Automatic loader is one of the important part of the artillery autoloader device the system. The agency’s work is normal or not that directly related to the whole system operation state, and even the development of entire situation. It has a very important significance that classifies and recognizes the fault through timely finding faults and monitoring the state. It can also avoid unnecessary trouble and loss and provide a powerful guarantee for the victory of war. The work environment of automatic loader is very bad and the vibration is also obvious, which leads to the background noise in the signal is quite large. A part of the useful signals may be covered by strong noise. The traditional signal analysis methods may not reach the expected effect of the diagnosis. Here introduced current signal analysis, as MCSA. It uses induction motor stator current as a signal analysis the point, and studies the characteristics and the corresponding relation of failure. As a new method of fault diagnosis, it used in some other means inconvenience or easily found the problem the implementation of the occasion. This paper’s processing method is real-time monitoring the four sets of dc servo motor operation by hall current sensor. And it can also transfer the electrical signals to DASP signal collection system for post processing. In the later processing, it can classify all kinds of signal under the condition, and extract current signal characteristic parameters which are related. Finally it can use BP neural network to classify and diagnosis for fault.
[1]
Bengt Fornberg,et al.
Stabilization of RBF-generated finite difference methods for convective PDEs
,
2011,
J. Comput. Phys..
[2]
Jem A. Rongong,et al.
System identification methods for metal rubber devices
,
2013
.
[3]
Athakorn Kengpol,et al.
The expert system for assessing customer satisfaction on fragrance notes: Using artificial neural networks
,
2006,
Comput. Ind. Eng..
[4]
Jin-Sung Kim,et al.
An expert system using an extended AND-OR graph
,
2008,
Knowl. Based Syst..
[5]
Yunxiang Liu,et al.
The Concept of Approximation Based on Fuzzy Dominance Relation in Decision-Making
,
2003,
RSFDGrC.
[6]
Chen Degang,et al.
Local reduction of decision system with fuzzy rough sets
,
2010
.
[7]
Chee Peng Lim,et al.
A hybrid neural network model for rule generation and its application to process fault detection and diagnosis
,
2007,
Eng. Appl. Artif. Intell..
[8]
Celso Kazuyuki Morooka,et al.
Automatic Downhole Card Generation And Classification
,
1996
.
[9]
Jay Lee,et al.
On-line fault detection using integrated neural networks
,
1992,
Defense, Security, and Sensing.