Abstract
The mine hoist sheave bearing is a large heavy-duty bearing, located in a derrick of tens of meters. Aiming at the difficulty of sheave bearing fault diagnosis, a combined fault-diagnosis method based on the improved complete ensemble EMD (ICEEMDAN) energy entropy and support vector machine (SVM) optimized by artificial fish swarm algorithm (AFSA) was proposed. Different location of the bearing defect will result in different frequency components and different amplitude energy of the frequency. According to this feature, the position of the bearing defect can be determined by calculating the ICEEMDAN energy entropy of different vibration signals. In view of the difficulty in selecting the penalty factor and radial basis kernel parameter in the SVM model, the AFSA was used to optimize them. The experimental results show that the accuracy rate of the optimized fault-diagnosis model is improved by 10% and the diagnostic accuracy rate is 97.5%.
Highlights
The head sheave is the key part in the multi-rope friction winder
In literature [5], a fault features extraction scheme based on MED-ICEEMDAN, mutual information, and sample entropy was proposed for the head sheave bearing vibration signals
In order to verify the effectiveness and reliability of the fault-diagnosis method based on ICEEMDAN and artificial fish swarm algorithm (AFSA)-support vector machine (SVM) in the fault diagnosis of the hoist sheave bearing, an experimental study
Summary
The head sheave is the key part in the multi-rope friction winder. The bearings of the head sheave are subjected to the heavy and complex loads. In literature [5], a fault features extraction scheme based on MED-ICEEMDAN, mutual information, and sample entropy was proposed for the head sheave bearing vibration signals. The fault-diagnosis method based on signal processing to extract fault characteristic information is defective as it needs to be executed and completed by professionals with professional knowledge and technology, and cannot provide the diagnosis results in time. This paper used the energy entropy of the intrinsic mode functions (IMFs) containing the main fault information to establish feature vector, according to the fact that different bearing faults have different ICEEMDAN energy entropy, and uses the artificial fish swarm algorithm to optimize the penalty factor and radial basis kernel parameter in the support vector machine model to obtain the optimal diagnostic model. Choice to use the IMFs obtained by ICEEMDAN decomposition of the signal to construct feature information
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
