文章摘要
李宏斌,徐楚林,温周斌.BP神经网络在扬声器异常音检测中的应用[J].声学技术,2014,33(6):522~525
BP神经网络在扬声器异常音检测中的应用
The application of BP neural network in loudspeaker's Rub & Buzz detection
投稿时间:2014-04-23  修订日期:2014-08-04
DOI:10.3969/j.issn1000-3630.2014.06.009
中文关键词: 扬声器异常音  人工神经网络  共轭梯度法  虚警率
英文关键词: loudspeaker's Rub & Buzz  ANN  conjugate gradient method  false alarm rate
基金项目:
作者单位E-mail
李宏斌 中国科学院声学研究所东海研究站, 上海 200032 feishastop@gmail.com 
徐楚林 中国科学院声学研究所东海研究站, 上海 200032
浙江中科电声研发中心, 浙江嘉善 314100 
 
温周斌 中国科学院声学研究所东海研究站, 上海 200032
浙江中科电声研发中心, 浙江嘉善 314100 
 
摘要点击次数: 1022
全文下载次数: 1467
中文摘要:
      提出一种采用人工神经网络判断扬声器是否存在异常音的方法.首先简单介绍了获取扬声器异常音曲线的方法和人工神经网络中的BP模型及其训练方法,并比较了基本BP算法和共轭梯度法两种训练方法的差异.再将所获得的异常音曲线作为人工神经网络的输入向量,将听音员的听测结果作为目标向量,并使用共轭梯度法进行网络的训练.最后通过已训练好的人工神经网络判断扬声器是否存在异常音.实验结果表明,该方法可替代传统的人工设置门限的方法,并可大幅降低扬声器异常音检测的虚警率.
英文摘要:
      This paper proposes a method of using neural network to judge whether a loudspeaker is good or not. First, the method of how to obtain the Rub & Buzz curve and the BP model including its training methods are simply introduced. Besides, the comparison between the basic BP algorithm and the conjugate gradient algorithm is also made. Then the Rub & Buzz curve is used as the BP network's input vector and the judgment result of experienced worker is used as the BP network's output vector and use the conjugate gradient algorithm to train the network. Finally, the trained BP network can judge whether the measured loudspeaker is good or not. The experimental results show that judging a loudspeaker is good or not by a threshold, which is set up by engineer, can be replaced by artificial neural network, and the false alarm rate is greatly reduced.
查看全文   查看/发表评论  下载PDF阅读器
关闭