A Degradation Condition Assessment Technique Based on online_ISSE Degradation Feature and Logistic Regression Model

Abstract

A degradation assessment technique based on an online improved symbol sequence entropy online_ISSE and a logistic regression model is proposed in this paper. Firstly, the threshold factor is introduced to retain the `coarse graining' information of direction changing and amplitude information, the `sensitivity' of improved symbol sequence entropy (SSE) to impact components is reduced and improved symbol sequence entropy (ISSE) is proposed. Then, a sliding window and Weibull distribution theory are used to effectively filter out the influence of fluctuations in the ISSE feature sequence, forming the degradation feature named online_ISSE. Finally, a logistic regression model is trained and constructed, and the health factor CV is calculated online to assess the degradation condition of the unknown signal samples. The lifetime vibration signal of the hoisting gearbox monitored from #8114 quay crane of the Shanghai Port Container Terminal is introduced for instance analysis. The results show that the proposed ISSE has a better effect in describing the complexity pattern than the SSE algorithm and that the degradation condition can be tracked and assessed accurately based on the technique proposed.

Multi-weighted symbolic sequence entropy: a novel approach to fault diagnosis and degradation monitoring of rotary machinery

“…The concept of the threshold factor α is introduced to enhance the SSE for capturing shock characteristics in the vibration process [46]. The symbolic equation can be expressed as follows:…”

“…In recent years, symbolic entropies have gained increasing attention for their application in fault diagnosis of rotary machinery, with successful implementations in rolling bearing diagnostics [44,45]. Furthermore, the Improved Symbolic Sequence Entropy (ISSE) was proposed by incorporating a threshold factor into the original SSE [46]. The inclusion of a threshold factor in the symbolization process of ISSE facilitates the retention of dynamic information related to directional and amplitude changes.…”

A complexity measurement technique for time-series based on improved KW entropy

“…In nonlinear analysis methods, symbolic dynamics analysis is an effective signal analysis method. Symbolic dynamics is proposed as a theoretical foundation for studying, nowadays, the method are used in a series of fields such as network security 15,16 , biomedicine 17,18 , and mechanical engineering 19,20 . Based on symbolic dynamics, symbolic analysis methods can discretize the original signal to extract the major trend of the signal, At the same time, they can also remove the noise, further improving the analysis effect and computational efficiency.…”

Improved KW entropy: a complexity measurement technique for time-series and its application in feature extraction of quay crane gearbox

“…The verification mostly uses the accelerated lifetime data of rolling bearing life from IMS and IEEE PHM 2012 (Nectoux et al 2012). There are relatively few literatures on quay crane hoisting gearbox and some typical research are listed including morphological fractal dimension (Sun et al 2019), symbol sequence entropy-logistic regression (Wang et al 2021b), improved symbol sequence entropy-singular value decomposition (Wang et al 2021a), etc. Compared with accelerated lifetime data, monitoring signal of quay crane is more complex and lasting with much noise and it is difficult to apply some effective methods to instance signal of quay crane, which also increases the difficulty of method verification.…”