Fault diagnosis method based on HBF neural network observer

Abstract

The invention provides a fault diagnosis method based on an HBF neural network observer. The fault diagnosis method is used for conducting intelligent fault diagnosis. According to the method, an HBF neural network is adopted, the similarity between vectors can be signified through the Mahalanobis-like distance, the neuron number and the calculating speed are lowered, meanwhile, the neural network state observer is established, an abstracted non-linear system in engineering is observed, the system output prediction in the next step can be conducted through the output value of the state observer, and thus system fault diagnosis and detection can be achieved.

Description

technical field [0001] The invention designs a neural network fault diagnosis and detection method, in particular relates to a fault diagnosis method based on an HBF neural network observer, and belongs to the technical field of pattern recognition. Background technique [0002] The development of fault diagnosis technology has mainly gone through three stages: manual diagnosis, modern diagnosis and intelligent diagnosis. So far, fault diagnosis methods can be divided into methods based on analytical models, methods based on signal processing and methods based on knowledge. With the development of science and technology, the system is becoming more and more complex, relying solely on traditional fault diagnosis methods based on mathematical models can no longer meet the reliability requirements of equipment, so intelligent fault diagnosis technology is getting more and more attention in various fields, especially in control In the field, such as the annual control meeting i...

AI Technical Summary

Problems solved by technology

[0020] The object of the present invention is to provide a kind of fault diagnosis method based on HBF neural network observer, to solve problems such as poor generalization ability and complicated calculation in the traditional neural network fault diagnosis method, reduce the number of neurons and the complexity of the network, Provides a new method for improving detection efficiency and accuracy

Images