Optimized ELM based on Whale Optimization Algorithm for gearbox diagnosis

Abstract

Extreme learning machine (ELM) is a fast and quick learning algorithm with better generalization performance. However, the randomness of input weight and hidden layer bias may affect the overall performance of ELM. This paper proposed a new approach to determine the optimized values of input weight and hidden layer bias for ELM using whale optimization algorithm (WOA), which we call WOA-ELM. An online gearbox vibration signals is used in this study. Empirical mode decomposition (EMD) and complementary mode decomposition (CEEMD) are used to decompose the signals into sub-signals known as intrinsic mode functions (IMFs). Then, statistical features are extracted from selected IMFs. WOA-ELM is used for classification of healthy and faulty condition of gearbox. The result shows that WOA-ELM provide better classification result as compared with conventional ELM. Therefore, this study provide a new diagnosis approach for gearbox application.

Swarm-Based Extreme Learning Machine Models for Global Optimization

“…The suggested algorithm requires an optimal set of input weights and assumptions, ideally maintaining the full column rank of H matrix. Isham et al [14] used a whale optimization algorithm (WOA) technique to determine the optimal value of the input weight and the hidden layer distortions. Huang et al [15] proposed a new learning algorithm called the ELM for single-hidden layers feedforward neural networks (SLFNs), which randomly chooses hidden nodes and analytically measures SLFN output weights.…”