Fault diagnostic method and diagnostic device of sensor

Abstract

The invention embodiment discloses a fault diagnostic method and diagnostic device of a sensor. The method includes the following steps: receiving output signals of the sensor; utilizing a wavelet packet to analyze the output signals; screening the conversion coefficient of the wavelet packet with the maximum amplitude, so as to reserve the data capable of representing the fault features; performing feature extraction according to the change rate of the component energies of the frequencies of the sensor, so as to obtain feature vectors; and inputting the feature vectors into a specified neural network, so as to obtain the fault type of the sensor, wherein the node number of the input and output layers of the neural network are determined by the dimension numbers of the feature vectors and the fault type numbers of the sensor respectively, and the network weight and the threshold are determined by training through a training sample. The fault diagnostic method and diagnostic device adopt the wavelet packet to perform refinement partition of the dynamic signals of the sensor, and determine the fault type of the sensor according to the output of the neural network, so as to effectively diagnose the catastrophic fault of the sensor.

Description

technical field [0001] The invention relates to the field of sensor fault diagnosis, in particular to a sensor fault diagnosis method and a diagnostic device. Background technique [0002] Sensors composed of precision components often work in harsh environments such as high temperature, high pressure, vibration, shock, pollution, electromagnetic interference, etc., making the sensor prone to failure, causing distortion of the output signal, and affecting the accuracy, stability and reliability of signal acquisition , and then affect the performance of the entire control system, and even pose a threat to the safety of vehicles. Therefore, the fault diagnosis of sensors is an important means to improve the reliability of control systems such as vehicles. According to the manifestations of sensor faults, they can be divided into slow-change faults and sudden-change faults. The present invention only relates to the diagnosis of sudden faults in sensors. [0003] When the sens...

AI Technical Summary

Problems solved by technology

In the prior art, the traditional fault diagnosis method based on signal analysis is based on Fourier transform. The inventor found in the process of realizing the present invention that although Fourier transform can effectively analyze stationary signals, what it uses is a The global transformation is either completely in the time domain or completely in the frequency domain, so it cannot express the time-frequency local properties of the signal, and this property is precisely the most fundamental and critical property of non-stationary signals

Therefore, there are great limitations in diagnosing sensor mutation faults with traditional signal analysis methods

Images