【全文链接或数据库名称(选填)】 基于隐半Markov模型的故障诊断和故障预测方法研究被引量:1Study on Fault Diagnosis and Prognosis Methods Based on Hidden Semi-Markov Model查看引文在线阅读下载全文收藏本页导出题录作 者:胡海峰[1] 安茂春[2] 秦国军[1] 胡茑庆[1] HU Hai-feng, AN Mao-chun, QIN Guo-jun, HU Niao-qing (1. School of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha 410073, Hunan, China;2. Pre-research Projects Management Center of General Armament Department, Beijing 100101, China) 机构地区:[1]国防科学技术大学机电工程与自动化学院,湖南长沙410073 [2]总装备部预研管理中心,北京100101 出 处:《兵工学报》 EI CAS CSCD 2009年第1期 69-75页,共7页 Acta Armamentarii 基 金:国家863计划资助项目(2006AA04Z423) 摘 要:隐半Markov模型(HSMM)是隐Markov模型(HMM)的一种扩展形式,通过在HMM结构中加入状态驻留时间分布参数,克服了HMM假设状态驻留时间服从指数分布的不足。HSMM不仅具有较强的模式分类能力,而且能对实际问题中的状态驻留时间进行合理建模,故既可用于故障诊断,又可用于故障预测。分析了利用HSMM进行故障诊断和预测的框架;并针对传统HSMM建模算法计算量和存储空间都比较大的缺点,引入并改进了一种快速递推算法,降低了计算复杂度和存储空间要求;最后将HSMM应用于直升机齿轮箱轴承故障诊断和GaAs激光器剩余使用寿命(RUL)预测,试验结果证明了这种方法的有效性。 A hidden semi-Markov model(HSMM) is an extension of hidden Markov model(HMM), designed to remove the exponential distribution of the state durations assumed in HMM by adding explicit time duration parameters.Besides HSMM powerful capability of pattern classification,it allows modeling the time duration of hidden states more reasonably,therefore,it can be used for either fault diagnosis or fault prognosis.A unified framework for both fault diagnosis and prognosis based on HSMM was presented.An efficient recursive algorithm which can reduce the computation complexity and storage of HSMM was introduced into HSMM model to facilitate the proposed HSMM-based diagnosis and prognosis.The proposed methods were applied to fault diagnosis of helicopter gearbox bearings and the remaining useful life(RUL) prediction of GaAs lasers respectively.The results show the validity of the methods. 关 键 词:人工智能隐半Markov模型快速递推算法故障诊断故障预测artificial intelligencehidden semi-Markov modelefficient recursive algorithmfault diagnosisfault prognosis分 类 号:TH17 [工业技术 > 机械、仪表工业]