基于RP与NMF的内燃机气阀故障诊断方法

发布时间：2018-02-24 05:48

本文关键词： 内燃机故障诊断递归图特征提取非负矩阵分解　出处：《科学技术与工程》2016年28期 　论文类型：期刊论文

【摘要】：针对传统的内燃机故障振动诊断方法,难以有效提取故障特征,诊断精度较低的缺点,提出一种基于递归图(recurrence plots,RP)与非负矩阵分解(non-negative matrix factorization,NMF)的内燃机故障诊断新方法。该方法是利用图像的方法来进行故障诊断:首先通过递归图将采集到的内燃机缸盖表面振动信号生成图像,然后用非负矩阵对得到递归图进行特征参数提取,最后用分类器进行分类识别完成故障诊断。将该方法应用于气阀机构8种工况下振动信号诊断实例中,结果表明:该方法克服了传统的振动诊断方法从时域或频域进行分析时参数选取和故障特征提取的难题,直接将信号生成图像,对图像进行自适应特征参数提取、分类识别,能有效诊断出内燃机气阀机构故障,故障识别精度高,为内燃机振动诊断探索了一条新途径。
[Abstract]:In view of the disadvantages of traditional fault vibration diagnosis method of internal combustion engine, it is difficult to extract fault features effectively and the diagnostic accuracy is low. A new method of internal combustion engine fault diagnosis based on recurrence graphs (RP) and non-negative matrix factorization (non-negative matrix factorization NMF) is proposed. This method uses image method to diagnose internal combustion engine. Firstly, the cylinder head table of internal combustion engine is collected by recursion graph. The surface vibration signal generates the image, Then the non-negative matrix is used to extract the characteristic parameters of the recursive graph, and finally the classifier is used to classify and identify the fault diagnosis. The method is applied to the vibration signal diagnosis of the valve mechanism under eight working conditions. The results show that this method overcomes the problems of parameter selection and fault feature extraction when the traditional vibration diagnosis method is analyzed in the time domain or frequency domain. The signal is directly generated from the image, and the image is extracted by adaptive feature parameters, and the image is classified and identified. It can effectively diagnose the fault of the internal combustion engine valve mechanism, and has high fault identification accuracy, which provides a new way for the vibration diagnosis of the internal combustion engine.
【作者单位】：火箭军工程大学;
【基金】：国家自然科学基金项目(51405498) 陕西省自然科学基金项目(2013JQ8023) 中国博士后基金(2015M582642)资助
【分类号】：TK407

【相似文献】