基于BP神经网络和灰色理论的示功图故障诊断  

Diagnosis of working drawing based on BP net and Grey Theory

作　　者：李训铭[1] 周志权[1] 

机构地区：[1]河海大学,江苏南京210036

出　　处：《电子设计工程》2012年第17期23-25,31,共4页Electronic Design Engineering

摘　　要：抽油井故障诊断系统是油井系统产量的关键,为了更好更快地对当前油井系统进行诊断以保证石油的产量,人们利用各种各样的技术来完成这一目标。示功图的诊断法是油田有杆抽油诊断的主要方法,文章根据示功图诊断的特点,提取出灰度矩阵特征向量,运用神经网络对有杆抽油油田典型故障诊断进行建模,最后用实例验证了此方法的正确性。实验证明,本系统不仅可行性好,而且故障识别率高,对增加油井产量有重要意义。Pumping well system fault diagnosis system is the key to production,for better and faster diagnosis of the current well system to ensure the production of oil,people uses a variety of technologies to achieve this goal. Diagnosis of working drawing is a major method in diagnosis of rod pumping oil. Through features of working drawing, we propose grey matrix characteristic vectors of working drawing. The diagnosis modeling is built for rod pumping fault based on the neural network. At last we use experiment to test correctness of this method. Our experiment shows that this system has not only large feasibility, but also a high error recognition rate, which has great importance to increasing of oil production.

关 键 词：BP神经网络 示功图 灰度矩阵 故障诊断 特征提取 

分 类 号：TE933[石油与天然气工程—石油机械设备]