一种复杂噪声环境下的机电系统故障在线监测声学处理方法

针对复杂背景噪声环境下的机电系统故障检测问题，文中提出了一种基于宽带声学处理的噪声抑制和故障监测方法。该方法以声学信号拾取和处理为出发点，通过对机电设备正常运行状态下声学信号进行采集、数据跟踪和复杂背景噪声抑制，建立系统正常运行状态声纹库，并进一步通过基于宽带声学处理的声纹信号匹配和模式识别技术来实现故障信号的检测与分类，进而实现对机电系统运行状态的在线监测和隐形故障的自主预警。该处理方法将基于数据跟踪的自相关噪声抑制技术与基于宽带声学处理的故障信号检测以及分类判型技术有机结合，可对机电系统早期隐性故障进行监测，有效解决了复杂噪声环境下的机电系统故障检测问题。仿真实验也证明了该处理方法的有效性和良好的实用性。

An Acoustic Treatment Method for On-Line Fault Monitoring of Electromechanical Systems in Complex Noise Environment

In view of the problem of electromechanical system fault detection under complex background noise environment, this study proposes a noise suppression and fault monitoring method based on broadband acoustic processing. This method starts from acoustic signal pick-up and processing, and establishes the voiceprint database of the normal operating state of the system by collecting, tracking the data and suppressing the complex background noise of the acoustic signal under the normal operating state of the electromechanical equipment. In addition, the proposed method further realizes the detection and classification of fault signals through the voiceprint signal matching and pattern recognition technology based on broadband acoustic processing, and then realizes the online monitoring of the operating state of the electromechanical system and the autonomous early warning of invisible faults. This processing method organically combines the autocorrelation noise suppression technology based on data tracking and the fault signal detection and classification technology based on broadband acoustic processing, which can monitor the early hidden faults of the electromechanical system and effectively solve the fault detection problem of the electromechanical system in the complex noise environment. The simulation experiment finally proves the effectiveness and good practicability of the proposed method.