摘要
为了实现液压挖掘机的整机故障诊断,提出基于BP神经网络的故障诊断方法。将BP神经网络应用于液压挖掘机的故障诊断中,研究BP神经网络的结构和算法。以液压挖掘机整机故障诊断为例,选择典型的故障样本训练神经网络,使神经网络具有较好容错性和稳定性,经过训练的神经网络就可以实时、准确地诊断出挖掘机的故障。并使用Matlab的神经网络工具箱进行模拟仿真,仿真结果表明:BP神经网络能够很好地应用于液压挖掘机的实际故障诊断,网络收敛速度快、学习记忆稳定,具有一定的工程实用价值。
A method based on BP neural network was proposed in order to achieve the fault diagnosis of hydraulic excavator. The structure and algorithm of the BP neural network were studied. Taking the whole fault diagnosis of hydraulic excavator as an example, the typical fault samples were selected to train the neural network and the neural network had good tolerance and stability. The trained neural network could be used to real - time, accurately diagnose the fault of hydraulic excavator. The application effect was verified by using the neural network toolbox of Matlab. The simulation results show the BP neural network can be used in the practical fault diagnosis of hydraulic excavator. It has high convergence rate and high stability of learning and memory, so it has certain practical engineering value.
出处
《机床与液压》
北大核心
2011年第23期160-164,共5页
Machine Tool & Hydraulics
基金
山东省优秀中青年科学家奖励基金项目(BS2010ZZ001)
关键词
神经网络
故障诊断
液压挖掘机
仿真
BP neural network
Fault diagnosis
Hydraulic excavator
Simulation
