摘要
针对液压系统的泄漏问题，提出了基于ＢＰ神经网络，以液压系统压力动态过渡过程为分析对象的故障诊断方法。该方法在通常ＢＰ神经网络的基础上，采用对学习样本加噪声的方法，提高了ＢＰ网络对噪声的抑制能力。它比传统方法，具有可靠性高，适用性广，而且成本低廉的特点。
This paper introduces a method based on BP neural networks for the leakage fault diagnosis of the Hydraulic Systems (HS). This method analysis the transient procedure of the pressure of HS. After adding noise on the learning patterns of the BP neural networks, the anti noise ability is increased than the usual BP networks. And this method for the leakage fault diagnosis is more reliable, widely used and less cost than the traditional method.
出处
《机械科学与技术》
CSCD
北大核心
1998年第1期116-118,共3页
Mechanical Science and Technology for Aerospace Engineering
基金
浙江大学流体传动及控制国家重点实验室开放基金
