Abstract
Rolling bearings are key components of rotating machinery, and predicting the remaining useful life (RUL) is of great significance in practical industrial scenarios and is being increasingly studied. A precise and reliable remaining useful life prediction result provides valuable information for decision-makers, which is essential to ensure the safety and reliability of mechanical systems. Generally, the RUL label is considered to be an ideal life curve, which is the benchmark for RUL prediction. However, the existing label construction methods make more use of expert experience and seldom mine knowledge from data and combine experience to assist in constructing a health index (HI). In this paper, a novel and simple approach of label construction is proposed for predicting the RUL accurately. More specifically, the degradation index of the multiscale frequency domain is first extracted. Furthermore, the fuzzy C-means (FCM) algorithm is innovatively used to divide the degradation data into several stages to obtain the turning point of degradation. Then, a nonlinear degradation index, the RUL label with the turning point, was constructed based on principal component analysis (PCA). Finally, the recurrent neural network (RNN) is used for prediction and verification. In order to verify the effectiveness of the proposed approach, two different bearing lifecycle datasets are gathered and analyzed. The analysis result confirms that the proposed method is able to achieve a better performance, which outperforms some existing methods.
Highlights
Rolling bearings are widely used in various mechanical systems as one of the most critical components
In previous studies, based on expert experience, the degradation stages of bearings are generally divided into three stages: normal condition, slight fault, and severe fault [4]. erefore, the degradation process can be divided into stages according to the fuzzy C-means (FCM) algorithm mentioned in Section 2.2, Value
Three clustering centers are set in the FCM algorithm with the maximum iteration as 100 and the error as 1e − 6. e result of membership degree function is shown in Figure 8. e membership degree from sample 1 to sample n1 is 0.85, and that of the other samples is below 0.5 in the first cluster. us, the samples from the first to n1 belong to the first group
Summary
Rolling bearings are widely used in various mechanical systems as one of the most critical components. The failure of rolling bearings is one of the most important causes of mechanical system failure [1]. Erefore, the diagnosis and prognosis of bearings play an important role in the performance of mechanical equipment [2,3,4]. Predicting the RUL of bearings is of great importance to prevent sudden failures in mechanical systems and has received much attention as a key issue in prognostics and health management (PHM) [5,6,7,8]. More and more data-driven methods have been proposed for RUL prediction. Lei et al divided the data-driven RUL prediction into four main steps, including data acquisition, HI construction, health stage division, and RUL prediction [10]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
