CAJ | 학술논문

提出基于隐马尔科夫模型（Hidden Markov Model，HMM）与改进距离测度法的齿轮箱故障诊断新方法。在改进的距离测度方法中通过两约束因子调整特征参数灵敏度的评价函数，通过评价函数获得最优特征参数子集，完成对特征参数降维；利用最优特征参数子集训练获得齿轮箱各状态下Markov模型；计算测试数据在各模型的对数似然概率，据概率值大小判断故障类型。齿轮箱验证实验结果表明，改进距离测度法与HMM方法结合能有效识别齿轮箱轴不对中、断齿、磨损等多故障模式，适用性较高，可用于实际齿轮箱系统故障诊断。
제출기우은마이과부모형（Hidden Markov Model，HMM）여개진거리측도법적치륜상고장진단신방법。재개진적거리측도방법중통과량약속인자조정특정삼수령민도적평개함수，통과평개함수획득최우특정삼수자집，완성대특정삼수강유；이용최우특정삼수자집훈련획득치륜상각상태하Markov모형；계산측시수거재각모형적대수사연개솔，거개솔치대소판단고장류형。치륜상험증실험결과표명，개진거리측도법여HMM방법결합능유효식별치륜상축불대중、단치、마손등다고장모식，괄용성교고，가용우실제치륜상계통고장진단。
With resorting to an experimental device for investigating multiple defects of gearbox a new approach for fault diagnosis of gearbox was proposed.In the improved distance measure method,two restraint factors were presented to adjust the evaluation function by which the superior features can be selected from the original feature set.Based on the HMM (Hidden Markov Model)theory,the superior features were used to train the HMM until it is convergent,and the HMM under each gearbox state can be obtained.Calculating the logarithmic likelihood probability of each HMM by use of testing data,the fault state can be identified based on the probability value.The testing results show that the combination of HMM and improved distance measure can effectively identify different gearbox failure patterns with high recognition accuracy,and can be applied to the real gearbox system for fault diagnosis.