Application of Fuzzy SOFM Neural Network and Rough Set Theory on Fault Diagnosis for Rotating Machinery

Rough set theory is a useful tool for attribute reduction of fault diagnosis for rotating machinery, but cannot be efficiently used to sample increased areas. Aiming at the problem of incremental attribute reduction, a novel attribute reduction algorithm was put forward based on the binary resolution matrix for the two updating situations and the algorithm had a low space complex. Finally, with the fault diagnosis experiments of the bearing, the attribute reduction method was proved to be correct.

Download Full-text

Diesel Engine Fault Diagnosis Based on Rough Sets

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.722.276 ◽

2013 ◽

Vol 722 ◽

pp. 276-281

Author(s):

Hong Xia Pan ◽

Jing Yi Tian

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Diesel Engine ◽

Set Theory ◽

Rough Set ◽

Cylinder Head ◽

Rough Set Theory ◽

Vibration Signal ◽

Fault Classification ◽

The Neural Network

This paper introduces the rough set theory and ROSETTA software characteristics, gives a diesel engine fault diagnosis system based on rough set theory and the vibration signal of cylinder head. Taking a certain type large power diesel engine as an example, the first to be extracted from the cylinder head vibration signal wavelet packet de-noising and time-frequency domain analysis, constructed eigenvalue for fault diagnosis, then use ROSETTA software reduction feature attributes, finally completed fault pattern classification through the neural network. By comparing the output results of the neural network before and after processing by the ROSETTA software, show that rough set theory can optimize the feature attributes, effectively reduce the input of the neural network nodes, and improve the fault classification accuracy.

Download Full-text

Novel Hybrid Approach for Fault Diagnosis in 3-DOF Flight Simulator Based on Rough Set Theory, Genetic Algorithm and Artificial Neural Network

2006 6th World Congress on Intelligent Control and Automation ◽

10.1109/wcica.2006.1714107 ◽

2006 ◽

Cited By ~ 1

Author(s):

Haibin Duan ◽

Daobo Wang ◽

Xiufen Yu

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Artificial Neural Network ◽

Fault Diagnosis ◽

Set Theory ◽

Rough Set ◽

Rough Set Theory ◽

Hybrid Approach ◽

Flight Simulator ◽

Artificial Neural

Download Full-text

The Application of Tolerant Rough Set Neural Network to Fighter Fault Diagnosis

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.341-342.809 ◽

2013 ◽

Vol 341-342 ◽

pp. 809-814

Author(s):

Guo Qiang Sun ◽

Hong Li Wang ◽

Jun Tao ◽

Xu Bing Li

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Set Theory ◽

Rough Set ◽

Rough Set Theory ◽

Useful Knowledge ◽

The Neural Network ◽

Catch Up ◽

Simulation Results ◽

Adaptive Ability

Conventional rough set theory is based on indiscernibility relation, which lacks the adaptive ability to data noise or data missing. Furthermore, it may present qualitatively whether or not the faults exist, but it cant compute accurately the value of the faults. Though the neural network has ability of approximating unknown nonlinear systems, but it cant distinguish the redundant knowledge from useful knowledge, so its classification ability cant catch up with the rough set classifier. This paper combines the rough set theory and the tolerant rough set neural network to diagnose the rudder faults of fighter, which solves well the problem of fault diagnosis and fault degree computation. Simulation results demonstrate the effectiveness of the proposed method.

Download Full-text