论文部分内容阅读
本文提出了应用差分计算和句法模式识别方法识别机械振动和噪声谱中谱峰的新方法。此方法数学概念清楚,使用效果好。本文中对此方法做了详细的讨论。由于引入了模拟人工分析思路的自学习功能和模糊数学方法,因而能有目的地对各种谱峰加以识别。试验研究表明,此方法能提取和识别出振动噪声谱中与机械状态有关的谱峰,有利于实现机械设备的状态监测和故障诊断的自动化。
In this paper, a new method to identify the peaks in the mechanical vibration and noise spectrum using differential computation and syntax pattern recognition is proposed. This method is clear mathematical concept, the use of good effect. This paper discusses this method in detail. Due to the introduction of self-learning functions and fuzzy mathematics to simulate artificial analysis, various spectrum peaks can be purposefully identified. Experimental results show that this method can extract and identify the spectrum of vibration noise spectrum related to the mechanical state, which is conducive to the automation of condition monitoring and fault diagnosis of mechanical equipment.