Machine fault detection, classification and grading method based on neural network unified modeling

Abstract

The invention relates to a machine fault detection, classification and grading method based on neural network unified modeling, and belongs to the technical field of machine fault detection methods and artificial intelligence. Firstly, the rotating speed, temperature, vibration and sound of a to-be-tested machine in the operation process are collected, sample annotation is added to sample featuresaccording to a machine fault annotation log and fault grade duration, and a classified and graded fault sample set is generated; samples are randomly extracted from the samples in the fault-free state to form a fault-free sample set, wherein the fault sample set and the fault-free sample set form a complete machine state sample set. The fault types and levels are coded according to a binary mode,and codes of different types and different levels are spliced into a code with unified fault detection, classification and grading. A deep neural network model is established and trained in a unifiedmanner, the model obtained through training has higher diagnosis accuracy and prediction capability, and grading results of various fault types can be diagnosed at the same time under the condition that various fault types coexist.

Description

technical field [0001] The invention relates to a machine fault detection, classification and grading method based on neural network unified modeling, which belongs to the field of machine fault detection method technology and artificial intelligence technology. Background technique [0002] A large number of key machinery and equipment in industrial production, especially the key machinery and equipment of assembly line operations, cannot be shut down for maintenance during a production cycle. Unexpected shutdown will cause major production accidents. For the operation and maintenance of these key machinery and equipment, the traditional way is to adopt a planned maintenance plan. The planned maintenance scheme does not consider the actual running state of the machine, so there is a problem that the machine in good condition is shut down for maintenance (over-maintenance), while the machine on the verge of failure is ignored (under-maintenance). The dangers of under-mainte...

AI Technical Summary

Problems solved by technology

However, since the artificial intelligence model requires targeted training for different devices, each monitoring and diagnosis solution requires a long period of data accumulation before it is officially launched.

Moreover, since the training samples are completely marked by h

Images