石化旋转机械故障诊断及维修管理优化研究

发布时间：2018-06-19 02:51

本文选题：石化旋转机械 + 以可靠性为中心的维修　；参考：《燕山大学》2011年硕士论文

【摘要】：旋转机械是石化企业生产中的核心设备，任何设备不可避免会出现故障，维修是保障其正常运行的重要手段。但石化旋转机械故障原因具有复杂性、多样性和不确性的特点，而且影响维修决策的因素很多，所以其维修决策管理过程非常复杂。为此，本文对石化旋转机械的故障诊断和维修管理优化进行了研究。建立了基于贝叶斯网络的故障诊断模型。为防止或避免同类故障的再次发生，首先将故障原因进行分类分析，提出了相应的维修措施；然后将故障模式与影响分析与贝叶斯网络方法相结合，，从而可定量地分析出影响设备运行的薄弱环节。以一台石化企业生产中的离心泵为应用实例，分析结果表明，该方法可为石化旋转机械的故障诊断提供一定的依据。开发了计算机辅助设备维修管理系统。该系统使用VB语言编写，采用模块化设计框架。它能够对设备的基本信息进行管理，并且建立了故障模式数据库，同时实现了贝叶斯网络的自动化分析。该系统可提高设备信息管理和故障诊断的效率。以单位时间内设备寿命管理费用最低为目标，建立了适用于各种寿命分布的基于几何过程维修优化模型，并引入了蒙特卡罗方法，运用Matlab编制了相应的仿真程序，对机械设备的最佳寿命周期进行预测。以服从二参数威布尔分布的离心泵作为分析实例。结果表明，所建立的模型具有一定的合理性，能够对机械设备的维修决策提供一定的指导。
[Abstract]:Rotating machinery is the core equipment in the production of petrochemical enterprises, any equipment will inevitably fail, maintenance is an important means to ensure its normal operation. However, the fault causes of petrochemical rotating machinery are complex, diverse and uncertain, and there are many factors that affect the maintenance decision, so the maintenance decision management process is very complex. Therefore, this paper studies the fault diagnosis and maintenance management optimization of petrochemical rotating machinery. A fault diagnosis model based on Bayesian network is established. In order to prevent or avoid the recurrence of similar faults, the causes of the faults are classified and analyzed, and the corresponding maintenance measures are put forward, and then the fault mode and the impact analysis are combined with the Bayesian network method. Thus, the weak links affecting the operation of the equipment can be quantitatively analyzed. Taking a centrifugal pump in the production of a petrochemical enterprise as an example, the analysis results show that the method can provide a certain basis for the fault diagnosis of petrochemical rotating machinery. The computer aided equipment maintenance management system is developed. The system is written in VB language and modular design framework is adopted. It can manage the basic information of the equipment, establish the fault mode database, and realize the automatic analysis of Bayesian network. The system can improve the efficiency of equipment information management and fault diagnosis. Aiming at the lowest cost of equipment life management in unit time, a maintenance optimization model based on geometric process is established, which is suitable for various life distributions. Monte Carlo method is introduced, and the corresponding simulation program is compiled with Matlab. The optimum life cycle of mechanical equipment is predicted. The centrifugal pump with two parameters Weibull distribution is taken as an example. The results show that the model is reasonable and can provide some guidance for the maintenance decision of mechanical equipment.
【学位授予单位】：燕山大学
【学位级别】：硕士
【学位授予年份】：2011
【分类号】：TH165.3

【参考文献】