基于BP神经网络的翻车机液压系统故障诊断  

Fault Diagnosis Based on BP Neural Network for Hydraulic Control System of Rotary Dump

作　　者：刘小平[1,2] 鄂东辰 高强[1,2] 张立杰[1,2] 

机构地区：[1]燕山大学先进锻压成形技术与科学教育部重点实验室,河北秦皇岛066004 [2]燕山大学河北省重型机械流体动力传输与控制重点实验室,河北秦皇岛066004

出　　处：《液压与气动》2016年第8期68-73,共6页Chinese Hydraulics & Pneumatics

摘　　要：为了快速诊断出翻车机液压系统故障产生的位置以及故障原因,提出了一种基于BP神经网络算法的翻车机液压系统故障诊断方法,在此基础上提出了大型液压系统故障诊断分块建模的原则。利用某公司C型转子式翻车机故障数据样本建立了整体、分块故障诊断BP神经网络模型,对比实验数据分析表明,采用分块建模原则建立的BP神经网络故障诊断模型对翻车机液压系统故障具有较高识别精度,对提高翻车机液压系统状态监测与故障诊断能力有较大实用价值和工程意义。In order to quickly diagnose the fault locations and causes of the hydraulic system of rotary dump, the fault diagnosis method of the hydraulic system of rotary dump based on the BP neural network algorithm is put for- ward, and on this basis the block modeling principle of fault diagnosis for a large hydraulic system is put forward. The integer and block model of BP neural network fault diagnosis model are presented based on the data samples of fault diagnosis for the C type rotary dump of a company. The analysis of experimental data shows, the BP neural network fault diagnosis model based on the block modeling principle has higher recognition rate for the faults of the hydraulic system of rotary dump. It has great practical value and engineering significance to improve the ability of the state monitoring and fault diagnosis of the hydraulic system of rotary dump.

关 键 词：翻车机 故障诊断 人工神经网络 液压系统 

分 类 号：TH137[机械工程—机械制造及自动化] TP182[自动化与计算机技术—控制理论与控制工程]