Weak signal detection method based on self-adaptive stochastic resonance filter

Abstract

The invention discloses a weak signal detection method based on a self-adaptive stochastic resonance filter. According to the detection method, a sensor is installed on a bearing to be detected to acquire the vibration signals of the bearing, and then envelope demodulation is performed on the vibration signals so that the input signals Z[n] of the filter are obtained; and the filter parameters are adjusted by using a genetic algorithm to filter the Z[n] and the SQI value of the output signals is calculated and optimized. The detection method has the following advantages that firstly, self-adaptive enhancement of the bearing fault weak signals can be realized under the condition that the fault frequency is unknown; secondly, the detection method has a great filtering effect so that the high-frequency and low-frequency noise interference can be simultaneously filtered; and thirdly, the computing speed can be enhanced by the genetic algorithm so as to enhance the efficiency of bearing fault diagnosis.

Description

technical field [0001] The invention relates to the technical field of weak signal detection, in particular to a weak signal detection method based on an adaptive stochastic resonance filter. Background technique [0002] Bearing fault diagnosis is of great significance to ensure the safety of personnel and reduce economic losses. When a bearing fails, it will generate periodic impact vibration. By detecting the impact cycle in the signal collected by the sensor, it can be judged whether the bearing has a fault and the type of fault. However, the collected signal is full of a lot of noise, and the noise makes it difficult to extract and detect the periodic signal effectively. [0003] Stochastic resonance is a nonlinear method that can use noise to enhance weak signals. Its unique characteristics have been widely used in the field of weak signal detection such as bearing fault diagnosis. The stochastic resonance filter is used to filter the signal to extract the weak signa...

AI Technical Summary

Problems solved by technology

However, the traditional grid search method takes a lot of computing time to search for the optimal parameters of the filter, so the grid search method is inefficient and cannot quickly realize bearing fault diagnosis

[0004] It can be seen from the above that for the existing weak signal detection technology based on stochastic resonance filter, both the signal-to-noise ratio index and the grid search method have certain limitations, and how to achieve a universal and efficient technical solution still needs to be solved. Further Discussion

Images