An Adaptive Fault Diagnosis Method Based on One-Dimensional Convolutional Neural Network

Abstract

The invention discloses an adaptive fault diagnosis method based on a one-dimensional convolutional neural network, which uses a one-dimensional convolutional neural network as the main model structure, directly inputs a one-dimensional time series signal, and can immediately output a high-precision diagnosis result. It is more convenient and efficient than the traditional way of manually extracting features for diagnosis, and requires less professional knowledge and experience for diagnostic personnel; at the same time, compared with fault diagnosis methods based on other neural network structures, the one-dimensional convolutional neural network model maintains diagnostic accuracy. At the same time, the model is simpler and the calculation is faster, which can provide a good guarantee for real-time fault diagnosis. As a real-time and rapid self-adaptive fault diagnosis method, the present invention can calmly deal with the diversity of fault types, and can be widely used in the fields of machinery manufacturing, aerospace, electrical, metallurgy and the like.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis and computer artificial intelligence, in particular to a method for fault diagnosis of mechanical equipment and parts based on artificial intelligence convolutional neural network (CNN). Background technique [0002] Existing mechanical equipment and parts are developing in the direction of high speed, high efficiency, and precision. However, in actual operation, the working conditions are complicated, and it is often necessary to analyze and troubleshoot equipment performance and potential faults to achieve early detection, Early detection, early avoidance. Among them, key components of mechanical equipment such as gears, bearings, compressor valves, and motors are often the key objects in the field of mechanical fault diagnosis and monitoring. In this field, traditional time-frequency analysis and other methods have achieved good results in small data environments and single-fault tasks...

AI Technical Summary

Problems solved by technology

When many devices are running, a second late diagnosis will bring incalculable losses. Every second must be counted, and the operating status of the diagnostic devices can be detected and diagnosed in a timely and accurate manner.

Images