压路机液压系统故障诊断研究

发布时间：2019-05-16 05:50

【摘要】：振动压路机作为一种重要的工程压实机械,广泛应用于道路工程、机场港口和市政建设等工程领域。在大型施工现场,往往是工程机械群协同作业的,如果压路机出现故障,与其协同作业的机器设备都要被迫停工,会影响工程的进度,拖延工期甚至带来很大的经济损失。液压系统是振动压路机的主要系统,其工作环境往往比较恶劣,工况相对复杂,发生故障的概率较高。开展振动压路机液压系统故障诊断的研究工作,有利于及时排除液压系统的故障,充分发挥振动压路机的最大效能,对确保工程质量、加快工程进度、提高经济效益有着十分重要的经济意义和现实意义。本文分析了全液压振动压路机的工作原理及液压系统的基本故障及排除方法等。提出了基于主成分分析方法对故障特征进行提取,然后通过模糊推理和模糊神经网络两种算法对故障进行模式识别。经过仿真分析比较,模糊神经网络对故障识别的鲁棒性和稳定性较好。文中对传统的主成分分析法进行改进,以轴向柱塞泵为例对其进行二次约简降维处理,降低了冗余度,并且保证降维后的数据仍携带足够的原样本数据信息。然后以主成分分析法降维后的数据为样本,利用模糊推理和模糊神经网络对故障进行识别,通过仿真分析比较,建立了基于主成分分析与模糊神经网络的压路机液压系统故障诊断模型。仿真结果表明,该模型对于压路机液压系统故障诊断具有良好的容错性和鲁棒性,避免了标准神经网路容易陷入局部收敛的缺点,该模型可以广泛的应用于压路机液压系统故障诊断中。
[Abstract]:Vibratory roller, as an important engineering compaction machine, is widely used in road engineering, airport port and municipal construction and other engineering fields. In the large construction site, it is often the cooperative operation of the construction machinery group. If the roller fails, the machinery and equipment working with it will be forced to stop work, which will affect the progress of the project and delay the construction period and even bring great economic losses. Hydraulic system is the main system of vibratory roller, its working environment is often bad, the working condition is relatively complex, and the probability of failure is high. The research work on fault diagnosis of hydraulic system of vibratory roller is helpful to eliminate the fault of hydraulic system in time, give full play to the maximum efficiency of vibratory roller, and ensure the quality of the project and speed up the progress of the project. It is of great economic and practical significance to improve economic efficiency. In this paper, the working principle of full hydraulic vibratory roller and the basic faults and troubleshooting methods of hydraulic system are analyzed. A principal component analysis (PCA) method is proposed to extract fault features, and then fuzzy reasoning and fuzzy neural network are used to recognize the fault pattern. The simulation results show that the fuzzy neural network has better robustness and stability to fault recognition. In this paper, the traditional principal component analysis method is improved, and the axial piston pump is taken as an example to reduce the redundancy, and to ensure that the data after dimension reduction still carry enough original sample data information. Then, taking the data after dimension reduction by principal component analysis as samples, fuzzy reasoning and fuzzy neural network are used to identify the faults, and through simulation analysis and comparison, A fault diagnosis model of hydraulic system of roller based on principal component analysis and fuzzy neural network is established. The simulation results show that the model has good fault tolerance and robustness for hydraulic system fault diagnosis of roller, and avoids the disadvantage that the standard neural network is easy to fall into local convergence. The model can be widely used in fault diagnosis of hydraulic system of roller.
【学位授予单位】：长安大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：U415.521

【参考文献】