为了达到制粉系统的智能自动控制,必需要对球磨机内的工作状态进行识别,利用音频信号的特征频率是一种适用的方法。而在现场测得的声音信号一定会包含有多种噪声信号,特别是当特征信号与噪声信号存在严重的频谱交叠,采取频域滤波方法无法获得较好的效果时,利用基于自适应神经模糊系统(ANFIS)的消噪技术,可以得到良好的分离效果。提高测得数据的精确度,进而有效地实现球磨机的自动控制。
In order to realize the automatic control of coal pulverizing system,it's necessary to recognize the different work conditions in the ball mills,and the character frequency of the sound signal is just a applicable way. But there are many kinds of noise contained in the sound signal which is from work spot,especially serious frequency- mixture happens berween character frequency and noise,the denosing based on Adaptive Network based Fuzzy Inference System (ANFIS)is a better way to separate them. It can improve the precision of soud signal data,and help to realize the automatic control of ball mills effectively.