欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为提高模拟电路故障诊断特征信息提取的高效性和实现故障模式分类的准确性,提出一种基于曲线波理论的多尺度几何分析方法和超限学习机相结合的模拟电路故障诊断新方法.通过曲波变换使用空域带通滤波算子来分解不同的尺度,对模拟电路故障特征提取后重构系统,提高稳定性、高效性并达到最优逼近,结合超限学习机训练过程不需要迭代的突出性能,大大提高了故障诊断速度.通过与其他故障诊断方法比较,结果表明了该方法的有效性.
英文摘要：
To improve the efficiency of feature information and achieve the accuracy of fault mode classification in analog circuit fault diagnosis,this paper presented a new method of analog circuit fault diagnosis that based on multi-scale geometric analysis of curvelet theory and extreme machine learning.The fault feature extraction of analog circuit got to optimal approximation,by using a band pass filter operator to decompose different scales of curvelet transform and reconfigurable system,which improved the stability and efficiency.On this basis,it combined the outstanding performance of extreme machine learning which does not require iterative training and learning,which greatly improved the speed of fault diagnosis.Compared with other fault diagnosis methods,the results show the effectiveness of the proposed method.
同期刊论文项目
同项目期刊论文
Design of test stimuli and minimisation of ambiguity in fault diagnosis of analogue circuits with to
Nonlinear correction of photoelectric displacement sensor based on least square support vector machi
A Novel Localization Algorithm Based on Isomap and Partial Least Squares for Wireless Sensor Network
Analysis of Electromagnetic Force Distribution on End winding of Electrical Submersible Motor During
EFFECT OF GRAIN BOUNDARY ON THE CHARACTERISTICS OF POLY-SI METAL-INSULATOR-SEMICONDUCTOR PHOTODETECT
Wideband Tuning of Impedance Matching Networks using Hierarchical Genetic Algorithms for Multistanda
期刊信息
位置：