The invention relates to the technical field of fault detection, and particularly discloses an anchor chain lifter hydraulic system fault detection method, which comprises the following steps of: designing and constructing a test bed formed by an anchor chain lifter hydraulic system, and performing parameter analysis on a pressure sensor mounted in a hydraulic system pipeline of the test bed; measurement parameters of each pressure sensor are preprocessed through an ANN fault diagnosis model, evaluation indexes with representative parameters are calculated, selected and used, the selected evaluation indexes serve as input of an ANN fault diagnosis model classifier, the calculation cost of the ANN fault diagnosis model is reduced, faults are classified more accurately, and the fault diagnosis efficiency is improved. The ANN neural network model is optimized in combination with the gradient descent method, the fault type can be rapidly and accurately determined, the accuracy of output fault diagnosis classification is high, the classification precision can reach 98.4% or above, and the good detection precision is achieved.
本发明涉及故障检测技术领域,具体公开了一种锚链提升器液压系统故障检测方法,通过设计并搭建由锚链提升器液压系统构成的试验台,对其液压系统管路中安装的压力传感器进行参数分析,通过ANN故障诊断模型对每一个压力传感器测量参数进行预处理,计算选择使用具有代表性参数评价指标,根据所选取的评价指标作为ANN故障诊断模型分类器的输入,减少ANN故障诊断模型的计算成本,进而更加精确地对故障进行分类,再结合梯度下降法优化ANN神经网络模型,能够快速精准确定故障类型,输出故障诊断分类的准确率高,分类精度能够达到98.4%以上,具有良好的检测精度。
Fault detection method for hydraulic system of anchor chain lifter
一种锚链提升器液压系统故障检测方法
11.08.2023
Patent
Elektronische Ressource
Chinesisch
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B66C Krane , CRANES / F15B SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL , Druckmittelbetriebene Systeme allgemein / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung |
Hydraulic lifter on-load descent method and hydraulic lifter on-load movement method
Europäisches Patentamt | 2020
|