Mechanical vibration monitoring for rotating mechanical equipment can improve the safety and reliability of the equipment. The traditional wired monitoring technology faces problems such as high-frequency signal pickup and high-precision data collection. Therefore, this paper proposes optimization techniques for mechanical vibration monitoring and signal processing based on wireless sensor networks. First, the hardware design uses high-performance STM32 as the control center and Si4463 as the wireless transceiver core. The monitoring node uses a high-precision MEMS acceleration sensor with a 16-bit resolution ADC acquisition chip to achieve high-frequency, high-precision acquisition of vibration signals. Then, the bearing vibration signal optimization method is studied, and the sparse Bayes algorithm is proposed as a compressed sensing reconstruction algorithm. Finally, the difference in reconstruction accuracy between this method and the traditional reconstruction algorithm is compared through experiments and the effect of this method on the reconstruction performance is analyzed when different parameters are selected.

旋转机械设备的机械振动监控可以提高设备的安全性和可靠性。传统的有线监控技术面临着高频信号采集和高精度数据采集等问题。因此，本文提出了基于无线传感器网络的机械振动监测和信号处理优化技术。首先，硬件设计使用高性能STM32作为控制中心，并使用Si4463作为无线收发器核心。监视节点使用具有16位分辨率ADC采集芯片的高精度MEMS加速度传感器来实现振动信号的高频，高精度采集。然后，研究了轴承振动信号的优化方法，提出了一种稀疏贝叶斯算法作为压缩感知重构算法。最后，通过实验比较了该方法与传统重建算法在重建精度上的差异，并分析了选择不同参数时该方法对重建性能的影响。