Rapid fault detection method and system based on normal wave energy ratio theory

Abstract

The invention discloses a fault rapid detection method and system based on a normal wave energy ratio theory. The method comprises the following steps: carrying out sound source signal simulation recombination according to sound source physical characteristics to obtain a simulation sound source signal; performing sound propagation process simulation according to the sound source position information to obtain a sound pressure value of a sound source reconstruction signal at the receiver; obtaining each normal wave energy distribution characteristic of the sound source reconstruction signal by inputting the sound pressure value of the sound source reconstruction signal and utilizing a normal wave energy ratio theory; training a deep learning model by taking each normal wave energy distribution feature and a fault physical feature as a training set; and utilizing the trained deep learning model to identify the fault type of a real acquisition signal. According to the invention, fault physical structures can be in one-to-one correspondence with sound signal features by using a sound source reconstruction technology; sound field rapid calculation in sound transmission is realized by using a normal wave-parabolic coupling theory; and features are extracted by adopting a normal wave energy ratio theory, so that rapid model training and rapid fault identification are realized.

Description

technical field [0001] The invention belongs to the field of industrial acoustic fault diagnosis, and in particular relates to a fast fault detection method and system based on the normal wave energy ratio theory. Background technique [0002] Real-time monitoring of the working status of large-scale industrial equipment and the prevention of accidents are crucial to modern production. Traditional monitoring solutions such as infrared monitoring, vibration monitoring, and thermal monitoring have obvious disadvantages. If the equipment needs to be pre-installed before leaving the factory, or the equipment needs to be modified later, the deployment cost, time cost, and decision-making cost are all high. Acoustic monitoring has gradually become one of the core solutions to solve fault diagnosis problems due to its non-invasive monitoring, low operating cost, and simple operation. Acoustic monitoring provides a non-contact technical path for the fault diagnosis industry. [000...

AI Technical Summary

Problems solved by technology

The advantage of manual detection is that it can collect the acoustic signal at the specified location of the target device in a targeted manner, so that it is convenient to capture key characteristic data during data processing and analysis, but the disadvantages of this method are also obvious, relying on human operation, and not flexible enough It is also impossible to monitor in real time

There are also some automatic real-time detection attempts in the prior art, but according to the work of the current named inventor, there are at least the following problems in the prior art: the correlation between sound source feature extraction and fault detection is not close, and the detection is accurate There is still much room for improvement

Images