The Application Of Wavelet Support Vector Machine Based On LabVIEW In Coal Mine Ventilator Fault Prediction

As the first problem when facing the coal mine safety which is an important safety issue in coal mining, gas outburst can be predicted so effectively by coal mine ventilation system. For this reason the prediction of the coal mine ventilator fault is of great significance to exclude the danger of gas outburst and keep the safety of coal mine and also available to maintain the normal order of coal mining and reduce the excessive service and lesson the expense of service. The fault of coal mine ventilation is mainly predicted in this article; at the same time a software platform in view of LabVIEW is developed to achieve the online prediction of mine ventilator fault.An early fault prediction method of combining wavelet and support vector machine of coal mine ventilator is proposed in this paper in view of the important role of coal mine ventilator as well as the actual demand not satisfied by online monitoring and fault diagnosis technology. What’s more, the failure of the coal mine ventilator accompanied by a large number of time-vary and burst signal can be conquered by the wavelet transform with the ability to deal with no stationary signals. In this paper, the vibration signal is processed by wavelet decomposition to decompose the vibration time sequence signal in accordance with the scale of coal mine ventilator, and the support vector machine method is used for prediction. In the meantime, combined with virtual machine technology, the result is shown in LabVIEW software platform to prove the superiority of the wavelet support vector machine prediction method by contrasting with the AR model, according to which the theoretical significance for coal mine ventilator failure prediction into practice can be seen.The practical and reliable prediction method for analyzing and forecasting the fault of ventilation can be provided through the study in this article, but also, the monitoring functions is improved and the theory of fault diagnosis of ventilation is enriched, which has an important theoretical significance. Again with the communication of large rotating machinery and equipment, the prediction method of this paper is same to be applied to other equipment for failure prediction, which has great application value for improving the accuracy.