Health indicator construction and remaining useful life estimation for mechanical systems using vibration signal prognostics

Thoppil, Nikhil M.; Vasu, V.; Rao, C.S.P.

doi:10.1007/s13198-021-01190-z

Cited by 11 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in (Yang et al, 2016), or constructed based on selected features, e.g. in (Thoppil, Vasu, & Rao, 2021). In more rare cases, only one feature is directly used if it is sufficient to reflect the degradation process, provided that it can be used to define a system-wide failure threshold, e.g.…”

Section: Feature Selectionmentioning

confidence: 99%

Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds

Loewen,

Wissbrock,

Bender

et al. 2024

PHME_CONF

View full text Add to dashboard Cite

Historical condition monitoring data from technical systems can be utilized to develop data-driven models for predicting the remaining useful life (RUL) of similar systems, whereas the Health Index (HI) often is a crucial component. The development of robust and accurate models requires meaningful features that reflect the system’s degradation process, enabling an accurate prediction of the system's HI. Traditionally, the identification of those is supported by one of various feature ranking methods. In literature, feature interdependencies and their transferability across various similar systems are not sufficiently considered in feature selection, exacerbating the challenge of HI prediction posed by the scarcity of data and system diversity in real-world applications. This work addresses this gaps by demonstrating how filter-based feature selection, incorporating failure thresholds and cross correlations, enhances feature selection leading to improved HI prediction. The proposed methodology is applied to a novel dataset* obtained from run-to-failure experiments on geared motors conducted as part of this study, which presents the aforementioned challenges. It is revealed that classical feature selection, consisting of feature ranking only, leaves potential untapped, which is utilized by the proposed selection methodology. It is shown that the proposed feature selection methodology leads to the best result with a RMSE of 0.14 in predicting the HI of a constructive different gearbox, while the features, determined by classical feature selection, lead to a RMSE of 0.19 at best.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds

Loewen,

Wissbrock,

Bender

et al. 2024

PHME_CONF

View full text Add to dashboard Cite

show abstract

“…In the approach, the hybrid deep learning-based model, CNN-SE-LSTM, is firstly trained to calculate a health indicator, using the data segments generated according to the data collected for trained specimens. In real-time prediction, once a sequence of data segments is obtained, the trained model is used to calculate a health indictor (HI) [22]. With all the health indicators calculated up to date, a RFL is predicted through a particle filter-based algorithm.…”

Section: Remaining Fatigue Life Prediction Model Based On Deep Learningmentioning

confidence: 99%

A Real-Time Remaining Fatigue Life Prediction Approach Based on a Hybrid Deep Learning Network

Zhu,

Zhang,

Luo

et al. 2023

Processes

View full text Add to dashboard Cite

Fatigue failure is a typical failure mode of welded structures. It is of great engineering significance to predict the remaining fatigue life of structures after a certain period of service. In this paper, a two-stage hybrid deep learning approach is proposed only using the response of structures under fatigue loading to predict the remaining fatigue life. In the first stage, a combination of convolutional neural network (CNN), squeeze-and-excitation (SE) block, and long short-term memory (LSTM) network is employed to calculate health indicator values based on the current measured data sequence. In the second stage, a particle filtering-based algorithm is utilized to predict the remaining fatigue life using the previously calculated health indicators. Experimental results on different welded specimens under the same loading conditions demonstrate that the hybrid deep learning approach achieves superior prediction accuracy and generalization ability compared to CNN, LSTM, or CNN-LSTM models in the first stage. Moreover, the average relative deviation between the predicted and actual fatigue life is less than 6% during the final quarter of the crack propagation and fracture stage.

show abstract

Similarity-based prediction method for machinery remaining useful life: A review

Xue

Huang

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Health indicator construction and remaining useful life estimation for mechanical systems using vibration signal prognostics

Cited by 11 publications

References 46 publications

Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds

Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds

A Real-Time Remaining Fatigue Life Prediction Approach Based on a Hybrid Deep Learning Network

Similarity-based prediction method for machinery remaining useful life: A review

Contact Info

Product

Resources

About