Abstract
The combination of feature extraction and pattern recognition can make it possible to realize wind turbine gearboxes based on vibration signals. However, these methods need to be constantly adjusted parameters and spend time training when processing different vibration signals, which is time-consuming. Aiming at reducing the number of parameters that need to be adjusted and training time, this paper proposes a variational mode decomposition (VMD) based on atomic search optimization (ASO) and neural random forest (NRF) fault diagnosis model. The parameters of the VMD are adaptively adjusted by the ASO, which has the advantages of less adjustment parameters. After ASO-VMD decomposition, signals will be used as the input of NRF. We evaluate our method on simulation gearbox model which is established by Solidworks and Adams. Experimental results show that our method has faster training speed and higher recognition accuracy without set many parameters manually.
Highlights
In recent years, resource shortages and environmental degradation have prompted countries to focus on the development of clean energy [1]
Variational mode decomposition (VMD) [12] is a fault adaptive processing method proposed by Dragomireskiy et al Due to its good anti-noise ability, VMD has been widely used in the field of fault diagnosis [13,14,15,16]
Compared to particle swarm optimization (PSO) and artificial fish algorithm (AFSA), atomic search optimization (ASO) only needs to set the initial number of atoms and the number of iterations to achieve VMD optimization, which minimizes the impact of setting parameters on the results
Summary
Resource shortages and environmental degradation have prompted countries to focus on the development of clean energy [1]. Lv et al [17] decomposes the fault signal through VMD, it uses the support vector machine (SVM) based on genetic algorithm to identify the fault and improve the generalization ability of the model; Yi et al [18] use particle swarm optimization (PSO) to find the optimal parameters of VMD to realize Bearing fault diagnosis; Wang et al [19] use PSO to minimize the average envelope entropy. A NOVEL WIND TURBINE GEARBOX FAULT DIAGNOSIS METHOD BASED ON ASO-VMD AND NRF. Common pattern recognition methods such as support vector machine [24, 25], artificial neural network [26,27,28] etc., are widely used in mechanical equipment fault diagnosis, and have achieved remarkable results. The ASO is used to select the optimal decomposition parameter of the VMD, under which the original fault signal is decomposed using VMD. In the final fault identification effect, the recognition accuracy of the method reaches 100 %, which can meet the actual fault diagnosis requirements
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.
