正在加载图片...
工程科学学报,第39卷,第7期:1101-1106,2017年7月 Chinese Journal of Engineering,Vol.39,No.7:1101-1106,July 2017 D0l:10.13374/j.issn2095-9389.2017.07.017:http://journals..ustb.edu.cn 基于小波包的开关电流电路故障诊断 张 镇”四,段哲民”,龙英) 1)西北工业大学电子信息学院,西安7100722)长沙学院电子与电气工程学院,长沙410022 ☒通信作者,Email:304952304@qg.com 摘要为提高开关电流电路故障诊断的精度,提出了一种基于小波包优选和优化BP神经网路的开关电流电路特征抽取与 识别方法.首先对开关电流电路原始响应信号进行多层次的小波包分解,接着计算N层分解后的归一化能量值,以特征偏离 度作为评价选择最优小波包基,构建最优故障特征向量,最后将提取的最优故障特征通过遗传算法优化的BP神经网络进行 分类.该方法以实例电路进行验证,结果表明所有的软故障均得到了有效的分类,说明了该方法在开关电流电路故障诊断中 的优越性 关键词开关电流电路;故障诊断:小波包变换:遗传算法;BP神经网络 分类号TH165.3 Fault detection in switched current circuits based on preferred wavelet packet ZHANG Zhen》,DUAN Zhe-min”,LONG Ying》 1)School of Electronic Information,Northwestern Polytechnic University,Xian 710072,China 2)Department of Electronie Electrical Engineering,Changsha University,Changsha 410022,China Corresponding author,E-mail:304952304@qq.com ABSTRACT In order to improve the accuracy of switched current circuit fault diagnosis,a feature extraction and recognition method of switched current circuit based on wavelet packet optimization and optimization of BP neural network was proposed.Firstly,the wavelet packet decomposition of the original response signal of the switched current circuit was carried out.Then,the normalized ener- gy value after the decomposition of the N layer was calculated,and the optimal wavelet packet basis was selected by using the charac- teristic deviation as the evaluation.Finally,the optimal fault feature vector was constructed.The extracted optimal fault characteristics were classified by BP neural network optimized by genetic algorithm.The results of this method were verified by the example circuit. The results show that all the soft faults are effectively classified,and the superiority of the method in the fault diagnosis of the switched current circuit is illustrated. KEY WORDS switched current circuit:fault detection;wavelet packet transform:genetic algorithm:BP neural network 电子电路的测试和故障诊断技术对提升电子产品 一步的降低所带来的影响. 的可靠性、降低生产成本等方面具有重要意义.开关 自20世纪80年代发展起来的开关电流电路,不 电容电路技术一直是模拟电路设计或数模混合电路设 同于开关电容的“电压模式”,该技术是一种基于“电 计中的主流技术.近年来,随着金属氧化物半导体 流模式”的模拟信号采样处理技术。电路的实现不需 (MOS)工艺向深亚微米和纳米工艺发展,导致开关电 要线性浮置电容,并且在用电流表示信号时,所需电压 容性能进一步降低,主要体现在开关电容电路中高质 的摆幅不大,因此具有良好的低电压工作特性.电流 量的线性浮置电容需要两层多晶硅,电源电压趋于进 模技术的应用给模拟电路设计的性能带来了显著 收稿日期:2016-12-13 基金项目:国家自然科学基金资助项目(61201108,61102035)工程科学学报,第 39 卷,第 7 期: 1101--1106,2017 年 7 月 Chinese Journal of Engineering,Vol. 39,No. 7: 1101--1106,July 2017 DOI: 10. 13374 /j. issn2095--9389. 2017. 07. 017; http: / /journals. ustb. edu. cn 基于小波包的开关电流电路故障诊断 张 镇1) ,段哲民1) ,龙 英2) 1) 西北工业大学电子信息学院,西安 710072 2) 长沙学院电子与电气工程学院,长沙 410022  通信作者,E-mail: 304952304@ qq. com 摘 要 为提高开关电流电路故障诊断的精度,提出了一种基于小波包优选和优化 BP 神经网路的开关电流电路特征抽取与 识别方法. 首先对开关电流电路原始响应信号进行多层次的小波包分解,接着计算 N 层分解后的归一化能量值,以特征偏离 度作为评价选择最优小波包基,构建最优故障特征向量,最后将提取的最优故障特征通过遗传算法优化的 BP 神经网络进行 分类. 该方法以实例电路进行验证,结果表明所有的软故障均得到了有效的分类,说明了该方法在开关电流电路故障诊断中 的优越性. 关键词 开关电流电路; 故障诊断; 小波包变换; 遗传算法; BP 神经网络 分类号 TH165. 3 Fault detection in switched current circuits based on preferred wavelet packet ZHANG Zhen1)  ,DUAN Zhe-min1) ,LONG Ying2) 1) School of Electronic Information,Northwestern Polytechnic University,Xi'an 710072,China 2) Department of Electronic & Electrical Engineering,Changsha University,Changsha 410022,China Corresponding author,E-mail: 304952304@ qq. com ABSTRACT In order to improve the accuracy of switched current circuit fault diagnosis,a feature extraction and recognition method of switched current circuit based on wavelet packet optimization and optimization of BP neural network was proposed. Firstly,the wavelet packet decomposition of the original response signal of the switched current circuit was carried out. Then,the normalized ener￾gy value after the decomposition of the N layer was calculated,and the optimal wavelet packet basis was selected by using the charac￾teristic deviation as the evaluation. Finally,the optimal fault feature vector was constructed. The extracted optimal fault characteristics were classified by BP neural network optimized by genetic algorithm. The results of this method were verified by the example circuit. The results show that all the soft faults are effectively classified,and the superiority of the method in the fault diagnosis of the switched current circuit is illustrated. KEY WORDS switched current circuit; fault detection; wavelet packet transform; genetic algorithm; BP neural network 收稿日期: 2016--12--13 基金项目: 国家自然科学基金资助项目( 61201108,61102035) 电子电路的测试和故障诊断技术对提升电子产品 的可靠性、降低生产成本等方面具有重要意义. 开关 电容电路技术一直是模拟电路设计或数模混合电路设 计中的主流技术. 近年来,随着金属氧化物半导体 ( MOS) 工艺向深亚微米和纳米工艺发展,导致开关电 容性能进一步降低,主要体现在开关电容电路中高质 量的线性浮置电容需要两层多晶硅,电源电压趋于进 一步的降低所带来的影响. 自 20 世纪 80 年代发展起来的开关电流电路,不 同于开关电容的“电压模式”,该技术是一种基于“电 流模式”的模拟信号采样处理技术. 电路的实现不需 要线性浮置电容,并且在用电流表示信号时,所需电压 的摆幅不大,因此具有良好的低电压工作特性. 电流 模技术的应用给模拟电路设计的性能带来了显著
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有