基于声信号的铝锭脱模故障诊断研究

针对铝锭铸造是否脱模的故障检测难题,尝试利用铸模敲击声音信号进行诊断分析。本文首先提出基于改进的小波包算法对敲击声音进行降噪,在对声音信号频域分析后,发现一次敲击后如果铝锭脱模,则一次敲击声音信号和二次敲击声音信号存在明显的峰值频率差,将其作为故障特征参数,并设定阈值,可以对铝锭是否脱模进行故障诊断。现场采集的声音处理实验证明了本文所提方法的有效性。

Investigation of aluminium ingot demoulding fault diagnosis based on acoustic signal analysis*

In view of the aluminium ingot casting demoulding problem of fault detection, try to take advantage of mould tapping acoustic signal to diagnose. After noise reduction using wavelet packet algorithm for tapping acoustic, the acoustic signal frequency domain analysis. If aluminum ingots have demoulding after first hit, there is obvious pitch frequency difference to the first percussion sound and the second knock sound. Pitch frequency difference as the fault feature parameter and setting a threshold value. It can be diagnosed whether aluminium ingots demould. The effectiveness for new method is demonstrated by the acoustic processing experiments.