生物免疫机理在往复压缩机在线状态监测中的应用  

Application of Biological Immune Mechanics for On-line Monitoring of Reciprocating Compressor

作　　者：窦唯[1] 刘树林[1] 孙明[2] 陈业生[3] 

机构地区：[1]大庆石油学院,黑龙江大庆163318 [2]哈尔滨铁路局齐齐哈尔工程总公司,黑龙江齐齐哈尔161000 [3]大庆石油管理局,黑龙江大庆163400

出　　处：《流体机械》2004年第5期16-19,38,共5页Fluid Machinery

基　　金：黑龙江省自然科学基金项目 (F0 1 0 7)

摘　　要：针对往复压缩机在线监测时难以提取异常特征的实际情况 ,提出了一种适于往复压缩机的在线状态监测方法。该方法是基于生物免疫系统反面选择机理 ,并结合人工神经网络进行监测的一种方法。该方法能有效地提取压缩机的异常特征 ,提高压缩机的在线状态监测的准确率。在线监测往复压缩机示功图的实例结果表明 ,该方法能准确监测出往复压缩机主要故障所引起的异常 ,并具有较好的在线性、准确性。A new approach which suits for on-line state monitoring of reciprocating compressors is presented.The approach is based on negative selection mechanism of the natural immune system and combined with artificial neural network to be used for monitoring.The approach is effective to extract abnormal characteristics of reciprocating compressors and improve the accuracy of on-line state monitoring of reciprocating compressor. The result by the example of reciprocating compressors dynamometer card of on-line state monitoring shows the approach can exactly detect the degree of abnormality of reciprocating compressors. It shows the approach is feasible and has better on-line quality, accuracy and robustness.

关 键 词：往复压缩机 免疫机理 反面选择算法 在线监测 

分 类 号：TH45[机械工程—机械制造及自动化]