基于Lyapunov指数的一类轴承故障检测的研究.pdfVIP

Proceedings of the 26th Chinese Control Conference July 26-31, 2007, Zhangji aj ie, Hunan, China 基于Lyapunov 指数的一类轴承故障检测研究* 陶新民，杜宝祥，徐 勇 尔滨工程大学信通学院，黑龙江 尔滨 150001 E-mail: taoxinmin@hrbeu.edu.cn 要：为了解决轴承故障检测应用中，异常数据样本分布不均且不易收集的实际问题，以及计算 Lyapunov 指数 的同时需计算嵌入维度和时间间隔的问题。本文提出利用正常样本形成相空间参数，不同运行状态下的样本在该空间 上的投影形成轨迹的Lyapunov 指数作为特征，并用遗传算法进行阈值优化的一类轴承故障检测模型。实验结果表明 基于Lyapunov 指数为特征可以有效地进行轴承故障检测。同时，我们将Lyapunov 指数为特征同Lyapunov 指数谱熵 为特征的检测器性能进行了比较，实验结果验证了基于Lyapunov 指数为特征的检测效果更加明显.最后，将本文建议 的算法同时域序列值为特征的MLP 及其他算法进行了比较，结果表明建议的算法在检测率上有明显提高。 关键词：故障检测，重构相空间，Lyapunov 指数，Lyapunov 指数谱熵，MLP One-class Bearings Fault Detection Model Based on Lyapunov Exponent Spectrum Tao Xinmin, Du Baoxiang, Xu Yong Department of Information and Communication ,Harbin Engineering University, Harbin 150001, P. R. China E-mail: taoxinmin@hrbeu.edu.cn Abstract: In order to avoid the practical application problems, abnormal data insufficiency and unavailability, and solve the difficulty of calculating embed dimension and time tag before calculating Lyapunov exponent, an one-class Bearings fault de- tection model based on Genetic Algorithm and Lyapunov Exponent Spectrum is proposed in this paper. The normal training samples are used to decide reconstructed phase space. Then the signals with different conditions will be proj ected into RPS, the Lyapunov exponent is calculated which is classified as features. The optimum decision threshold values are determined by Genetic Algorithm. The results show that Lyapunov exponent for fault detection is more efficient than for fault diagnosis. In experiment, the performance of detector with largest Lyapunov exponent and Lyapunov exponent spect