Abstract
Mining machines are strongly nonlinear systems, and their transmission vibration signals are nonlinear mixtures of different kinds of vibration sources. In addition, vibration signals measured by the accelerometer are contaminated by noise. As a result, it is inefficient and ineffective for the blind source separation (BSS) algorithm to separate the critical independent sources associated with the transmission fault vibrations. For this reason, a new method based on wavelet de-noising and nonlinear independent component analysis (ICA) is presented in this paper to tackle the nonlinear BSS problem with additive noise. The wavelet de-noising approach was first employed to eliminate the influence of the additive noise in the BSS procedure. Then, the radial basis function (RBF) neural network combined with the linear ICA was applied to the de-noised vibration signals. Vibration sources involved with the machine faults were separated. Subsequently, wavelet package decomposition (WPD) was used to extract distinct fault features from the source signals. Lastly, an RBF classifier was used to recognize the fault patterns. Field data acquired from a mining machine was used to evaluate and validate the proposed diagnostic method. The experimental analysis results show that critical fault vibration source component can be separated by the proposed method, and the fault detection rate is superior to the linear ICA based approaches.
Highlights
A mining machine is the most important piece of equipment for coal mining [1]
The experimental analysis results show that critical fault vibration source component can be separated by the proposed method, and the fault detection rate is superior to the linear independent component analysis (ICA) based approaches
In order to bridge the aforementioned research gap in the fault detection of mining machines, this paper proposes a novel wavelet-based nonlinear ICA separator for fault vibration source extraction from mining machine vibration signals
Summary
A mining machine is the most important piece of equipment for coal mining [1]. A simple failure of the machine will cause severe safety accidents and serious economic losses. Pan et al [9] proposed a blind separation technology to realize the fault feature extraction of aero-engine from multi-sensor vibration signals. Chen et al [10] used a linear blind signal separation method to fuse the multi-sensor vibration signals of a rotating machine and extracted a useful feature for fault detection. Previous studies show that linear blind signal separation based on the independent component analysis (ICA) can produce good fault source separation performance. When the nonlinearity of the mixed observation signals increases, ICA is not effective and, in some cases, even fails to identify the fault vibration source [14]. In order to bridge the aforementioned research gap in the fault detection of mining machines, this paper proposes a novel wavelet-based nonlinear ICA separator for fault vibration source extraction from mining machine vibration signals.
Sign-in/Register to view highlights & summary 
Published Version (
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