Abstract
An efficient intelligent fault diagnosis model was proposed in this paper to timely and accurately offer a dependable basis for identifying the rolling bearing condition in the actual production application. The model is mainly based on an improved butterfly optimizer algorithm- (BOA-) optimized kernel extreme learning machine (KELM) model. Firstly, the roller bearing’s vibration signals in the four states that contain normal state, outer race failure, inner race failure, and rolling ball failure are decomposed into several intrinsic mode functions (IMFs) using the complete ensemble empirical mode decomposition based on adaptive noise (CEEMDAN). Then, the amplitude energy entropies of IMFs are designated as the features of the rolling bearing. In order to eliminate redundant features, a random forest was used to receive the contributions of features to the accuracy of results, and subsets of features were set up by removing one feature in the descending order, using the classification accuracy of the SBOA-KELM model as the criterion to obtain the optimal feature subset. The salp swarm algorithm (SSA) was introduced to BOA to improve optimization ability, obtain optimal KELM parameters, and avoid the BOA deteriorating into local optimization. Finally, an optimal SBOA-KELM model was constructed for the identification of rolling bearings. In the experiment, SBOA was validated against ten other competitive optimization algorithms on 30 IEEE CEC2017 benchmark functions. The experimental results validated that the SBOA was evident over existing algorithms for most function problems. SBOA-KELM employed for diagnosing the fault diagnosis of rolling bearings obtained improved classification performance and higher stability. Therefore, the proposed SBOA-KELM model can be effectively used to diagnose faults of rolling bearings.
Highlights
As a core component of mechanical, the rolling bearings are widely used in rotating machinery types such as wind turbines, aeroengines, ships, and automobiles
SBOA-kernel extreme learning machine (KELM) Method. e flowchart of the proposed SBOA-KLEM is shown in Figure 1. e whole flow includes feature extraction based on CEEMDAN energy entropy, feature selection based on random forest, and classification based on butterfly optimizer algorithm- (BOA-)KELM. e first step is to extract features, using the CEEMDAN method to decompose the raw vibration signals of bearing into multiple intrinsic mode functions (IMFs), computing each IMF’s energy entropy and normalizing. e second step is to select the feature from the CEEMDAN energy entropy to reduce data redundancy. e third step is to optimize the two critical parameters of the KLEM using SBOA. en, the optimal parameters and feature combination are used to train an optimal KELM
A series of IMFs are obtained by decomposing the vibration signals using CEEMDAN in the four rolling bearings states
Summary
As a core component of mechanical, the rolling bearings are widely used in rotating machinery types such as wind turbines, aeroengines, ships, and automobiles. It is a considerable probability of a mechanical failure due to a bearing failure. Ere are various faults of rolling bearing, including outer race, inner race, and ball, in general due to a long-term complex environment. When those faults get serious, they may cause a sudden breakdown of the machine, even the entire system, leading to substantial financial losses, and even cause casualties among workers. Xu et al [1] proposed a new expert system based on belief rules (BRB) built from multiple activated BRB subsystems in the meantime for diagnosing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
