摘要
针对可调品质因子小波变换(Tunable Q-factor wavelet trans-form,TQWT)采用网格搜索和优化算法调参存在评估计算代价高的问题,提出基于贝叶斯优化TQWT参数的故障诊断算法。通过贝叶斯优化算法在TQWT参数空间内求取熵-峭综合目标函数最优解,据此设置TQWT参数分解轴承故障信号,选择熵-峭指标最小值对应子带信号,经TQWT逆变换后进行包络解调分析,最终由重构信号包络谱判别轴承故障类型。仿真实验和实测轴承信号分析表明,该算法可以准确提取轴承故障特征频率信息,实现早期故障诊断。
It is costly to use the grid search and optimization algorithm to tune the parameters of tunable quality-factor wavelet transform(TQWT).A method for bearing fault diagnosis based on the Bayesian optimization of TQWT parameters was proposed.The optimal solution of the entropy-kurtosis synthetic objective function was solved by using the Bayesian optimization algorithm in the space of TQWT parameters,according to which the TQWT parameters were set to decompose the original bearing fault signals.The sub-band signal with the minimum value of the entropy-kurtosis index was selected to reconstruct its feature signals with the inverse TQWT transform,and the signal was then processed with an envelope demodulation algorithm.The type of bearing fault was judged with the reconstructed feature signal envelope spectrum.The simulation results on the actually measured bearing vibration signals and their analysis show that the proposed method can accurately extract the characteristic frequency information on fault and diagnose bearing faults at an early stage.
作者
张乐
彭先龙
朱华双
ZHANG Le;PENG Xianlong;ZHU Huashuang(School of Mechanical Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)
出处
《机械科学与技术》
CSCD
北大核心
2024年第3期504-512,共9页
Mechanical Science and Technology for Aerospace Engineering
基金
陕西省自然科学基础研究计划(2020JM-521)。
关键词
贝叶斯优化
TQWT
熵-峭指标
故障诊断
bayesian optimization
TQWT
entropy-kurtosis index
fault diagnosis
