Ning Sun

The cutting sound signal of a coal mining shearer is an important signal source for identifying the coal–rock cutting mode and load state. However, the coal–rock cutting sound signal directly collected from the industrial field always contains a large amount of background noise, which is not conducive to the subsequent feature extraction and recognition. Therefore, efficient noise elimination for the original signal is required. An intelligent processing method based on an improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) denoising algorithm is constructed for the cutting sound signal in this paper. CEEMDAN first decomposes the sound to generate a series of intrinsic modal functions (IMFs). Because the denoising threshold of each IMF is usually obtained by an experimental test or an empirical formula in the traditional CEEMDAN method, obtaining an optimal threshold set for each IMF is difficult. The processing effect is often restricted. To overcome this problem, the fruit fly optimization algorithm (FOA) was introduced for CEEMDAN threshold determination. Moreover, in the basic FOA, the scouting bee mutation operation and adaptive dynamic adjustment search strategy are applied to maintain the convergence speed and global search ability. The simulation result shows that the signal waveform processed by the improved CEEMDAN denoising algorithm is smoother than the other four typical eliminate noise signal algorithms. The output signal’s signal-to-noise ratio and mean square error are significantly improved. Finally, an industrial application of a shearer in a coal mining working face is performed to demonstrate the practical effect.

The traditional bistable stochastic resonance model has always had the drawback of being difficult when choosing accurate system parameters when a weak signal is enhanced. This paper proposes a parameter self-tuning adaptive optimization method based on the bat optimization algorithm to address this issue. The cubic mapping strategy of chaos optimization is introduced in the initial process of the individual position of the bat algorithm. Chaos is characterized by randomness, sensitivity, fractal dimension, and universality. The initial problem of the algorithm falling into local extremums is overcome. The global search capability of the basic bat optimization algorithm has been improved. The improved bat optimization algorithm’s objective function is the signal-to-noise ratio (SNR) of the target weak signal output by the bistable stochastic resonance model. An adaptive signal enhancement algorithm based on the improved bat optimization algorithm and bistable stochastic resonance (IBA-BSR) model is constructed to increase the proportion of weak signals in the mixed signal. Simulation signals are created to validate the proposed algorithm’s feasibility. The engineering application effect of this algorithm is further demonstrated by enhancing the sound signal of coal and rock cutting by a shearer in a coal face. Engineering test results demonstrate that this algorithm can significantly increase the SNR of coal and rock cutting sound signals by 42.4537 dB, and the effect is remarkable.