Equipment state recognition and fault prognostics method based on DD-HSMM model

• Article •

Equipment state recognition and fault prognostics method based on DD-HSMM model

WANG Ning, SUN Shu-dong, LI Shu-min, CAI Zhi-qiang

1.School of Mechanical Engineering，Northwestern Polytechnical University,Xi'an 710072,China;2.Key Laboratory of Contemporary Design and Integrated Manufacturing Technology, Ministry of Education,Northwestern Polytechnical University, Xi'an 710072, China

Online:2012-08-15 Published:2012-08-25

基于DD-HSMM的设备运行状态识别与故障预测方法

王宁，孙树栋，李淑敏，蔡志强,

1.西北工业大学机电学院，陕西西安710072;2.西北工业大学现代设计与集成制造教育部重点实验室，陕西西安710072

Abstract

Abstract: Aiming at the problem of equipment operation state identification and fault prognosis, a Duration-Dependent Hidden Semi-Markov Model(DD-HSMM)was proposed. In this model, the historical operation information was merged into estimation process of Markov state transition probability matrix, thus the matrix had time variant characteristics. Furthermore, the parameter estimation method of Hidden Semi-Markov Model(HSMM)was studied based on improved forward-backward algorithm to make self-renewal by using historical operation information. The basic steps for predicting the Remaining Useful Life(RUL)of equipment was built by using fault rate method. Through a case of a rolling bearing's operation state to demonstrate the modeling process of proposed model, and the result showed that the proposed method was more effective than traditional HSMM model.

Key words: duration-dependent state transition probabilities, hidden semi-Markov model, hazard rate, state recognition, remaining useful life

摘要： 针对设备运行状态识别与故障预测问题，提出一种基于时变转移概率的隐半Markov模型。该模型将设备历史运行信息融入Markov状态转移概率矩阵的估计过程中，使Markov状态转移概率矩阵具有时变特性。基于改进前向后向算法研究了相应的隐半Markov模型参数估计方法，使其能够不断综合利用历史运行信息进行自我更新，以更加符合设备真实运行的过程。同时以该模型为基础，利用故障率方法建立了对设备剩余使用寿命进行预测的基本步骤。通过某滚动轴承运行状态识别实例演示了该模型的建模过程，证明了基于该模型的设备状态识别与预测方法比传统隐半Markov模型方法更为有效。

关键词: 时变转移概率, 隐半Markov模型, 故障率, 状态识别, 剩余有效寿命

CLC Number:

TP391

WANG Ning,, SUN Shu-dong,, LI Shu-min,, CAI Zhi-qiang,. Equipment state recognition and fault prognostics method based on DD-HSMM model[J]. .

王宁,,孙树栋,,李淑敏,,蔡志强,. 基于DD-HSMM的设备运行状态识别与故障预测方法[J]. .

[1]	. Prediction method of tool remaining useful life based on transfer learning [J]. , 2021, 27(6): 1541-1549.
[2]	. Current research and challenges of deep learning for equipment remaining useful life prediction [J]. , 2021, 27(1): 35-53.
[3]	. Prediction method for remaining useful life of gearbox based on kernel estimation and stochastic filtering theory [J]. , 2020, 26(第3): 632-640.
[4]	. Tool wear condition recognition based on kernel principal component and grey wolf optimizer algorithm [J]. , 2020, 26(11): 3031-3039.
[5]	. Remaining useful life prediction of turbofan engine based on Autoencoder-BLSTM [J]. , 2019, 25(第7): 1611-1619.
[6]	. Digital twin model for cutting tools in machining process [J]. , 2019, 25(第6): 1474-1480.
[7]	. Maintenance decision-making based on condition-based maintenance for fleet [J]. , 2019, 25(第3): 661-672.
[8]	. Multi-variable similarity-based information fusion method for remaining useful life prediction [J]. , 2018, 24(第4): 813-819.
[9]	. Economic optimization model for imperfect preventive maintenance under reliability constraints [J]. , 2018, 24(第12): 3019-3026.
[10]	. Remaining useful life prediction based on support vector data description [J]. , 2018, 24(第11): 2725-2733.
[11]	. Life state recognition of slewing bearing based on improved fuzzy C-means [J]. , 2018, 24(第11): 2751-2758.
[12]	. Equipment health diagnostics and prognostics method based on adaptive HSMM [J]. , 2016, 22(第9期): 2187-2194.
[13]	. Preventive maintenance strategy based on life prediction [J]. , 2014, 20(5): 1133-.
[14]	. Prediction of real-time remaining useful life and maintenance decision model considering imperfect preventive maintenance [J]. , 2014, 20(09): 2259-2266.
[15]	YANG Zhi-bo, DONG Ming+. Dynamic Bayesian networks for predicting remaining useful life of equipment [J]. , 2007, 13(09): 0-0.