Method, device and system for identifying health degradation state of mechanical device

Abstract

The invention discloses a method, device and system for identifying a health degradation state of a mechanical device, belonging to the field of mechanical state monitoring and health degradation state identification. The method for identifying the health degradation state of the mechanical device comprises the following steps: obtaining multiple monitoring signals of the mechanical device; extracting time domain features, power spectrum features and eigenmode energy features of the monitoring signals; then using a GSOM network to fuse the above features to obtain a fusion feature; then constructing a GenSVM model, and training the GenSVM model by means of the above fusion feature data, so as to obtain a test model; and finally, performing real-time collection on the multiple monitoring signals of the mechanical device to be tested, obtaining the fusion feature of the above signals, and inputting the fusion feature data into the test model to obtain a health degradation state identification result. The method for identifying the health degradation state of the mechanical device disclosed by the invention and the device and system based on the method for identifying the health degradation state of the mechanical device can accurately identify the health degradation state of the mechanical device in real time, realize real-time monitoring of the mechanical device state, and ensure the secure, stable and long-term operation of a numerically-controlled machine tool.

Description

technical field [0001] The invention belongs to the technical field of mechanical state monitoring and health degradation state identification, and specifically relates to a growing self-organizing map (growing self-organizing maps, GSOM) network and a generalized multiclass support vector machine (Generalized multiclass support vector machine, GenSVM) Machinery health degradation monitoring method, device and system. Background technique [0002] As the core production equipment in manufacturing, metallurgy, chemical industry, environmental protection and many other process production industries, mechanical equipment directly affects the production efficiency, product quality and maintenance cost of the enterprise, especially the sudden Faults and safety accidents often lead to the interruption of the entire production process and cause major production losses. Therefore, it is very important to identify the health degradation status of mechanical equipment in real time du...

AI Technical Summary

Problems solved by technology

However, when identifying the health degradation state of mechanical equipment, a single SVM model is only suitable for the identification of two types of degradation states, and cannot identify multiple

Images