Adaptive Enhancement for Coal-Rock Cutting Sound Based on Parameter Self-Tuning Bistable Stochastic Resonance Model
Author:
Xu Jie,Xu Jing,Ren Chaofan,Liu Yanxin,Sun Ning
Abstract
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.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Jiangsu Province
China Postdoctoral Science Foundation
Natural Science Foundation for Colleges and Universities of Jiangsu Province
Subject
Geometry and Topology,Logic,Mathematical Physics,Algebra and Number Theory,Analysis