Application Of Gearbox Fault Diagnosis In The Safe Production

With the development of science and technology, high performance, high efficiency, high automation and high reliability have become the tendency of mechanical equipments. Because of the advantages of the fixed transmission ratio, the lager transmission torque and the compact structure, the gear case is widely applied to adjusting velocity and transferring power. Although gear is an important component of machine equipments, it arises some faults frequently, which leads to poor performance of the whole machine in operating condition. In the fault diagnosis of the gearbox ,to pick up the fault information effectively and judge the fault property and origin properly, selecting the valid signal process and fault diagnosis method is the key to the success or failure of the diagnosis, the improving diagnosis sensitivity.In this paper, based on the analysis of the traditional diagnosis method, the face of the intelligent diagnosis of the gearbox is explored valuably, the technology of the artificial neural networks theory is applied to the fault diagnosis of the gearbox. In this paper, based on the analysis of present research situation, the fault mechanism and diagnosis method of the gearbox in the practical state of work are studied.The type of the gearbox is JZQ250 and made as test objects. Firstly, based on the fault Mechanism and vibration trait of the gearbox in the practical state of work, the experiment Project on condition testing and fault diagnosis of the gearbox is designed, the vibration Signals of the gearbox are tested. Then with modularized programming thought the neural network predicting model is realized by using the neural network toolbox in MATLAB. The experiment is done by using the kurtosis index of data. Given the neural network input and target output, the weight and bias value are obtained after training, at last the neural network model is established, which is applied to predicting the gearbox fault tendency. From the result of simulation and experience in the dissertation, we can see the model can effectively predict the typical fault of gearbox and can be applied to the fault diagnosis of gearbox.