The conventional signal processing based methods are difficult to achieve satisfactory results for rolling element bearings (REBs)’ weak fault due to the serious influence of interference signal. Intelligent classification technology and the arising popular monitoring technology-performance evaluation assessment (PDA) are the research hotspots of fault diagnosis of REB in recent years, which could resolve the above problem to some extent. Especially the latter could reflect the operating status of the equipment more comprehensively. Effective feature extraction basing on signal processing methods and intelligent algorithm are the two key aspects for the above two technologies which will determine their effectiveness to great extent. Multifractal detrended fluctuation analyses (MDFA) is an effective non-stationary signal processing method which could reveal the multifractality buried in nonlinear and nonstationary vibration signals of REB, and continuous hidden markov model (CHMM) is a mature intelligent algorithm with solid theoretical basis and rich mathematical structure. So a diagnosis method basing on combination of MDFA with CHMM is proposed in the paper, and it could deal with both fault classification and PDA tasks for the diagnosis of REBs. Effectiveness of the proposed method is validated by two different diagnosis experiments, one for fault classification and another for lifecycle performance evaluation of REBs. Compared to state-of-the-art peer methods, the proposed method has the best performance when dealing with fault diagnosis tasks for REBs.

由于干扰信号的严重影响，传统的基于信号处理的方法难以对滚动轴承（REB）的弱故障取得满意的结果。智能分类技术和兴起的流行的监测技术-性能评价评估（PDA）是近年来REB故障诊断的研究热点，可以在一定程度上解决上述问题。尤其是后者可以更全面地反映设备的运行状态。基于信号处理方法和智能算法的有效特征提取是上述两种技术的两个关键方面，将在很大程度上决定其有效性。多重分形去趋势涨落分析（MDFA）是一种有效的非平稳信号处理方法，可以揭示隐藏在REB非线性和非平稳振动信号中的多重分形，而连续隐马尔可夫模型（CHMM）是一种成熟的智能算法，具有坚实的理论基础和丰富的经验。数学结构。因此本文提出了一种基于MDFA与CHMM相结合的诊断方法，它可以同时处理故障分类和PDA任务对REBs的诊断。所提出方法的有效性通过两个不同的诊断实验得到验证，一个用于故障分类，另一个用于 REB 的生命周期性能评估。与最先进的对等方法相比，所提出的方法在处理 REB 的故障诊断任务时具有最佳性能。