掘进机液压系统故障检测方法研究与仿真

发布时间：2019-03-28 12:39

【摘要】：部分断面掘进机作为现代化煤矿掘进的主力机械,液压系统构成复杂,易在恶劣的工作环境中发生液压泵损坏、液压马达噪声过大、单向阀泄漏等故障,但是,这些故障特征之间存在较强的关联性,且故障之前不存在准确的区分标准,传统的诊断方法没有利用这种关联判断故障,仅以简单阀值理论进行判断,难以满足智能诊断要求。为此提出一种采用模糊理论与BP神经网络结合的诊断方法,通过模糊理论对故障关联性产生的模糊性进行判断,再利用BP神经网络进行分析,以柱塞泵为例建立部分断面掘进机液压系统故障诊断的模型,对液压泵的故障状态进行诊断。与标准BP神经网络模型诊断方法对比研究表明,模糊神经网络模型收敛速度快,精度高,更适用于部分断面掘进机液压系统的故障诊断。
[Abstract]:As the main machinery of modern coal mine excavation, some cross-section tunneling machines have complex hydraulic system, which is easy to cause damage of hydraulic pump, excessive noise of hydraulic motor, leakage of one-way valve and so on in harsh working environment. There is a strong correlation between these fault features, and there is no accurate distinction standard before the fault. The traditional diagnosis method does not use this correlation to judge the fault, but only by the simple threshold theory, so it is difficult to meet the requirements of intelligent diagnosis. Therefore, a diagnosis method based on the combination of fuzzy theory and BP neural network is put forward. Fuzzy theory is used to judge the fuzziness of fault correlation, and then BP neural network is used to analyze it. Taking plunger pump as an example, the fault diagnosis model of hydraulic system of partial cross-section tunneling machine is established, and the fault state of hydraulic pump is diagnosed. Compared with the standard BP neural network model diagnosis method, the fuzzy neural network model has the advantages of fast convergence speed and high precision, which is more suitable for fault diagnosis of hydraulic system of some cross-section roadheader.
【作者单位】：河南理工大学电气工程与自动化学院;
【分类号】：TD421.5

【相似文献】