Research on Fault Diagnosis System of Mine Ventilator
Based on Elman Neural Network
Ren Zihui, Li Jiangang, Liu Yanxia*
(College of Information and Electrical Engineering, 5 CUMT, JiangSu XuZhou 221116)
Brief author introduction:Ren Zihui, (1962-), male, Ph.D., Professor, is mainly engaged in electrical and
mechanical equipment condition monitoring and fault diagnosis, harmonic direction of mine. E-mail:
ckljg@163.com
Abstract: This paper introduced the theory, learning algorithm and technical route of Elman neural.
Though acquainting fault signals on-site and normalizing characteristic data, this method realized
intelligent diagnosis of ventilator by constructing optimum structure and parameters based on Elman
neural network. Compared with the traditional BP neural network, Elman network had a better
10 comprehensive performance in diagnosis of ventilator. The result for the fault diagnosis of a ventilator
showed that the Elman network improves the study speed, represses the network to sink local minimum,
shortens the study time, and Elman neural is a effective method for the fault diagnosis of ventilator.
Keywords: mine ventilator; Elman neural network; fault diagnosis
15 0 Introduction
As one the most important part of four pieces in the coal mine, the main ventilator takes the
task of methane drainage, offering fresh air to mine Laneway. The reliability of its running
directly affects the security and stability of the production equipment. As a result, the fault
diagnosis of ventilator is a key way to increase reliability of the system. However, due to the
20 highly nonlinear relationship between symptoms and faults, it’s difficult to use the mathematical
model of a linear relationship to locate the fault diagnosis. The artificial neural network has the
capabilities of arbitrary accuracy, self-organization, self-learning and parallel processing for any
continuous nonlinear approximation, so it has been widely used in fault diagnosis. Neural network
for fault diagnosis of the main fan can establish a reliable sample database and has sufficient
25 capacity to improve the efficiency and accuracy of the fault diagnosis [1]. This paper introduces a
neural network of fault diagnosis based on Elman has been achieved good results in the fault
identification of ventilator diagnosis. The capabilities of network structure, training speed and
generalization of Elman neural network are better than the traditional BP neural network.