摘要
气力输送中颗粒相质量流量是其运行时需要监测的重要参数之一。利用声发射信号来监测颗粒相质量流量能够做到实时在线测量。利用集合经验模态分解(EEMD)算法基于原始信号进行分解的优势以及人工神经网络优良的非线性映射能力,建立一个EEMD与BP神经网络联合质量流量测量模型,并以随机实验数据样本对网络进行训练,以实现对颗粒相质量流量的在线估计。联合模型与实验结果吻合度较好,为稀相气力输送中颗粒相质量流量在线测量提供了一种简单、可靠的方法。
The particle mass flow rate in pneumatic conveying is one of the important parameters to be monitored during the operation.The real time on-line measurement can be realized by using the acoustic emission signals to monitoring the particle mass flow rate.In this paper,by using the Ensemble Empirical Mode Decomposition(EEMD) algorithm,which can decompose the signals based on the original signal,and the artificial neural network,which has the excellent nonlinear mapping ability,an EEMD and BP neural network combined mass flow measurement model is established.The experimental data samples are used to train the network to achieve the mass flow online estimation.It is found that result of the joint model is in good agreement with the experimental result.This work provides a simple and reliable method for the on-line measurement of particle mass rate flow in pneumatic conveying.
出处
《噪声与振动控制》
CSCD
2018年第1期220-224,共5页
Noise and Vibration Control
基金
中央高校基本科研业务费专项资金资助项目(2017ZZD001)
中央高校基本科研业务费专项资金资助项目(2015XS83)
关键词
声学
气力输送
EEMD
神经网络
声发射
质量流量
acoustics
pneumatic conveying
EEMD
neural network
acoustic emission
mass flow rate
