A hybrid degradation tendency measurement method for mechanical equipment based on moving window and Grey-Markov model

作者：Jiang, Wei; Zhou, Jianzhong^*; Zheng, Yang; Liu, Han

来源：Measurement Science and Technology, 2017, 28(11): 115003.

DOI：10.1088/1361-6501/aa8396

• degradation tendency measurement
• mechanical equipment
• normalized degradation index
• moving window
• Grey-Markov model
• combination prediction models

Accurate degradation tendency measurement is vital for the secure operation of mechanical equipment. However, the existing techniques and methodologies for degradation measurement still face challenges, such as lack of appropriate degradation indicator, insufficient accuracy, and poor capability to track the data fluctuation. To solve these problems, a hybrid degradation tendency measurement method for mechanical equipment based on a moving window and Grey-Markov model is proposed in this paper. In the proposed method, a 1D normalized degradation index based on multi-feature fusion is designed to assess the extent of degradation. Subsequently, the moving window algorithm is integrated with the Grey-Markov model for the dynamic update of the model. Two key parameters, namely the step size and the number of states, contribute to the adaptive modeling and multi-step prediction. Finally, three types of combination prediction models are established to measure the degradation trend of equipment. The effectiveness of the proposed method is validated with a case study on the health monitoring of turbine engines. Experimental results show that the proposed method has better performance, in terms of both measuring accuracy and data fluctuation tracing, in comparison with other conventional methods.

• 出版日期2017-11
• 单位华中科技大学