scholarly journals Prediction Method of Bearing RUL Based on DNN and GBDT Algorithm

CONVERTER ◽  
2021 ◽  
pp. 669-679
Author(s):  
Qu Jinglei, Et al.
Keyword(s):  
Time Domain ◽  
Prediction Error ◽  
Prediction Accuracy ◽  
Prediction Method ◽  
Prediction Performance ◽  
Remaining Useful Life ◽  
Prior Model ◽  
Useful Life ◽  
Model Features ◽  
Collaborative Prediction

In view of the lack of effective model and the large prediction error in the traditional prediction methods, a collaborative prediction method for remaining useful life of bearing based on DNN and GBDT is proposed. Firstly, the degradation characteristics are constructed through normalization processing of parameters in time domain and frequency domain that can clearly represent the healthy running state of bearings, in order to improve the correlation of degradation characteristics, the prior model features are generated based on DNN. Secondly, a regression model of GBDT based on the prior model features is presented. Finally, the experimental results show that compared with other algorithms such as DNN, GBDT, SVR, RF, DT, the proposed method has better prediction performance evaluation results, higher prediction accuracy and efficiency compared with other algorithms.

A method based on Dempster-Shafer theory and support vector regression-particle filter for remaining useful life prediction of crusher roller sleeve

2019 ◽  
Vol 20 (1) ◽  
pp. 106
Author(s):  
Haiping Liu ◽  
Jianjun Wu ◽  
Xiang Ye ◽  
Taijian Liao ◽  
Minlin Chen
Keyword(s):  
Particle Filter ◽  
Support Vector Regression ◽  
Prediction Method ◽  
Vibration Signal ◽  
Prediction Performance ◽  
Remaining Useful Life ◽  
Support Vector ◽  
Dempster Shafer Theory ◽  
Useful Life ◽  
Shafer Theory

In order to solve the problem of accurately predicting the remaining useful life (RUL) of crusher roller sleeve under the partially observable and nonlinear nonstationary running state, a new method of RUL prediction based on Dempster-Shafer (D-S) data fusion and support vector regression-particle filter (SVR-PF) is proposed. First, it adopts the correlation analysis to select the features of temperature and vibration signal, and subsequently utilize wavelet to denoising the features. Lastly, comparing the prediction performance of the proposed method integrates temperature and vibration signal sources to predict the RUL with the prediction performance of single source and other prediction methods. The experiment results indicate that the proposed prediction method is capable of fusing different data sources to predict the RUL and the prediction accuracy of RUL can be improved when data are less available.

Hybrid remaining useful life prediction method. A case study on railway D-cables

2021 ◽  
pp. 107746
Author(s):  
Yu Zang ◽  
Wei Shangguan ◽  
Baigen Cai ◽  
Huasheng Wang ◽  
Michael. G. Pecht
Keyword(s):  
Life Prediction ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Useful Life

Remaining useful life prediction method for machine tools based on meta-action theory

2021 ◽  
pp. 1748006X2110025
Author(s):  
Zongyi Mu ◽  
Yan Ran ◽  
Genbao Zhang ◽  
Hongwei Wang ◽  
Xin Yang
Keyword(s):  
Machine Tools ◽  
Life Prediction ◽  
Action Theory ◽  
Prediction Method ◽  
Operational Reliability ◽  
Remaining Useful Life ◽  
Practical Application ◽  
Dynamic Prediction ◽  
Degradation Model ◽  
Useful Life

Remaining useful life (RUL) is a crucial indictor to measure the performance degradation of machine tools. It directly affects the accuracy of maintenance decision-making, thus affecting operational reliability of machine tools. Currently, most RUL prediction methods are for the parts. However, due to the interaction among the parts, even RUL of all the parts cannot reflect the real RUL of the whole machine. Therefore, an RUL prediction method for the whole machine is needed. To predict RUL of the whole machine, this paper proposes an RUL prediction method with dynamic prediction objects based on meta-action theory. Firstly, machine tools are decomposed into the meta-action unit chains (MUCs) to obtain suitable prediction objects. Secondly, the machining precision unqualified rate (MPUR) control chart is used to conduct an out of control early warning for machine tools’ performance. At last, the Markov model is introduced to determine the prediction objects in next prediction and the Wiener degradation model is established to predict RUL of machine tools. According to the practical application, feasibility and effectiveness of the method is proved.

Diamond-Coated Mechanical Seal Remaining Useful Life Prediction Based on Convolution Neural Network

2019 ◽  
Vol 34 (05) ◽  
pp. 2051007
Author(s):  
Zhibin Lin ◽  
Hongli Gao ◽  
Erqing Zhang ◽  
Weiqing Cao ◽  
Kesi Li
Keyword(s):  
Nuclear Power ◽  
Signal To Noise Ratio ◽  
Prediction Method ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Mechanical Seal ◽  
Process Industries ◽  
Petroleum Chemical ◽  
Useful Life

Reliable remaining useful life (RUL) prediction of industrial equipment key components is of considerable importance in condition-based maintenance to avoid catastrophic failure, promote reliability and reduce cost during the production. Diamond-coated mechanical seal is one of the most critical wearing components in petroleum chemical, nuclear power and other process industries. Estimating the RUL is of critical importance. We consider the data-driven approaches for diamond-coated mechanical seal RUL estimation based on AE sensor data, since it is difficult to construct an explicit mathematical degradation model of seal. The challenges of this work are dealing with the noisy AE sensor data and modeling the degradation process with fluctuation. Faced with these challenges, we propose a pipeline method CDF-CNN to estimate the RUL for mechanical seal: WPD-KLD to raise the signal-to-noise ratio, novel CDF-based statistics to represent seal degradation process and CNN structure to estimate RUL. To acquire AE sensor data, several diamond-coated seals are tested from new to failure in three working conditions. Experimental results demonstrate that the proposed method can accurately predict the RUL of diamond-coated mechanical seal based on AE signals. The proposed prediction method can be generalized to other various mechanical assets.

scholarly journals A Remaining Useful Life Prediction Method Considering the Dimension Optimization and the Iterative Speed

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 180383-180394 ◽  
Author(s):  
Yiming Li ◽  
Xiangmin Meng ◽  
Zhongchao Zhang ◽  
Guiqiu Song
Keyword(s):  
Life Prediction ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Useful Life

scholarly journals Bearing Remaining Useful Life Prediction Based on Naive Bayes and Weibull Distributions

Entropy ◽  
2018 ◽  
Vol 20 (12) ◽  
pp. 944
Author(s):  
Nannan Zhang ◽  
Lifeng Wu ◽  
Zhonghua Wang ◽  
Yong Guan
Keyword(s):  
Naive Bayes ◽  
Prediction Method ◽  
Naïve Bayes ◽  
Remaining Useful Life ◽  
Statistical Characteristics ◽  
Mechanical Equipment ◽  
Weibull Distributions ◽  
Health States ◽  
Testing Stage ◽  
Useful Life

Bearing plays an important role in mechanical equipment, and its remaining useful life (RUL) prediction is an important research topic of mechanical equipment. To accurately predict the RUL of bearing, this paper proposes a data-driven RUL prediction method. First, the statistical method is used to extract the features of the signal, and the root mean square (RMS) is regarded as the main performance degradation index. Second, the correlation coefficient is used to select the statistical characteristics that have high correlation with the RMS. Then, In order to avoid the fluctuation of the statistical feature, the improved Weibull distributions (WD) algorithm is used to fit the fluctuation feature of bearing at different recession stages, which is used as input of Naive Bayes (NB) training stage. During the testing stage, the true fluctuation feature of the bearings are used as the input of NB. After the NB testing, five classes are obtained: health states and four states for bearing degradation. Finally, the exponential smoothing algorithm is used to smooth the five classes, and to predict the RUL of bearing. The experimental results show that the proposed method is effective for RUL prediction of bearing.

Sign in / Sign up

Export Citation Format

Share Document