针对采用SOM 网络进行多故障诊断时,要求多故障模式相似且不包含标准故障输出的限制,提出将SOM 网络与可拓理论相结合的多故障诊断方法.首先采用SOM 网络对训练样本进行聚类,得到故障模式及其聚类中心.然后针对每种故障模式的每个特征构造在聚类中心处取得最大值的关联函数,并以各特征的关联函数值为基础,设计多故障评价指标实现多故障诊断.最后采用汽轮发电机组振动信号的频谱数据对算法进行验证,结果表明该方法能够正确识别待诊断样本的单故障和多故障模式,具有可行性.
This paper proposes a multi-fault diagnosis algorithm combining SOM network with extension theory to meet the requirement that multi-fault modes should be similar and do not contain the standard fault output when SOM network is used for multi-fault diagnosis. First, the training samples are clustered by SOM network, and the fault modes and these clustering centers can be obtained. Second, the dependent function of each feature for each fault mode is set up where the maximum value can be obtained at the clustering center. Next, the evaluation index of multi-fault modes is designed for multi-fault diagnosis, which is based on the dependent function values of features. Finally, the spectrum data of vibration signal of steam turbine generator unit is adopted to verify the algorithm. The results show that both single-fault mode and multi-fault modes can be correctly distinguished by this method, so the algorithm is feasible.
[1] Kohonen T. Essentials of the self-organizing map[J]. Neural Networks, 2013, 37: 52-65.
[2] 吴俊芬, 胡念苏, 赵瑜. 基于自组织特征映射神经网络的汽轮机回热 系统故障诊断[J]. 武汉大学学报: 工学版, 2003, 36(4): 99-102. Wu Junfen, Hu Niansu, Zhao Yu. Fault diagnosis of steam turbine regenerative system based on self-organizing neural network[J]. Engineering Journal of Wuhan University, 2003, 36(4): 99-102.
[3] 尤丽静, 陈在平. 基于自组织神经网络的轴流风机不对中故障诊断研 究[J]. 天津理工大学学报, 2010, 26(1): 68-70. You Lijing, Chen Zaiping. Misalignment fault diagnosis of the axial flow fan based on self-organizing neural network[J]. Journal of Tianjin University of Technology, 2010, 26(1): 68-70.
[4] 张彼德. 汽轮发电机组振动多故障诊断模型及方法研究[D]. 重庆: 重 庆大学, 2002: 36-38. Zhang Bide. Study on diagnosis models and methods of steam turbine generators-Sets vibration multiple fault[D]. Chongqing: Chongqing University, 2002: 36-38.
[5] 杨春燕, 蔡文. 可拓工程[M]. 北京: 科学出版社, 2007. Yang Chunyan, Cai Wen. Extension engineering[M]. Beijing: Science Press, 2007.
[6] 邹云峰, 吴为麟, 李智勇. 基于自组织映射神经网络的低压故障电弧 聚类分析[J]. 仪器仪表学报, 2010, 31(3): 571-576. Zou Yunfeng, Wu Weilin, Li Zhiyong. Cluster analysis of arc fault in lowvoltage based on SOM neural network[J]. Chinese Journal of Scientific Instrument, 2010, 31(3): 571-576.
[7] 王永林. 关于可拓评价中几种关联函数的分析[J]. 计算机工程与应用, 2010, 46(12): 56-59. Wang Yonglin. Analysis on some dependent functions of extension evaluation [J]. Computer Engineering and Applications, 2010, 46(12): 56-59.
[8] 徐慧, 周建美, 蒋峥峥. 基于侧距的关联函数构造及应用[J]. 南通大学 学报: 自然科学版, 2010, 9(2): 9-13. Xu Hui, Zhou Jianmei, Jiang Zhengzheng. Construction and application of dependent function based on lateral distance[J]. Journal of Nantong University: Natural Science Edition, 2010, 9(2): 9-13.
[9] 张彼德, 欧健, 孙才新, 等. 汽轮发电机多故障诊断的SOM神经网络方 法[J]. 重庆大学学报: 自然科学版, 2005, 28(2): 36-38. Zhang Bide, Ou Jian, Sun Caixin, et al. Application of SOM neural network in multiple fault diagnosis of turbo generator set[J]. Journal of Chongqing University: Natural Science Edition, 2005, 28(2): 36-38.
