中文摘要：

隐马尔可夫树（Hidden Markov tree，HMT）模型作为一种小波变换系数的统计模型，可以表示小波系数的统计相关性及非高斯性。由于离散小波变换（Discrete wavelet transform，DWT）不具有平移不变性，应用基于DWT的HMT模型进行机械状态诊断时容易出现误诊。为了获得平移不变性，提出一种基于二分树复小波变换（Dual-tree complex wavelet transform，DTCWT）的HMT模型。实例表明与使用基于DWT的HMT模型进行状态识别相比，使用基于DTCWT的HMT模型的状态识别率有显著提高。

英文摘要：

As a statistical model of wavelet coefficients, hidden Markov tree （HMT） can consider the statistical dependencies and non-Gaussian statistics of wavelet coefficients. Due to shift-variance of discrete wavelet transform （DWT）, if DWT-based HMT model is used for machine condition diagnosis, it is likely to get incorrect results. To obtain shift-invariance, DT CWT-based （dual-tree complex wavelet transform） HMT model is developed, Experiments show that DT CWT-based HMT model can get much higher recognition rates in comparison with DWT-based HMT model.