Abstract

Predicting the remaining useful life (RUL) of mechanical equipment can improve production efficiency while effectively reducing the life cycle cost and failure rate. This paper proposes a method for predicting the remaining service life of equipment through a combination of a deep convolutional autoencoder (DCAE) and a convolutional neural network (CNN). For rolling bearings, a health indicator (HI) could be built by combining DCAE and self-organizing map (SOM) networks, performing more advanced characterization against the original vibration data and modeling the degradation state of the rolling bearings. The HI serves as the label of the original vibration data, and the original data with such label is input into the prediction model of the RUL based on a one-dimensional convolutional neural network (1D-CNN). The model was trained for predicting the RUL of a rolling bearing. The bearing degradation dataset was evaluated to verify the method’s effectiveness. The results demonstrate that the constructed HI can characterize the bearing degradation state effectively and that the method of predicting the RUL can accurately predict the bearing degradation trend.

Highlights

  • The deep learning (DL)-based data-driven method has become a hotspot in the field of prognostic and health management (PHM) as a result of the promotion of enormous industrial status monitoring data and computing power enhancement [1,2,3,4]

  • Data-driven prediction methods are generally utilized to extract features that are sensitive to the current degradation state and to predict future damage by taking advantage of the existing historical data upon obtaining a model that complies with the laws of nature

  • As the high-precision mechanical equipment develops and the monitoring equipment rapidly upgrades, higher requirements have been placed on the prediction of the remaining useful life (RUL) of rolling bearings in the context of massive monitoring data, such as how to extract useful information from massive data and how to accurately model the degradation state of rolling bearings [30,31]

Read more

Summary

Introduction

The deep learning (DL)-based data-driven method has become a hotspot in the field of prognostic and health management (PHM) as a result of the promotion of enormous industrial status monitoring data and computing power enhancement [1,2,3,4]. Some researchers combined the physical model with the data-driven method based on deep learning and have achieved good results in RUL prediction for rolling bearings [14,15,16,17,18]. Through the current research results of scholars, it can be found that the main processes of the life analysis and prediction methods of mechanical equipment are data acquisition, degradation state modeling and RUL prediction. As the high-precision mechanical equipment develops and the monitoring equipment rapidly upgrades, higher requirements have been placed on the prediction of the RUL of rolling bearings in the context of massive monitoring data, such as how to extract useful information from massive data and how to accurately model the degradation state of rolling bearings [30,31].

The part is the modeling of is divided twointo parts as parts shownasinshown
Background
Convolutional Layer
Pooling Layer
Degradation Modeling of Rolling Bearings
Method
Prediction of the RUL
12. Two curvescurves describing the labeling method:
Evaluation Index
Conclusions

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 call

Disclaimer: 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.