基于贝叶斯网络船用柴油机故障诊断系统的研究

发布时间：2018-08-19 17:28

【摘要】：船用柴油机作为船舶主要动力装置,一旦发生故障,将会影响船舶的正常运行,并可能造成巨大的经济损失,甚至危及人身安全。船用柴油机结构的复杂性导致船用柴油机故障原因具有明显的不确定性,从而致使维护人员难以对故障进行准确定位和及时排除。所以采用贝叶斯网络实现船用柴油机故障的准确定位和及时排除具有十分重大的意义。贝叶斯网络被认为是进行不确定性知识表达和推理最有效的理论模型之一。由于贝叶斯网络具有理论基础坚实、推理算法高效以及学习能力强等优点,所以本文将其引入到船用柴油机故障诊断问题中进行研究,来解决船用柴油机故障的不确定性问题。本文首先以船用柴油机为研究对象,对其常见故障进行了分析,并结合贝叶斯网络的特点,将船用柴油机故障诊断中涉及到的信息,分别用故障症状节点、观测操作节点以及故障原因节点进行表示,建立了基于“故障症状节点-观测操作节点-故障原因节点”结构的船用柴油机故障的诊断贝叶斯网络模型；然后根据故障诊断系统需要采集船用柴油机工作参数作为证据信息进行故障诊断的需求,设计实现了基于PLC的柴油机工作参数采集监测系统,该系统的主要功能是获取船用柴油机的状态信息,为故障诊断系统进行故障诊断提供证据信息,同时,该系统也可以用于监测柴油机的运行状态；最后利用Access建立后台数据库,用Visual C++6.0编程实现了整个故障诊断系统,包括知识库管理模块、网络构建模块、推理解释模块、参数学习模块、证据收集模块和人机界面。并通过故障实例推理验证了该方案的可行性和优越性。
[Abstract]:As the main power equipment of the ship, the marine diesel engine will affect the normal operation of the ship once it breaks down, and may cause huge economic losses and even endanger the personal safety. The complexity of marine diesel engine structure leads to the obvious uncertainty of the fault cause of marine diesel engine, which makes it difficult for maintenance personnel to locate the fault accurately and remove it in time. So it is of great significance to use Bayesian network to accurately locate and eliminate the faults of marine diesel engine. Bayesian network is considered to be one of the most effective theoretical models for uncertain knowledge representation and reasoning. Because Bayesian network has the advantages of solid theoretical foundation, high efficiency of reasoning algorithm and strong learning ability, so this paper introduces it into marine diesel engine fault diagnosis problem to solve the problem of marine diesel engine fault uncertainty. In this paper, the common faults of marine diesel engine are analyzed, and combined with the characteristics of Bayesian network, the information involved in the fault diagnosis of marine diesel engine is used as the fault symptom node, respectively. The Bayesian network model of marine diesel engine fault diagnosis based on the structure of "symptom node, observation operation node and fault cause node" is established. Then according to the need of fault diagnosis system to collect the working parameters of marine diesel engine as evidence information for fault diagnosis, a diesel engine working parameter acquisition and monitoring system based on PLC is designed and implemented. The main function of the system is to obtain the state information of marine diesel engine, to provide evidence information for fault diagnosis system, at the same time, the system can also be used to monitor the running status of diesel engine. Finally, the background database is established by using Access. The whole fault diagnosis system is programmed with Visual C 6.0, including knowledge base management module, network construction module, reasoning explanation module, parameter learning module, evidence collection module and man-machine interface. The feasibility and superiority of the scheme are verified by fault case reasoning.
【学位授予单位】：大连海事大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：U672.74

【相似文献】