Research on Early Fault Diagnosis of the Main Carrying Structure of Vibrating Screen

The large-scale vibrating screen has been applied widely in coal industry and other industrial areas as a kind of important device. As vibration mechanical device, it works very hardly and works in very bad environment so that the structure of screen is damaged easily. Therefore, it is very important that how to detect the fault of structure as early as possible to make the repair schedule reasonably and economically and to avoid the body hurt and device damage. As a kind of important structure of vibrating screen, the lower crossbeam is the main carrying structure and it is easily damaged, so it is regarded as a researched object in this thesis and it is tested under the load in the laboratory. Based on the test, acoustic emission wave signals can be got-ten by modern acoustic emission testing technique. Then, the ?wavelet packet - energy? from the characteristics of acquiring signals is used as neural network input vector. In the BP network structure design, the design of a hidden layer with variable number of BP network is established. Based on the error by contrast, the best nerve number can be identified in the hidden layer. Through integrated analysis, using Levenberg-Marquard BP study algorithm, network-training errors are relatively small, the acoustic emission signal is used in BP neural network as a pattern of recognition. In Matlab6.5, neural network model identification is created and taking advantage of nonlinearity and the ability of learning and memory of Neural Network, this model is fixed by training structure of network with training samples. The work presented shows that acoustical emission signal processing and research on early fatigue fault diagnosis based on the wavelet and the neural network is viable.