基于自回归移动模型汽车传动系统故障诊断  

Fault Diagnosis of Automobile Transmission System Based on Autoregressive Moving Model

作　　者：付小丹 FU Xiaodan(Jiangsu Polytechnic of Information Technology,Wuxi 214000,China)

机构地区：[1]江苏信息职业技术学院,江苏无锡214000

出　　处：《汽车实用技术》2023年第20期110-116,共7页Automobile Applied Technology

摘　　要：针对复杂汽车传动系统故障集,提出基于自回归移动模型的故障诊断算法研究。以随机差分理论为基础构建故障信号的时序模型,并确定影响序列值的各种参数,采集原始故障数据,进行A/D转换和数据标准化处理,为保留离散型数据的原始特征并降低系统噪声干扰,采用数据升维理念形成二维纹理图像,并利用局部二值特征算子提取二维图像的细节。实验结果显示,提出诊断算法具有更好故障特征分类性能和样本检验一致性,平均诊断精度可以达到99.27%。Aiming at the complex fault set of automobile transmission system,a fault diagnosis algorithm based on autoregressive moving model is proposed.Based on the random difference theory,the timing model of the fault signal is constructed,and various parameters affecting the sequence value are determined.The original fault data is collected,and A/D conversion and data standar-dization are carried out.In order to retain the original features of the discrete data and reduce the interference of system noise,two-dimensional texture images are formed by using the concept of data dimension enhancement.Local binary feature operators are used to extract the details of two-dimen-sional images.The experimental results show that the proposed algorithm has better fault feature classification performance and sample test consistency,with an average diagnosis accuracy of 99.27%.

关 键 词：自回归移动模型 变速箱 齿轮组 离散型 升维处理 

分 类 号：TP306[自动化与计算机技术—计算机系统结构]