Research On Wavelet Neural Network In Coal Mine Ventilator Status Monitoring Base On LabVIEW

The coal mine ventilator system is called"the mine pit lung"in the mine production. The coal mine ventilator system may dilute density of the gas, forestall trouble's occurrence, its working condition, it's performance relate staff's personal safety and the production benefit. Therefore, ventilator's safe operation is focus for technical personnel and the coal mine administrative personnels. The monitor,monitoring and the failure diagnosis of mine pit main ventilator's have made the unprecedented progress.The paper discusses about how to research a vibration fault diagnosis system on Wavelet Neural Network (WNN) based on Virtual Instrument (VI). As the fault signal is non-stationary, transient one, In view of the superiority of Wavelet Transform to non-stationary signal,we introduce the principle of wavelet to eliminate signal noise and extract its features. Firstly, we use Mallat algorithm based on principle of mufti-resolution to eliminate vibration, and then decompose and reform the vibration signal, deal with the coefficient of high-frequency, extracting the characteristic vectors as the input signal of the neural network. Using the MATLAB script in LabVIEW, which offers a better solution of realizing the function.Secondly, this paper gives a kind of improved algorithm about self-accommodation learning speed, which we use to diagnose fault and do the noise pattern recognition. Comparing standard BP algorithm with the improve one, we find that using the improved method will improve the accuracy of prediction error, Significantly accelerate the network convergence speed,so we conclude that the improved algorithm can effectively work the system.At last this paper gives a way to use VI to finish the diagnosis work, introduces the vibration fault diagnosis system based on LabVIEW The paper discusses how to research on software design, introduces the process of design, operation instruction, and interface of each function module. The result indicates that using this system can satisfy the request of vibration testing and diagnosis, and offer advanced theory and practical basis in the field of he coal mine ventilator diagnosis.