Research On Fault Diagnosis Of Shearer Bearing Based On ASGSO-RBF Algorithm

Coal resources has a very important position and role in Chinese energy system structure. As the key equipment of coal mine production process, sheareris a complex machine, which is a mechanical, electronic, electric, hydraulic, and so on. The shearerequipment safe and stable operation is very important for ensuring the safety of coal production and promoting enterprise production efficiency. Because sheareris often in wet, dust particles, electromagnetic interference and other complex downhole environment, bearing damage and other shearerkey parts failure often happens to shearer. Once such failure occurs, will lead to the entire coal mine production process stagnation, and even paralysis. For shearer rolling bearing fault, this paper in-depth research and analysis of shearer in the running environment, characteristics and influencing factors resulting in bearing fault of Shearer Based on, put forward a kind of the RBF neural network combined with self-adaptive step glowworm swarm optimization (ASGSO)algorithm to realize the effective identification of bearing fault of shearer nonlinear system.The RBF neural network provides great time-varying data processing ability and network stability. So, it can directly better represent the dynamic properties of the essential non-linear system. On the basis of wavelet packet and RBF neural network, put forward the method of shearer bearing fault diagnosis that resolve and draw energy spectrum of characteristic from each node by wavelet packet and optimize RBF neural network by self-adaptive step glowworm swarm optimization algorithm. Of vibration sensor output signal wavelet packet decomposition, using their cost function based on local discriminant basis (LDB) algorithm to cut of wavelet packet decomposition, to obtain the optimal characteristics of energy spectrum, the processed as a feature vector training ASGSO-RBF neural network, the diagnosis model is established.The online fast and accurate search for the RBF weights, centers and widths in the solution space is done due to the great global multi-target search ability of the enhanced ASGSO algorithm. With the identification theory, The identification system of shearer bearing fault is proposed by using the ASGSO-RBF coupling algorithm. The identification experiments are performed with the monitored history-data of the pits. The results demonstrate that in the context of higher learning efficiency, it greatly outperforms the pure RBF neural network, the GSO-RBF coupling model and the BP neural network commonly used in the engineering in terms of identification accuracy and generalization. Furthermore, the proposed method is highly robust and thus theoretically helpful to the prevention and relief of the shearer trouble disasters.