Fault diagnosis method and system of integrated processing platform of angular acceleration signals

Abstract

The invention discloses a fault diagnosis method and system of an integrated processing platform of angular acceleration signals. Compared with the prior art, the method has the advantages that faultdetection is not only performed on a sensor, the fault detection is also performed on an integrated control platform to remove the interference of a hardware system, so that the fault diagnosis of thesensor is more reliable; angular acceleration sensor data are processed by adopting wavelet decomposition, an original signal can be decomposed into components of different frequency bands, so that fault features can be better characterized more detailed in the frequency domain, and the fault diagnosis accuracy can be improved; the adopted Bayesian regularization algorithm is a modification of the Levenberg-Marquardt algorithm, which can well improve the generalization ability of a neural network and optimize the structure of the neural network, thus improving the performance of the neural network.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, and in particular relates to a fault diagnosis method and system of an angular acceleration signal comprehensive processing platform. Background technique [0002] Angular accelerometers are widely used in military, industrial and other fields, and play an important role in the control of various equipment. Therefore, it is very important to detect and deal with the fault of the angular acceleration signal in time. The fault diagnosis expert system of the angular acceleration signal comprehensive processing platform is designed to be able to collect angular acceleration sensor signals in multiple channels, and to diagnose the faults of the sensor and the comprehensive processing platform. In the search for the existing sensor fault diagnosis method, it was found that the invention patent, CN 102680017 A, "a sensor fault diagnosis method and diagnostic device" mentioned a sensor fault dia...

AI Technical Summary

Problems solved by technology

In the search for the existing sensor fault diagnosis method, it was found that the invention patent, CN 102680017 A, "a sensor fault diagnosis method and diagnostic device" mentioned a sensor fault diagnosis method and diagnostic device, but found from the patent, It is only aimed at the sudden failure of the sensor, ignoring the failure of the device, and the fault characteristic parameters obtained by using the wavelet packet decomposition method are not necessarily applicable to the angular acceleration signal

In addition, the artificial neural network is a common method for fault diagnosis, but the traditional BP neural network has the disadvantages of slow convergence speed and easy to fall into local optimal solution.

Images