A Novel Improved ELM Algorithm for a Real Industrial Application

Hai-Gang Zhang,Yi-Xin Yin,Sen Zhang

doi:10.1155/2014/824765

Abstract

It is well known that the feedforward neural networks meet numbers of difficulties in the applications because of its slow learning speed. The extreme learning machine (ELM) is a new single hidden layer feedforward neural network method aiming at improving the training speed. Nowadays ELM algorithm has received wide application with its good generalization performance under fast learning speed. However, there are still several problems needed to be solved in ELM. In this paper, a new improved ELM algorithm named R-ELM is proposed to handle the multicollinear problem appearing in calculation of the ELM algorithm. The proposed algorithm is employed in bearing fault detection using stator current monitoring. Simulative results show that R-ELM algorithm has better stability and generalization performance compared with the original ELM and the other neural network methods.

Highlights

In the last few years, feedforward neural networks have received very wide range of applications and development
In order to test and verify its effectiveness, the improved extreme learning machine (ELM) algorithm is employed in bearing fault detection using stator current monitoring
Unlike Huang’s method based on Ridge Regression to add a threshold to every element of matrix HTH(β = (HTH + 1/C)−1HTT), the proposed R-ELM algorithm just set a proper threshold to some singular element to matrix D after LDLT decomposition to HTH

Summary

Introduction

In the last few years, feedforward neural networks have received very wide range of applications and development. The most widely used method in feedforward neural network is gradientbased learning algorithm. Compared with traditional feedforward network learning algorithms such as back-propagation (BP) algorithm, ELM has the following advantages: (1) the fast training speed, (2) good generalization performance, (3) partially overcoming the problem of local minima, and (4) not needing manual intervention like setting a stop criterion or learning rate. This section proposes an improved ELM algorithm named R-ELM to overcome the multicollinear problems. In this paper, bearing fault detection using stator current monitoring is employed to verify the effective and robust performance of our proposed ELM algorithm. A new improved ELM algorithm is proposed in order to overcome the multicollinear problem. In order to test and verify its effectiveness, the improved ELM algorithm is employed in bearing fault detection using stator current monitoring.

The Improved Extreme Learning Machine Algorithm

Stator Current Feature Extraction of Bearing Fault

Simulative Results for Bearing Fault Detection

Conclusions