基于IBA-ELM的发动机燃油系统故障诊断研究  

FAULT DIAGNOSIS OF ENGINE FUEL SYSTEM BASED ON IBA-ELM

作　　者：靖婉婷 王海瑞[1] 林雅慧 Jing Wanting;Wang Hairui;Lin Yahui(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,Yunnan,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《计算机应用与软件》2018年第11期89-93,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(61263023)

摘　　要：发动机是整个机械设备的"心脏"。由于燃油系统结构组成较为复杂,因而也是故障的频发部件。选用极限学习机ELM(Extreme Learning Machine)方法对发动机燃油系统的故障进行分类。虽然极限学习机的学习速度非常快,但是该方法的分类准确度还有很大的提升空间。蝙蝠算法BA(Bat Algorithm)又具有很强的寻优能力,故提出一种基于改进的蝙蝠算法优化极限学习机的故障诊断模型。实验结果表明,改进的蝙蝠算法在很大程度上提高了极限学习机的分类精度和泛化能力。Engine is the heart of the entire machinery and equipment.As the fuel system composition is complicated,it frequently breaks down.Thus,the Extreme Learning Machine(ELM)method is used to classify the faults of the engine fuel system.Although the learning speed of ELM is very fast,the classification accuracy of this method still need improvement.As the Bat algorithm(BA)has strong search ability for excellence,a fault diagnosis model based on ELM improved by bat algorithm is proposed.The experimental results show that the improved bat algorithm greatly improves the classification accuracy and generalization ability of ELM.

关 键 词：发动机 燃油系统 极限学习机 蝙蝠算法 故障诊断 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]