针对许多基于振动信号的故障诊断方法在不同负荷下的诊断不全面的问题。提出了一种基于功率谱密度（PSD，Power Spectral Density）与支持向量机（SVM，Support Vector Machine）的故障诊断方法。该方法将振动信号功率经过滑动平均滤波（MAF，Moving Average Filter）处理，计算样本中每个周期的标准化信号的功率谱特征，再使用核方法SVM进行特征分类，从而实现故障诊断。经过柴油机实机测试，该方法对于不同负荷下的故障识别率达到96.72%，能有效识别不同负荷下的柴油机进排气阀间隙增大故障。
Abstract
For many fault diagnosis methods based on vibration signals, the diagnosis is not comprehensive under different loads. A fault diagnosis method based on power spectral density (PSD) and support vector machine (SVM) is proposed.In this method, the vibration signal power is processed by moving average filter (MAF), and the power spectral density (PSD) of the normalized signal of each period in the sample are calculated, and then the kernel method SVM is used for feature classification, so as to realize fault diagnosis. After the actual diesel engine test, the fault recognition rate of this method under different loads reaches 96.72%, and it can effectively identify the faults of the diesel engine intake and exhaust valve gap increase under different loads.
关键词
故障诊断 /
振动测试 /
信号处理 /
支持向量机
{{custom_keyword}} /
Key words
fault detection /
vibration measurement /
signal analysis /
SVM
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] AHMAD T-A，ALIREZA M. Fault detection of injectors in diesel engines using vibration time-frequency analysis[J]. Applied Acoustics，2019,143:48-58.
[2] SIANO D， D’AGOSTINO D. Knock Detection in SI Engines by Using the Discrete Wavelet Transform of the Engine Block Vibrational Signals[J]. Energy Procedia，2015，81： 673-688.
[3] 张海龙，宋业栋，李鑫，等. 基于优化VMD与欧氏距离的柴油机故障识别[J].振动、测试与诊断，2020，40(05)：911-915.
ZHANG Hailong, SONG Yedong, LI Xin, et al. Diesel engine fault identification based on optimized VMD and Euclidean distance[J]. Vibration, Measurement & Diagnosis, 2020, 40(05): 911-915.
[4] 杨建国. 高速柴油机气门漏气故障的振动诊断[J].航海技术，1997(06): 41-44.
YANG Jianguo. Vibration Diagnosis of Valve Leakage Fault in High Speed Diesel Engine[J]. Navigation Technology, 1997(06): 41-44.
[5] 郑毅，杨建国. 基于HHT的柴油机气阀漏气振动诊断方法研究[J]. 柴油机，2017，39(02): 24-27+32.
ZHENG Yi, YANG Jianguo. Research on Diesel Engine Valve Leakage Vibration Diagnosis Method Based on HHT [J]. Diesel Engine, 2017, 39(02): 24-27+32.
[6] 杨东，宋汉江，霍柏琦，等. 基于特征相关分析的柴油机故障诊断方法研究[J]. 现代制造工程，2018(12)：147-152.
YANG Dong, SONG Hanjiang, HUO Baiqi, et al. Research on Diesel Engine Fault Diagnosis Method Based on Feature Correlation Analysis[J]. Modern Manufacturing Engineering, 2018(12): 147-152.
[7] 贾翔宇，贾继德，韩佳佳，等. 基于压缩小波变换的柴油机失火故障诊断[J]. 军事交通学院学报，2017，19(07)：31-35.
JIA Xiangyu, JIA Jide, HAN Jiajia, et al. Diesel engine misfire fault diagnosis based on compressed wavelet transform [J]. Journal of Military Transportation College, 2017, 19(07): 31-35.
[8] 廖舒琅，毕凤荣，田从丰，等.基于QPSO-MC-GCN的柴油机典型故障诊断方法研究[J]. 振动与冲击，2022，41(17)：268-275.
LIAO Shulang, BI Fengrong, TIAN Congfeng, et al. Research on typical fault diagnosis method of diesel engine based on QPSO-MC-GCN [J]. Journal of Vibration and Shock, 2022, 41(17): 268-275.
[9] 刘东川，邓艾东，赵敏，等.基于改进深度森林的旋转机械故障诊断方法[J]. 振动与冲击，2022，41(21)：19-27.
LIU Dongchuan, DENG Aidong, ZHAO Min, et al. Rotating Machinery Fault Diagnosis Method Based on Improved Deep Forest [J]. Journal of Vibration and Shock, 2022, 41(21): 19-27.
[10] 张俊红，孙诗跃，朱小龙，等. 基于改进卷积神经网络的柴油机故障诊断方法研究[J]. 振动与冲击，2022，41(06)：139-146.
ZHANG Junhong, SUN Shiyue, ZHU Xiaolong, et al. Research on Diesel Engine Fault Diagnosis Method Based on Improved Convolutional Neural Network [J]. Journal of Vibration and Shock, 2022, 41(06): 139-146.
[11] 赵学智，叶邦彦，陈统坚. 傅里叶变换的时频聚集性度量准则研究[J].振动.测试与诊断，2017，37(05)：948-956.
ZHAO Xuezhi, YE Bangyan, CHEN Tongjian. Research on Time-Frequency Aggregation Metrics of Fourier Transform [J]. Vibration, Measurement & Diagnosis, 2017, 37(05): 948-956.
[12] 章余，景博，焦晓璇，等. 基于改进的CNN-SVM的机载燃油泵故障诊断[J]. 噪声与振动控制，2022，42(06)：137-142.
ZHANG Yu, JING Bo, JIAO Xiaoxuan, et al. Fault Diagnosis of Airborne Fuel Pump Based on Improved CNN-SVM [J]. Noise and Vibration Control, 2022, 42(06): 137-142.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1768 KB)
