大型机械设备振动系统故障诊断仿真研究

发布时间：2019-05-13 13:53

【摘要】：大型机械设备组成结构复杂,容易产生故障,通过对大型机械设备的振动系统故障诊断,提高大型机械设备的稳定运行性能。传统的故障诊断方法采用海量振动样本特征数据聚类分析方法进行故障分类和诊断,诊断性能受到振动数据样本采集和环境的特征的限制,故障检测效果不好。提出一种基于大型机械设备振动系统故障特征专家系统构建的故障诊断模型,并采用abaqus软件进行仿真分析。构建故障诊断专家系统,包括对模糊数据库、模糊知识库和模糊推理机的构建,设计故障诊断的神经网络模糊控制学习算法,通过设计人机结构,实现对大型机械设备振动系统故障的准确推断决策。利用abaqus软件在计算机上建立测试虚拟样机,实现故障诊断在线模型仿真,了解复杂机械系统设计的故障运行性能。仿真结果表明,该系统能有效提高对大型机械设备振动系统的故障诊断能力,实现智能故障诊断控制和自适应故障处理,在机械状态监测等领域具有较好的应用价值。
[Abstract]:The composition and structure of large mechanical equipment is complex and easy to cause faults. Through the fault diagnosis of vibration system of large mechanical equipment, the stable operation performance of large mechanical equipment can be improved. The traditional fault diagnosis method uses massive vibration sample feature data clustering analysis method for fault classification and diagnosis. The diagnosis performance is limited by vibration data collection and environmental characteristics, and the fault detection effect is not good. A fault diagnosis model based on fault characteristics expert system of vibration system of large mechanical equipment is proposed, and the simulation analysis is carried out by using abaqus software. The fault diagnosis expert system is constructed, including the construction of fuzzy database, fuzzy knowledge base and fuzzy inference engine, the learning algorithm of neural network fuzzy control for fault diagnosis is designed, and the man-machine structure is designed. The accurate inference and decision of vibration system fault of large mechanical equipment is realized. The virtual prototype of test is established on the computer by using abaqus software, and the online model simulation of fault diagnosis is realized, and the fault operation performance of complex mechanical system design is understood. The simulation results show that the system can effectively improve the fault diagnosis ability of large mechanical equipment vibration system, realize intelligent fault diagnosis control and adaptive fault treatment, and has good application value in mechanical condition monitoring and other fields.
【作者单位】：济源职业技术学院;
【分类号】：TH17

【相似文献】