
采用粒子群算法的自适应变步长随机共振研究
Research of self-adaptive step-changed stochastic resonance using particle swarm optimization
The traditional adaptive stochastic resonance (SR) can only achieve one-parameter optimization, and it is very difficult to select the calculation step of step-changed stochastic resonance (SCSR), a new adaptive SCSR based on particle swarm optimization (PSO), which can realize the adaptive solving of optimal output of SCSR, is proposed in this paper. The output signal to noise ratio of bi-stable system is determined as the fitness function of PSO algorithm, and the structure parameters and calculation step of SCSR are selected adaptively, as a result, the weak signal which under the conditions of large parameter can be detected optimally. The proposed method is applied to simulation data and vibration signals measured on defective bearings with inner race fault. The results shows that the proposed method has advantages of simplicity, fast convergence speed and wide range of applications, and possesses a good prospect of engineering application.
变步长随机共振 / 粒子群算法 / 自适应 / 多参数同步优化 {{custom_keyword}} /
step-changed stochastic resonance (SCSR) / particle swarm optimization (PSO) / self-adaptive / multi-parameter optimization {{custom_keyword}} /
/
〈 |
|
〉 |