基于蚁群算法优化选取阈值的EMD消噪方法

摘要/Abstract

摘要：

为了改进经验模式分解(EMD)算法的消噪性能,在传统EMD消噪分解的基础上，参照小波阈值的消噪方法,提出了一种基于自适应阈值的EMD消噪方法。首先,建立去噪阈值和均方误差之间的对应函数，在所选阈值保证均方误差最小的前提下,利用具有较好全局搜索性的蚁群算法,根据建立的函数搜索阈值,克服了传统方法中硬阈值和软阈值固定选取的缺陷,实现了最优阈值的选取。仿真信号分析和实际轴承故障信号分析表明，该方法与传统的EMD消噪方法、软硬阈值分析方法相比，消噪效果更加明显。

关键词: 经验模式分解(EMD), 优化阈值, 蚁群算法, 消噪

Abstract:

To further enhance the de-noising performance of EMD algorithm, this paper proposed a de-noising method based on adaptive threshold of EMD referred to the method of threshold-based wavelet de-noising. First, the relationship between the mean square error(MSE) and the threshold function were established, then the optimal threshold of each intrinsic mode function(IMF) level were searched and obtained by the ant colony algorithm which realized to get the minimum MSE. So this method eliminates the disadvantages of soft and hard threshold de-noising method effectively. The experimental results indicate that the method is more effective in noise reduction in comparison with the conventional soft and hard threshold-based EMD de-noising methods, the method works better.

Key words: empirical mode decomposition(EMD), optimal threshold, ant colony algorithm, signal de-noising

中图分类号:

TH311

张根保, 范秀君. 基于蚁群算法优化选取阈值的EMD消噪方法[J]. 中国机械工程, 2014, 25(4): 427-432.

Zhang Genbao, Fan Xiujun. Method for De-nosing Based on Optimal Threshold of EMD Optimized by Ant Colony Algorithm[J]. China Mechanical Engineering, 2014, 25(4): 427-432.

参考文献

[1]熊炘,杨世锡,周晓峰.旋转机械振动信号的固有模式函数降噪方法[J].浙江大学学报(工学版),2011,45(8):1376-1381.
Xiong Xin,Yang Shixi,Zhou Xiaofeng.IMF-based Denoising Method for Vibration Signal in Rotating Machinery[J].Journal of Zhejiang University(Engineering Science),2011,45(8):1376-1381.
[2]冷军发,荆双喜,陈东海.基于EMD与同态滤波解调的矿用齿轮箱故障诊断[J].振动、测试与诊断,2011,31(4):435-438.
Leng Junfa,Jing Shuangxi,Chen Donghai.The Fault Diagnosis Method for Mine Based on the EMD and Homomorphic Filtering[J].Journal of Vibration,Measurement & Diagnosis,2011,31(4):435-438.
[3]刘智.改进的正交小波变换阈值去噪算法研究[J].计算机仿真,2011,28(8):272-275.
Liu Zhi.Image Denoising Threshold Method Based on Improved Coefficient Weighted Mean[J].Computer Simulation, 2011, 28(8): 272-275.
[4]张弦,王宏力.进化小波消噪方法及其在滚动轴承故障诊断中的应用[J].机械工程学报,2010,46(15):76-80.
Zhang Xian,Wang Hongli.Evolutionary Wavelet Denoising and Its Application to Ball Bearing Fault Diagnosis[J].Journal of Mechanical Engineering,2010,46(15):76-80.
[5]涂建成,席旭刚,罗志增.一种改进闭值的平移不变量小波消噪方法[J].信息与控制,2011,40(2):150-154.
Tu Jiancheng,Xi Xugang,Luo Zhizeng.A Tanslation-invariant Wavelet Denoising Method Based on Improved Threshold[J]. Information and Control,2011,40(2):150-154.
[6]Donoho D L,Johnstone I M.Adapt to Unknown Smoothness via Wavelet Shrinkage[J].Journal of the American Statistical Association,1995,90(432):1200-1224.
[7]行鸿彦,黄敏松.基于Hilbert-Huang变换的QRS波检测算法研究[J].仪器仪表学报,2009,30(7):1469-1475.
Xing Hongyan,Huang Minsong.Research on QRS Complex Detection Algorithm Based on Hilbert-huang Transform[J]. Chinese Journal of Scientific Instrument,2009,30(7):1469-1475.
[8]周小林,孙东松.基于多尺度EMD的激光雷达信号分段去噪[J].红外与激光工程,2006,35:477-482.
Zhou Xiaolin,Sun Dongsong.Lidar Signal Subsection Denoising Based on Multi-dimension EMD[J].Infrared and Laser Engineering,2006,35:477-482.
[9]李惠光,尹玉.基于BEMD和自适应阈值的多尺度边缘检测[J].工业控制计算机,2008,21(6):63-67.
Li Huiguang,Yin Yu.Multi-scale Edge Detection Based on EMD and Adaptive Thresholds[J].Industrial Control Computer, 2008, 21(6):63-67.
[10]武仁杰.蚁群算法在自动组卷建模中的应用研究[J].电子与信息学报,2011,28(8):380-383.
Wu Renjie.Study on Intelligently Composing Test Paper Based on Ant Colony Optimization[J].Computer Simulation, 2011, 28(8):380-383.
[11]胡小丽,金明.基于EMD的图像信号去噪的改进算法[J].电子测量技术,2009,32(11):58-61.
Hu Xiaoli,Jin Ming.Improved Algorithm of Image Signal Denoising Based on EMD[J].Electronic Mea-surement Technology, 2009,32(11):58-61.
[12]王静,范毅方.基于小波阈值的sEMG信号消噪方法研究[J].计算机仿真, 2010,27(2):325-327.
Wang Jing,Fan Yifang.Denoising of sEMG SignalBased on Wavelet Threshold Shrinkage[J].Computer Simulation, 2010, 27(2): 325-327.
[13]张通,张骏,张怡.基于改进小波阈值的激光陀螺漂移信号降噪[J].仪器仪表学报,2011,32(2):258-262.
Zhang Tong,Zhang Jun,Zhang Yi.Ring Laser Gyro Drift Signal Denoising Based on Improved Wavelet Threshold[J]. Chinese Journal of Scientific Instrument,2011,32(2):258-262.
[14]臧玉萍,张德江,王维正.小波分层阈值降噪法及其在发动机振动信号分析中的应用[J].振动与冲击,2009,28(8):57-60.
Zang Yuping,Zhang Dejiang,Wang Weizheng.A Wavelet Layered Threshold De-noising Method and Its Application in the Engine Vibration Signal Analysis[J].Journal of Vibration and Shock,2009,28(8):57-60.

[1]	辜勇, 袁源乙, 张列, 段晶晶. 带时间窗的多中心半开放式车辆路径问题[J]. 中国机械工程, 2020, 31(14): 1733-1740.
[2]	乔东平, 裴杰, 文笑雨, 肖艳秋, 焦建强, . [车间调度]一种求解单机总加权延迟调度问题的改进蚁群算法[J]. 中国机械工程, 2018, 29(22): 2703-2710.
[3]	侯仰强1;王天琪1;李亮玉1;张志臣1;赵娜2. 基于蚁群算法-粒子群算法的白车身侧围点焊机器人路径规划[J]. 中国机械工程, 2017, 28(24): 2990-2994.
[4]	张玉存, 徐飞, 付献斌. 先验概率与曲线概率阈值分割相结合的消噪方法[J]. 中国机械工程, 2017, 28(08): 936-940,945.
[5]	张铁, 苏杰汶. 基于改进蚁群算法的机器人末端路径排序优化[J]. 中国机械工程, 2016, 27(19): 2624-2629.
[6]	王恒升, 陈伟锋, 王思远. 基于末端杆件螺旋运动的凿岩机械臂孔序规划[J]. 中国机械工程, 2016, 27(13): 1748-1754.
[7]	方清华, 倪丽萍, 李一鸣. 求解物流Web服务组合问题的两阶段多目标蚁群算法[J]. 中国机械工程, 2016, 27(10): 1327-1336.
[8]	黄风立, 顾金梅, 张礼兵, 徐春光, 王海燕. 基于禁忌制造特征动态调整的STEP-NC工艺路线蚁群优化方法[J]. 中国机械工程, 2016, 27(05): 596-602.
[9]	吴长友, 戴宁, 刘浩, 程筱胜, 李大伟, 沈振宏, 孙登广. 基于改进蚁群算法的分形刀轨连接技术[J]. 中国机械工程, 2016, 27(01): 58-65.
[10]	谢志江, 梁欢, 宋代平. 基于连续蚁群算法的3-RPS并联机构正解[J]. 中国机械工程, 2015, 26(6): 799-803.
[11]	姜康, 胡龙. 复杂环境下的装配路径求解与优化[J]. 中国机械工程, 2015, 26(5): 632-636.
[12]	谢伟松, 邓铮, 丁伯慧 . 用GAAA优化多阶段装配过程中的夹具布局[J]. 中国机械工程, 2015, 26(5): 658-663.
[13]	刘琼, 刘秀城, 张超勇, 饶运清. 基于改进蚁群算法的带时间窗废品收集车辆路径问题[J]. 中国机械工程, 2015, 26(2): 247-244.
[14]	钱立军, 邱利宏, 陈朋. 基于模糊PID扭矩识别的混合动力汽车优化控制[J]. 中国机械工程, 2015, 26(13): 1752-1759.
[15]	汤洪涛, 刘璐, 陈明, 鲁建厦. 基于Stigmergy的Holonic控制架构与调度策略[J]. 中国机械工程, 2015, 26(1): 49-54,62.