other related applications to call.

Description

technical field [0001] The present invention relates to the technical field of air compressor control, and in particular, the present invention relates to a life prediction method for an air compressor. Background technique [0002] Among the many energy sources used, compressed air is one of the most popular energy sources after electricity. Industry, mining, engineering, medical and agriculture are all used more and more widely, especially in industry, where the amount of use is extremely considerable. In view of the fact that air compressors have been widely used in all walks of life, under the premise of large-scale and automatic factories, the diagnosis of air compressor faults has also been developed accordingly. [0003] Traditional air compressor fault diagnosis methods include traditional manual inspection methods, regular maintenance and expert diagnosis systems. Traditional manual inspection is not predictive and can only be processed afterwards; the expert diag...

AI Technical Summary

Problems solved by technology

Traditional manual inspection is not predictive and can only be processed afterwards; the expert diagnosis system uses the knowledge base and inference engine to complete fault location and diagnosis, but the knowledge base is updated slowly and the system lacks generalization; the intelligent algorithm system can predict the cause of the fault in advance, Adaptable, but requires a large number of experimental sample data, and it is impossible to predict how long it will fail

Images