Abstract
The recognition of shearer cutting state is the key technology to realize the intelligent control of the shearer, which has become a highly difficult subject concerned by the world. This paper takes the sound signal as analytic objects and proposes a novel recognition method based on the combination of variational mode decomposition (VMD), principal component analysis method (PCA), and least square support vector machine (LSSVM). VMD can decompose a signal into various modes by using calculus of variation and effectively avoid the false component and mode mixing problems. On this basis, an improved gravitational search algorithm (IGSA) is designed by using the position update mechanism of Levy flight strategy to find the optimal parameter combination of VMD. Then, the feature extraction is achieved by calculating the envelope entropy and kurtosis of the decomposed intrinsic mode functions (IMFs). To avoid dimensional disasters and reinforce the classification performance, PCA is introduced to choose useful features, and the LSSVM-based classifier is reasonably constructed. Finally, the experimental results indicate that the proposed method is more feasible and superior in the recognition of shearer cutting states.
Highlights
In the coal mining face, the shearer plays an indispensable role, and the continuous, safe, and reliable operation of the shearer is an important guarantee to achieve high production and efficiency of coal mining
In [29], a new fault diagnosis method is proposed by using particle swarm optimization variational mode decomposition (PSO-VMD) to distinguish different work states of hydraulic pumps
In order to verify the decomposition performance of proposed improved gravitational search algorithm (IGSA)-VMD, a simulated signal is used in this paper, which is a mixed signal composed of four cosine signals with different frequencies. e mathematical expression and waveform of the signal are shown in Figure 4: X(t) cos(2π · 20t) + 1 cos(2π · 50t) + 1 cos(2π · 60t) + 1 cos(2π · 100t)
Summary
In the coal mining face, the shearer plays an indispensable role, and the continuous, safe, and reliable operation of the shearer is an important guarantee to achieve high production and efficiency of coal mining. Kumar et al [9] proposed a bearing fault diagnosis method based on the statistical features of sound signal and Bayes classifier. The acoustic-based fault diagnosis techniques have been successfully applied to many rotating parts, such as gears and bearings, there is still little research in the field of coal-rock cutting state recognition. Common signal processing methods include empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), local mean decomposition (LMD), and variational mode decomposition (VMD) Among these methods, EMD, firstly proposed by Huang et al in 1998 [14], has been widely used and achieved significant results [15,16,17]. In [29], a new fault diagnosis method is proposed by using particle swarm optimization variational mode decomposition (PSO-VMD) to distinguish different work states of hydraulic pumps.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
